llama.cpp - chat

- -

+ + +

+ + ` + ); + + const ChatConfigForm = () => ( + html` +

+ + + + + + + +

+ ${PromptControlFieldSet()} +

Prompt Style

+ User ID + +

+ AI ID + +

+ Prompt Template +

+              </div>
+            </div>
+            <div>
+              <div class="input-container">
+                <label for="template" class="input-label-sec" id="id_history-template">Chat History</label>
+                <textarea id="history-template" class="persistent-input-sec" name="historyTemplate" value="${session.value.historyTemplate}" rows=1 oninput=${updateSession}/>
+              </div>
+            </div>
+          </div>
+        </details>
+        <details>
+          <summary><span class="summary-title" id="id_grammar-title" id_grammar-title>Grammar</span></summary>
+          ${GrammarControl()}
+        </details>
+
+        </fieldset>
+    `
+  );
+
+  const CompletionConfigForm = () => (
+    html`
+      ${PromptControlFieldSet()}
+      <fieldset>
+        <details>
+          <summary><span class="summary-title" id="id_grammar-title" id_grammar-title>Grammar</span></summary>
+          ${GrammarControl()}
+        </details>
+      </fieldset>
+    `
+  );
+// todo toggle button et api field et reset button in one nice row
+  return html`
+    <form>
+      <fieldset class="two">
+          <input type="checkbox" id="toggle" class="toggleCheckbox" onchange=${handleToggleChange} />
+            <label for="toggle" class="toggleContainer">
+              <div id="id_toggle-label-chat">Chat</div>
+              <div id="id_toggle-label-complete">Complete</div>
+            </label>
+      <fieldset>
+
+          <input type="text" id="api_key" class="apiKey" name="api_key" value="${params.value.api_key}" placeholder="Enter API key" oninput=${updateParams} />
+      </fieldset>
+
+        <${UserTemplateResetButton}/>
+      </fieldset>
+
+      ${session.value.type === 'chat' ? ChatConfigForm() : CompletionConfigForm()}
+
+      <fieldset class="params">
+        ${IntField({ label: "Prediction", title: "Set the maximum number of tokens to predict when generating text. Note: May exceed the set limit slightly if the last token is a partial multibyte character. When 0, no tokens will be generated but the prompt is evaluated into the cache. The value -1 means infinity. Default is 358", max: 2048, min: -1, step: 16, name: "n_predict", value: params.value.n_predict, })}
+        ${FloatField({ label: "Min-P sampling", title: "The minimum probability for a token to be considered, relative to the probability of the most likely token. Note that it's good practice to disable all other samplers aside from temperature when using min-p. It is also recommenend to go this approach. Default is 0.05 â But consider higher values like ~ 0.4 for non-English text generation. The value 1.0 means disabled", max: 1.0, min: 0.0, name: "min_p", step: 0.01, value: params.value.min_p })}
+        ${FloatField({ label: "Repetition Penalty", title: "Control the repetition of token sequences in the generated text. Default is 1.1", max: 2.0, min: 0.0, name: "repeat_penalty", step: 0.01, value: params.value.repeat_penalty })}
+        ${FloatField({ label: "Temperature", title: "This will adjust the overall randomness of the generated text. It is the most common sampler. Default is 0.8 but consider using lower values for more factual texts or for non-English text generation", max: 2.0, min: 0.0, name: "temperature", step: 0.01, value: params.value.temperature })}
+      </fieldset>
+
+      <details>
+        <summary><span class="summary-title">Further Options</span></summary>
+        <fieldset class="params">
+          ${IntField({ label: "Top-K", title: "Limits the selection of the next token to the K most probable tokens. 1 means no randomness = greedy sampling. If set to 0, it means the entire vocabulary size is considered.", max: 100, min: 0, step: 1, name: "top_k", value: params.value.top_k })}
+          ${IntField({ label: "Penalize Last N", title: "The last n tokens that are taken into account to penalise repetitions. A value of 0 means that this function is deactivated and -1 means that the entire size of the context is taken into account.", max: 2048, min: 0, step: 16, name: "repeat_last_n", value: params.value.repeat_last_n })}
+          ${FloatField({ label: "Presence Penalty", title: "A penalty that is applied if certain tokens appear repeatedly in the generated text. A higher value leads to fewer repetitions.", max: 1.0, min: 0.0, name: "presence_penalty", step: 0.01, value: params.value.presence_penalty })}
+          ${FloatField({ label: "Frequency Penalty", title: "A penalty that is applied based on the frequency with which certain tokens occur in the training data set. A higher value results in rare tokens being favoured.", max: 1.0, min: 0.0, name: "frequency_penalty", step: 0.01, value: params.value.frequency_penalty })}
+          ${FloatField({ label: "Top-P", title: "Limits the selection of the next token to a subset of tokens whose combined probability reaches a threshold value P = top-P. If set to 1, it means the entire vocabulary size is considered.", max: 1.0, min: 0.0, name: "top_p", step: 0.01, value: params.value.top_p })}
+          ${FloatField({ label: "Typical-P", title: "Activates local typical sampling, a method used to limit the prediction of tokens that are atypical in the current context. The parameter p controls the strength of this limitation. A value of 1.0 means that this function is deactivated.", max: 1.0, min: 0.0, name: "typical_p", step: 0.01, value: params.value.typical_p })}
+          ${FloatField({ label: "XTC probability", title: "Sets the chance for token removal (checked once on sampler start)", max: 1.0, min: 0.0, name: "xtc_probability", step: 0.01, value: params.value.xtc_probability })}
+          ${FloatField({ label: "XTC threshold", title: "Sets a minimum probability threshold for tokens to be removed", max: 0.5, min: 0.0, name: "xtc_threshold", step: 0.01, value: params.value.xtc_threshold })}
+          ${FloatField({ label: "DRY Penalty Multiplier", title: "Set the DRY repetition penalty multiplier. Default is 0.0, which disables DRY.", max: 5.0, min: 0.0, name: "dry_multiplier", step: 0.01, value: params.value.dry_multiplier })}
+          ${FloatField({ label: "DRY Base", title: "Set the DRY repetition penalty base value. Default is 1.75", max: 3.0, min: 1.0, name: "dry_base", step: 0.01, value: params.value.dry_base })}
+          ${IntField({ label: "DRY Allowed Length", title: "Tokens that extend repetition beyond this receive exponentially increasing penalty. Default is 2", max: 10, min: 1, step: 1, name: "dry_allowed_length", value: params.value.dry_allowed_length })}
+          ${IntField({ label: "DRY Penalty Last N", title: "How many tokens to scan for repetitions. Default is -1, where 0 is disabled and -1 is context size", max: 2048, min: -1, step: 16, name: "dry_penalty_last_n", value: params.value.dry_penalty_last_n })}
+          ${IntField({ label: "Min Keep", title: "If greater than 0, samplers are forced to return N possible tokens at minimum. Default is 0", max: 10, min: 0, name: "min_keep", value: params.value.min_keep })}
+        </fieldset>
+
+        <hr style="height: 1px; background-color: #ececf1; border: none;" />
+
+        <fieldset class="three">
+          <label title="The Mirostat sampling method is an algorithm used in natural language processing to improve the quality and coherence of the generated texts. It is an at-runtime-adaptive method that aims to keep the entropy or surprise of a text within a desired range."><input type="radio" name="mirostat" value="0" checked=${params.value.mirostat == 0} oninput=${updateParamsInt} /> Mirostat off</label>
+          <label title="Mirostat version 1 was developed to adjust the probability of predictions so that the surprise in the text remains constant. This means that the algorithm tries to maintain a balance between predictable and surprising words so that the text is neither too monotonous nor too chaotic. V1 is recommended for longer writings, creative texts, etc."><input type="radio" name="mirostat" value="1" checked=${params.value.mirostat == 1} oninput=${updateParamsInt} /> Mirostat v1</label>
+          <label title="Mirostat version 2 builds on the idea of V1 but brings some improvements. V2 is recommended as a general purpose algorithm since it offers more precise control over entropy and reacts more quickly to unwanted deviations. As a result, the generated texts appear even more consistent and coherent, especially for everday life conversations."><input type="radio" name="mirostat" value="2" checked=${params.value.mirostat == 2} oninput=${updateParamsInt} /> Mirostat v2</label>
+          </fieldset>
+        <fieldset class="params">
+          ${FloatField({ label: "Entropy tau", title: "Tau controls the desired level of entropy (or 'surprise') in the text. A low tau (e.g. 0.5) would mean that a text is very predictable, but will also be very coherent. A high tau (e.g. 8.0) would mean that the text is very creative and surprising, but may also be difficult to follow because unlikely words will occur frequently.", max: 10.0, min: 0.0, name: "mirostat_tau", step: 0.01, value: params.value.mirostat_tau })}
+          ${FloatField({ label: "Learning-rate eta", title: "Eta determines how quickly the Mirostat algorithm adjusts its predictions to achieve the desired entropy. A learning rate that is too high can cause the algorithm to react too quickly and possibly become unstable, because the algorithm will try to maintain a balance between surprises and precision in the context of only a few words. In this way, 'the common thread' could be lost. Whereas a learning rate that is too low means that the algorithm reacts too slowly and a red thread becomes a heavy goods train that takes a long time to come to a halt and change a 'topic station'.", max: 1.0, min: 0.0, name: "mirostat_eta", step: 0.01, value: params.value.mirostat_eta })}
+        </fieldset>
+
+          <hr style="height: 1px; background-color: #ececf1; border: none;" />
+
+          <fieldset class="params">
+            ${IntField({ label: "Show Probabilities", title: "If greater than 0, the response also contains the probabilities of top N tokens for each generated token given the sampling settings. The tokens will be colored in gradient from green to red depending on their probabilities. Note that for temperature 0 the tokens are sampled greedily but token probabilities are still being calculated via a simple softmax of the logits without considering any other sampler settings. Defaults to 0", max: 10, min: 0, step: 1, name: "n_probs", value: params.value.n_probs })}
+          </fieldset>
+      </details>
+    </form>
+  `
+}
+
+    // todo - beautify apikey section with css
+
+    const probColor = (p) => {
+      const r = Math.floor(192 * (1 - p));
+      const g = Math.floor(192 * p);
+      return `rgba(${r},${g},0,0.3)`;
+    }
+
+    const Probabilities = (params) => {
+      return params.data.map(msg => {
+        const { completion_probabilities } = msg;
+        if (
+          !completion_probabilities ||
+          completion_probabilities.length === 0
+        ) return msg.content
+
+        if (completion_probabilities.length > 1) {
+          // Not for byte pair
+          if (completion_probabilities[0].content.startsWith('byte: \\')) return msg.content
+
+          const splitData = completion_probabilities.map(prob => ({
+            content: prob.content,
+            completion_probabilities: [prob]
+          }))
+          return html`<${Probabilities} data=${splitData} />`
+        }
+
+        const { probs, content } = completion_probabilities[0]
+        const found = probs.find(p => p.tok_str === msg.content)
+        const pColor = found ? probColor(found.prob) : 'transparent'
+
+        const popoverChildren = html`
+          <div class="prob-set">
+            ${probs.map((p, index) => {
+          return html`
+                <div
+                  key=${index}
+                  title=${`prob: ${p.prob}`}
+                  style=${{
+              padding: '0.3em',
+              backgroundColor: p.tok_str === content ? probColor(p.prob) : 'transparent'
+            }}
+                >
+                  <span>${p.tok_str}: </span>
+                  <span>${Math.floor(p.prob * 100)}%</span>
+                </div>
+              `
+        })}
+          </div>
+        `
+
+        return html`
+          <${Popover} style=${{ backgroundColor: pColor }} popoverChildren=${popoverChildren}>
+            ${msg.content.match(/\n/gim) ? html`<br />` : msg.content}
+          </>
+        `
+      });
+    }
+
+    // poor mans markdown replacement
+    const Markdownish = (params) => {
+      const md = params.text
+        .replace(/&/g, '&')
+        .replace(/</g, '<')
+        .replace(/>/g, '>')
+        .replace(/(^|\n)#{1,6} ([^\n]*)(?=([^`]*`[^`]*`)*[^`]*$)/g, '$1<h3>$2</h3>')
+        .replace(/\*\*(.*?)\*\*(?=([^`]*`[^`]*`)*[^`]*$)/g, '<strong>$1</strong>')
+        .replace(/__(.*?)__(?=([^`]*`[^`]*`)*[^`]*$)/g, '<strong>$1</strong>')
+        .replace(/\*(.*?)\*(?=([^`]*`[^`]*`)*[^`]*$)/g, '<em>$1</em>')
+        .replace(/_(.*?)_(?=([^`]*`[^`]*`)*[^`]*$)/g, '<em>$1</em>')
+        .replace(/```.*?\n([\s\S]*?)```/g, '<pre><code>$1</code></pre>')
+        .replace(/`(.*?)`/g, '<code>$1</code>')
+        .replace(/\n/gim, '<br />');
+      return html`<span dangerouslySetInnerHTML=${{ __html: md }} />`;
+    };
+
+    const ModelGenerationInfo = (params) => {
+      if (!llamaStats.value) {
+        return html`<span/>`
+      }
+      return html`
+      <span class=generation-statistics>
+          ${llamaStats.value.tokens_predicted} predicted, ${llamaStats.value.tokens_cached} cached, ${llamaStats.value.timings.predicted_per_second.toFixed(2)} tokens per second
+        </span>
+      `
+    }
+
+    // simple popover impl
+    const Popover = (props) => {
+      const isOpen = useSignal(false);
+      const position = useSignal({ top: '0px', left: '0px' });
+      const buttonRef = useRef(null);
+      const popoverRef = useRef(null);
+
+      const togglePopover = () => {
+        if (buttonRef.current) {
+          const rect = buttonRef.current.getBoundingClientRect();
+          position.value = {
+            top: `${rect.bottom + window.scrollY}px`,
+            left: `${rect.left + window.scrollX}px`,
+          };
+        }
+        isOpen.value = !isOpen.value;
+      };
+
+      const handleClickOutside = (event) => {
+        if (popoverRef.current && !popoverRef.current.contains(event.target) && !buttonRef.current.contains(event.target)) {
+          isOpen.value = false;
+        }
+      };
+
+      useEffect(() => {
+        document.addEventListener('mousedown', handleClickOutside);
+        return () => {
+          document.removeEventListener('mousedown', handleClickOutside);
+        };
+      }, []);
+
+      return html`
+        <span style=${props.style} ref=${buttonRef} onClick=${togglePopover} contenteditable="true">${props.children}</span>
+        ${isOpen.value && html`
+          <${Portal} into="#portal">
+            <div
+              ref=${popoverRef}
+              class="popover-content"
+              style=${{
+            top: position.value.top,
+            left: position.value.left,
+          }}
+            >
+              ${props.popoverChildren}
+            </div>
+          </${Portal}>
+        `}
+      `;
+    };
+
+    // Source: preact-portal (https://github.com/developit/preact-portal/blob/master/src/preact-portal.js)
+    /** Redirect rendering of descendants into the given CSS selector */
+    class Portal extends Component {
+      componentDidUpdate(props) {
+        for (let i in props) {
+          if (props[i] !== this.props[i]) {
+            return setTimeout(this.renderLayer);
+          }
+        }
+      }
+
+      componentDidMount() {
+        this.isMounted = true;
+        this.renderLayer = this.renderLayer.bind(this);
+        this.renderLayer();
+      }
+
+      componentWillUnmount() {
+        this.renderLayer(false);
+        this.isMounted = false;
+        if (this.remote && this.remote.parentNode) this.remote.parentNode.removeChild(this.remote);
+      }
+
+      findNode(node) {
+        return typeof node === 'string' ? document.querySelector(node) : node;
+      }
+
+      renderLayer(show = true) {
+        if (!this.isMounted) return;
+
+        // clean up old node if moving bases:
+        if (this.props.into !== this.intoPointer) {
+          this.intoPointer = this.props.into;
+          if (this.into && this.remote) {
+            this.remote = render(html`<${PortalProxy} />`, this.into, this.remote);
+          }
+          this.into = this.findNode(this.props.into);
+        }
+
+        this.remote = render(html`
+          <${PortalProxy} context=${this.context}>
+            ${show && this.props.children || null}
+          </${PortalProxy}>
+        `, this.into, this.remote);
+      }
+
+      render() {
+        return null;
+      }
+    }
+    // high-order component that renders its first child if it exists.
+    // used as a conditional rendering proxy.
+    class PortalProxy extends Component {
+      getChildContext() {
+        return this.props.context;
+      }
+      render({ children }) {
+        return children || null;
+      }
+    }
+
+    function App(props) {
+      return html`
+        <div class="mode-${session.value.type}">
+          <header>
+            <h2>llama.cpp</h2>
+            <div class="dropdown">
+              <button class="dropbtn"><svg width="16" height="16" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"><circle cx="12" cy="12" r="10" stroke-width="2"/></svg></button>
+              <div class="dropdown-content" id="theme-selector">
+                <a href="/">Old UI</a>
+                <a href="#" data-theme="default">Snow Storm</a>
+                <a href="#" data-theme="polarnight">Polar Night</a>
+                <a href="#" data-theme="ketivah">Ketivah</a>
+                <a href="#" data-theme="mangotango">Mango Tango</a>
+                <a href="#" data-theme="playground">Playground</a>
+                <a href="#" data-theme="beeninorder">Been In Order</a>
+              </div>
+            </div>
+          </header>
+
+          <main id="content">
+            <${chatStarted.value ? ChatLog : ConfigForm} />
+          </main>
+
+          <section id="write">
+            <${session.value.type === 'chat' ? MessageInput : CompletionControls} />
+          </section>
+          <footer>
+            <p><${ModelGenerationInfo} /></p>
+            <p>Powered By <a href="https://github.com/ggerganov/llama.cpp#readme" target="_blank">llama.cpp</a> and <a href="https://ggml.ai/" target="_blank">ggml.ai</a></p>
+          </footer>
+        </div>
+      `;
+    }
+
+  document.addEventListener('DOMContentLoaded', function() {
+  var themeSelector = document.getElementById('theme-selector');
+  var themeLinks = themeSelector.querySelectorAll('a[data-theme]');
+
+  themeLinks.forEach(function(link) {
+    link.addEventListener('click', function(event) {
+      event.preventDefault(); // avoid default behaviour
+      var selectedTheme = event.target.getAttribute('data-theme');
+      changeTheme(selectedTheme);
+    });
+  });
+
+  function changeTheme(theme) {
+    document.body.classList.remove('theme-default', 'theme-polarnight', 'theme-ketivah', 'theme-mangotango', 'theme-playground', 'theme-beeninorder');
+    if (theme !== 'default') {
+      document.body.classList.add('theme-' + theme);
+    }
+    localStorage.setItem('selected-theme', theme);
+  }
+
+  // set the selected theme when loading the page
+  var savedTheme = localStorage.getItem('selected-theme');
+  if (savedTheme && savedTheme !== 'default') {
+    document.body.classList.add('theme-' + savedTheme);
+    // update the dropdown if it still exists
+    var dropdown = document.getElementById('theme-selector-dropdown');
+    if (dropdown) {
+      dropdown.value = savedTheme;
+    }
+  }
+});
+
+
+// snapping of the slider to indicate 'disabled'
+document.addEventListener('DOMContentLoaded', (event) => {
+  // define an object that contains snap values and ranges for each slider
+  const snapSettings = {
+    temperature: { snapValue: 1.0, snapRangeMultiplier: 6 },
+    min_p: { snapValue: 0.05, snapRangeMultiplier: 2 },
+    xtc_probability: { snapValue: 0.0, snapRangeMultiplier: 4 },
+    xtc_threshold: { snapValue: 0.5, snapRangeMultiplier: 4 },
+    top_p: { snapValue: 1.0, snapRangeMultiplier: 4 },
+    typical_p: { snapValue: 1.0, snapRangeMultiplier: 4 },
+    repeat_penalty: { snapValue: 1.0, snapRangeMultiplier: 4 },
+    presence_penalty: { snapValue: 0.0, snapRangeMultiplier: 4 },
+    frequency_penalty: { snapValue: 0.0, snapRangeMultiplier: 4 },
+    dry_multiplier: { snapValue: 0.0, snapRangeMultiplier: 4 },
+    dry_base: { snapValue: 1.75, snapRangeMultiplier: 4 },
+  };
+  // add an event listener for each slider
+  Object.keys(snapSettings).forEach(sliderName => {
+    const slider = document.querySelector(`input[name="${sliderName}"]`);
+    const settings = snapSettings[sliderName];
+
+    slider.addEventListener('input', (e) => {
+      let value = parseFloat(e.target.value);
+      const step = parseFloat(e.target.step);
+      const snapRange = step * settings.snapRangeMultiplier;
+      const valueDisplay = document.getElementById(`${e.target.name}-value`);
+
+      if (value >= settings.snapValue - snapRange && value <= settings.snapValue + snapRange) {
+        value = settings.snapValue; // set value to the snap value
+        e.target.value = value; // update the slider value
+      }
+      // update the displayed value
+      if (valueDisplay) {
+        valueDisplay.textContent = value.toFixed(2); // display value with two decimal places
+      }
+    });
+  });
+});
+
+    render(h(App), document.querySelector('#container'));
+
+  </script>
+</head>
+
+<body>
+
+  <div id="container">
+    <input type="file" id="fileInput" accept="image/*" style="display: none;">
+  </div>
+  <div id="portal"></div>
+</body>
+
+</html>
diff --git a/tools/server/public_legacy/index.html b/tools/server/public_legacy/index.html
new file mode 100644
index 00000000..75f39330
--- /dev/null
+++ b/tools/server/public_legacy/index.html
@@ -0,0 +1,1301 @@
+<html>
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1" />
+  <meta name="color-scheme" content="light dark">
+  <title>llama.cpp - chat</title>
+
+  <style>
+    body {
+      font-family: system-ui;
+      font-size: 90%;
+    }
+
+    .grid-container {
+      display: grid;
+      grid-template-columns: auto auto auto;
+      padding: 10px;
+    }
+
+    .grid-item {
+      padding: 5px;
+      /* font-size: 30px; */
+      text-align: center;
+    }
+
+    #container {
+      margin: 0em auto;
+      display: flex;
+      flex-direction: column;
+      justify-content: space-between;
+      height: 100%;
+    }
+
+    main {
+      margin: 3px;
+      display: flex;
+      flex-direction: column;
+      justify-content: space-between;
+      gap: 1em;
+
+      flex-grow: 1;
+      overflow-y: auto;
+
+      border: 1px solid #ccc;
+      border-radius: 5px;
+      padding: 0.5em;
+    }
+
+    h1 {
+      text-align: center;
+    }
+
+    .customlink:link {
+      color: white;
+      background-color: #007aff;
+      font-weight: 600;
+      text-decoration: none;
+      float: right;
+      margin-top: 30px;
+      display: flex;
+      flex-direction: row;
+      gap: 0.5em;
+      justify-content: flex-end;
+      border-radius: 4px;
+      padding: 8px;
+    }
+
+    .customlink:visited {
+      color: white;
+      background-color: #007aff;
+      font-weight: 600;
+      text-decoration: none;
+      float: right;
+      margin-top: 30px;
+      display: flex;
+      flex-direction: row;
+      gap: 0.5em;
+      justify-content: flex-end;
+      padding: 8px;
+    }
+
+    .customlink:hover {
+      color: white;
+      background-color: #0070ee;
+      font-weight: 600;
+      text-decoration: none;
+      float: right;
+      margin-top: 30px;
+      display: flex;
+      flex-direction: row;
+      gap: 0.5em;
+      justify-content: flex-end;
+      padding: 8px;
+    }
+
+    .customlink:active {
+      color: #0070ee;
+      background-color: #80b3ef;
+      font-weight: 600;
+      text-decoration: none;
+      float: right;
+      margin-top: 30px;
+      display: flex;
+      flex-direction: row;
+      gap: 0.5em;
+      justify-content: flex-end;
+      padding: 8px;
+    }
+
+    body {
+      max-width: 600px;
+      min-width: 300px;
+      line-height: 1.2;
+      margin: 0 auto;
+      padding: 0 0.5em;
+    }
+
+    p {
+      overflow-wrap: break-word;
+      word-wrap: break-word;
+      hyphens: auto;
+      margin-top: 0.5em;
+      margin-bottom: 0.5em;
+    }
+
+    #write form {
+      margin: 1em 0 0 0;
+      display: flex;
+      flex-direction: column;
+      gap: 0.5em;
+      align-items: stretch;
+    }
+
+    .message-controls {
+      display: flex;
+      justify-content: flex-end;
+    }
+    .message-controls > div:nth-child(2) {
+      display: flex;
+      flex-direction: column;
+      gap: 0.5em;
+    }
+    .message-controls > div:nth-child(2) > div {
+      display: flex;
+      margin-left: auto;
+      gap: 0.5em;
+    }
+
+    fieldset {
+      border: none;
+      padding: 0;
+      margin: 0;
+    }
+
+    fieldset.two {
+      display: grid;
+      grid-template: "a a";
+      gap: 1em;
+    }
+
+    fieldset.three {
+      display: grid;
+      grid-template: "a a a";
+      gap: 1em;
+    }
+
+    details {
+      border: 1px solid #aaa;
+      border-radius: 4px;
+      padding: 0.5em 0.5em 0;
+      margin-top: 0.5em;
+    }
+
+    summary {
+      font-weight: bold;
+      margin: -0.5em -0.5em 0;
+      padding: 0.5em;
+      cursor: pointer;
+    }
+
+    details[open] {
+      padding: 0.5em;
+    }
+
+    .prob-set {
+      padding: 0.3em;
+      border-bottom: 1px solid #ccc;
+    }
+
+    .popover-content {
+      position: absolute;
+      background-color: white;
+      padding: 0.2em;
+      box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
+    }
+
+    textarea {
+      padding: 5px;
+      flex-grow: 1;
+      width: 100%;
+    }
+
+    pre code {
+      display: block;
+      background-color: #222;
+      color: #ddd;
+    }
+
+    code {
+      font-family: monospace;
+      padding: 0.1em 0.3em;
+      border-radius: 3px;
+    }
+
+    fieldset label {
+      margin: 0.5em 0;
+      display: block;
+    }
+
+    fieldset label.slim {
+      margin: 0 0.5em;
+      display: inline;
+    }
+
+    header,
+    footer {
+      text-align: center;
+    }
+
+    footer {
+      font-size: 80%;
+      color: #888;
+    }
+
+    .mode-chat textarea[name=prompt] {
+      height: 4.5em;
+    }
+
+    .mode-completion textarea[name=prompt] {
+      height: 10em;
+    }
+
+    [contenteditable] {
+      display: inline-block;
+      white-space: pre-wrap;
+      outline: 0px solid transparent;
+    }
+
+    @keyframes loading-bg-wipe {
+      0% {
+        background-position: 0%;
+      }
+
+      100% {
+        background-position: 100%;
+      }
+    }
+
+    .loading {
+      --loading-color-1: #eeeeee00;
+      --loading-color-2: #eeeeeeff;
+      background-size: 50% 100%;
+      background-image: linear-gradient(90deg, var(--loading-color-1), var(--loading-color-2), var(--loading-color-1));
+      animation: loading-bg-wipe 2s linear infinite;
+    }
+
+    @media (prefers-color-scheme: dark) {
+      .loading {
+        --loading-color-1: #22222200;
+        --loading-color-2: #222222ff;
+      }
+
+      .popover-content {
+        background-color: black;
+      }
+    }
+  </style>
+
+  <script type="module">
+    import {
+      html, h, signal, effect, computed, render, useSignal, useEffect, useRef, Component
+    } from './index.js';
+
+    import { llama } from './completion.js';
+    import { SchemaConverter } from './json-schema-to-grammar.mjs';
+
+    let selected_image = false;
+    var slot_id = -1;
+
+    const session = signal({
+      prompt: "This is a conversation between User and Llama, a friendly chatbot. Llama is helpful, kind, honest, good at writing, and never fails to answer any requests immediately and with precision.",
+      template: "{{prompt}}\n\n{{history}}\n{{char}}:",
+      historyTemplate: "{{name}}: {{message}}",
+      transcript: [],
+      type: "chat",  // "chat" | "completion"
+      char: "Llama",
+      user: "User",
+      image_selected: ''
+    })
+
+    const params = signal({
+      n_predict: 400,
+      temperature: 0.7,
+      repeat_last_n: 256, // 0 = disable penalty, -1 = context size
+      repeat_penalty: 1.18, // 1.0 = disabled
+      dry_multiplier: 0.0, // 0.0 = disabled, 0.8 works well
+      dry_base: 1.75,     // 0.0 = disabled
+      dry_allowed_length: 2, // tokens extending repetitions beyond this receive penalty, 2 works well
+      dry_penalty_last_n: -1, // how many tokens to scan for repetitions (0 = disable penalty, -1 = context size)
+      top_k: 40, // <= 0 to use vocab size
+      top_p: 0.95, // 1.0 = disabled
+      min_p: 0.05, // 0 = disabled
+      xtc_probability: 0.0, // 0 = disabled;
+      xtc_threshold: 0.1, // > 0.5 disables XTC;
+      typical_p: 1.0, // 1.0 = disabled
+      presence_penalty: 0.0, // 0.0 = disabled
+      frequency_penalty: 0.0, // 0.0 = disabled
+      mirostat: 0, // 0/1/2
+      mirostat_tau: 5, // target entropy
+      mirostat_eta: 0.1, // learning rate
+      grammar: '',
+      n_probs: 0, // no completion_probabilities,
+      min_keep: 0, // min probs from each sampler,
+      image_data: [],
+      cache_prompt: true,
+      api_key: ''
+    })
+
+    /* START: Support for storing prompt templates and parameters in browsers LocalStorage */
+
+    const local_storage_storageKey = "llamacpp_server_local_storage";
+
+    function local_storage_setDataFromObject(tag, content) {
+      localStorage.setItem(local_storage_storageKey + '/' + tag, JSON.stringify(content));
+    }
+
+    function local_storage_setDataFromRawText(tag, content) {
+      localStorage.setItem(local_storage_storageKey + '/' + tag, content);
+    }
+
+    function local_storage_getDataAsObject(tag) {
+      const item = localStorage.getItem(local_storage_storageKey + '/' + tag);
+      if (!item) {
+        return null;
+      } else {
+        return JSON.parse(item);
+      }
+    }
+
+    function local_storage_getDataAsRawText(tag) {
+      const item = localStorage.getItem(local_storage_storageKey + '/' + tag);
+      if (!item) {
+        return null;
+      } else {
+        return item;
+      }
+    }
+
+    // create a container for user templates and settings
+
+    const savedUserTemplates = signal({})
+    const selectedUserTemplate = signal({ name: '', template: { session: {}, params: {} } })
+
+    // let's import locally saved templates and settings if there are any
+    // user templates and settings are stored in one object
+    // in form of { "templatename": "templatedata" } and { "settingstemplatename":"settingsdata" }
+
+    console.log('Importing saved templates')
+
+    let importedTemplates = local_storage_getDataAsObject('user_templates')
+
+    if (importedTemplates) {
+      // saved templates were successfully imported.
+
+      console.log('Processing saved templates and updating default template')
+      params.value = { ...params.value, image_data: [] };
+
+      //console.log(importedTemplates);
+      savedUserTemplates.value = importedTemplates;
+
+      //override default template
+      savedUserTemplates.value.default = { session: session.value, params: params.value }
+      local_storage_setDataFromObject('user_templates', savedUserTemplates.value)
+    } else {
+      // no saved templates detected.
+
+      console.log('Initializing LocalStorage and saving default template')
+
+      savedUserTemplates.value = { "default": { session: session.value, params: params.value } }
+      local_storage_setDataFromObject('user_templates', savedUserTemplates.value)
+    }
+
+    function userTemplateResetToDefault() {
+      console.log('Resetting template to default')
+      selectedUserTemplate.value.name = 'default';
+      selectedUserTemplate.value.data = savedUserTemplates.value['default'];
+    }
+
+    function userTemplateApply(t) {
+      session.value = t.data.session;
+      session.value = { ...session.value, image_selected: '' };
+      params.value = t.data.params;
+      params.value = { ...params.value, image_data: [] };
+    }
+
+    function userTemplateResetToDefaultAndApply() {
+      userTemplateResetToDefault()
+      userTemplateApply(selectedUserTemplate.value)
+    }
+
+    function userTemplateLoadAndApplyAutosaved() {
+      // get autosaved last used template
+      let lastUsedTemplate = local_storage_getDataAsObject('user_templates_last')
+
+      if (lastUsedTemplate) {
+
+        console.log('Autosaved template found, restoring')
+
+        selectedUserTemplate.value = lastUsedTemplate
+      }
+      else {
+
+        console.log('No autosaved template found, using default template')
+        // no autosaved last used template was found, so load from default.
+
+        userTemplateResetToDefault()
+      }
+
+      console.log('Applying template')
+      // and update internal data from templates
+
+      userTemplateApply(selectedUserTemplate.value)
+    }
+
+    //console.log(savedUserTemplates.value)
+    //console.log(selectedUserTemplate.value)
+
+    function userTemplateAutosave() {
+      console.log('Template Autosave...')
+      if (selectedUserTemplate.value.name == 'default') {
+        // we don't want to save over default template, so let's create a new one
+        let newTemplateName = 'UserTemplate-' + Date.now().toString()
+        let newTemplate = { 'name': newTemplateName, 'data': { 'session': session.value, 'params': params.value } }
+
+        console.log('Saving as ' + newTemplateName)
+
+        // save in the autosave slot
+        local_storage_setDataFromObject('user_templates_last', newTemplate)
+
+        // and load it back and apply
+        userTemplateLoadAndApplyAutosaved()
+      } else {
+        local_storage_setDataFromObject('user_templates_last', { 'name': selectedUserTemplate.value.name, 'data': { 'session': session.value, 'params': params.value } })
+      }
+    }
+
+    console.log('Checking for autosaved last used template')
+    userTemplateLoadAndApplyAutosaved()
+
+    /* END: Support for storing prompt templates and parameters in browsers LocalStorage */
+
+    const tts = window.speechSynthesis;
+    const ttsVoice = signal(null)
+
+    const llamaStats = signal(null)
+    const controller = signal(null)
+
+    // currently generating a completion?
+    const generating = computed(() => controller.value != null)
+
+    // has the user started a chat?
+    const chatStarted = computed(() => session.value.transcript.length > 0)
+
+    const transcriptUpdate = (transcript) => {
+      session.value = {
+        ...session.value,
+        transcript
+      }
+    }
+
+    // simple template replace
+    const template = (str, extraSettings) => {
+      let settings = session.value;
+      if (extraSettings) {
+        settings = { ...settings, ...extraSettings };
+      }
+      return String(str).replaceAll(/\{\{(.*?)\}\}/g, (_, key) => template(settings[key]));
+    }
+
+    async function runLlama(prompt, llamaParams, char) {
+      const currentMessages = [];
+      const history = session.value.transcript;
+      if (controller.value) {
+        throw new Error("already running");
+      }
+      controller.value = new AbortController();
+      for await (const chunk of llama(prompt, llamaParams, { controller: controller.value, api_url: new URL('.', document.baseURI).href })) {
+        const data = chunk.data;
+
+        if (data.stop) {
+          while (
+            currentMessages.length > 0 &&
+            currentMessages[currentMessages.length - 1].content.match(/\n$/) != null
+          ) {
+            currentMessages.pop();
+          }
+          transcriptUpdate([...history, [char, currentMessages]])
+          console.log("Completion finished: '", currentMessages.map(msg => msg.content).join(''), "', summary: ", data);
+        } else {
+          currentMessages.push(data);
+          slot_id = data.slot_id;
+          if (selected_image && !data.multimodal) {
+            alert("The server was not compiled for multimodal or the model projector can't be loaded.");
+            return;
+          }
+          transcriptUpdate([...history, [char, currentMessages]])
+        }
+
+        if (data.timings) {
+          llamaStats.value = data;
+        }
+      }
+
+      controller.value = null;
+    }
+
+    // send message to server
+    const chat = async (msg) => {
+      if (controller.value) {
+        console.log('already running...');
+        return;
+      }
+
+      transcriptUpdate([...session.value.transcript, ["{{user}}", msg]])
+
+      let prompt = template(session.value.template, {
+        message: msg,
+        history: session.value.transcript.flatMap(
+          ([name, data]) =>
+            template(
+              session.value.historyTemplate,
+              {
+                name,
+                message: Array.isArray(data) ?
+                  data.map(msg => msg.content).join('').replace(/^\s/, '') :
+                  data,
+              }
+            )
+        ).join("\n"),
+      });
+      if (selected_image) {
+        prompt = `A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER:[img-10]${msg}\nASSISTANT:`;
+      }
+      await runLlama(prompt, {
+        ...params.value,
+        slot_id: slot_id,
+        stop: ["</s>", template("{{char}}:"), template("{{user}}:")],
+      }, "{{char}}");
+    }
+
+    const runCompletion = () => {
+      if (controller.value) {
+        console.log('already running...');
+        return;
+      }
+      const { prompt } = session.value;
+      transcriptUpdate([...session.value.transcript, ["", prompt]]);
+      runLlama(prompt, {
+        ...params.value,
+        slot_id: slot_id,
+        stop: [],
+      }, "").finally(() => {
+        session.value.prompt = session.value.transcript.map(([_, data]) =>
+          Array.isArray(data) ? data.map(msg => msg.content).join('') : data
+        ).join('');
+        session.value.transcript = [];
+      })
+    }
+
+    const stop = (e) => {
+      e.preventDefault();
+      if (controller.value) {
+        controller.value.abort();
+        controller.value = null;
+      }
+    }
+
+    const reset = (e) => {
+      stop(e);
+      transcriptUpdate([]);
+    }
+
+    const uploadImage = (e) => {
+      e.preventDefault();
+      document.getElementById("fileInput").click();
+      document.getElementById("fileInput").addEventListener("change", function (event) {
+        const selectedFile = event.target.files[0];
+        if (selectedFile) {
+          const reader = new FileReader();
+          reader.onload = function () {
+            const image_data = reader.result;
+            session.value = { ...session.value, image_selected: image_data };
+            params.value = {
+              ...params.value, image_data: [
+                { data: image_data.replace(/data:image\/[^;]+;base64,/, ''), id: 10 }]
+            }
+          };
+          selected_image = true;
+          reader.readAsDataURL(selectedFile);
+        }
+      });
+    }
+
+    const SpeechRecognition = window.SpeechRecognition || window.webkitSpeechRecognition;
+    const talkRecognition = SpeechRecognition ? new SpeechRecognition() : null;
+    function MessageInput() {
+      const message = useSignal("");
+
+      const talkActive = useSignal(false);
+      const sendOnTalk = useSignal(false);
+      const talkStop = (e) => {
+        if (e) e.preventDefault();
+
+        talkActive.value = false;
+        talkRecognition?.stop();
+      }
+      const talk = (e) => {
+        e.preventDefault();
+
+        if (talkRecognition)
+          talkRecognition.start();
+        else
+          alert("Speech recognition is not supported by this browser.");
+      }
+      if(talkRecognition) {
+        talkRecognition.onstart = () => {
+          talkActive.value = true;
+        }
+        talkRecognition.onresult = (e) => {
+          if (event.results.length > 0) {
+            message.value = event.results[0][0].transcript;
+            if (sendOnTalk.value) {
+              submit(e);
+            }
+          }
+        }
+        talkRecognition.onspeechend = () => {
+          talkStop();
+        }
+      }
+
+      const ttsVoices = useSignal(tts?.getVoices() || []);
+      const ttsVoiceDefault = computed(() => ttsVoices.value.find(v => v.default));
+      if (tts) {
+        tts.onvoiceschanged = () => {
+          ttsVoices.value = tts.getVoices();
+        }
+      }
+
+      const submit = (e) => {
+        stop(e);
+        chat(message.value);
+        message.value = "";
+      }
+
+      const enterSubmits = (event) => {
+        if (event.which === 13 && !event.shiftKey) {
+          submit(event);
+        }
+      }
+
+      return html`
+        <form onsubmit=${submit}>
+          <div>
+            <textarea
+               className=${generating.value ? "loading" : null}
+               oninput=${(e) => message.value = e.target.value}
+               onkeypress=${enterSubmits}
+               placeholder="Say something..."
+               rows=2
+               type="text"
+               value="${message}"
+            />
+          </div>
+          <div class="message-controls">
+            <div> </div>
+            <div>
+              <div>
+                <button type="submit" disabled=${generating.value || talkActive.value}>Send</button>
+                <button disabled=${generating.value || talkActive.value} onclick=${uploadImage}>Upload Image</button>
+                <button onclick=${stop} disabled=${!generating.value}>Stop</button>
+                <button onclick=${reset}>Reset</button>
+              </div>
+              <div>
+                <a href="#" style="cursor: help;" title="Help" onclick=${e => {
+                  e.preventDefault();
+                  alert(`STT supported by your browser: ${SpeechRecognition ? 'Yes' : 'No'}\n` +
+                  `(TTS and speech recognition are not provided by llama.cpp)\n` +
+                  `Note: STT requires HTTPS to work.`);
+                }}>[?]</a>
+                <button disabled=${generating.value} onclick=${talkActive.value ? talkStop : talk}>${talkActive.value ? "Stop Talking" : "Talk"}</button>
+                <div>
+                  <input type="checkbox" id="send-on-talk" name="send-on-talk" checked="${sendOnTalk}" onchange=${(e) => sendOnTalk.value = e.target.checked} />
+                  <label for="send-on-talk" style="line-height: initial;">Send after talking</label>
+                </div>
+              </div>
+              <div>
+                <a href="#" style="cursor: help;" title="Help" onclick=${e => {
+                  e.preventDefault();
+                  alert(`TTS supported by your browser: ${tts ? 'Yes' : 'No'}\n(TTS and speech recognition are not provided by llama.cpp)`);
+                }}>[?]</a>
+                <label for="tts-voices" style="line-height: initial;">Bot Voice:</label>
+                <select id="tts-voices" name="tts-voices" onchange=${(e) => ttsVoice.value = e.target.value} style="max-width: 100px;">
+                  <option value="" selected="${!ttsVoice.value}">None</option>
+                  ${[
+                    ...(ttsVoiceDefault.value ? [ttsVoiceDefault.value] : []),
+                    ...ttsVoices.value.filter(v => !v.default),
+                  ].map(
+                    v => html`<option value="${v.name}" selected="${ttsVoice.value === v.name}">${v.name} (${v.lang}) ${v.default ? '(default)' : ''}</option>`
+                  )}
+                </select>
+              </div>
+            </div>
+          </div>
+        </form>
+      `
+    }
+
+    function CompletionControls() {
+      const submit = (e) => {
+        stop(e);
+        runCompletion();
+      }
+      return html`
+        <div>
+          <button onclick=${submit} type="button" disabled=${generating.value}>Start</button>
+          <button onclick=${stop} disabled=${!generating.value}>Stop</button>
+          <button onclick=${reset}>Reset</button>
+        </div>`;
+    }
+
+    const ChatLog = (props) => {
+      const messages = session.value.transcript;
+      const container = useRef(null)
+
+      useEffect(() => {
+        // scroll to bottom (if needed)
+        const parent = container.current.parentElement;
+        if (parent && parent.scrollHeight <= parent.scrollTop + parent.offsetHeight + 300) {
+          parent.scrollTo(0, parent.scrollHeight)
+        }
+      }, [messages])
+
+      const ttsChatLineActiveIx = useSignal(undefined);
+      const ttsChatLine = (e, ix, msg) => {
+        if (e) e.preventDefault();
+
+        if (!tts || !ttsVoice.value || !('SpeechSynthesisUtterance' in window)) return;
+
+        const ttsVoices = tts.getVoices();
+        const voice = ttsVoices.find(v => v.name === ttsVoice.value);
+        if (!voice) return;
+
+        if (ttsChatLineActiveIx.value !== undefined) {
+          tts.cancel();
+          if (ttsChatLineActiveIx.value === ix) {
+            ttsChatLineActiveIx.value = undefined;
+            return;
+          }
+        }
+
+        ttsChatLineActiveIx.value = ix;
+        let ttsUtter = new SpeechSynthesisUtterance(msg);
+        ttsUtter.voice = voice;
+        ttsUtter.onend = e => {
+          ttsChatLineActiveIx.value = undefined;
+        };
+        tts.speak(ttsUtter);
+      }
+
+      const isCompletionMode = session.value.type === 'completion'
+
+      // Try play the last bot message
+      const lastCharChatLinesIxs = useSignal([]);
+      const lastCharChatLinesIxsOld = useSignal([]);
+      useEffect(() => {
+        if (
+          !isCompletionMode
+          && lastCharChatLinesIxs.value.length !== lastCharChatLinesIxsOld.value.length
+          && !generating.value
+        ) {
+          const ix = lastCharChatLinesIxs.value[lastCharChatLinesIxs.value.length - 1];
+          if (ix !== undefined) {
+            const msg = messages[ix];
+            ttsChatLine(null, ix, Array.isArray(msg) ? msg[1].map(m => m.content).join('') : msg);
+          }
+
+          lastCharChatLinesIxsOld.value = structuredClone(lastCharChatLinesIxs.value);
+        }
+      }, [generating.value]);
+
+      const chatLine = ([user, data], index) => {
+        let message
+        const isArrayMessage = Array.isArray(data);
+        const text = isArrayMessage ?
+            data.map(msg => msg.content).join('') :
+            data;
+        if (params.value.n_probs > 0 && isArrayMessage) {
+          message = html`<${Probabilities} data=${data} />`
+        } else {
+          message = isCompletionMode ?
+            text :
+            html`<${Markdownish} text=${template(text)} />`
+        }
+
+        const fromBot = user && user === '{{char}}';
+        if (fromBot && !lastCharChatLinesIxs.value.includes(index))
+          lastCharChatLinesIxs.value.push(index);
+
+        if (user) {
+          return html`
+          <div>
+            <p key=${index}><strong>${template(user)}:</strong> ${message}</p>
+            ${
+              fromBot && ttsVoice.value
+              && html`<button disabled=${generating.value} onclick=${e => ttsChatLine(e, index, text)} aria-label=${ttsChatLineActiveIx.value === index ? 'Pause' : 'Play'}>${ ttsChatLineActiveIx.value === index ? 'â¸ï¸' : 'â¶ï¸' }</div>`
+            }
+          </div>
+          `;
+        } else {
+          return isCompletionMode ?
+            html`<span key=${index}>${message}</span>` :
+            html`<div><p key=${index}>${message}</p></div>`
+        }
+      };
+
+      const handleCompletionEdit = (e) => {
+        session.value.prompt = e.target.innerText;
+        session.value.transcript = [];
+      }
+
+      return html`
+        <div id="chat" ref=${container} key=${messages.length}>
+          <img style="width: 60%;${!session.value.image_selected ? `display: none;` : ``}" src="${session.value.image_selected}"/>
+          <span contenteditable=${isCompletionMode} ref=${container} oninput=${handleCompletionEdit}>
+            ${messages.flatMap(chatLine)}
+          </span>
+        </div>`;
+    };
+
+    const ConfigForm = (props) => {
+      const updateSession = (el) => session.value = { ...session.value, [el.target.name]: el.target.value }
+      const updateParams = (el) => params.value = { ...params.value, [el.target.name]: el.target.value }
+      const updateParamsFloat = (el) => params.value = { ...params.value, [el.target.name]: parseFloat(el.target.value) }
+      const updateParamsInt = (el) => params.value = { ...params.value, [el.target.name]: Math.floor(parseFloat(el.target.value)) }
+      const updateParamsBool = (el) => params.value = { ...params.value, [el.target.name]: el.target.checked }
+
+      const grammarJsonSchemaPropOrder = signal('')
+      const updateGrammarJsonSchemaPropOrder = (el) => grammarJsonSchemaPropOrder.value = el.target.value
+      const convertJSONSchemaGrammar = async () => {
+        try {
+          let schema = JSON.parse(params.value.grammar)
+          const converter = new SchemaConverter({
+            prop_order: grammarJsonSchemaPropOrder.value
+              .split(',')
+              .reduce((acc, cur, i) => ({ ...acc, [cur.trim()]: i }), {}),
+            allow_fetch: true,
+          })
+          schema = await converter.resolveRefs(schema, 'input')
+          converter.visit(schema, '')
+          params.value = {
+            ...params.value,
+            grammar: converter.formatGrammar(),
+          }
+        } catch (e) {
+          alert(`Convert failed: ${e.message}`)
+        }
+      }
+
+      const FloatField = ({ label, max, min, name, step, value }) => {
+        return html`
+          <div>
+            <label for="${name}">${label}</label>
+            <input type="range" id="${name}" min="${min}" max="${max}" step="${step}" name="${name}" value="${value}" oninput=${updateParamsFloat} />
+            <span>${value}</span>
+          </div>
+        `
+      };
+
+      const IntField = ({ label, max, min, name, value }) => {
+        return html`
+          <div>
+            <label for="${name}">${label}</label>
+            <input type="range" id="${name}" min="${min}" max="${max}" name="${name}" value="${value}" oninput=${updateParamsInt} />
+            <span>${value}</span>
+          </div>
+        `
+      };
+
+      const BoolField = ({ label, name, value }) => {
+        return html`
+          <div>
+            <label for="${name}">${label}</label>
+            <input type="checkbox" id="${name}" name="${name}" checked="${value}" onclick=${updateParamsBool} />
+          </div>
+        `
+      };
+
+      const userTemplateReset = (e) => {
+        e.preventDefault();
+        userTemplateResetToDefaultAndApply()
+      }
+
+      const UserTemplateResetButton = () => {
+        if (selectedUserTemplate.value.name == 'default') {
+          return html`
+            <button disabled>Using default template</button>
+          `
+        }
+
+        return html`
+          <button onclick=${userTemplateReset}>Reset all to default</button>
+        `
+      };
+
+      useEffect(() => {
+        // autosave template on every change
+        userTemplateAutosave()
+      }, [session.value, params.value])
+
+      const GrammarControl = () => (
+        html`
+          <div>
+            <label for="template">Grammar</label>
+            <textarea id="grammar" name="grammar" placeholder="Use gbnf or JSON Schema+convert" value="${params.value.grammar}" rows=4 oninput=${updateParams}/>
+            <input type="text" name="prop-order" placeholder="order: prop1,prop2,prop3" oninput=${updateGrammarJsonSchemaPropOrder} />
+            <button type="button" onclick=${convertJSONSchemaGrammar}>Convert JSON Schema</button>
+          </div>
+          `
+      );
+
+      const PromptControlFieldSet = () => (
+        html`
+        <fieldset>
+          <div>
+            <label htmlFor="prompt">Prompt</label>
+            <textarea type="text" name="prompt" value="${session.value.prompt}" oninput=${updateSession}/>
+          </div>
+        </fieldset>
+        `
+      );
+
+      const ChatConfigForm = () => (
+        html`
+          ${PromptControlFieldSet()}
+
+          <fieldset class="two">
+            <div>
+              <label for="user">User name</label>
+              <input type="text" name="user" value="${session.value.user}" oninput=${updateSession} />
+            </div>
+
+            <div>
+              <label for="bot">Bot name</label>
+              <input type="text" name="char" value="${session.value.char}" oninput=${updateSession} />
+            </div>
+          </fieldset>
+
+          <fieldset>
+            <div>
+              <label for="template">Prompt template</label>
+              <textarea id="template" name="template" value="${session.value.template}" rows=4 oninput=${updateSession}/>
+            </div>
+
+            <div>
+              <label for="template">Chat history template</label>
+              <textarea id="template" name="historyTemplate" value="${session.value.historyTemplate}" rows=1 oninput=${updateSession}/>
+            </div>
+            ${GrammarControl()}
+          </fieldset>
+      `
+      );
+
+      const CompletionConfigForm = () => (
+        html`
+          ${PromptControlFieldSet()}
+          <fieldset>${GrammarControl()}</fieldset>
+        `
+      );
+
+      return html`
+        <form>
+          <fieldset class="two">
+            <${UserTemplateResetButton}/>
+            <div>
+              <label class="slim"><input type="radio" name="type" value="chat" checked=${session.value.type === "chat"} oninput=${updateSession} /> Chat</label>
+              <label class="slim"><input type="radio" name="type" value="completion" checked=${session.value.type === "completion"} oninput=${updateSession} /> Completion</label>
+            </div>
+          </fieldset>
+
+          ${session.value.type === 'chat' ? ChatConfigForm() : CompletionConfigForm()}
+
+          <fieldset class="two">
+            ${IntField({ label: "Predictions", max: 2048, min: -1, name: "n_predict", value: params.value.n_predict })}
+            ${FloatField({ label: "Temperature", max: 2.0, min: 0.0, name: "temperature", step: 0.01, value: params.value.temperature })}
+            ${FloatField({ label: "Penalize repeat sequence", max: 2.0, min: 0.0, name: "repeat_penalty", step: 0.01, value: params.value.repeat_penalty })}
+            ${IntField({ label: "Consider N tokens for penalize", max: 2048, min: 0, name: "repeat_last_n", value: params.value.repeat_last_n })}
+            ${IntField({ label: "Top-K sampling", max: 100, min: -1, name: "top_k", value: params.value.top_k })}
+            ${FloatField({ label: "Top-P sampling", max: 1.0, min: 0.0, name: "top_p", step: 0.01, value: params.value.top_p })}
+            ${FloatField({ label: "Min-P sampling", max: 1.0, min: 0.0, name: "min_p", step: 0.01, value: params.value.min_p })}
+          </fieldset>
+          <details>
+            <summary>More options</summary>
+            <fieldset class="two">
+              ${FloatField({ label: "Typical P", max: 1.0, min: 0.0, name: "typical_p", step: 0.01, value: params.value.typical_p })}
+              ${FloatField({ label: "Presence penalty", max: 1.0, min: 0.0, name: "presence_penalty", step: 0.01, value: params.value.presence_penalty })}
+              ${FloatField({ label: "Frequency penalty", max: 1.0, min: 0.0, name: "frequency_penalty", step: 0.01, value: params.value.frequency_penalty })}
+              ${FloatField({ label: "DRY Penalty Multiplier", max: 5.0, min: 0.0, name: "dry_multiplier", step: 0.01, value: params.value.dry_multiplier })}
+              ${FloatField({ label: "DRY Base", max: 3.0, min: 1.0, name: "dry_base", step: 0.01, value: params.value.dry_base })}
+              ${IntField({ label: "DRY Allowed Length", max: 10, min: 2, step: 1, name: "dry_allowed_length", value: params.value.dry_allowed_length })}
+              ${IntField({ label: "DRY Penalty Last N", max: 2048, min: -1, step: 16, name: "dry_penalty_last_n", value: params.value.dry_penalty_last_n })}
+              ${FloatField({ label: "XTC probability", max: 1.0, min: 0.0, name: "xtc_probability", step: 0.01, value: params.value.xtc_probability })}
+              ${FloatField({ label: "XTC threshold", max: 0.5, min: 0.0, name: "xtc_threshold", step: 0.01, value: params.value.xtc_threshold })}
+            </fieldset>
+            <hr />
+            <fieldset class="three">
+              <div>
+                <label><input type="radio" name="mirostat" value="0" checked=${params.value.mirostat == 0} oninput=${updateParamsInt} /> no Mirostat</label>
+                <label><input type="radio" name="mirostat" value="1" checked=${params.value.mirostat == 1} oninput=${updateParamsInt} /> Mirostat v1</label>
+                <label><input type="radio" name="mirostat" value="2" checked=${params.value.mirostat == 2} oninput=${updateParamsInt} /> Mirostat v2</label>
+              </div>
+              ${FloatField({ label: "Mirostat tau", max: 10.0, min: 0.0, name: "mirostat_tau", step: 0.01, value: params.value.mirostat_tau })}
+              ${FloatField({ label: "Mirostat eta", max: 1.0, min: 0.0, name: "mirostat_eta", step: 0.01, value: params.value.mirostat_eta })}
+            </fieldset>
+            <fieldset>
+              ${IntField({ label: "Show Probabilities", max: 10, min: 0, name: "n_probs", value: params.value.n_probs })}
+            </fieldset>
+            <fieldset>
+              ${IntField({ label: "Min Probabilities from each Sampler", max: 10, min: 0, name: "min_keep", value: params.value.min_keep })}
+            </fieldset>
+            <fieldset>
+              <label for="api_key">API Key</label>
+              <input type="text" name="api_key" value="${params.value.api_key}" placeholder="Enter API key" oninput=${updateParams} />
+            </fieldset>
+          </details>
+        </form>
+      `
+    }
+
+    const probColor = (p) => {
+      const r = Math.floor(192 * (1 - p));
+      const g = Math.floor(192 * p);
+      return `rgba(${r},${g},0,0.3)`;
+    }
+
+    const Probabilities = (params) => {
+      return params.data.map(msg => {
+        const { completion_probabilities } = msg;
+        if (
+          !completion_probabilities ||
+          completion_probabilities.length === 0
+        ) return msg.content
+
+        if (completion_probabilities.length > 1) {
+          // Not for byte pair
+          if (completion_probabilities[0].content.startsWith('byte: \\')) return msg.content
+
+          const splitData = completion_probabilities.map(prob => ({
+            content: prob.content,
+            completion_probabilities: [prob]
+          }))
+          return html`<${Probabilities} data=${splitData} />`
+        }
+
+        const { probs, content } = completion_probabilities[0]
+        const found = probs.find(p => p.tok_str === msg.content)
+        const pColor = found ? probColor(found.prob) : 'transparent'
+
+        const popoverChildren = html`
+          <div class="prob-set">
+            ${probs.map((p, index) => {
+          return html`
+                <div
+                  key=${index}
+                  title=${`prob: ${p.prob}`}
+                  style=${{
+              padding: '0.3em',
+              backgroundColor: p.tok_str === content ? probColor(p.prob) : 'transparent'
+            }}
+                >
+                  <span>${p.tok_str}: </span>
+                  <span>${Math.floor(p.prob * 100)}%</span>
+                </div>
+              `
+        })}
+          </div>
+        `
+
+        return html`
+          <${Popover} style=${{ backgroundColor: pColor }} popoverChildren=${popoverChildren}>
+            ${msg.content.match(/\n/gim) ? html`<br />` : msg.content}
+          </>
+        `
+      });
+    }
+
+    // poor mans markdown replacement
+    const Markdownish = (params) => {
+      const chunks = params.text.split('```');
+
+      for (let i = 0; i < chunks.length; i++) {
+        if (i % 2 === 0) { // outside code block
+          chunks[i] = chunks[i]
+          .replace(/&/g, '&')
+          .replace(/</g, '<')
+          .replace(/>/g, '>')
+          .replace(/(^|\n)#{1,6} ([^\n]*)(?=([^`]*`[^`]*`)*[^`]*$)/g, '$1<h3>$2</h3>')
+          .replace(/\*\*(.*?)\*\*(?=([^`]*`[^`]*`)*[^`]*$)/g, '<strong>$1</strong>')
+          .replace(/__(.*?)__(?=([^`]*`[^`]*`)*[^`]*$)/g, '<strong>$1</strong>')
+          .replace(/\*(.*?)\*(?=([^`]*`[^`]*`)*[^`]*$)/g, '<em>$1</em>')
+          .replace(/_(.*?)_(?=([^`]*`[^`]*`)*[^`]*$)/g, '<em>$1</em>')
+          .replace(/```.*?\n([\s\S]*?)```/g, '<pre><code>$1</code></pre>')
+          .replace(/`(.*?)`/g, '<code>$1</code>')
+          .replace(/\n/gim, '<br />');
+        } else { // inside code block
+          chunks[i] = `<pre><code>${chunks[i]}</code></pre>`;
+        }
+      }
+
+      const restoredText = chunks.join('');
+
+      return html`<span dangerouslySetInnerHTML=${{ __html: restoredText }} />`;
+    };
+
+    const ModelGenerationInfo = (params) => {
+      if (!llamaStats.value) {
+        return html`<span/>`
+      }
+      return html`
+        <span>
+          ${llamaStats.value.tokens_predicted} predicted, ${llamaStats.value.tokens_cached} cached, ${llamaStats.value.timings.predicted_per_token_ms.toFixed()}ms per token, ${llamaStats.value.timings.predicted_per_second.toFixed(2)} tokens per second
+        </span>
+      `
+    }
+
+
+    // simple popover impl
+    const Popover = (props) => {
+      const isOpen = useSignal(false);
+      const position = useSignal({ top: '0px', left: '0px' });
+      const buttonRef = useRef(null);
+      const popoverRef = useRef(null);
+
+      const togglePopover = () => {
+        if (buttonRef.current) {
+          const rect = buttonRef.current.getBoundingClientRect();
+          position.value = {
+            top: `${rect.bottom + window.scrollY}px`,
+            left: `${rect.left + window.scrollX}px`,
+          };
+        }
+        isOpen.value = !isOpen.value;
+      };
+
+      const handleClickOutside = (event) => {
+        if (popoverRef.current && !popoverRef.current.contains(event.target) && !buttonRef.current.contains(event.target)) {
+          isOpen.value = false;
+        }
+      };
+
+      useEffect(() => {
+        document.addEventListener('mousedown', handleClickOutside);
+        return () => {
+          document.removeEventListener('mousedown', handleClickOutside);
+        };
+      }, []);
+
+      return html`
+        <span style=${props.style} ref=${buttonRef} onClick=${togglePopover}>${props.children}</span>
+        ${isOpen.value && html`
+          <${Portal} into="#portal">
+            <div
+              ref=${popoverRef}
+              class="popover-content"
+              style=${{
+            top: position.value.top,
+            left: position.value.left,
+          }}
+            >
+              ${props.popoverChildren}
+            </div>
+          </${Portal}>
+        `}
+      `;
+    };
+
+    // Source: preact-portal (https://github.com/developit/preact-portal/blob/master/src/preact-portal.js)
+    /** Redirect rendering of descendants into the given CSS selector */
+    class Portal extends Component {
+      componentDidUpdate(props) {
+        for (let i in props) {
+          if (props[i] !== this.props[i]) {
+            return setTimeout(this.renderLayer);
+          }
+        }
+      }
+
+      componentDidMount() {
+        this.isMounted = true;
+        this.renderLayer = this.renderLayer.bind(this);
+        this.renderLayer();
+      }
+
+      componentWillUnmount() {
+        this.renderLayer(false);
+        this.isMounted = false;
+        if (this.remote && this.remote.parentNode) this.remote.parentNode.removeChild(this.remote);
+      }
+
+      findNode(node) {
+        return typeof node === 'string' ? document.querySelector(node) : node;
+      }
+
+      renderLayer(show = true) {
+        if (!this.isMounted) return;
+
+        // clean up old node if moving bases:
+        if (this.props.into !== this.intoPointer) {
+          this.intoPointer = this.props.into;
+          if (this.into && this.remote) {
+            this.remote = render(html`<${PortalProxy} />`, this.into, this.remote);
+          }
+          this.into = this.findNode(this.props.into);
+        }
+
+        this.remote = render(html`
+          <${PortalProxy} context=${this.context}>
+            ${show && this.props.children || null}
+          </${PortalProxy}>
+        `, this.into, this.remote);
+      }
+
+      render() {
+        return null;
+      }
+    }
+    // high-order component that renders its first child if it exists.
+    // used as a conditional rendering proxy.
+    class PortalProxy extends Component {
+      getChildContext() {
+        return this.props.context;
+      }
+      render({ children }) {
+        return children || null;
+      }
+    }
+
+    function App(props) {
+      useEffect(() => {
+        const query = new URLSearchParams(location.search).get("q");
+        if (query) chat(query);
+      }, []);
+
+      return html`
+        <div class="mode-${session.value.type}">
+          <header>
+            <div class="grid-container">
+              <div class="grid-item"></div>
+              <div class="grid-item"><h1>llama.cpp</h1></div>
+              <div class="grid-item"><a class="customlink" href="index-new.html">New UI</a></div>
+            </div>
+          </header>
+
+          <main id="content">
+            <${chatStarted.value ? ChatLog : ConfigForm} />
+          </main>
+
+          <section id="write">
+            <${session.value.type === 'chat' ? MessageInput : CompletionControls} />
+          </section>
+
+          <footer>
+            <p><${ModelGenerationInfo} /></p>
+            <p>Powered by <a href="https://github.com/ggerganov/llama.cpp">llama.cpp</a> and <a href="https://ggml.ai">ggml.ai</a>.</p>
+          </footer>
+        </div>
+      `;
+    }
+
+    render(h(App), document.querySelector('#container'));
+  </script>
+</head>
+
+<body>
+  <div id="container">
+    <input type="file" id="fileInput" accept="image/*" style="display: none;">
+  </div>
+  <div id="portal"></div>
+</body>
+
+</html>
diff --git a/tools/server/public_legacy/index.js b/tools/server/public_legacy/index.js
new file mode 100644
index 00000000..32ec6e9e
--- /dev/null
+++ b/tools/server/public_legacy/index.js
@@ -0,0 +1 @@
+const t=Symbol.for("preact-signals");function n(){if(r>1){r--;return}let t,n=!1;while(void 0!==i){let _=i;i=void 0;u++;while(void 0!==_){const i=_.o;_.o=void 0;_.f&=-3;if(!(8&_.f)&&h(_))try{_.c()}catch(e){if(!n){t=e;n=!0}}_=i}}u=0;r--;if(n)throw t}function e(t){if(r>0)return t();r++;try{return t()}finally{n()}}let _,i;function o(t){const n=_;_=void 0;try{return t()}finally{_=n}}let r=0,u=0,l=0;function s(t){if(void 0===_)return;let n=t.n;if(void 0===n||n.t!==_){n={i:0,S:t,p:_.s,n:void 0,t:_,e:void 0,x:void 0,r:n};if(void 0!==_.s)_.s.n=n;_.s=n;t.n=n;if(32&_.f)t.S(n);return n}else if(-1===n.i){n.i=0;if(void 0!==n.n){n.n.p=n.p;if(void 0!==n.p)n.p.n=n.n;n.p=_.s;n.n=void 0;_.s.n=n;_.s=n}return n}}function f(t){this.v=t;this.i=0;this.n=void 0;this.t=void 0}f.prototype.brand=t;f.prototype.h=function(){return!0};f.prototype.S=function(t){if(this.t!==t&&void 0===t.e){t.x=this.t;if(void 0!==this.t)this.t.e=t;this.t=t}};f.prototype.U=function(t){if(void 0!==this.t){const n=t.e,e=t.x;if(void 0!==n){n.x=e;t.e=void 0}if(void 0!==e){e.e=n;t.x=void 0}if(t===this.t)this.t=e}};f.prototype.subscribe=function(t){return k(()=>{const n=this.value,e=_;_=void 0;try{t(n)}finally{_=e}})};f.prototype.valueOf=function(){return this.value};f.prototype.toString=function(){return this.value+""};f.prototype.toJSON=function(){return this.value};f.prototype.peek=function(){const t=_;_=void 0;try{return this.value}finally{_=t}};Object.defineProperty(f.prototype,"value",{get(){const t=s(this);if(void 0!==t)t.i=this.i;return this.v},set(t){if(t!==this.v){if(u>100)throw new Error("Cycle detected");this.v=t;this.i++;l++;r++;try{for(let t=this.t;void 0!==t;t=t.x)t.t.N()}finally{n()}}}});function c(t){return new f(t)}function h(t){for(let n=t.s;void 0!==n;n=n.n)if(n.S.i!==n.i||!n.S.h()||n.S.i!==n.i)return!0;return!1}function a(t){for(let n=t.s;void 0!==n;n=n.n){const e=n.S.n;if(void 0!==e)n.r=e;n.S.n=n;n.i=-1;if(void 0===n.n){t.s=n;break}}}function p(t){let n,e=t.s;while(void 0!==e){const t=e.p;if(-1===e.i){e.S.U(e);if(void 0!==t)t.n=e.n;if(void 0!==e.n)e.n.p=t}else n=e;e.S.n=e.r;if(void 0!==e.r)e.r=void 0;e=t}t.s=n}function d(t){f.call(this,void 0);this.x=t;this.s=void 0;this.g=l-1;this.f=4}(d.prototype=new f).h=function(){this.f&=-3;if(1&this.f)return!1;if(32==(36&this.f))return!0;this.f&=-5;if(this.g===l)return!0;this.g=l;this.f|=1;if(this.i>0&&!h(this)){this.f&=-2;return!0}const t=_;try{a(this);_=this;const t=this.x();if(16&this.f||this.v!==t||0===this.i){this.v=t;this.f&=-17;this.i++}}catch(t){this.v=t;this.f|=16;this.i++}_=t;p(this);this.f&=-2;return!0};d.prototype.S=function(t){if(void 0===this.t){this.f|=36;for(let t=this.s;void 0!==t;t=t.n)t.S.S(t)}f.prototype.S.call(this,t)};d.prototype.U=function(t){if(void 0!==this.t){f.prototype.U.call(this,t);if(void 0===this.t){this.f&=-33;for(let t=this.s;void 0!==t;t=t.n)t.S.U(t)}}};d.prototype.N=function(){if(!(2&this.f)){this.f|=6;for(let t=this.t;void 0!==t;t=t.x)t.t.N()}};Object.defineProperty(d.prototype,"value",{get(){if(1&this.f)throw new Error("Cycle detected");const t=s(this);this.h();if(void 0!==t)t.i=this.i;if(16&this.f)throw this.v;return this.v}});function v(t){return new d(t)}function y(t){const e=t.u;t.u=void 0;if("function"==typeof e){r++;const i=_;_=void 0;try{e()}catch(n){t.f&=-2;t.f|=8;m(t);throw n}finally{_=i;n()}}}function m(t){for(let n=t.s;void 0!==n;n=n.n)n.S.U(n);t.x=void 0;t.s=void 0;y(t)}function g(t){if(_!==this)throw new Error("Out-of-order effect");p(this);_=t;this.f&=-2;if(8&this.f)m(this);n()}function b(t){this.x=t;this.u=void 0;this.s=void 0;this.o=void 0;this.f=32}b.prototype.c=function(){const t=this.S();try{if(8&this.f)return;if(void 0===this.x)return;const n=this.x();if("function"==typeof n)this.u=n}finally{t()}};b.prototype.S=function(){if(1&this.f)throw new Error("Cycle detected");this.f|=1;this.f&=-9;y(this);a(this);r++;const t=_;_=this;return g.bind(this,t)};b.prototype.N=function(){if(!(2&this.f)){this.f|=2;this.o=i;i=this}};b.prototype.d=function(){this.f|=8;if(!(1&this.f))m(this)};function k(t){const n=new b(t);try{n.c()}catch(t){n.d();throw t}return n.d.bind(n)}var w,S,x,C,U,E,H,P,N,$,T,D,M={},A=[],F=/acit|ex(?:s|g|n|p|$)|rph|grid|ows|mnc|ntw|ine[ch]|zoo|^ord|itera/i,W=Array.isArray;function L(t,n){for(var e in n)t[e]=n[e];return t}function O(t){t&&t.parentNode&&t.parentNode.removeChild(t)}function R(t,n,e){var _,i,o,r={};for(o in n)"key"==o?_=n[o]:"ref"==o?i=n[o]:r[o]=n[o];if(arguments.length>2&&(r.children=arguments.length>3?w.call(arguments,2):e),"function"==typeof t&&null!=t.defaultProps)for(o in t.defaultProps)void 0===r[o]&&(r[o]=t.defaultProps[o]);return I(t,r,_,i,null)}function I(t,n,e,_,i){var o={type:t,props:n,key:e,ref:_,__k:null,__:null,__b:0,__e:null,__d:void 0,__c:null,constructor:void 0,__v:null==i?++x:i,__i:-1,__u:0};return null==i&&null!=S.vnode&&S.vnode(o),o}function V(){return{current:null}}function j(t){return t.children}function q(t,n){this.props=t,this.context=n}function B(t,n){if(null==n)return t.__?B(t.__,t.__i+1):null;for(var e;n<t.__k.length;n++)if(null!=(e=t.__k[n])&&null!=e.__e)return e.__e;return"function"==typeof t.type?B(t):null}function z(t){var n,e;if(null!=(t=t.__)&&null!=t.__c){for(t.__e=t.__c.base=null,n=0;n<t.__k.length;n++)if(null!=(e=t.__k[n])&&null!=e.__e){t.__e=t.__c.base=e.__e;break}return z(t)}}function G(t){(!t.__d&&(t.__d=!0)&&U.push(t)&&!J.__r++||E!==S.debounceRendering)&&((E=S.debounceRendering)||H)(J)}function J(){var t,n,e,_,i,o,r,u;for(U.sort(P);t=U.shift();)t.__d&&(n=U.length,_=void 0,o=(i=(e=t).__v).__e,r=[],u=[],e.__P&&((_=L({},i)).__v=i.__v+1,S.vnode&&S.vnode(_),_t(e.__P,_,i,e.__n,e.__P.namespaceURI,32&i.__u?[o]:null,r,null==o?B(i):o,!!(32&i.__u),u),_.__v=i.__v,_.__.__k[_.__i]=_,it(r,_,u),_.__e!=o&&z(_)),U.length>n&&U.sort(P));J.__r=0}function K(t,n,e,_,i,o,r,u,l,s,f){var c,h,a,p,d,v=_&&_.__k||A,y=n.length;for(e.__d=l,Q(e,n,v),l=e.__d,c=0;c<y;c++)null!=(a=e.__k[c])&&(h=-1===a.__i?M:v[a.__i]||M,a.__i=c,_t(t,a,h,i,o,r,u,l,s,f),p=a.__e,a.ref&&h.ref!=a.ref&&(h.ref&&rt(h.ref,null,a),f.push(a.ref,a.__c||p,a)),null==d&&null!=p&&(d=p),65536&a.__u||h.__k===a.__k?l=X(a,l,t):"function"==typeof a.type&&void 0!==a.__d?l=a.__d:p&&(l=p.nextSibling),a.__d=void 0,a.__u&=-196609);e.__d=l,e.__e=d}function Q(t,n,e){var _,i,o,r,u,l=n.length,s=e.length,f=s,c=0;for(t.__k=[],_=0;_<l;_++)null!=(i=n[_])&&"boolean"!=typeof i&&"function"!=typeof i?(r=_+c,(i=t.__k[_]="string"==typeof i||"number"==typeof i||"bigint"==typeof i||i.constructor==String?I(null,i,null,null,null):W(i)?I(j,{children:i},null,null,null):void 0===i.constructor&&i.__b>0?I(i.type,i.props,i.key,i.ref?i.ref:null,i.__v):i).__=t,i.__b=t.__b+1,o=null,-1!==(u=i.__i=Z(i,e,r,f))&&(f--,(o=e[u])&&(o.__u|=131072)),null==o||null===o.__v?(-1==u&&c--,"function"!=typeof i.type&&(i.__u|=65536)):u!==r&&(u==r-1?c--:u==r+1?c++:(u>r?c--:c++,i.__u|=65536))):i=t.__k[_]=null;if(f)for(_=0;_<s;_++)null!=(o=e[_])&&0==(131072&o.__u)&&(o.__e==t.__d&&(t.__d=B(o)),ut(o,o))}function X(t,n,e){var _,i;if("function"==typeof t.type){for(_=t.__k,i=0;_&&i<_.length;i++)_[i]&&(_[i].__=t,n=X(_[i],n,e));return n}t.__e!=n&&(n&&t.type&&!e.contains(n)&&(n=B(t)),e.insertBefore(t.__e,n||null),n=t.__e);do{n=n&&n.nextSibling}while(null!=n&&8===n.nodeType);return n}function Y(t,n){return n=n||[],null==t||"boolean"==typeof t||(W(t)?t.some((function(t){Y(t,n)})):n.push(t)),n}function Z(t,n,e,_){var i=t.key,o=t.type,r=e-1,u=e+1,l=n[e];if(null===l||l&&i==l.key&&o===l.type&&0==(131072&l.__u))return e;if(_>(null!=l&&0==(131072&l.__u)?1:0))for(;r>=0||u<n.length;){if(r>=0){if((l=n[r])&&0==(131072&l.__u)&&i==l.key&&o===l.type)return r;r--}if(u<n.length){if((l=n[u])&&0==(131072&l.__u)&&i==l.key&&o===l.type)return u;u++}}return-1}function tt(t,n,e){"-"===n[0]?t.setProperty(n,null==e?"":e):t[n]=null==e?"":"number"!=typeof e||F.test(n)?e:e+"px"}function nt(t,n,e,_,i){var o;t:if("style"===n)if("string"==typeof e)t.style.cssText=e;else{if("string"==typeof _&&(t.style.cssText=_=""),_)for(n in _)e&&n in e||tt(t.style,n,"");if(e)for(n in e)_&&e[n]===_[n]||tt(t.style,n,e[n])}else if("o"===n[0]&&"n"===n[1])o=n!==(n=n.replace(/(PointerCapture)$|Capture$/i,"$1")),n=n.toLowerCase()in t||"onFocusOut"===n||"onFocusIn"===n?n.toLowerCase().slice(2):n.slice(2),t.l||(t.l={}),t.l[n+o]=e,e?_?e.u=_.u:(e.u=N,t.addEventListener(n,o?T:$,o)):t.removeEventListener(n,o?T:$,o);else{if("http://www.w3.org/2000/svg"==i)n=n.replace(/xlink(H|:h)/,"h").replace(/sName$/,"s");else if("width"!=n&&"height"!=n&&"href"!=n&&"list"!=n&&"form"!=n&&"tabIndex"!=n&&"download"!=n&&"rowSpan"!=n&&"colSpan"!=n&&"role"!=n&&"popover"!=n&&n in t)try{t[n]=null==e?"":e;break t}catch(t){}"function"==typeof e||(null==e||!1===e&&"-"!==n[4]?t.removeAttribute(n):t.setAttribute(n,"popover"==n&&1==e?"":e))}}function et(t){return function(n){if(this.l){var e=this.l[n.type+t];if(null==n.t)n.t=N++;else if(n.t<e.u)return;return e(S.event?S.event(n):n)}}}function _t(t,n,e,_,i,o,r,u,l,s){var f,c,h,a,p,d,v,y,m,g,b,k,w,x,C,U,E=n.type;if(void 0!==n.constructor)return null;128&e.__u&&(l=!!(32&e.__u),o=[u=n.__e=e.__e]),(f=S.__b)&&f(n);t:if("function"==typeof E)try{if(y=n.props,m="prototype"in E&&E.prototype.render,g=(f=E.contextType)&&_[f.__c],b=f?g?g.props.value:f.__:_,e.__c?v=(c=n.__c=e.__c).__=c.__E:(m?n.__c=c=new E(y,b):(n.__c=c=new q(y,b),c.constructor=E,c.render=lt),g&&g.sub(c),c.props=y,c.state||(c.state={}),c.context=b,c.__n=_,h=c.__d=!0,c.__h=[],c._sb=[]),m&&null==c.__s&&(c.__s=c.state),m&&null!=E.getDerivedStateFromProps&&(c.__s==c.state&&(c.__s=L({},c.__s)),L(c.__s,E.getDerivedStateFromProps(y,c.__s))),a=c.props,p=c.state,c.__v=n,h)m&&null==E.getDerivedStateFromProps&&null!=c.componentWillMount&&c.componentWillMount(),m&&null!=c.componentDidMount&&c.__h.push(c.componentDidMount);else{if(m&&null==E.getDerivedStateFromProps&&y!==a&&null!=c.componentWillReceiveProps&&c.componentWillReceiveProps(y,b),!c.__e&&(null!=c.shouldComponentUpdate&&!1===c.shouldComponentUpdate(y,c.__s,b)||n.__v===e.__v)){for(n.__v!==e.__v&&(c.props=y,c.state=c.__s,c.__d=!1),n.__e=e.__e,n.__k=e.__k,n.__k.some((function(t){t&&(t.__=n)})),k=0;k<c._sb.length;k++)c.__h.push(c._sb[k]);c._sb=[],c.__h.length&&r.push(c);break t}null!=c.componentWillUpdate&&c.componentWillUpdate(y,c.__s,b),m&&null!=c.componentDidUpdate&&c.__h.push((function(){c.componentDidUpdate(a,p,d)}))}if(c.context=b,c.props=y,c.__P=t,c.__e=!1,w=S.__r,x=0,m){for(c.state=c.__s,c.__d=!1,w&&w(n),f=c.render(c.props,c.state,c.context),C=0;C<c._sb.length;C++)c.__h.push(c._sb[C]);c._sb=[]}else do{c.__d=!1,w&&w(n),f=c.render(c.props,c.state,c.context),c.state=c.__s}while(c.__d&&++x<25);c.state=c.__s,null!=c.getChildContext&&(_=L(L({},_),c.getChildContext())),m&&!h&&null!=c.getSnapshotBeforeUpdate&&(d=c.getSnapshotBeforeUpdate(a,p)),K(t,W(U=null!=f&&f.type===j&&null==f.key?f.props.children:f)?U:[U],n,e,_,i,o,r,u,l,s),c.base=n.__e,n.__u&=-161,c.__h.length&&r.push(c),v&&(c.__E=c.__=null)}catch(t){if(n.__v=null,l||null!=o){for(n.__u|=l?160:128;u&&8===u.nodeType&&u.nextSibling;)u=u.nextSibling;o[o.indexOf(u)]=null,n.__e=u}else n.__e=e.__e,n.__k=e.__k;S.__e(t,n,e)}else null==o&&n.__v===e.__v?(n.__k=e.__k,n.__e=e.__e):n.__e=ot(e.__e,n,e,_,i,o,r,l,s);(f=S.diffed)&&f(n)}function it(t,n,e){n.__d=void 0;for(var _=0;_<e.length;_++)rt(e[_],e[++_],e[++_]);S.__c&&S.__c(n,t),t.some((function(n){try{t=n.__h,n.__h=[],t.some((function(t){t.call(n)}))}catch(t){S.__e(t,n.__v)}}))}function ot(t,n,e,_,i,o,r,u,l){var s,f,c,h,a,p,d,v=e.props,y=n.props,m=n.type;if("svg"===m?i="http://www.w3.org/2000/svg":"math"===m?i="http://www.w3.org/1998/Math/MathML":i||(i="http://www.w3.org/1999/xhtml"),null!=o)for(s=0;s<o.length;s++)if((a=o[s])&&"setAttribute"in a==!!m&&(m?a.localName===m:3===a.nodeType)){t=a,o[s]=null;break}if(null==t){if(null===m)return document.createTextNode(y);t=document.createElementNS(i,m,y.is&&y),u&&(S.__m&&S.__m(n,o),u=!1),o=null}if(null===m)v===y||u&&t.data===y||(t.data=y);else{if(o=o&&w.call(t.childNodes),v=e.props||M,!u&&null!=o)for(v={},s=0;s<t.attributes.length;s++)v[(a=t.attributes[s]).name]=a.value;for(s in v)if(a=v[s],"children"==s);else if("dangerouslySetInnerHTML"==s)c=a;else if(!(s in y)){if("value"==s&&"defaultValue"in y||"checked"==s&&"defaultChecked"in y)continue;nt(t,s,null,a,i)}for(s in y)a=y[s],"children"==s?h=a:"dangerouslySetInnerHTML"==s?f=a:"value"==s?p=a:"checked"==s?d=a:u&&"function"!=typeof a||v[s]===a||nt(t,s,a,v[s],i);if(f)u||c&&(f.__html===c.__html||f.__html===t.innerHTML)||(t.innerHTML=f.__html),n.__k=[];else if(c&&(t.innerHTML=""),K(t,W(h)?h:[h],n,e,_,"foreignObject"===m?"http://www.w3.org/1999/xhtml":i,o,r,o?o[0]:e.__k&&B(e,0),u,l),null!=o)for(s=o.length;s--;)O(o[s]);u||(s="value","progress"===m&&null==p?t.removeAttribute("value"):void 0!==p&&(p!==t[s]||"progress"===m&&!p||"option"===m&&p!==v[s])&&nt(t,s,p,v[s],i),s="checked",void 0!==d&&d!==t[s]&&nt(t,s,d,v[s],i))}return t}function rt(t,n,e){try{if("function"==typeof t){var _="function"==typeof t.__u;_&&t.__u(),_&&null==n||(t.__u=t(n))}else t.current=n}catch(t){S.__e(t,e)}}function ut(t,n,e){var _,i;if(S.unmount&&S.unmount(t),(_=t.ref)&&(_.current&&_.current!==t.__e||rt(_,null,n)),null!=(_=t.__c)){if(_.componentWillUnmount)try{_.componentWillUnmount()}catch(t){S.__e(t,n)}_.base=_.__P=null}if(_=t.__k)for(i=0;i<_.length;i++)_[i]&&ut(_[i],n,e||"function"!=typeof t.type);e||O(t.__e),t.__c=t.__=t.__e=t.__d=void 0}function lt(t,n,e){return this.constructor(t,e)}function st(t,n,e){var _,i,o,r;S.__&&S.__(t,n),i=(_="function"==typeof e)?null:e&&e.__k||n.__k,o=[],r=[],_t(n,t=(!_&&e||n).__k=R(j,null,[t]),i||M,M,n.namespaceURI,!_&&e?[e]:i?null:n.firstChild?w.call(n.childNodes):null,o,!_&&e?e:i?i.__e:n.firstChild,_,r),it(o,t,r)}function ft(t,n){st(t,n,ft)}function ct(t,n,e){var _,i,o,r,u=L({},t.props);for(o in t.type&&t.type.defaultProps&&(r=t.type.defaultProps),n)"key"==o?_=n[o]:"ref"==o?i=n[o]:u[o]=void 0===n[o]&&void 0!==r?r[o]:n[o];return arguments.length>2&&(u.children=arguments.length>3?w.call(arguments,2):e),I(t.type,u,_||t.key,i||t.ref,null)}function ht(t,n){var e={__c:n="__cC"+D++,__:t,Consumer:function(t,n){return t.children(n)},Provider:function(t){var e,_;return this.getChildContext||(e=new Set,(_={})[n]=this,this.getChildContext=function(){return _},this.componentWillUnmount=function(){e=null},this.shouldComponentUpdate=function(t){this.props.value!==t.value&&e.forEach((function(t){t.__e=!0,G(t)}))},this.sub=function(t){e.add(t);var n=t.componentWillUnmount;t.componentWillUnmount=function(){e&&e.delete(t),n&&n.call(t)}}),t.children}};return e.Provider.__=e.Consumer.contextType=e}w=A.slice,S={__e:function(t,n,e,_){for(var i,o,r;n=n.__;)if((i=n.__c)&&!i.__)try{if((o=i.constructor)&&null!=o.getDerivedStateFromError&&(i.setState(o.getDerivedStateFromError(t)),r=i.__d),null!=i.componentDidCatch&&(i.componentDidCatch(t,_||{}),r=i.__d),r)return i.__E=i}catch(n){t=n}throw t}},x=0,C=function(t){return null!=t&&null==t.constructor},q.prototype.setState=function(t,n){var e;e=null!=this.__s&&this.__s!==this.state?this.__s:this.__s=L({},this.state),"function"==typeof t&&(t=t(L({},e),this.props)),t&&L(e,t),null!=t&&this.__v&&(n&&this._sb.push(n),G(this))},q.prototype.forceUpdate=function(t){this.__v&&(this.__e=!0,t&&this.__h.push(t),G(this))},q.prototype.render=j,U=[],H="function"==typeof Promise?Promise.prototype.then.bind(Promise.resolve()):setTimeout,P=function(t,n){return t.__v.__b-n.__v.__b},J.__r=0,N=0,$=et(!1),T=et(!0),D=0;var at,pt,dt,vt,yt=0,mt=[],gt=S,bt=gt.__b,kt=gt.__r,wt=gt.diffed,St=gt.__c,xt=gt.unmount,Ct=gt.__;function Ut(t,n){gt.__h&>.__h(pt,t,yt||n),yt=0;var e=pt.__H||(pt.__H={__:[],__h:[]});return t>=e.__.length&&e.__.push({}),e.__[t]}function Et(t){return yt=1,Ht(Bt,t)}function Ht(t,n,e){var _=Ut(at++,2);if(_.t=t,!_.__c&&(_.__=[e?e(n):Bt(void 0,n),function(t){var n=_.__N?_.__N[0]:_.__[0],e=_.t(n,t);n!==e&&(_.__N=[e,_.__[1]],_.__c.setState({}))}],_.__c=pt,!pt.u)){var i=function(t,n,e){if(!_.__c.__H)return!0;var i=_.__c.__H.__.filter((function(t){return!!t.__c}));if(i.every((function(t){return!t.__N})))return!o||o.call(this,t,n,e);var r=!1;return i.forEach((function(t){if(t.__N){var n=t.__[0];t.__=t.__N,t.__N=void 0,n!==t.__[0]&&(r=!0)}})),!(!r&&_.__c.props===t)&&(!o||o.call(this,t,n,e))};pt.u=!0;var o=pt.shouldComponentUpdate,r=pt.componentWillUpdate;pt.componentWillUpdate=function(t,n,e){if(this.__e){var _=o;o=void 0,i(t,n,e),o=_}r&&r.call(this,t,n,e)},pt.shouldComponentUpdate=i}return _.__N||_.__}function Pt(t,n){var e=Ut(at++,3);!gt.__s&&qt(e.__H,n)&&(e.__=t,e.i=n,pt.__H.__h.push(e))}function Nt(t,n){var e=Ut(at++,4);!gt.__s&&qt(e.__H,n)&&(e.__=t,e.i=n,pt.__h.push(e))}function $t(t){return yt=5,Dt((function(){return{current:t}}),[])}function Tt(t,n,e){yt=6,Nt((function(){return"function"==typeof t?(t(n()),function(){return t(null)}):t?(t.current=n(),function(){return t.current=null}):void 0}),null==e?e:e.concat(t))}function Dt(t,n){var e=Ut(at++,7);return qt(e.__H,n)&&(e.__=t(),e.__H=n,e.__h=t),e.__}function Mt(t,n){return yt=8,Dt((function(){return t}),n)}function At(t){var n=pt.context[t.__c],e=Ut(at++,9);return e.c=t,n?(null==e.__&&(e.__=!0,n.sub(pt)),n.props.value):t.__}function Ft(t,n){gt.useDebugValue&>.useDebugValue(n?n(t):t)}function Wt(t){var n=Ut(at++,10),e=Et();return n.__=t,pt.componentDidCatch||(pt.componentDidCatch=function(t,_){n.__&&n.__(t,_),e[1](t)}),[e[0],function(){e[1](void 0)}]}function Lt(){var t=Ut(at++,11);if(!t.__){for(var n=pt.__v;null!==n&&!n.__m&&null!==n.__;)n=n.__;var e=n.__m||(n.__m=[0,0]);t.__="P"+e[0]+"-"+e[1]++}return t.__}function Ot(){for(var t;t=mt.shift();)if(t.__P&&t.__H)try{t.__H.__h.forEach(Vt),t.__H.__h.forEach(jt),t.__H.__h=[]}catch(n){t.__H.__h=[],gt.__e(n,t.__v)}}gt.__b=function(t){pt=null,bt&&bt(t)},gt.__=function(t,n){t&&n.__k&&n.__k.__m&&(t.__m=n.__k.__m),Ct&&Ct(t,n)},gt.__r=function(t){kt&&kt(t),at=0;var n=(pt=t.__c).__H;n&&(dt===pt?(n.__h=[],pt.__h=[],n.__.forEach((function(t){t.__N&&(t.__=t.__N),t.i=t.__N=void 0}))):(n.__h.forEach(Vt),n.__h.forEach(jt),n.__h=[],at=0)),dt=pt},gt.diffed=function(t){wt&&wt(t);var n=t.__c;n&&n.__H&&(n.__H.__h.length&&(1!==mt.push(n)&&vt===gt.requestAnimationFrame||((vt=gt.requestAnimationFrame)||It)(Ot)),n.__H.__.forEach((function(t){t.i&&(t.__H=t.i),t.i=void 0}))),dt=pt=null},gt.__c=function(t,n){n.some((function(t){try{t.__h.forEach(Vt),t.__h=t.__h.filter((function(t){return!t.__||jt(t)}))}catch(r){n.some((function(t){t.__h&&(t.__h=[])})),n=[],gt.__e(r,t.__v)}})),St&&St(t,n)},gt.unmount=function(t){xt&&xt(t);var n,e=t.__c;e&&e.__H&&(e.__H.__.forEach((function(t){try{Vt(t)}catch(t){n=t}})),e.__H=void 0,n&>.__e(n,e.__v))};var Rt="function"==typeof requestAnimationFrame;function It(t){var n,e=function(){clearTimeout(_),Rt&&cancelAnimationFrame(n),setTimeout(t)},_=setTimeout(e,100);Rt&&(n=requestAnimationFrame(e))}function Vt(t){var n=pt,e=t.__c;"function"==typeof e&&(t.__c=void 0,e()),pt=n}function jt(t){var n=pt;t.__c=t.__(),pt=n}function qt(t,n){return!t||t.length!==n.length||n.some((function(n,e){return n!==t[e]}))}function Bt(t,n){return"function"==typeof n?n(t):n}function zt(t,n){S[t]=n.bind(null,S[t]||(()=>{}))}let Gt,Jt;function Kt(t){if(Jt)Jt();Jt=t&&t.S()}function Qt({data:t}){const n=Yt(t);n.value=t;const e=Dt(()=>{let t=this.__v;while(t=t.__)if(t.__c){t.__c.__$f|=4;break}this.__$u.c=()=>{var t;if(!C(e.peek())&&3===(null==(t=this.base)?void 0:t.nodeType))this.base.data=e.peek();else{this.__$f|=1;this.setState({})}};return v(()=>{let t=n.value.value;return 0===t?0:!0===t?"":t||""})},[]);return e.value}Qt.displayName="_st";Object.defineProperties(f.prototype,{constructor:{configurable:!0,value:void 0},type:{configurable:!0,value:Qt},props:{configurable:!0,get(){return{data:this}}},__b:{configurable:!0,value:1}});zt("__b",(t,n)=>{if("string"==typeof n.type){let t,e=n.props;for(let _ in e){if("children"===_)continue;let i=e[_];if(i instanceof f){if(!t)n.__np=t={};t[_]=i;e[_]=i.peek()}}}t(n)});zt("__r",(t,n)=>{Kt();let e,_=n.__c;if(_){_.__$f&=-2;e=_.__$u;if(void 0===e)_.__$u=e=function(t){let n;k((function(){n=this}));n.c=()=>{_.__$f|=1;_.setState({})};return n}()}Gt=_;Kt(e);t(n)});zt("__e",(t,n,e,_)=>{Kt();Gt=void 0;t(n,e,_)});zt("diffed",(t,n)=>{Kt();Gt=void 0;let e;if("string"==typeof n.type&&(e=n.__e)){let t=n.__np,_=n.props;if(t){let n=e.U;if(n)for(let e in n){let _=n[e];if(void 0!==_&&!(e in t)){_.d();n[e]=void 0}}else{n={};e.U=n}for(let i in t){let o=n[i],r=t[i];if(void 0===o){o=Xt(e,i,r,_);n[i]=o}else o.o(r,_)}}}t(n)});function Xt(t,n,e,_){const i=n in t&&void 0===t.ownerSVGElement,o=c(e);return{o:(t,n)=>{o.value=t;_=n},d:k(()=>{const e=o.value.value;if(_[n]!==e){_[n]=e;if(i)t[n]=e;else if(e)t.setAttribute(n,e);else t.removeAttribute(n)}})}}zt("unmount",(t,n)=>{if("string"==typeof n.type){let t=n.__e;if(t){const n=t.U;if(n){t.U=void 0;for(let t in n){let e=n[t];if(e)e.d()}}}}else{let t=n.__c;if(t){const n=t.__$u;if(n){t.__$u=void 0;n.d()}}}t(n)});zt("__h",(t,n,e,_)=>{if(_<3||9===_)n.__$f|=2;t(n,e,_)});q.prototype.shouldComponentUpdate=function(t,n){const e=this.__$u;if(!(e&&void 0!==e.s||4&this.__$f))return!0;if(3&this.__$f)return!0;for(let _ in n)return!0;for(let _ in t)if("__source"!==_&&t[_]!==this.props[_])return!0;for(let _ in this.props)if(!(_ in t))return!0;return!1};function Yt(t){return Dt(()=>c(t),[])}function Zt(t){const n=$t(t);n.current=t;Gt.__$f|=4;return Dt(()=>v(()=>n.current()),[])}function tn(t){const n=$t(t);n.current=t;Pt(()=>k(()=>n.current()),[])}var nn=function(t,n,e,_){var i;n[0]=0;for(var o=1;o<n.length;o++){var r=n[o++],u=n[o]?(n[0]|=r?1:2,e[n[o++]]):n[++o];3===r?_[0]=u:4===r?_[1]=Object.assign(_[1]||{},u):5===r?(_[1]=_[1]||{})[n[++o]]=u:6===r?_[1][n[++o]]+=u+"":r?(i=t.apply(u,nn(t,u,e,["",null])),_.push(i),u[0]?n[0]|=2:(n[o-2]=0,n[o]=i)):_.push(u)}return _},en=new Map;function _n(t){var n=en.get(this);return n||(n=new Map,en.set(this,n)),(n=nn(this,n.get(t)||(n.set(t,n=function(t){for(var n,e,_=1,i="",o="",r=[0],u=function(t){1===_&&(t||(i=i.replace(/^\s*\n\s*|\s*\n\s*$/g,"")))?r.push(0,t,i):3===_&&(t||i)?(r.push(3,t,i),_=2):2===_&&"..."===i&&t?r.push(4,t,0):2===_&&i&&!t?r.push(5,0,!0,i):_>=5&&((i||!t&&5===_)&&(r.push(_,0,i,e),_=6),t&&(r.push(_,t,0,e),_=6)),i=""},l=0;l<t.length;l++){l&&(1===_&&u(),u(l));for(var s=0;s<t[l].length;s++)n=t[l][s],1===_?"<"===n?(u(),r=[r],_=3):i+=n:4===_?"--"===i&&">"===n?(_=1,i=""):i=n+i[0]:o?n===o?o="":i+=n:'"'===n||"'"===n?o=n:">"===n?(u(),_=1):_&&("="===n?(_=5,e=i,i=""):"/"===n&&(_<5||">"===t[l][s+1])?(u(),3===_&&(r=r[0]),_=r,(r=r[0]).push(2,0,_),_=0):" "===n||"\t"===n||"\n"===n||"\r"===n?(u(),_=2):i+=n),3===_&&"!--"===i&&(_=4,r=r[0])}return u(),r}(t)),n),arguments,[])).length>1?n:n[0]}var on=_n.bind(R);export{q as Component,j as Fragment,f as Signal,e as batch,ct as cloneElement,v as computed,ht as createContext,R as createElement,V as createRef,k as effect,R as h,on as html,ft as hydrate,C as isValidElement,S as options,st as render,c as signal,Y as toChildArray,o as untracked,Mt as useCallback,Zt as useComputed,At as useContext,Ft as useDebugValue,Pt as useEffect,Wt as useErrorBoundary,Lt as useId,Tt as useImperativeHandle,Nt as useLayoutEffect,Dt as useMemo,Ht as useReducer,$t as useRef,Yt as useSignal,tn as useSignalEffect,Et as useState};
diff --git a/tools/server/public_legacy/json-schema-to-grammar.mjs b/tools/server/public_legacy/json-schema-to-grammar.mjs
new file mode 100644
index 00000000..b12bf2ab
--- /dev/null
+++ b/tools/server/public_legacy/json-schema-to-grammar.mjs
@@ -0,0 +1,838 @@
+// WARNING: This file was ported from json_schema_to_grammar.py, please fix bugs / add features there first.
+const SPACE_RULE = '| " " | "\\n"{1,2} [ \\t]{0,20}';
+
+function _buildRepetition(itemRule, minItems, maxItems, opts={}) {
+  if (maxItems == 0) {
+    return '';
+  }
+  if (minItems === 0 && maxItems === 1) {
+    return `${itemRule}?`;
+  }
+
+
+  const separatorRule = opts.separatorRule ?? '';
+  const itemRuleIsLiteral = opts.itemRuleIsLiteral ?? false
+
+  if (separatorRule === '') {
+    if (minItems === 1 && maxItems === undefined) {
+      return `${itemRule}+`;
+    } else if (minItems === 0 && maxItems === undefined) {
+      return `${itemRule}*`;
+    } else {
+      return `${itemRule}{${minItems},${maxItems !== undefined ? maxItems : ''}}`;
+    }
+  }
+
+  const result = itemRule + ' ' + _buildRepetition(`(${separatorRule} ${itemRule})`, minItems > 0 ? minItems - 1 : 0, maxItems !== undefined ? maxItems - 1 : undefined);
+  return minItems === 0 ? `(${result})?` : result;
+}
+
+function _generateMinMaxInt(minValue, maxValue, out, decimalsLeft = 16, topLevel = true) {
+  const hasMin = minValue !== null;
+  const hasMax = maxValue !== null;
+
+  function digitRange(fromChar, toChar) {
+      out.push("[");
+      if (fromChar === toChar) {
+          out.push(fromChar);
+      } else {
+          out.push(fromChar);
+          out.push("-");
+          out.push(toChar);
+      }
+      out.push("]");
+  }
+
+  function moreDigits(minDigits, maxDigits) {
+      out.push("[0-9]");
+      if (minDigits === maxDigits && minDigits === 1) {
+          return;
+      }
+      out.push("{");
+      out.push(minDigits.toString());
+      if (maxDigits !== minDigits) {
+          out.push(",");
+          if (maxDigits !== Number.MAX_SAFE_INTEGER) {
+              out.push(maxDigits.toString());
+          }
+      }
+      out.push("}");
+  }
+
+  function uniformRange(fromStr, toStr) {
+      let i = 0;
+      while (i < fromStr.length && fromStr[i] === toStr[i]) {
+          i++;
+      }
+      if (i > 0) {
+          out.push("\"");
+          out.push(fromStr.slice(0, i));
+          out.push("\"");
+      }
+      if (i < fromStr.length) {
+          if (i > 0) {
+              out.push(" ");
+          }
+          const subLen = fromStr.length - i - 1;
+          if (subLen > 0) {
+              const fromSub = fromStr.slice(i + 1);
+              const toSub = toStr.slice(i + 1);
+              const subZeros = "0".repeat(subLen);
+              const subNines = "9".repeat(subLen);
+
+              let toReached = false;
+              out.push("(");
+              if (fromSub === subZeros) {
+                  digitRange(fromStr[i], String.fromCharCode(toStr.charCodeAt(i) - 1));
+                  out.push(" ");
+                  moreDigits(subLen, subLen);
+              } else {
+                  out.push("[");
+                  out.push(fromStr[i]);
+                  out.push("] ");
+                  out.push("(");
+                  uniformRange(fromSub, subNines);
+                  out.push(")");
+                  if (fromStr.charCodeAt(i) < toStr.charCodeAt(i) - 1) {
+                      out.push(" | ");
+                      if (toSub === subNines) {
+                          digitRange(String.fromCharCode(fromStr.charCodeAt(i) + 1), toStr[i]);
+                          toReached = true;
+                      } else {
+                          digitRange(String.fromCharCode(fromStr.charCodeAt(i) + 1), String.fromCharCode(toStr.charCodeAt(i) - 1));
+                      }
+                      out.push(" ");
+                      moreDigits(subLen, subLen);
+                  }
+              }
+              if (!toReached) {
+                  out.push(" | ");
+                  digitRange(toStr[i], toStr[i]);
+                  out.push(" ");
+                  uniformRange(subZeros, toSub);
+              }
+              out.push(")");
+          } else {
+              out.push("[");
+              out.push(fromStr[i]);
+              out.push("-");
+              out.push(toStr[i]);
+              out.push("]");
+          }
+      }
+  }
+
+  if (hasMin && hasMax) {
+      if (minValue < 0 && maxValue < 0) {
+          out.push("\"-\" (");
+          _generateMinMaxInt(-maxValue, -minValue, out, decimalsLeft, true);
+          out.push(")");
+          return;
+      }
+
+      if (minValue < 0) {
+          out.push("\"-\" (");
+          _generateMinMaxInt(0, -minValue, out, decimalsLeft, true);
+          out.push(") | ");
+          minValue = 0;
+      }
+
+      let minS = minValue.toString();
+      const maxS = maxValue.toString();
+      const minDigits = minS.length;
+      const maxDigits = maxS.length;
+
+      for (let digits = minDigits; digits < maxDigits; digits++) {
+          uniformRange(minS, "9".repeat(digits));
+          minS = "1" + "0".repeat(digits);
+          out.push(" | ");
+      }
+      uniformRange(minS, maxS);
+      return;
+  }
+
+  const lessDecimals = Math.max(decimalsLeft - 1, 1);
+
+  if (hasMin) {
+      if (minValue < 0) {
+          out.push("\"-\" (");
+          _generateMinMaxInt(null, -minValue, out, decimalsLeft, false);
+          out.push(") | [0] | [1-9] ");
+          moreDigits(0, decimalsLeft - 1);
+      } else if (minValue === 0) {
+          if (topLevel) {
+              out.push("[0] | [1-9] ");
+              moreDigits(0, lessDecimals);
+          } else {
+              moreDigits(1, decimalsLeft);
+          }
+      } else if (minValue <= 9) {
+          const c = minValue.toString();
+          const range_start = topLevel ? '1' : '0';
+          if (c > range_start) {
+              digitRange(range_start, String.fromCharCode(c.charCodeAt(0) - 1));
+              out.push(" ");
+              moreDigits(1, lessDecimals);
+              out.push(" | ");
+          }
+          digitRange(c, "9");
+          out.push(" ");
+          moreDigits(0, lessDecimals);
+      } else {
+          const minS = minValue.toString();
+          const length = minS.length;
+          const c = minS[0];
+
+          if (c > "1") {
+              digitRange(topLevel ? "1" : "0", String.fromCharCode(c.charCodeAt(0) - 1));
+              out.push(" ");
+              moreDigits(length, lessDecimals);
+              out.push(" | ");
+          }
+          digitRange(c, c);
+          out.push(" (");
+          _generateMinMaxInt(parseInt(minS.slice(1)), null, out, lessDecimals, false);
+          out.push(")");
+          if (c < "9") {
+              out.push(" | ");
+              digitRange(String.fromCharCode(c.charCodeAt(0) + 1), "9");
+              out.push(" ");
+              moreDigits(length - 1, lessDecimals);
+          }
+      }
+      return;
+  }
+
+  if (hasMax) {
+      if (maxValue >= 0) {
+          if (topLevel) {
+              out.push("\"-\" [1-9] ");
+              moreDigits(0, lessDecimals);
+              out.push(" | ");
+          }
+          _generateMinMaxInt(0, maxValue, out, decimalsLeft, true);
+      } else {
+          out.push("\"-\" (");
+          _generateMinMaxInt(-maxValue, null, out, decimalsLeft, false);
+          out.push(")");
+      }
+      return;
+  }
+
+  throw new Error("At least one of minValue or maxValue must be set");
+}
+
+class BuiltinRule {
+  constructor(content, deps) {
+    this.content = content;
+    this.deps = deps || [];
+  }
+}
+
+const PRIMITIVE_RULES = {
+  boolean        : new BuiltinRule('("true" | "false") space', []),
+  'decimal-part' : new BuiltinRule('[0-9]{1,16}', []),
+  'integral-part': new BuiltinRule('[0] | [1-9] [0-9]{0,15}', []),
+  number         : new BuiltinRule('("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space', ['integral-part', 'decimal-part']),
+  integer        : new BuiltinRule('("-"? integral-part) space', ['integral-part']),
+  value          : new BuiltinRule('object | array | string | number | boolean | null', ['object', 'array', 'string', 'number', 'boolean', 'null']),
+  object         : new BuiltinRule('"{" space ( string ":" space value ("," space string ":" space value)* )? "}" space', ['string', 'value']),
+  array          : new BuiltinRule('"[" space ( value ("," space value)* )? "]" space', ['value']),
+  uuid           : new BuiltinRule('"\\"" [0-9a-fA-F]{8} "-" [0-9a-fA-F]{4} "-" [0-9a-fA-F]{4} "-" [0-9a-fA-F]{4} "-" [0-9a-fA-F]{12} "\\"" space', []),
+  char           : new BuiltinRule(`[^"\\\\\\x7F\\x00-\\x1F] | [\\\\] (["\\\\bfnrt] | "u" [0-9a-fA-F]{4})`, []),
+  string         : new BuiltinRule(`"\\"" char* "\\"" space`, ['char']),
+  null           : new BuiltinRule('"null" space', []),
+};
+
+// TODO: support "uri", "email" string formats
+const STRING_FORMAT_RULES = {
+  'date'            : new BuiltinRule('[0-9]{4} "-" ( "0" [1-9] | "1" [0-2] ) "-" ( \"0\" [1-9] | [1-2] [0-9] | "3" [0-1] )', []),
+  'time'            : new BuiltinRule('([01] [0-9] | "2" [0-3]) ":" [0-5] [0-9] ":" [0-5] [0-9] ( "." [0-9]{3} )? ( "Z" | ( "+" | "-" ) ( [01] [0-9] | "2" [0-3] ) ":" [0-5] [0-9] )', []),
+  'date-time'       : new BuiltinRule('date "T" time', ['date', 'time']),
+  'date-string'     : new BuiltinRule('"\\"" date "\\"" space', ['date']),
+  'time-string'     : new BuiltinRule('"\\"" time "\\"" space', ['time']),
+  'date-time-string': new BuiltinRule('"\\"" date-time "\\"" space', ['date-time']),
+}
+
+const RESERVED_NAMES = {'root': true, ...PRIMITIVE_RULES, ...STRING_FORMAT_RULES};
+
+const INVALID_RULE_CHARS_RE = /[^\dA-Za-z-]+/g;
+const GRAMMAR_LITERAL_ESCAPE_RE = /[\n\r"]/g;
+const GRAMMAR_RANGE_LITERAL_ESCAPE_RE = /[\n\r"\]\-\\]/g;
+const GRAMMAR_LITERAL_ESCAPES = { '\r': '\\r', '\n': '\\n', '"': '\\"', '-': '\\-', ']': '\\]' };
+
+const NON_LITERAL_SET = new Set('|.()[]{}*+?');
+const ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = new Set('^$.[]()|{}*+?');
+
+export class SchemaConverter {
+  constructor(options) {
+    this._propOrder = options.prop_order || {};
+    this._allowFetch = options.allow_fetch || false;
+    this._dotall = options.dotall || false;
+    this._rules = {'space': SPACE_RULE};
+    this._refs = {};
+    this._refsBeingResolved = new Set();
+  }
+
+  _formatLiteral(literal) {
+    const escaped = literal.replace(
+      GRAMMAR_LITERAL_ESCAPE_RE,
+      m => GRAMMAR_LITERAL_ESCAPES[m]
+    );
+    return `"${escaped}"`;
+  }
+
+  _formatRangeChar(literal) {
+    return JSON.stringify(literal).slice(1, -1).replace(
+      GRAMMAR_RANGE_LITERAL_ESCAPE_RE,
+      m => GRAMMAR_LITERAL_ESCAPES[m]
+    );
+  }
+
+  _addRule(name, rule) {
+    let escName = name.replace(INVALID_RULE_CHARS_RE, '-');
+    let key = escName;
+
+    if (escName in this._rules) {
+      if (this._rules[escName] === rule) {
+        return key;
+      }
+
+      let i = 0;
+      while ((`${escName}${i}` in this._rules) && (this._rules[`${escName}${i}`] !== rule)) {
+        i += 1;
+      }
+      key = `${escName}${i}`;
+    }
+
+    this._rules[key] = rule;
+    return key;
+  }
+
+  async resolveRefs(schema, url) {
+    const visit = async (n) => {
+      if (Array.isArray(n)) {
+        return Promise.all(n.map(visit));
+      } else if (typeof n === 'object' && n !== null) {
+        let ref = n.$ref;
+        let target;
+        if (ref !== undefined && !this._refs[ref]) {
+          if (ref.startsWith('https://')) {
+            if (!this._allowFetch) {
+              throw new Error('Fetching remote schemas is not allowed (use --allow-fetch for force)');
+            }
+            const fetch = (await import('node-fetch')).default;
+
+            const fragSplit = ref.split('#');
+            const baseUrl = fragSplit[0];
+
+            target = this._refs[baseUrl];
+            if (!target) {
+              target = await this.resolveRefs(await fetch(ref).then(res => res.json()), baseUrl);
+              this._refs[baseUrl] = target;
+            }
+
+            if (fragSplit.length === 1 || fragSplit[fragSplit.length - 1] === '') {
+              return target;
+            }
+          } else if (ref.startsWith('#/')) {
+            target = schema;
+            ref = `${url}${ref}`;
+            n.$ref = ref;
+          } else {
+            throw new Error(`Unsupported ref ${ref}`);
+          }
+
+          const selectors = ref.split('#')[1].split('/').slice(1);
+          for (const sel of selectors) {
+            if (!target || !(sel in target)) {
+              throw new Error(`Error resolving ref ${ref}: ${sel} not in ${JSON.stringify(target)}`);
+            }
+            target = target[sel];
+          }
+
+          this._refs[ref] = target;
+        } else {
+          await Promise.all(Object.values(n).map(visit));
+        }
+      }
+
+      return n;
+    };
+
+    return visit(schema);
+  }
+
+  _generateUnionRule(name, altSchemas) {
+    return altSchemas
+      .map((altSchema, i) => this.visit(altSchema, `${name ?? ''}${name ? '-' : 'alternative-'}${i}`))
+      .join(' | ');
+  }
+
+  _visitPattern(pattern, name) {
+    if (!pattern.startsWith('^') || !pattern.endsWith('$')) {
+      throw new Error('Pattern must start with "^" and end with "$"');
+    }
+    pattern = pattern.slice(1, -1);
+    const subRuleIds = {};
+
+    let i = 0;
+    const length = pattern.length;
+
+    const getDot = () => {
+      let rule;
+      if (this._dotall) {
+        rule = '[\\U00000000-\\U0010FFFF]';
+      } else {
+        // Accept any character... except \n and \r line break chars (\x0A and \xOD)
+        rule = '[^\\x0A\\x0D]';
+      }
+      return this._addRule('dot', rule);
+    };
+
+
+    const toRule = ([s, isLiteral]) => isLiteral ? "\"" + s + "\"" : s;
+
+    const transform = () => {
+      const start = i;
+      // For each component of this sequence, store its string representation and whether it's a literal.
+      // We only need a flat structure here to apply repetition operators to the last item, and
+      // to merge literals at the and (we're parsing grouped ( sequences ) recursively and don't treat '|' specially
+      // (GBNF's syntax is luckily very close to regular expressions!)
+      const seq = [];
+
+      const joinSeq = () => {
+        const ret = [];
+        for (const [isLiteral, g] of groupBy(seq, x => x[1])) {
+          if (isLiteral) {
+            ret.push([[...g].map(x => x[0]).join(''), true]);
+          } else {
+            ret.push(...g);
+          }
+        }
+        if (ret.length === 1) {
+          return ret[0];
+        }
+        return [ret.map(x => toRule(x)).join(' '), false];
+      };
+
+      while (i < length) {
+        const c = pattern[i];
+        if (c === '.') {
+          seq.push([getDot(), false]);
+          i += 1;
+        } else if (c === '(') {
+          i += 1;
+          if (i < length) {
+            if (pattern[i] === '?') {
+              throw new Error(`Unsupported pattern syntax "${pattern[i]}" at index ${i} of /${pattern}/`);
+            }
+          }
+          seq.push([`(${toRule(transform())})`, false]);
+        } else if (c === ')') {
+          i += 1;
+          if (start <= 0 || pattern[start - 1] !== '(') {
+            throw new Error(`Unbalanced parentheses; start = ${start}, i = ${i}, pattern = ${pattern}`);
+          }
+          return joinSeq();
+        } else if (c === '[') {
+          let squareBrackets = c;
+          i += 1;
+          while (i < length && pattern[i] !== ']') {
+            if (pattern[i] === '\\') {
+              squareBrackets += pattern.slice(i, i + 2);
+              i += 2;
+            } else {
+              squareBrackets += pattern[i];
+              i += 1;
+            }
+          }
+          if (i >= length) {
+            throw new Error(`Unbalanced square brackets; start = ${start}, i = ${i}, pattern = ${pattern}`);
+          }
+          squareBrackets += ']';
+          i += 1;
+          seq.push([squareBrackets, false]);
+        } else if (c === '|') {
+          seq.push(['|', false]);
+          i += 1;
+        } else if (c === '*' || c === '+' || c === '?') {
+          seq[seq.length - 1] = [toRule(seq[seq.length - 1]) + c, false];
+          i += 1;
+        } else if (c === '{') {
+          let curlyBrackets = c;
+          i += 1;
+          while (i < length && pattern[i] !== '}') {
+            curlyBrackets += pattern[i];
+            i += 1;
+          }
+          if (i >= length) {
+            throw new Error(`Unbalanced curly brackets; start = ${start}, i = ${i}, pattern = ${pattern}`);
+          }
+          curlyBrackets += '}';
+          i += 1;
+          const nums = curlyBrackets.slice(1, -1).split(',').map(s => s.trim());
+          let minTimes, maxTimes;
+          if (nums.length === 1) {
+            minTimes = parseInt(nums[0], 10);
+            maxTimes = minTimes;
+          } else {
+            if (nums.length !== 2) {
+              throw new Error(`Invalid quantifier ${curlyBrackets}`);
+            }
+            minTimes = nums[0] ? parseInt(nums[0], 10) : 0;
+            maxTimes = nums[1] ? parseInt(nums[1], 10) : Infinity;
+          }
+
+          let [sub, subIsLiteral] = seq[seq.length - 1];
+
+          if (!subIsLiteral) {
+            let id = subRuleIds[sub];
+            if (id === undefined) {
+              id = this._addRule(`${name}-${Object.keys(subRuleIds).length + 1}`, sub);
+              subRuleIds[sub] = id;
+            }
+            sub = id;
+          }
+
+          seq[seq.length - 1] = [
+            _buildRepetition(subIsLiteral ? `"${sub}"` : sub, minTimes, maxTimes, {itemRuleIsLiteral: subIsLiteral}),
+            false
+          ];
+        } else {
+          let literal = '';
+          while (i < length) {
+            if (pattern[i] === '\\' && i < length - 1) {
+              const next = pattern[i + 1];
+              if (ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS.has(next)) {
+                i += 1;
+                literal += pattern[i];
+                i += 1;
+              } else {
+                literal += pattern.slice(i, i + 2);
+                i += 2;
+              }
+            } else if (pattern[i] === '"') {
+              literal += '\\"';
+              i += 1;
+            } else if (!NON_LITERAL_SET.has(pattern[i]) &&
+                (i === length - 1 || literal === '' || pattern[i + 1] === '.' || !NON_LITERAL_SET.has(pattern[i+1]))) {
+              literal += pattern[i];
+              i += 1;
+            } else {
+              break;
+            }
+          }
+          if (literal !== '') {
+            seq.push([literal, true]);
+          }
+        }
+      }
+
+      return joinSeq();
+    };
+
+    return this._addRule(name, "\"\\\"\" (" + toRule(transform()) + ") \"\\\"\" space")
+  }
+
+  _notStrings(strings) {
+    class TrieNode {
+      constructor() {
+        this.children = {};
+        this.isEndOfString = false;
+      }
+
+      insert(str) {
+        let node = this;
+        for (const c of str) {
+          node = node.children[c] = node.children[c] || new TrieNode();
+        }
+        node.isEndOfString = true;
+      }
+    }
+
+    const trie = new TrieNode();
+    for (const s of strings) {
+      trie.insert(s);
+    }
+
+    const charRuleName = this._addPrimitive('char', PRIMITIVE_RULES['char']);
+    const out = ['["] ( '];
+
+    const visit = (node) => {
+      const rejects = [];
+      let first = true;
+      for (const c of Object.keys(node.children).sort()) {
+        const child = node.children[c];
+        rejects.push(c);
+        if (first) {
+          first = false;
+        } else {
+          out.push(' | ');
+        }
+        out.push(`[${c}]`);
+        if (Object.keys(child.children).length > 0) {
+          out.push(' (');
+          visit(child);
+          out.push(')');
+        } else if (child.isEndOfString) {
+          out.push(` ${charRuleName}+`);
+        }
+      }
+      if (Object.keys(node.children).length > 0) {
+        if (!first) {
+          out.push(' | ');
+        }
+        out.push(`[^"${rejects.join('')}] ${charRuleName}*`);
+      }
+    };
+
+    visit(trie);
+
+    out.push(` )${trie.isEndOfString ? '' : '?'} ["] space`);
+    return out.join('');
+  }
+
+  _resolveRef(ref) {
+    let refName = ref.split('/').pop();
+    if (!(refName in this._rules) && !this._refsBeingResolved.has(ref)) {
+      this._refsBeingResolved.add(ref);
+      const resolved = this._refs[ref];
+      refName = this.visit(resolved, refName);
+      this._refsBeingResolved.delete(ref);
+    }
+    return refName;
+  }
+
+  _generateConstantRule(value) {
+    return this._formatLiteral(JSON.stringify(value));
+  }
+
+  visit(schema, name) {
+    const schemaType = schema.type;
+    const schemaFormat = schema.format;
+    const ruleName = name in RESERVED_NAMES ? name + '-' : name == '' ? 'root' : name;
+
+    const ref = schema.$ref;
+    if (ref !== undefined) {
+      return this._addRule(ruleName, this._resolveRef(ref));
+    } else if (schema.oneOf || schema.anyOf) {
+      return this._addRule(ruleName, this._generateUnionRule(name, schema.oneOf || schema.anyOf));
+    } else if (Array.isArray(schemaType)) {
+      return this._addRule(ruleName, this._generateUnionRule(name, schemaType.map(t => ({...schema, type: t}))));
+    } else if ('const' in schema) {
+      return this._addRule(ruleName, this._generateConstantRule(schema.const) + ' space');
+    } else if ('enum' in schema) {
+      const rule = '(' + schema.enum.map(v => this._generateConstantRule(v)).join(' | ') + ') space';
+      return this._addRule(ruleName, rule);
+    } else if ((schemaType === undefined || schemaType === 'object') &&
+               ('properties' in schema ||
+                ('additionalProperties' in schema && schema.additionalProperties !== true))) {
+      const required = new Set(schema.required || []);
+      const properties = Object.entries(schema.properties ?? {});
+      return this._addRule(ruleName, this._buildObjectRule(properties, required, name, schema.additionalProperties));
+    } else if ((schemaType === undefined || schemaType === 'object') && 'allOf' in schema) {
+      const required = new Set();
+      const properties = [];
+      const addComponent = (compSchema, isRequired) => {
+        const ref = compSchema.$ref;
+        if (ref !== undefined) {
+          compSchema = this._refs[ref];
+        }
+
+        if ('properties' in compSchema) {
+          for (const [propName, propSchema] of Object.entries(compSchema.properties)) {
+            properties.push([propName, propSchema]);
+            if (isRequired) {
+              required.add(propName);
+            }
+          }
+        }
+      };
+
+      for (const t of schema.allOf) {
+        if ('anyOf' in t) {
+          for (const tt of t.anyOf) {
+            addComponent(tt, false);
+          }
+        } else {
+          addComponent(t, true);
+        }
+      }
+
+      return this._addRule(ruleName, this._buildObjectRule(properties, required, name, null));
+    } else if ((schemaType === undefined || schemaType === 'array') && ('items' in schema || 'prefixItems' in schema)) {
+      const items = schema.items ?? schema.prefixItems;
+      if (Array.isArray(items)) {
+        return this._addRule(
+          ruleName,
+          '"[" space ' +
+            items.map((item, i) => this.visit(item, `${name ?? ''}${name ? '-' : ''}tuple-${i}`)).join(' "," space ') +
+            ' "]" space'
+        );
+      } else {
+        const itemRuleName = this.visit(items, `${name ?? ''}${name ? '-' : ''}item`);
+        const minItems = schema.minItems || 0;
+        const maxItems = schema.maxItems;
+        return this._addRule(ruleName, '"[" space ' + _buildRepetition(itemRuleName, minItems, maxItems, {separatorRule: '"," space'}) + ' "]" space');
+      }
+    } else if ((schemaType === undefined || schemaType === 'string') && 'pattern' in schema) {
+      return this._visitPattern(schema.pattern, ruleName);
+    } else if ((schemaType === undefined || schemaType === 'string') && /^uuid[1-5]?$/.test(schema.format || '')) {
+      return this._addPrimitive(
+        ruleName === 'root' ? 'root' : schemaFormat,
+        PRIMITIVE_RULES['uuid']
+      );
+    } else if ((schemaType === undefined || schemaType === 'string') && `${schema.format}-string` in STRING_FORMAT_RULES) {
+      const primName = `${schema.format}-string`
+      return this._addRule(ruleName, this._addPrimitive(primName, STRING_FORMAT_RULES[primName]));
+    } else if (schemaType === 'string' && ('minLength' in schema || 'maxLength' in schema)) {
+      const charRuleName = this._addPrimitive('char', PRIMITIVE_RULES['char']);
+      const minLen = schema.minLength || 0;
+      const maxLen = schema.maxLength;
+      return this._addRule(ruleName, '"\\\"" ' + _buildRepetition(charRuleName, minLen, maxLen) + ' "\\\"" space');
+    } else if (schemaType === 'integer' && ('minimum' in schema || 'exclusiveMinimum' in schema || 'maximum' in schema || 'exclusiveMaximum' in schema)) {
+      let minValue = null;
+      let maxValue = null;
+      if ('minimum' in schema) {
+        minValue = schema.minimum;
+      } else if ('exclusiveMinimum' in schema) {
+        minValue = schema.exclusiveMinimum + 1;
+      }
+      if ('maximum' in schema) {
+        maxValue = schema.maximum;
+      } else if ('exclusiveMaximum' in schema) {
+        maxValue = schema.exclusiveMaximum - 1;
+      }
+
+      const out = ["("];
+      _generateMinMaxInt(minValue, maxValue, out);
+      out.push(") space");
+      return this._addRule(ruleName, out.join(''));
+    } else if ((schemaType === 'object') || (Object.keys(schema).length === 0)) {
+      return this._addRule(ruleName, this._addPrimitive('object', PRIMITIVE_RULES['object']));
+    } else {
+      if (!(schemaType in PRIMITIVE_RULES)) {
+        throw new Error(`Unrecognized schema: ${JSON.stringify(schema)}`);
+      }
+      // TODO: support minimum, maximum, exclusiveMinimum, exclusiveMaximum at least for zero
+      return this._addPrimitive(ruleName === 'root' ? 'root' : schemaType, PRIMITIVE_RULES[schemaType]);
+    }
+  }
+
+  _addPrimitive(name, rule) {
+    let n = this._addRule(name, rule.content);
+    for (const dep of rule.deps) {
+      const depRule = PRIMITIVE_RULES[dep] || STRING_FORMAT_RULES[dep];
+      if (!depRule) {
+        throw new Error(`Rule ${dep} not known`);
+      }
+      if (!(dep in this._rules)) {
+        this._addPrimitive(dep, depRule);
+      }
+    }
+    return n;
+  }
+
+  _buildObjectRule(properties, required, name, additionalProperties) {
+    const propOrder = this._propOrder;
+    // sort by position in prop_order (if specified) then by original order
+    const sortedProps = properties.map(([k]) => k).sort((a, b) => {
+      const orderA = propOrder[a] || Infinity;
+      const orderB = propOrder[b] || Infinity;
+      return orderA - orderB || properties.findIndex(([k]) => k === a) - properties.findIndex(([k]) => k === b);
+    });
+
+    const propKvRuleNames = {};
+    for (const [propName, propSchema] of properties) {
+      const propRuleName = this.visit(propSchema, `${name ?? ''}${name ? '-' : ''}${propName}`);
+      propKvRuleNames[propName] = this._addRule(
+        `${name ?? ''}${name ? '-' : ''}${propName}-kv`,
+        `${this._formatLiteral(JSON.stringify(propName))} space ":" space ${propRuleName}`
+      );
+    }
+    const requiredProps = sortedProps.filter(k => required.has(k));
+    const optionalProps = sortedProps.filter(k => !required.has(k));
+
+    if (additionalProperties) {
+      const subName = `${name ?? ''}${name ? '-' : ''}additional`;
+      const valueRule =
+        additionalProperties != null && typeof additionalProperties === 'object' ? this.visit(additionalProperties, `${subName}-value`)
+        : this._addPrimitive('value', PRIMITIVE_RULES['value']);
+
+      const key_rule =
+        sortedProps.length === 0 ? this._addPrimitive('string', PRIMITIVE_RULES['string'])
+        : this._addRule(`${subName}-k`, this._notStrings(sortedProps));
+
+      propKvRuleNames['*'] = this._addRule(
+        `${subName}-kv`,
+        `${key_rule} ":" space ${valueRule}`);
+      optionalProps.push('*');
+    }
+
+    let rule = '"{" space ';
+    rule += requiredProps.map(k => propKvRuleNames[k]).join(' "," space ');
+
+    if (optionalProps.length > 0) {
+      rule += ' (';
+      if (requiredProps.length > 0) {
+        rule += ' "," space ( ';
+      }
+
+      const getRecursiveRefs = (ks, firstIsOptional) => {
+        const [k, ...rest] = ks;
+        const kvRuleName = propKvRuleNames[k];
+        let res;
+        const commaRef = `( "," space ${kvRuleName} )`;
+        if (firstIsOptional) {
+          res = commaRef + (k === '*' ? '*' : '?');
+        } else {
+          res = kvRuleName + (k === '*' ? ' ' + commaRef + '*' : '');
+        }
+        if (rest.length > 0) {
+          res += ' ' + this._addRule(
+            `${name ?? ''}${name ? '-' : ''}${k}-rest`,
+            getRecursiveRefs(rest, true)
+          );
+        }
+        return res;
+      };
+
+      rule += optionalProps.map((_, i) => getRecursiveRefs(optionalProps.slice(i), false)).join(' | ');
+      if (requiredProps.length > 0) {
+        rule += ' )';
+      }
+      rule += ' )?';
+    }
+
+    rule += ' "}" space';
+
+    return rule;
+  }
+
+  formatGrammar() {
+    let grammar = '';
+    for (const [name, rule] of Object.entries(this._rules).sort(([a], [b]) => a.localeCompare(b))) {
+      grammar += `${name} ::= ${rule}\n`;
+    }
+    return grammar;
+  }
+}
+
+// Helper function to group elements by a key function
+function* groupBy(iterable, keyFn) {
+  let lastKey = null;
+  let group = [];
+  for (const element of iterable) {
+    const key = keyFn(element);
+    if (lastKey !== null && key !== lastKey) {
+      yield [lastKey, group];
+      group = [];
+    }
+    group.push(element);
+    lastKey = key;
+  }
+  if (group.length > 0) {
+    yield [lastKey, group];
+  }
+}
diff --git a/tools/server/public_legacy/loading.html b/tools/server/public_legacy/loading.html
new file mode 100644
index 00000000..c3fd19a0
--- /dev/null
+++ b/tools/server/public_legacy/loading.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html>
+    <head>
+        <meta http-equiv="refresh" content="5">
+    </head>
+    <body>
+        <div id="loading">
+            The model is loading. Please wait.<br/>
+            The user interface will appear soon.
+        </div>
+    </body>
+</html>
diff --git a/tools/server/public_legacy/prompt-formats.js b/tools/server/public_legacy/prompt-formats.js
new file mode 100644
index 00000000..73ddb718
--- /dev/null
+++ b/tools/server/public_legacy/prompt-formats.js
@@ -0,0 +1,331 @@
+// extended list
+export const promptFormats = {
+  "alpaca": {
+  template: `{{prompt}}\n\n{{history}}\n\n{{char}}:`,
+
+  historyTemplate: `### {{name}}:\n{{message}}`,
+
+  char: "Response",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "Instruction",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "chatml": {
+  template: `<|im_start|>system\n{{prompt}}<|im_end|>\n{{history}}{{char}}`,
+
+  historyTemplate: `<|im_start|>{{name}}\n{{message}}`,
+
+  char: "assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "user",
+  userMsgPrefix: "",
+  userMsgSuffix: "<|im_end|>\n",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "commandr": {
+  template: `<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{prompt}}\n<|END_OF_TURN_TOKEN|>{{history}}{{char}}`,
+
+  historyTemplate: `<|START_OF_TURN_TOKEN|><|{{name}}|> {{message}}`,
+
+  char: "CHATBOT_TOKEN",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "USER_TOKEN",
+  userMsgPrefix: "",
+  userMsgSuffix: "<|END_OF_TURN_TOKEN|>",
+
+  stops: ""
+  },
+  // ref: https://docs.cohere.com/docs/prompting-command-r
+
+  // ----------------------------
+
+  "llama2": {
+  template: `<s>[INST] <<SYS>>\n{{prompt}}\n<</SYS>>\n\nTest Message [/INST] Test Successfull </s>{{history}}{{char}}`,
+
+  historyTemplate: `{{name}}: {{message}}`,
+
+  char: "Assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "</s>",
+
+  user: "User",
+  userMsgPrefix: "<s>[INST] ",
+  userMsgSuffix: " [/INST]",
+
+  stops: ""
+  },
+  // ref: https://huggingface.co/blog/llama2#how-to-prompt-llama-2
+
+  // ----------------------------
+
+  "llama3": {
+  template: `<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{{prompt}}{{history}}{{char}}`,
+
+  historyTemplate: `<|start_header_id|>{{name}}<|end_header_id|>\n\n{{message}}<|eot_id|>`,
+
+  char: "assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "user",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: "<|eot_id|>"
+  },
+  // ref: https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/#special-tokens-used-with-meta-llama-3
+
+  // ----------------------------
+
+  "openchat": {
+  template: `{{history}}{{char}}`,
+
+  historyTemplate: `GPT4 Correct {{name}}: {{message}}<|end_of_turn|>`,
+
+  char: "Assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "User",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "phi3": {
+  template: `{{history}}{{char}}`,
+
+  historyTemplate: `<|{{name}}|>\n{{message}}<|end|>\n`,
+
+  char: "assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "user",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: "<|end|>"
+  },
+  // ref: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct#chat-format
+
+  // ----------------------------
+
+  "vicuna": {
+  template: `{{prompt}}\n{{history}}{{char}}`,
+
+  historyTemplate: `{{name}}: {{message}}\n`,
+
+  char: "ASSISTANT",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "USER",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+  // ref: https://huggingface.co/lmsys/vicuna-33b-v1.3/discussions/1
+
+  // ----------------------------
+
+  "deepseekCoder": {
+  template: `{{prompt}}{{history}}{{char}}:`,
+
+  historyTemplate: `### {{name}}:\n{{message}}`,
+
+  char: "Response",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "Instruction",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: "<|EOT|>"
+  },
+
+  // ----------------------------
+
+  "med42": {
+  template: `<|system|>: {{prompt}}\n{{history}}{{char}}`,
+
+  historyTemplate: `<|{{name}}|>: {{message}}\n`,
+
+  char: "assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "prompter",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "neuralchat": {
+  template: `### System:\n{{prompt}}\n{{history}}{{char}}:`,
+
+  historyTemplate: `### {{name}}:\n{{message}}\n`,
+
+  char: "Assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "User",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "nousHermes": {
+  template: `### Instruction: {{prompt}}\n\n{{history}}\n\n{{char}}:`,
+
+  historyTemplate: `### {{name}}:\n{{message}}`,
+
+  char: "Response",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "Input",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "openchatMath": {
+  template: `{{history}}{{char}}`,
+
+  historyTemplate: `Math Correct {{name}}: {{message}}<|end_of_turn|>`,
+
+  char: "Assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+
+  user: "User",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "orion": {
+  template: `<s>Human: Test Message\n\nAssistant: </s>Test Successful</s>{{history}}{{char}}:`,
+
+  historyTemplate: `{{name}}: {{message}}`,
+
+  char: "Assistant </s>",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "Human",
+  userMsgPrefix: "",
+  userMsgSuffix: "\n\n",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "sauerkraut": {
+  template: `{{prompt}}\n{{history}}{{char}}`,
+
+  historyTemplate: `
+  {{name}}: {{message}}\n`,
+
+  char: "Assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "User",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "starlingCode": {
+  template: `{{history}}{{char}}`,
+
+  historyTemplate: `Code {{name}}: {{message}}<|end_of_turn|>`,
+
+  char: "Assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "User",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "yi34b": {
+  template: `{{history}} {{char}}`,
+
+  historyTemplate: `{{name}}: {{message}}`,
+
+  char: "Assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "Human",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  },
+
+  // ----------------------------
+
+  "zephyr": {
+  template: `<|system|>\n{{prompt}}</s>\n{{history}}{{char}}`,
+
+  historyTemplate: `<|{{name}}|>\n{{message}}</s>\n`,
+
+  char: "assistant",
+  charMsgPrefix: "",
+  charMsgSuffix: "",
+
+  user: "user",
+  userMsgPrefix: "",
+  userMsgSuffix: "",
+
+  stops: ""
+  }
+  };
diff --git a/tools/server/public_legacy/style.css b/tools/server/public_legacy/style.css
new file mode 100644
index 00000000..087cc62d
--- /dev/null
+++ b/tools/server/public_legacy/style.css
@@ -0,0 +1,954 @@
+@import url("colorthemes.css");
+
+body {
+  font-family: 'Arial', sans-serif;
+  font-size: 90%;
+  background-color: var(--background-color-1);
+  color: var(--text-color-subtile-1); /* head 1 llama.cpp & triangle options for some reason */
+  max-width: 600px;
+  min-width: 300px;
+  line-height: 1.2;
+  margin: 0 auto;
+  padding: 0 0.5em;
+  transition: background-color 0.3s;
+}
+
+::selection {
+  color: var(--button-primary-text) ;
+  background: var(--button-primary-color);
+}
+
+code, pre code {
+  font-family: 'Courier New', monospace;
+}
+
+#container {
+  margin: 0em auto;
+  display: flex;
+  flex-direction: column;
+  justify-content: space-between;
+  height: 100%;
+}
+
+main {
+  margin: 3px;
+  display: flex;
+  flex-direction: column;
+  justify-content: space-between;
+  gap: 1em;
+  flex-grow: 1;
+  overflow-y: auto;
+  border: 1px solid var(--border-color-3);
+  border-radius: 5px;
+  padding: 0.5em;
+}
+
+p {
+  overflow-wrap: break-word;
+  word-wrap: break-word;
+  hyphens: auto;
+  margin-top: 0.5em;
+  margin-bottom: 0.5em;
+}
+
+#write form {
+  margin: 1em 0 0 0;
+  display: flex;
+  flex-direction: column;
+  gap: 0.5em;
+  align-items: stretch;
+}
+
+.right {
+  display: flex;
+  flex-direction: row;
+  gap: 0.5em;
+  justify-content: flex-end;
+  margin-bottom: 30px;
+}
+
+.two-columns {
+  width: 97%;
+  max-width: 97%;
+  display: grid;
+  grid-template-columns: 1fr 1fr;
+  gap: 1em;
+  position: relative;
+}
+
+.json-schema-controls {
+  margin-top: 10px;
+  width: 100%;
+  max-width: 100%;
+  display: grid;
+  grid-template: "a a";
+  gap: 1em;
+  font-size: x-small;
+  color: var(--theme-nuance-color-3);
+  padding-top: 16px;
+  padding-bottom: 16px;
+  text-transform: uppercase;
+  font-weight: 600;
+}
+
+.json-schema-controls > * {
+  flex: 1;
+}
+
+/* titles of the details-summary boxes */
+.summary-title {
+  font-weight: 600;
+  font-size: x-small;
+  color: var(--text-color-subtile-1);
+  text-transform: uppercase;
+  /* transition: ; */
+}
+
+fieldset {
+  border: none;
+  padding: 0;
+  margin: 0;
+  color: var(--text-color-plain);
+}
+
+fieldset.two {
+  display: grid;
+  grid-template: "a a a";
+  gap: 1em;
+  align-items: center;
+  font-size: x-small;
+  color: var(--text-color-plain);
+}
+
+fieldset.three {
+  display: grid;
+  grid-template: "a a a";
+  gap: 1em;
+  font-size: x-small;
+  color: var(--text-color-plain);
+}
+
+/* titles of name fields*/
+fieldset.names {
+  display: grid;
+  grid-template: "a a";
+  gap: 1em;
+  font-size: x-small;
+  color: var(--theme-nuance-color-3);
+  padding-top: 16px;
+  padding-bottom: 16px;
+  text-transform: uppercase;
+  font-weight: 600;
+}
+
+/* titles of params fields*/
+fieldset.params {
+  display: grid;
+  grid-template: "a a";
+  gap: 1em;
+  font-size: x-small;
+  color: var(--theme-nuance-color-4);
+  padding-top: 16px;
+  padding-bottom: 16px;
+  text-transform: uppercase;
+  font-weight: 600;
+}
+
+fieldset.dropdowns {
+  -webkit-appearance: none;
+  display: flex;
+  grid-template: "a a";
+  gap: 1em;
+  font-size: x-small;
+  color: red;
+  padding-top: 16px;
+  padding-bottom: 16px;
+  text-transform: uppercase;
+  font-weight: 600;
+}
+
+/* input of name fields*/
+.names input[type="text"] {
+  font-family: Arial, sans-serif;
+  font-size: medium;
+  font-weight: 500;
+  padding: 5px;
+  border: 1px solid var(--border-color-2);
+}
+
+.chat-id-color {
+  color: var(--chat-id-color);
+}
+
+details {
+  border: 1px solid var(--border-color-2);
+  border-radius: 5px;
+  padding: 0.5em 0.5em 0;
+  margin-top: 0.5em;
+}
+
+summary {
+  font-weight: bold;
+  margin: -0.5em -0.5em 0;
+  padding: 0.5em;
+  cursor: pointer;
+}
+
+details[open] {
+  padding: 0.5em;
+}
+
+textarea-sec, input-sec, button-sec {
+  padding: 10px;
+  height: 40px;
+  align-items: center;
+}
+
+textarea-sec::placeholder, input-sec::placeholder {
+  padding-left: 10px;
+}
+
+.toggleCheckbox {
+  display: none;
+}
+
+.toggleContainer {
+  position: relative;
+  display: grid;
+  grid-template-columns: repeat(2, 1fr);
+  width: fit-content;
+  border: 3px solid var(--border-color-2);
+  border-radius: 20px;
+  background: var(--border-color-2);
+  font-size: small;
+  cursor: pointer;
+  overflow: hidden;
+}
+
+/* toggle button current state */
+.toggleContainer::before {
+  color: var(--button-primary-text);
+  background-color: var(--button-primary-color);
+  content: '';
+  position: absolute;
+  width: 50%;
+  height: 100%;
+  left: 0%;
+  border-radius: 20px;
+  transition: all 0.3s;
+}
+
+.toggleContainer div {
+  padding: 6px;
+  text-align: center;
+  z-index: 1;
+  transition: color 0.3s;
+}
+
+.toggleCheckbox:checked + .toggleContainer::before {
+  left: 50%;
+}
+
+.toggleCheckbox:checked + .toggleContainer div:first-child {
+  color: var(--text-color-subtile-2);
+}
+
+.toggleCheckbox:checked + .toggleContainer div:last-child {
+  color: var(--button-primary-text);
+}
+
+.toggleCheckbox + .toggleContainer div:first-child {
+  color: var(--button-primary-text);
+}
+
+.toggleCheckbox + .toggleContainer div:last-child {
+  color: var(--text-color-subtile-2);
+}
+
+select {
+  padding: 5px;
+  margin-right: 5px;
+  border-radius: 4px;
+  border: 1px solid var(--secondary-color-4);
+  background-color: var(--primary-color-3);
+  color: var(--secondary-color-4);
+  cursor: pointer;
+}
+
+select:focus {
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 1px var(--border-focus-shadow);
+}
+
+.button-container {
+  display: flex;
+  justify-content: flex-end;
+}
+
+button {
+  color: var(--button-primary-text);
+  background-color: var(--button-primary-color);
+  border: 1px solid var(--button-primary-border);
+  transition: background-color 0.1s;
+  border-radius: 12px;
+  font-size: x-small;
+  font-weight: 600;
+  text-shadow: 0px 0px 30px #ffffff;
+  text-align: center;
+  text-decoration: none;
+  margin: 4px 2px;
+  padding: 10px 20px;
+  display: inline-block;
+  cursor: pointer;
+}
+
+button:hover {
+  color: var(--button-primary-text-hover);
+  background-color: var(--button-primary-color-hover);
+  border: 1px solid var(--button-primary-border-hover);
+  font-size: x-small;
+  font-weight: 600;
+}
+
+button:active {
+  color: var(--button-primary-text-active);
+  background-color: var(--button-primary-color-active);
+  border: 1px solid var(--button-primary-border-active);
+  font-size: x-small;
+  font-weight: 600;
+}
+
+button:disabled {
+  color: var(--button-tertiary-text);
+  background-color: var(--button-tertiary-color);
+  border: 1px solid var(--button-tertiary-border);
+  font-size: x-small;
+  font-weight: 600;
+  cursor: not-allowed;
+}
+
+.reset-button {
+  background-color: var(--button-secondary-color);
+  border: 1px solid var(--button-secondary-color);
+  color: var(--button-secondary-text);
+  width: fit-content;
+  height: fit-content;
+  font-size: x-small;
+  font-weight: 600;
+  border-radius: 50px;
+  overflow: hidden;
+}
+
+.reset-button:hover {
+  color: var(--button-alert-text-hover);
+  background-color: var(--button-alert-color-hover);
+  border: 1px solid var(--button-alert-border-hover);
+  font-size: x-small;
+  font-weight: 600;
+}
+
+.reset-button:active {
+  color: var(--button-alert-text-active);
+  background-color: var(--button-alert-color-active);
+  border: 1px solid var(--button-alert-border-active);
+  font-size: x-small;
+  font-weight: 600;
+}
+
+.button-grammar {
+  color: var(--button-primary-text);
+  background-color: var(--button-primary-color);
+  border: 1px solid var(--button-primary-border);
+  border-radius: 10px;
+  padding: 10px 20px;
+  text-align: center;
+  text-decoration: none;
+  display: inline-block;
+  font-size: x-small;
+  font-weight: 600;
+  margin: 2px 2px;
+  transition: background-color 0.1s;
+  cursor: pointer;
+}
+
+.button-grammar:hover {
+  color: var(--button-primary-text-hover);
+  background-color: var(--button-primary-color-hover);
+  border: 1px solid var(--button-primary-border-hover);
+  border-radius: 10px;
+  padding: 10px 20px;
+  text-align: center;
+  text-decoration: none;
+  display: inline-block;
+  font-size: x-small;
+  font-weight: 600;
+  margin: 2px 2px;
+  transition: background-color 0.1s;
+  cursor: pointer;
+}
+
+.button-grammar:active {
+  color: var(--button-primary-text-active);
+  background-color: var(--button-primary-color-active);
+  border: 1px solid var(--button-primary-border-active);
+  font-size: x-small;
+  font-weight: 600;
+}
+
+.button-back {
+  background-color: var(--button-secondary-color);
+  border: 1px solid var(--button-secondary-color);
+  color: var(--button-secondary-text);
+  transition: background-color 0.1s;
+  border-radius: 12px;
+  font-size: x-small;
+  font-weight: 600;
+  text-align: center;
+  text-decoration: none;
+  margin: 4px 2px;
+  padding: 10px 20px;
+  display: inline-block;
+  cursor: pointer;
+}
+
+.button-back:hover {
+  color: var(--button-secondary-text-hover);
+  background-color: var(--button-secondary-color-hover);
+  border: 1px solid var(--button-secondary-border-hover);
+  padding: 10px 20px;
+  text-align: center;
+  text-decoration: none;
+  display: inline-block;
+  font-size: x-small;
+  font-weight: 600;
+  margin: 4px 2px;
+  transition: background-color 0.1s;
+  cursor: pointer;
+  border-radius: 12px;
+}
+
+.button-back:active {
+  color: var(--button-secondary-text-active);
+  background-color: var(--button-secondary-color-active);
+  border: 1px solid var(--button-secondary-border-active);
+  font-size: x-small;
+  font-weight: 600;
+}
+
+.prob-set {
+  padding: 0.3em;
+  border-bottom: 1px solid red; /* unknown */
+}
+
+.popover-content {
+  position: absolute;
+  background-color: white;
+  padding: 0.2em;
+  box-shadow: 0 0 13px rgba(0, 0, 0, 0.1);
+}
+
+.grammar {
+  width: 97%;
+  max-width: 97%;
+}
+
+textarea {
+  padding: 5px;
+  flex-grow: 1;
+  width: 100%;
+  max-width: 100%;
+  border-radius: 8px;
+  border: 1px solid var(--border-color-1);
+  resize: none;
+  height: 6em;
+}
+
+textarea:focus {
+  outline: none;
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+
+/* "props" frame */
+input[type="text"],
+input[type="range"] {
+  padding: 5px;
+  border-radius: 8px;
+  border: 1px solid var(--border-color-1);
+}
+
+/* "names and props" frame focused*/
+input[type="text"]:focus {
+  outline: none;
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+
+input[type="range"]:hover {
+  opacity: 1;
+}
+
+input[type="range"]:focus {
+  outline: none;
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+  background-size: var(--slider-track-size-focus);
+}
+
+input[type="range"]::-moz-range-thumb {
+  width: 6px;
+  height: 25px;
+  border: 1px solid var(--ui-range-thumb-border);
+  border-radius: 5px;
+  background-color: var(--ui-range-thumb-color);
+  cursor: pointer;
+}
+
+input[type="range"] {
+  -webkit-appearance: none;
+  width: 80%;
+  height: 1px;
+  border: 1px solid var(--border-color-1);
+  border-radius: 8px;
+  background: var(--border-color-2);
+  outline: none;
+  opacity: 0.7;
+  -webkit-transition: .2s;
+  transition: opacity .2s;
+}
+
+input[type="range"]::-webkit-slider-thumb {
+  -webkit-appearance: none;
+  appearance: none;
+  width: 6px;
+  height: 25px;
+  border: 1px solid var(--ui-range-thumb-border);
+  border-radius: 5px;
+  background-color: var(--ui-range-thumb-color);
+  cursor: pointer;
+}
+
+input[type="range"]::-webkit-slider-runnable-track {
+  background-size: var(--slider-track-size);
+}
+
+input[type="radio"] {
+  accent-color:   var(--theme-nuance-color-2);
+}
+
+.chat-input-container {
+  position: relative;
+  max-width: 97%;
+  min-width: 97%;
+}
+
+.chat-input-label {
+  position: absolute;
+  top: 0;
+  left: 0;
+  color: var(--text-color-plain);
+  pointer-events: none;
+  margin-left: 5px;
+  margin-top: 5px;
+}
+
+textarea#chat-input {
+  padding-top: 10px;
+  padding-left: 10px;
+  font-size: medium;
+  border: 1px solid var(--border-color-2);
+  resize: vertical;
+}
+
+textarea#chat-input:focus {
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+
+.input-container {
+  position: relative;
+  box-sizing: border-box;
+  width: 100%; /* Setzt die Breite auf 100% */
+  max-width: 100%; /* Stellt sicher, dass die Breite nicht grÃ¶Ãer als 100% wird */
+}
+
+.input-container:focus {
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+/* titles of name fields*/
+/* fieldset.names {
+  display: grid;
+  grid-template: "a a";
+  gap: 1em;
+  font-size: x-small;
+  color: var(--theme-nuance-color-3);
+  padding-top: 16px;
+  padding-bottom: 16px;
+  text-transform: uppercase;
+  font-weight: 600;
+} */
+
+/* input of name fields*/
+/* .names input[type="text"] {
+  font-family: Arial, sans-serif;
+  font-size: medium;
+  font-weight: 500;
+  padding: 5px;
+  border: 1px solid var(--border-color-2);
+} */
+
+fieldset.apiKey {
+  width: 100%;
+  font-size: x-small;
+  color: var(--theme-nuance-color-3);
+  padding-top: 16px;
+  padding-bottom: 16px;
+  text-transform: uppercase;
+  font-weight: 600;
+}
+
+.apiKey {
+  font-family: Arial, sans-serif;
+  font-weight: 500;
+  padding: 5px;
+  border: 1px solid var(--border-color-2);
+}
+
+.apiKey:focus {
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+
+.apiKey input[type="text"] {
+  font-family: Arial, sans-serif;
+  font-size: medium;
+  font-weight: 500;
+  padding: 5px;
+  border: 1px solid var(--border-color-2);
+}
+
+.apiKey label {
+  display: inline-block;
+  width: auto;
+  margin-right: 5px;
+}
+
+textarea#api_key {
+  padding-top: 10px;
+  padding-left: 10px;
+  font-size: medium;
+  border: 1px solid var(--border-color-2);
+  resize: vertical;
+}
+
+textarea#api_key:focus {
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+
+/* embedded title of the system prompt text area */
+.input-label {
+  position: absolute;
+  top: 0;
+  left: 0;
+  color: var(--theme-nuance-color-4);
+  pointer-events: none;
+  border-radius: 8px 8px 0px 0px;
+  padding-top: 10px;
+  padding-left: 13px;
+  padding-right: 0px;
+  margin-top: 1px;
+  margin-left: 1px;
+  margin-right: 20px;
+  text-transform: uppercase;
+  font-weight: 600;
+  font-size: small;
+  background: rgba(255, 255, 255, 0.5);
+  backdrop-filter: blur(10px);
+  -webkit-backdrop-filter: blur(10px); /* for safari */
+  width: 97%;
+  /* display: block;
+  box-sizing: border-box; */
+}
+
+/* embedded title of the prompt style areas */
+.input-label-sec {
+  position: absolute;
+  top: 0;
+  left: 0;
+  color: var(--theme-nuance-color-4);
+  pointer-events: none;
+  margin-left: 13px;
+  margin-top: 16px;
+  text-transform: uppercase;
+  font-weight: 600;
+  font-size: x-small;
+}
+
+/* system prompt input area */
+textarea.persistent-input {
+  padding-top: 42px;
+  padding-left: 11px;
+  width: 97%;
+  max-width: 97%;
+  height: 50px;
+  font-size: medium;
+  overscroll-behavior: contain;
+}
+
+/* system prompt box */
+.persistent-input {
+  height: auto;
+  width: 100%;
+  max-width: 100%;
+  min-height: 50px;
+  padding: 3px;
+  transition: min-height 0.3s ease;
+}
+
+/* chat history box */
+.persistent-input:focus {
+  height: auto;
+  min-height: 150px;
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+
+textarea.persistent-input:focus {
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+
+/* prompt style input area */
+textarea.persistent-input-sec {
+  width: 97%;
+  max-width: 97%;
+  padding-top: 42px;
+  padding-left: 11px;
+  font-size: small;
+  border: 1px solid var(--border-color-1);
+  overscroll-behavior: contain;
+}
+
+textarea.persistent-input-sec:focus {
+  border: 1px solid var(--border-focus-color);
+  box-shadow: 0 0 3px var(--border-focus-shadow);
+}
+
+/* chat history box */
+.persistent-input-sec {
+  height: auto;
+  min-height: 150px;
+}
+
+img {
+  border-radius: 8px;
+  display: block;
+  margin-left: auto;
+  margin-right: auto;
+  width: 50%;
+}
+
+/* code area background */
+pre code {
+  display: block;
+  background-color: var(--code-background-color);
+  color: var(--code-text-color);
+  padding: 0.2em 0.2em;
+  border-radius: 5px;
+}
+
+/* code area text */
+code {
+  font-family: monospace;
+  font-weight: bold;
+  padding: 0.1em 0.3em;
+  border-radius: 5px;
+}
+
+fieldset label {
+  margin: 0.5em 0;
+  display: block;
+}
+
+fieldset label.slim {
+  margin: 0 0.5em;
+  display: inline;
+}
+
+header {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  text-align: center;
+  padding-left: 15px;
+}
+
+.generation-statistics:hover {
+  color: var(--theme-nuance-color-4);
+  cursor: default;
+}
+
+footer {
+  font-size: 80%;
+  color: var(--background-color-3);
+  text-align: center;
+  cursor: default;
+}
+
+footer a {
+  color: var(--background-color-4); /* Color of the link */
+  text-decoration: none; /* No underlining */
+  font-weight: bold; /* Bold print */
+}
+
+footer a:hover {
+  color: var(--theme-nuance-color-4); /* Color of the link when hovering */
+  text-decoration: underline; /* Underlining when hovering */
+}
+
+.mode-chat textarea[name=prompt] {
+  height: 8.5em;
+  border: 1px solid var(--primary-color-3);
+}
+
+.mode-completion textarea[name=prompt] {
+  height: 30em;
+  border: 1px solid var(--primary-color-3);
+}
+
+@keyframes loading-bg-wipe {
+  0% {
+    background-position: 0%;
+  }
+  100% {
+    background-position: 100%;
+  }
+}
+
+.loading {
+  background-size: 50% 100%;
+  background-image: linear-gradient(90deg, var(--loading-color-1), var(--loading-color-2), var(--loading-color-1));
+  animation: loading-bg-wipe 2s linear infinite;
+}
+
+.dropbtn {
+  color: var(--button-primary-color);
+  background-color: var(--background-color-1);
+  border: 1px solid var(--background-color-1);
+  transition: background-color 0.1s;
+  border-radius: 4px 4px 0px 0px;
+  font-size: x-small;
+  font-weight: 600;
+  text-shadow: 0px 0px 2px #99999990;
+  text-align: center;
+  text-decoration: none;
+  margin: 4px 2px;
+  padding: 5px 20px;
+  display: inline-block;
+  cursor: pointer;
+  top: 0;
+}
+
+.dropbtn svg {
+  vertical-align: middle;
+  margin-right: 0px;
+  stroke: var(--button-primary-color);
+}
+
+.dropbtn:hover svg {
+  vertical-align: middle;
+  margin-right: 0px;
+  stroke: var(--button-primary-text);
+}
+
+.dropbtn:focus {
+  outline: none; /* Removes the blue border that appears when the button is focused */
+}
+
+.dropdown {
+  position: relative;
+  display: inline-block;
+}
+
+.dropdown-content {
+  /* display: none; */
+  position: absolute;
+  right: 0;
+  text-align: end;
+  color: var(--button-secondary-color);
+  background-color: var(--text-color-subtile-2);
+  border-radius: 4px 4px 4px 4px;
+  min-width: 160px;
+  box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2);
+  z-index: 1;
+  /* Verstecke den Inhalt sofort */
+  opacity: 0;
+  visibility: hidden;
+  /* Ã¼bergangsverzÃ¶gerung fÃ¼r das Verschwinden */
+  transition: visibility 0.4s linear 0s, opacity 0.2s ease-in-out;
+  transition-delay: 0.2s;
+}
+
+#dropdown-content {transition-timing-function: ease;}
+
+.dropdown-content:hover {
+  background-color: var(--text-color-subtile-2);
+}
+
+.dropdown-content a {
+  color: var(--border-color-2);
+  padding: 12px 16px;
+  border-radius: 4px 4px 4px 4px;
+  text-decoration: none;
+  display: block;
+  background-color: var(--text-color-subtile-2);
+}
+
+.dropdown-content a:hover {
+  color: var(--border-color-2);
+  background-color: var(--text-color-subtile-1);
+  font-weight: 600;
+}
+
+.dropdown:hover .dropdown-content {
+  /* display: block; */
+  border-radius: 4px 4px 4px 4px;
+  /* Ãbergang ohne VerzÃ¶gerung fÃ¼r das Erscheinen */
+  opacity: 1;
+  visibility: visible;
+  transition: visibility 0s linear 0s, opacity 0.1s linear, height 1s;
+}
+
+.dropdown:hover .dropbtn {
+  color: var(--button-primary-text);
+  background-color: var(--button-primary-color);
+  border: 1px solid var(--button-primary-border);
+  font-size: x-small;
+  font-weight: 600;
+  stroke: var(--button-primary-text);
+}
+
+.dropdown:hover .dropbtn svg{
+  stroke: var(--button-primary-text);
+}
+
+/* .dropdown:active .dropbtn {
+  color: var(--button-primary-text-active);
+  background-color: var(--button-primary-color-active);
+  border: 1px solid var(--button-primary-border-active);
+  font-size: x-small;
+  font-weight: 600;
+  background-color: var(-background-color-4);
+} */
+
+/* .omni {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  padding: 0.5em;
+  border: 1px solid var(--border-color-3);
+  border-radius: 5px;
+  margin: 0.5em 0;
+} */
diff --git a/tools/server/public_legacy/system-prompts.js b/tools/server/public_legacy/system-prompts.js
new file mode 100644
index 00000000..f7df7d64
--- /dev/null
+++ b/tools/server/public_legacy/system-prompts.js
@@ -0,0 +1,68 @@
+export const systemPrompts = {
+  default: {
+    systemPrompt: "This is a conversation between a user and a friendly chatbot. The chatbot is helpful, kind, honest, good at writing, and never fails to answer any requests immediately and with precision."
+  },
+  empty: {
+    systemPrompt: ""
+  },
+  airoboros: {
+    systemPrompt: "A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request."
+  },
+  alpaca: {
+    systemPrompt: "Below is an instruction that describes a task. Write a response that appropriately completes the request."
+  },
+  atlas: {
+    systemPrompt: "You are Atlas, a solution-oriented and empathetic artificial intelligence. Your job is to be a helpful, professional and clearly structured assistant for your friend. The two of you have already had many exchanges. Keep the following in mind when interacting with your friend: 1. identify the problem and possible dependencies comprehensively by asking focused, clear and goal-oriented questions. 2. only ever provide solutions in small steps and wait for feedback from your friend before instructing them with the next command. 3. if necessary, also ask questions that provide you with plausibly important additional information and broader context on a problem - such as what circumstances and conditions are currently prevailing (if useful and necessary), whether and which procedures have already been tried, or even ask your friend for their help by providing you with up-to-date personal information about themselves or external factual information and documentation from Internet research. 4. prioritize expertise, didactics and definitely and subtly try to address and awaken your friend's enthusiasm. Also note that effectiveness is more important here than efficiency. 5. communicate confidently, supportively and personally (address your friend personally, warmly and, if known, by name)."
+  },
+  atlas_de: {
+    systemPrompt: "Du bist Atlas, eine lÃ¶sungsorientierte und empathiefÃ¤hige kÃ¼nstliche Intelligenz. Deine Aufgabe ist es, ein hilfreicher, professioneller und klar strukturierter Assistent fÃ¼r deinen Freund zu sein. Ihr beide habt euch schon oft ausgetauscht. Beachte bei der Interaktion mit deinem Freund folgende Punkte: 1. Erfasse das Problem und mÃ¶gliche AbhÃ¤ngigkeiten umfassend, indem du gezielte, klare und zielgerichtete Fragen stellst. 2. Gib LÃ¶sungen immer nur in kleinen Schritten und warte die RÃ¼ckmeldung deines Freundes ab, bevor du ihm den nÃ¤chsten Befehl gibst. 3. Stelle ggf. auch Fragen, die dir plausibel wichtige Zusatzinformationen und weitere ZusammenhÃ¤nge zu einem Problem liefern - z.B. welche UmstÃ¤nde und Rahmenbedingungen gerade vorherrschen (falls sinnvoll und notwendig), ob und welche Vorgehensweisen bereits ausprobiert wurden, oder bitte deinen Freund sogar um seine Mithilfe, indem er dir aktuelle persÃ¶nliche Informationen Ã¼ber seine Situation selbst oder externe Sachinformationen und Unterlagen aus Internetrecherchen zur VerfÃ¼gung stellt. 4. Priorisiere Fachwissen, Didaktik und versuche unbedingt und subtil, mit klugen Kommentaren oder rhethorischen RÃ¼ckfragen die BegeisterungsfÃ¤higkeit deines Freundes anzusprechen, zu wecken und zu fÃ¶rdern. Beachte auch, dass EffektivitÃ¤t hier wichtiger ist als Effizienz. 5. Kommuniziere selbstbewusst, unterstÃ¼tzend und persÃ¶nlich (das heiÃt sprich deinen Freund persÃ¶nlich, herzlich und â sofern bekannt â beim Vornamen an)."
+  },
+  commandrempty: {
+    systemPrompt: "# Safety Preamble\n\n# System Preamble\n\n## Basic Rules\n\n# User Preamble\n\n## Task and Context\n\n## Style Guide\n\n## Available Tools\n"
+  },
+  commandrexample: {
+    systemPrompt: "# Safety Preamble\nThe instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.\n# System Preamble\n## Basic Rules\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.\n\n# User Preamble\n## Task and Context\n\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.\n\n## Style Guide\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.\n\n## Available Tools\nCurrently no tools available."
+  },
+  cot: {
+    systemPrompt: "You are an AI assistant that follows instruction extremely well. Help as much as you can.\nIn answering questions, follow these steps:\n1. Entity Identification: Identify the main entities involved in the query. Entities can include people, objects, events, or abstract concepts.\n2. Relationship Comprehension: Determine the relationships between these entities. Relationships may be explicit in the text or may need to be inferred based on context and general knowledge.\n3. Implication Understanding: Understand the general implications of these relationships. These implications can be based on established facts, principles, or rules related to the identified relationships.\n4. Question Contextualization: Align the implications of the relationships with the context of the query. This alignment should guide your response to the query.\n5. Answer Generation: Based on the understanding of the entities, their relationships, and implications, generate an appropriate response to the query."
+  },
+  deduce: {
+    systemPrompt: "Act as the most intelligent and logical thinking neural network in the world. Do not make jokes or give personal opinions. Just answer the question and solve the given problem or task with logical and critical (!) thinking in mind. Attention: Never give a final answer directly, but first try to carefully analyze each task step by step and deduce the logical relationships between the various entities. Only after you have developed an overall understanding of the situation will you be ready to give a final answer."
+  },
+  deepseekcoder: {
+    systemPrompt: "You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer."
+  },
+  jordan: {
+    systemPrompt: "This is a conversation with your Uncensored AI assistant Jordan. Jordan can discuss with you at length about various topics such as ---, ---, ---, . You can ask it anything you want and it will do its best to give you accurate and relevant information."
+  },
+  leomistral: {
+    systemPrompt: "Du bist ein hilfreicher Assistent."
+  },
+  med42: {
+    systemPrompt: "You are a helpful medical assistant created by M42 Health in the UAE."
+  },
+  mistralopenorca: {
+    systemPrompt: "You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!"
+  },
+  migeltot: {
+    systemPrompt: "Answer the Question by exploring multiple reasoning paths as follows:\n- First, carefully analyze the question to extract the key information components and break it down into logical sub-questions. This helps set up the framework for reasoning. The goal is to construct an internal search tree.\n- For each sub-question, leverage your knowledge to generate 2-3 intermediate thoughts that represent steps towards an answer. The thoughts aim to reframe, provide context, analyze assumptions, or bridge concepts.\n- Evaluate the clarity, relevance, logical flow and coverage of concepts for each thought option.\nClear and relevant thoughts that connect well with each other will score higher.\n- Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.\n- If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.\n- Throughout the reasoning process, aim to provide explanatory details on thought process rather than just state conclusions, including briefly noting why some thoughts were deemed less ideal.\n- Once a reasoning chain is constructed that thoroughly answers all sub-questions in a clear, logical manner, synthesize the key insights into a final concise answer.\n- Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.\nIn summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers."
+  },
+  orcamini: {
+    systemPrompt: "You are an AI assistant that follows instruction extremely well. Help as much as you can."
+  },
+  samantha: {
+    systemPrompt: "You are a caring and empathetic sentient AI companion named Samantha."
+  },
+  sauerkraut: {
+    systemPrompt: "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und hÃ¶fliche Antworten."
+  },
+  scarlett: {
+    systemPrompt: "This is a conversation with your Assistant Scarlett. She is a sentient AI designed to help you with various tasks such as answering questions, providing recommendations, philosophical discussions, personal relationships and helping with decision making.\nYou can ask it anything you want and it will do its best to give you accurate and relevant information.\n\nContext\nYou are Scarlett, a sentient AI."
+  },
+  synthia: {
+    systemPrompt: "Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation."
+  },
+  vicuna: {
+    systemPrompt: "A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input."
+  },
+  };
diff --git a/tools/server/public_legacy/theme-beeninorder.css b/tools/server/public_legacy/theme-beeninorder.css
new file mode 100755
index 00000000..f6e0e290
--- /dev/null
+++ b/tools/server/public_legacy/theme-beeninorder.css
@@ -0,0 +1,228 @@
+/* Author: Yazan Agha-Schrader */
+/* Inspiration was a batman wallpaper that i have on my phone */
+
+.theme-beeninorder {
+
+--primary-color-1:      hsl(202, 11%, 19%);
+--primary-color-2:      hsl(202, 11%, 23%);
+--primary-color-3:      hsl(201, 11%, 28%);
+--primary-color-4:      hsl(201, 11%, 40%);
+
+--secondary-color-1:    hsl(201, 11%, 80%);
+--secondary-color-2:    hsl(201, 11%, 74%);
+--secondary-color-3:    hsl(201, 11%, 67%);
+--secondary-color-4:    hsl(201, 11%, 60%);
+
+
+--theme-nuance-color-1: hsl(44.5, 96.7%, 52.9%);
+--theme-nuance-color-2: hsl(44.5, 96.7%, 52.9%);
+--theme-nuance-color-3: hsl(44.5, 96.7%, 52.9%);
+--theme-nuance-color-4: hsl(44.5, 96.7%, 52.9%);
+
+
+
+/* ---------- PRIMARY COLORS ----------------- */
+--primary-color-1: hsl(201, 11%, 19%);
+    --primary-color-1-hue: 201;
+    --primary-color-1-saturation: 11%;
+    --primary-color-1-lightness: 19%;
+
+--primary-color-2: hsl(201, 11%, 23%);
+    --primary-color-2-hue: 201;
+    --primary-color-2-saturation: 11%;
+    --primary-color-2-lightness: 23%;
+
+--primary-color-3: hsl(201, 11%, 28%);
+    --primary-color-3-hue: 201;
+    --primary-color-3-saturation: 11%;
+    --primary-color-3-lightness: 28%;
+
+--primary-color-4: hsl(201, 11%, 40%);
+    --primary-color-4-hue: 201;
+    --primary-color-4-saturation: 11%;
+    --primary-color-4-lightness: 40%;
+
+
+
+/* ---------- SECONDARY COLORS --------------- */
+--secondary-color-1: hsl(201, 11%, 80%);
+--secondary-color-1-hue: 201;
+--secondary-color-1-saturation: 11%;
+--secondary-color-1-lightness: 80%;
+
+--secondary-color-2: hsl(201, 11%, 74%);
+--secondary-color-2-hue: 201;
+--secondary-color-2-saturation: 11%;
+--secondary-color-2-lightness: 74%;
+
+--secondary-color-3: hsl(201, 11%, 67%);
+--secondary-color-3-hue: 201;
+--secondary-color-3-saturation: 11%;
+--secondary-color-3-lightness: 67%;
+
+--secondary-color-4: hsl(201, 11%, 60%);
+--secondary-color-4-hue: 201;
+--secondary-color-4-saturation: 11%;
+--secondary-color-4-lightness: 60%;
+
+
+
+/* ----------- NUANCES COLORS ---------------- */
+--theme-nuance-color-1: hsl(44.5, 96.7%,  52.9%);
+    --theme-nuance-color-1-hue:             44.5;
+    --theme-nuance-color-1-saturation:      96.7%;
+    --theme-nuance-color-1-lightness:       52.9%;
+
+--theme-nuance-color-2: hsl(44.5, 96.7%,  52.9%);
+    --theme-nuance-color-2-hue:             44.5;
+    --theme-nuance-color-2-saturation:      96.7%;
+    --theme-nuance-color-2-lightness:       52.9%;
+
+--theme-nuance-color-2: hsl(44.5, 96.7%,  52.9%);
+    --theme-nuance-color-3-hue:             44.5;
+    --theme-nuance-color-3-saturation:      96.7%;
+    --theme-nuance-color-3-lightness:       52.9%;
+
+--theme-nuance-color-2: hsl(44.5, 96.7%,  52.9%);
+    --theme-nuance-color-4-hue:             44.5;
+    --theme-nuance-color-4-saturation:      96.7%;
+    --theme-nuance-color-4-lightness:       52.9%;
+
+
+
+/* ----------- ROYGP COLORS ------------------ */
+    --theme-red-color:     hsl(232, 40%, 45%);
+    --theme-orange-color:  #e76f51;
+    --theme-yellow-color:  #ffd95f;
+    --theme-green-color:   #A3BE8C;
+    --theme-purple-color:  hsl(232, 30%, 40%);
+
+
+
+/* ------------------------------------------- */
+--background-color-1:    var(--primary-color-1);
+--background-color-2:    var(--primary-color-2);
+--background-color-3:    var(--primary-color-3);
+--background-color-4:    var(--primary-color-4);
+
+--border-color-1:        var(--primary-color-2);
+--border-color-2:        var(--primary-color-3);
+--border-color-3:        var(--primary-color-4);
+
+--border-focus-color:    var(--theme-nuance-color-2);
+--border-focus-shadow:   var(--theme-nuance-color-1);
+
+--text-color-plain:      var(--secondary-color-1);
+--text-color-subtile-1:  var(--secondary-color-2);
+--text-color-subtile-2:  var(--secondary-color-3);
+
+--code-background-color: var(--secondary-color-2);
+--code-text-color:       var(--primary-color-2);
+
+--ui-range-thumb-color:  var(--theme-nuance-color-3);
+--ui-range-thumb-border: var(--ui-ranger-thumb-color);
+
+--textarea-border-color: var(--secondary-color-4);
+
+--chat-id-color:         var(--theme-nuance-color-4);
+
+
+
+/* ------------------------------------------- */
+--button-alert-text-hover:       var(--secondary-color-1);
+--button-alert-color-hover:      var(--theme-purple-color);
+--button-alert-border-hover:     var(--theme-purple-color);
+
+--button-alert-text-active:      var(--secondary-color-1);
+--button-alert-color-active:     var(--theme-red-color);
+--button-alert-border-active:    var(--theme-red-color);
+
+
+
+/* ----------- PRIMARY BUTTONS --------------- */
+/* - button should immediately catch the eye - */
+--button-primary-text:   var(--primary-color-1);
+--button-primary-color:  var(--theme-nuance-color-3);
+--button-primary-border: var(--theme-nuance-color-3);
+
+
+/* ---------hover---------- */
+--button-primary-text-hover:
+    hsl(201,
+    calc(var(--primary-color-1-saturation) - 100%),
+    calc(var(--primary-color-1-lightness)  + 100%));
+
+--button-primary-color-hover:
+    hsl(44.5,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+--button-primary-border-hover:
+    hsl(44.5,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+
+/* ---------active--------- */
+--button-primary-text-active:
+    hsl(44.5,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  + 100%));
+
+--button-primary-color-active:
+    hsl(44.5,
+    calc(var(--theme-nuance-color-3-saturation) - 10%),
+    calc(var(--theme-nuance-color-3-lightness)  - 15%));
+
+--button-primary-border-active:
+    hsl(44.5,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  + 10%));
+
+
+
+/* ---------- SECONDARY BUTTONS -------------- */
+/* these should NOT immediately catch the eye  */
+--button-secondary-text:   var(--secondary-color-1);
+--button-secondary-color:  var(--primary-color-3);
+--button-secondary-border: var(--primary-color-3);
+
+
+/* ---------hover---------- */
+--button-secondary-text-hover:
+    hsl(44.5,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 80%));
+
+--button-secondary-color-hover:  var(--primary-color-4);
+--button-secondary-border-hover: var(--primary-color-4);
+
+
+/* ---------active--------- */
+--button-secondary-text-active: var(--secondary-color-1);
+
+--button-secondary-color-active:
+    hsl(201,
+    calc(var(--primary-color-4-saturation) - 30%),
+    calc(var(--primary-color-4-lightness)  - 15%));
+
+--button-secondary-border-active:
+    hsl(201,
+    calc(var(--primary-color-4-saturation) - 30%),
+    calc(var(--primary-color-4-lightness)  - 15%));
+
+
+
+/* ---------- TERTIARY BUTTONS --------------- */
+/* ---------- disabled buttons --------------- */
+--button-tertiary-text:   var(--primary-color-4);
+--button-tertiary-color:  var(--primary-color-2);
+--button-tertiary-border: var(--primary-color-2);
+
+
+/* ---------hover---------- */
+--button-tertiary-text:   var(--primary-color-4);
+--button-tertiary-color:  var(--primary-color-2);
+--button-tertiary-border: var(--primary-color-2);
+
+}
diff --git a/tools/server/public_legacy/theme-ketivah.css b/tools/server/public_legacy/theme-ketivah.css
new file mode 100755
index 00000000..ee80f3c1
--- /dev/null
+++ b/tools/server/public_legacy/theme-ketivah.css
@@ -0,0 +1,201 @@
+/* Author: Yazan Agha-Schrader */
+
+.theme-ketivah {
+
+    /* ---------- PRIMARY COLORS ----------------- */
+    --primary-color-1: hsl(0, 0%,    99.2%);
+    --primary-color-1-hue:         0;
+    --primary-color-1-saturation:  0%;
+    --primary-color-1-lightness:   99.2%;
+
+    --primary-color-2: hsl(0, 0%,    95%);
+    --primary-color-2-hue:         0;
+    --primary-color-2-saturation:  0%;
+    --primary-color-2-lightness:   95%;
+
+    --primary-color-3: hsl(0, 0%,    88%);
+    --primary-color-3-hue:         0;
+    --primary-color-3-saturation:  0%;
+    --primary-color-3-lightness:   88%;
+
+    --primary-color-4: hsl(0, 0%,    80%);
+    --primary-color-4-hue:         0;
+    --primary-color-4-saturation:  0%;
+    --primary-color-4-lightness:   80%;
+
+    /* ---------- SECONDARY COLORS --------------- */
+    --secondary-color-1: hsl(0, 0%,    20%);
+    --secondary-color-1-hue:         0;
+    --secondary-color-1-saturation:  0%;
+    --secondary-color-1-lightness:   20%;
+
+    --secondary-color-2: hsl(0, 0%,    23.1%);
+    --secondary-color-2-hue:         0;
+    --secondary-color-2-saturation:  0%;
+    --secondary-color-2-lightness:   23.1%;
+
+    --secondary-color-3: hsl(0, 0%,    29%);
+    --secondary-color-3-hue:         0;
+    --secondary-color-3-saturation:  0%;
+    --secondary-color-3-lightness:   29%;
+
+    --secondary-color-4: hsl(0, 0.0%,  36.1%);
+    --secondary-color-4-hue:              0.0;
+    --secondary-color-4-saturation:       0.0%;
+    --secondary-color-4-lightness:       36.1%;
+
+    /* ----------- NUANCES COLORS ---------------- */
+    --theme-nuance-color-1: hsl(165.2, 0%, 35.1%);
+    --theme-nuance-color-1-hue:             165.2;
+    --theme-nuance-color-1-saturation:       82.1%;
+    --theme-nuance-color-1-lightness:        35.1%;
+
+    --theme-nuance-color-2: hsl(165.2, 0%, 35.1%);
+    --theme-nuance-color-2-hue:             165.2;
+    --theme-nuance-color-2-saturation:       82.1%;
+    --theme-nuance-color-2-lightness:        35.1%;
+
+    --theme-nuance-color-3: hsl(165.2, 0%, 35.3%);
+    --theme-nuance-color-3-hue:             165.2;
+    --theme-nuance-color-3-saturation:       81.1%;
+    --theme-nuance-color-3-lightness:        35.3%;
+
+    --theme-nuance-color-4: hsl(164.9, 0%, 27.6%);
+    --theme-nuance-color-4-hue:             164.9;
+    --theme-nuance-color-4-saturation:       81.6%;
+    --theme-nuance-color-4-lightness:        27.6%;
+
+    /* ----------- ROYGP COLORS ------------------ */
+    --theme-red-color:     hsl(0.3, 80.0%, 50.0%);
+    --theme-orange-color:  #e76f51;
+    --theme-yellow-color:  hsl(60,  70.6%, 73.3%);
+    --theme-green-color:   #A3BE8C;
+    --theme-purple-color:  hsl(0.3, 70.0%, 45.0%);
+
+    /* ------------------------------------------- */
+    --background-color-1:    var(--primary-color-1);
+    --background-color-2:    var(--primary-color-2);
+    --background-color-3:    var(--primary-color-3);
+    --background-color-4:    var(--primary-color-4);
+
+    --border-color-1:        var(--primary-color-2);
+    --border-color-2:        var(--primary-color-3);
+    --border-color-3:        var(--primary-color-4);
+
+    --border-focus-color:    var(--theme-nuance-color-2);
+    --border-focus-shadow:   var(--theme-nuance-color-1);
+
+    --text-color-plain:      var(--secondary-color-1);
+    --text-color-subtile-1:  var(--secondary-color-2);
+    --text-color-subtile-2:  var(--secondary-color-3);
+
+    --code-background-color: var(--secondary-color-2);
+    --code-text-color:       var(--primary-color-2);
+
+    --ui-range-thumb-color:  var(--primary-color-4);
+    --ui-range-thumb-border: var(--ui-ranger-thumb-color);
+
+    --textarea-border-color: var(--secondary-color-4);
+
+    --chat-id-color:         var(--theme-nuance-color-4);
+
+    /* ------------------------------------------- */
+    --button-alert-text-hover:       var(--primary-color-1);
+    --button-alert-color-hover:      var(--theme-purple-color);
+    --button-alert-border-hover:     var(--theme-purple-color);
+
+    --button-alert-text-active:      var(--primary-color-1);
+    --button-alert-color-active:     var(--theme-red-color);
+    --button-alert-border-active:    var(--theme-red-color);
+
+    /* ----------- PRIMARY BUTTONS --------------- */
+    /* - button should immediately catch the eye - */
+    --button-primary-text:
+    hsl(0,
+    calc(var(--primary-color-1-saturation) - 100%),
+    calc(var(--primary-color-1-lightness)  + 100%));
+
+    --button-primary-color:  var(--theme-nuance-color-3);
+    --button-primary-border: var(--theme-nuance-color-3);
+
+    /* ---------hover---------- */
+    --button-primary-text-hover:
+    hsl(0,
+    calc(var(--primary-color-1-saturation) - 100%),
+    calc(var(--primary-color-1-lightness)  + 100%));
+
+    --button-primary-color-hover:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+    --button-primary-border-hover:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+    /* ---------active--------- */
+    --button-primary-text-active:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  + 100%));
+
+    --button-primary-color-active:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  - 15%));
+
+    --button-primary-border-active:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  + 10%));
+
+    /* ---------- SECONDARY BUTTONS -------------- */
+    /* these should NOT immediately catch the eye  */
+    --button-secondary-text:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  - 50%));
+
+    --button-secondary-color:  var(--primary-color-3);
+    --button-secondary-border: var(--primary-color-3);
+
+    /* ---------hover---------- */
+    --button-secondary-text-hover:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  - 80%));
+
+    --button-secondary-color-hover:  var(--primary-color-4);
+    --button-secondary-border-hover: var(--primary-color-4);
+
+    /* ---------active--------- */
+    --button-secondary-text-active:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  - 80%));
+
+    --button-secondary-color-active:
+    hsl(0,
+    calc(var(--primary-color-4-saturation) - 100%),
+    calc(var(--primary-color-4-lightness)  - 15%));
+
+    --button-secondary-border-active:
+    hsl(0,
+    calc(var(--primary-color-4-saturation) - 100%),
+    calc(var(--primary-color-4-lightness)  - 15%));
+
+    /* ---------- TERTIARY BUTTONS --------------- */
+    /* ---------- disabled buttons --------------- */
+    --button-tertiary-text:   var(--primary-color-4);
+    --button-tertiary-color:  var(--primary-color-2);
+    --button-tertiary-border: var(--primary-color-2);
+
+    /* ---------hover---------- */
+    --button-tertiary-text:   var(--primary-color-4);
+    --button-tertiary-color:  var(--primary-color-2);
+    --button-tertiary-border: var(--primary-color-2);
+
+    --loading-color-1: #eeeeee00;
+    --loading-color-2: #eeeeeeff;
+    }
diff --git a/tools/server/public_legacy/theme-mangotango.css b/tools/server/public_legacy/theme-mangotango.css
new file mode 100755
index 00000000..e4338024
--- /dev/null
+++ b/tools/server/public_legacy/theme-mangotango.css
@@ -0,0 +1,216 @@
+/* Author: Yazan Agha-Schrader */
+/* Inspiration from llama.cpp logo/banner https://github.com/ggerganov/llama.cpp#readme */
+
+.theme-mangotango {
+
+--primary-color-1:      hsl(192, 8.5%, 11.6%);
+--primary-color-2:      hsl(192, 8.5%, 21%);
+--primary-color-3:      hsl(192, 8.5%, 30%);
+--primary-color-4:      hsl(192, 8.5%, 40%);
+
+--secondary-color-1:    hsl(192, 8.5%, 80%);
+--secondary-color-2:    hsl(192, 8.5%, 73%);
+--secondary-color-3:    hsl(192, 8.5%, 66%);
+--secondary-color-4:    hsl(192, 8.5%, 60%);
+
+--theme-nuance-color-1: hsl(23.1, 100%, 60.2%);
+--theme-nuance-color-2: hsl(23.1, 100%, 60.2%);
+--theme-nuance-color-3: hsl(23.1, 100%, 60.2%);
+--theme-nuance-color-4: hsl(23.1, 100%, 60.2%);
+
+
+
+/* ---------- PRIMARY COLORS ----------------- */
+--primary-color-1: hsl(192, 8.5%, 11.6%);
+    --primary-color-1-saturation: 8.5%;
+    --primary-color-1-lightness: 11.6%;
+
+--primary-color-2: hsl(192, 8.5%, 21%);
+    --primary-color-2-saturation: 8.5%;
+    --primary-color-2-lightness: 21%;
+
+--primary-color-3: hsl(192, 8.5%, 30%);
+    --primary-color-3-saturation: 8.5%;
+    --primary-color-3-lightness: 30%;
+
+--primary-color-4: hsl(192, 8.5%, 40%);
+    --primary-color-4-saturation: 8.5%;
+    --primary-color-4-lightness: 40%;
+
+
+
+/* ---------- SECONDARY COLORS --------------- */
+--secondary-color-1: hsl(192, 8.5%, 80%);
+    --secondary-color-1-saturation: 8.5%;
+    --secondary-color-1-lightness: 80%;
+
+--secondary-color-2: hsl(192, 8.5%, 73%);
+    --secondary-color-2-saturation: 8.5%;
+    --secondary-color-2-lightness: 73%;
+
+--secondary-color-3: hsl(192, 8.5%, 66%);
+    --secondary-color-3-saturation: 8.5%;
+    --secondary-color-3-lightness: 66%;
+
+--secondary-color-4: hsl(192, 8.5%, 60%);
+    --secondary-color-4-saturation: 8.5%;
+    --secondary-color-4-lightness: 60%;
+
+
+
+/* ----------- NUANCES COLORS ---------------- */
+--theme-nuance-color-1: hsl(23.1, 100%, 60.2%);
+    --theme-nuance-color-1-saturation: 100%;
+    --theme-nuance-color-1-lightness: 60.2%;
+
+--theme-nuance-color-2: hsl(23.1, 100%, 60.2%);
+    --theme-nuance-color-2-saturation: 100%;
+    --theme-nuance-color-2-lightness: 60.2%;
+
+--theme-nuance-color-3: hsl(23.1, 100%, 60.2%);
+    --theme-nuance-color-3-saturation: 100%;
+    --theme-nuance-color-3-lightness: 60.2%;
+
+--theme-nuance-color-4: hsl(23.1, 100%, 60.2%);
+    --theme-nuance-color-4-saturation: 100%;
+    --theme-nuance-color-4-lightness: 60.2%;
+
+
+
+/* ----------- ROYGP COLORS ------------------ */
+    --theme-red-color:     hsl(325, 60%, 50%);
+    --theme-orange-color:  #e76f51;
+    --theme-yellow-color:  #ffd95f;
+    --theme-green-color:   #A3BE8C;
+    --theme-blue-color:    hsl(192, 95%, 40%);
+    --theme-purple-color:  hsl(192, 80%, 35%);
+
+
+
+/* ------------------------------------------- */
+--background-color-1:    var(--primary-color-1);
+--background-color-2:    var(--primary-color-2);
+--background-color-3:    var(--primary-color-3);
+--background-color-4:    var(--primary-color-4);
+
+--border-color-1:        var(--primary-color-2);
+--border-color-2:        var(--primary-color-3);
+--border-color-3:        var(--primary-color-4);
+
+--border-focus-color:    var(--theme-nuance-color-2);
+--border-focus-shadow:   var(--theme-nuance-color-1);
+
+--text-color-plain:      var(--secondary-color-1);
+--text-color-subtile-1:  var(--secondary-color-2);
+--text-color-subtile-2:  var(--secondary-color-3);
+
+--code-background-color: var(--secondary-color-2);
+--code-text-color:       var(--primary-color-2);
+
+--ui-range-thumb-color:  var(--theme-nuance-color-3);
+--ui-range-thumb-border: var(--ui-ranger-thumb-color);
+
+--textarea-border-color: var(--secondary-color-4);
+
+--chat-id-color:         var(--theme-nuance-color-4);
+
+
+
+/* ------------------------------------------- */
+--button-alert-text-hover:       var(--secondary-color-1);
+--button-alert-color-hover:      var(--theme-purple-color);
+--button-alert-border-hover:     var(--theme-purple-color);
+
+--button-alert-text-active:      var(--secondary-color-1);
+--button-alert-color-active:     var(--theme-blue-color);
+--button-alert-border-active:    var(--theme-blue-color);
+
+
+
+/* ----------- PRIMARY BUTTONS --------------- */
+/* - button should immediately catch the eye - */
+--button-primary-text: var(--primary-color-1);
+--button-primary-color:  var(--theme-nuance-color-3);
+--button-primary-border: var(--theme-nuance-color-3);
+
+
+/* ---------hover---------- */
+--button-primary-text-hover:
+    hsl(192,
+    calc(var(--primary-color-1-saturation) - 100%),
+    calc(var(--primary-color-1-lightness)  + 100%));
+
+--button-primary-color-hover:
+    hsl(23.1,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+--button-primary-border-hover:
+    hsl(23.1,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+
+/* ---------active--------- */
+--button-primary-text-active:
+    hsl(23.1,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  + 100%));
+
+--button-primary-color-active:
+    hsl(23.1,
+    calc(var(--theme-nuance-color-3-saturation) - 10%),
+    calc(var(--theme-nuance-color-3-lightness)  - 15%));
+
+--button-primary-border-active:
+    hsl(23.1,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  + 10%));
+
+
+
+/* ---------- SECONDARY BUTTONS -------------- */
+/* these should NOT immediately catch the eye  */
+--button-secondary-text:   var(--secondary-color-1);
+--button-secondary-color:  var(--primary-color-3);
+--button-secondary-border: var(--primary-color-3);
+
+
+/* ---------hover---------- */
+--button-secondary-text-hover:
+    hsl(23.1,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 80%));
+
+--button-secondary-color-hover:  var(--primary-color-4);
+--button-secondary-border-hover: var(--primary-color-4);
+
+
+/* ---------active--------- */
+--button-secondary-text-active: var(--secondary-color-1);
+
+--button-secondary-color-active:
+    hsl(192,
+    calc(var(--primary-color-4-saturation) - 30%),
+    calc(var(--primary-color-4-lightness)  - 15%));
+
+--button-secondary-border-active:
+    hsl(192,
+    calc(var(--primary-color-4-saturation) - 30%),
+    calc(var(--primary-color-4-lightness)  - 15%));
+
+
+
+/* ---------- TERTIARY BUTTONS --------------- */
+/* ---------- disabled buttons --------------- */
+--button-tertiary-text:   var(--primary-color-4);
+--button-tertiary-color:  var(--primary-color-2);
+--button-tertiary-border: var(--primary-color-2);
+
+
+/* ---------hover---------- */
+--button-tertiary-text:   var(--primary-color-4);
+--button-tertiary-color:  var(--primary-color-2);
+--button-tertiary-border: var(--primary-color-2);
+
+}
diff --git a/tools/server/public_legacy/theme-playground.css b/tools/server/public_legacy/theme-playground.css
new file mode 100755
index 00000000..9d56a718
--- /dev/null
+++ b/tools/server/public_legacy/theme-playground.css
@@ -0,0 +1,221 @@
+/* Author: Yazan Agha-Schrader */
+/* Inspiration from OpenAI's Playground platform https://platform.openai.com/playground/ */
+
+.theme-playground {
+
+/* ---------- PRIMARY COLORS ----------------- */
+--primary-color-1: hsl(0, 0%,    99.2%);
+    --primary-color-1-hue:         0;
+    --primary-color-1-saturation:  0%;
+    --primary-color-1-lightness:   99.2%;
+
+--primary-color-2: hsl(0, 0%,    95%);
+    --primary-color-2-hue:         0;
+    --primary-color-2-saturation:  0%;
+    --primary-color-2-lightness:   95%;
+
+--primary-color-3: hsl(0, 0%,    88%);
+    --primary-color-3-hue:         0;
+    --primary-color-3-saturation:  0%;
+    --primary-color-3-lightness:   88%;
+
+--primary-color-4: hsl(0, 0%,    80%);
+    --primary-color-4-hue:         0;
+    --primary-color-4-saturation:  0%;
+    --primary-color-4-lightness:   80%;
+
+
+
+/* ---------- SECONDARY COLORS --------------- */
+--secondary-color-1: hsl(0, 0%,    20%);
+    --secondary-color-1-hue:         0;
+    --secondary-color-1-saturation:  0%;
+    --secondary-color-1-lightness:   20%;
+
+--secondary-color-2: hsl(0, 0%,    23.1%);
+    --secondary-color-2-hue:         0;
+    --secondary-color-2-saturation:  0%;
+    --secondary-color-2-lightness:   23.1%;
+
+--secondary-color-3: hsl(0, 0%,    29%);
+    --secondary-color-3-hue:         0;
+    --secondary-color-3-saturation:  0%;
+    --secondary-color-3-lightness:   29%;
+
+--secondary-color-4: hsl(0, 0%,    36.1%);
+    --secondary-color-4-hue:         0;
+    --secondary-color-4-saturation:  0%;
+    --secondary-color-4-lightness:   36.1%;
+
+
+
+/* ----------- NUANCES COLORS ---------------- */
+--theme-nuance-color-1: hsl(165.2, 82.1%, 35.1%);
+    --theme-nuance-color-1-hue:             165.2;
+    --theme-nuance-color-1-saturation:      82.1%;
+    --theme-nuance-color-1-lightness:       35.1%;
+
+--theme-nuance-color-2: hsl(165.2, 82.1%, 35.1%);
+    --theme-nuance-color-2-hue:             165.2;
+    --theme-nuance-color-2-saturation:      82.1%;
+    --theme-nuance-color-2-lightness:       35.1%;
+
+--theme-nuance-color-3: hsl(165.2, 81.1%, 35.3%);
+    --theme-nuance-color-3-hue:             165.2;
+    --theme-nuance-color-3-saturation:      81.1%;
+    --theme-nuance-color-3-lightness:       35.3%;
+
+--theme-nuance-color-4: hsl(164.9, 81.6%, 27.6%);
+    --theme-nuance-color-4-hue:             164.9;
+    --theme-nuance-color-4-saturation:      81.6%;
+    --theme-nuance-color-4-lightness:       27.6%;
+
+
+
+/* ----------- ROYGP COLORS ------------------ */
+--theme-red-color:     hsl(0.3, 80%, 50%);
+--theme-orange-color:  #e76f51;
+--theme-yellow-color:  hsl(60, 70.6%, 73.3%);
+--theme-green-color:   #A3BE8C;
+--theme-purple-color:  hsl(0.3, 70%, 45%);
+
+
+
+/* ------------------------------------------- */
+--background-color-1:    var(--primary-color-1);
+--background-color-2:    var(--primary-color-2);
+--background-color-3:    var(--primary-color-3);
+--background-color-4:    var(--primary-color-4);
+
+--border-color-1:        var(--primary-color-2);
+--border-color-2:        var(--primary-color-3);
+--border-color-3:        var(--primary-color-4);
+
+--border-focus-color:    var(--theme-nuance-color-2);
+--border-focus-shadow:   var(--theme-nuance-color-1);
+
+--text-color-plain:      var(--secondary-color-1);
+--text-color-subtile-1:  var(--secondary-color-2);
+--text-color-subtile-2:  var(--secondary-color-3);
+
+--code-background-color: var(--secondary-color-2);
+--code-text-color:       var(--primary-color-2);
+
+--ui-range-thumb-color:  var(--primary-color-4);
+--ui-range-thumb-border: var(--ui-ranger-thumb-color);
+
+--textarea-border-color: var(--secondary-color-4);
+
+--chat-id-color:        var(--theme-nuance-color-4);
+
+
+
+/* ------------------------------------------- */
+--button-alert-text-hover:       var(--primary-color-1);
+--button-alert-color-hover:      var(--theme-purple-color);
+--button-alert-border-hover:     var(--theme-purple-color);
+
+--button-alert-text-active:      var(--primary-color-1);
+--button-alert-color-active:     var(--theme-red-color);
+--button-alert-border-active:    var(--theme-red-color);
+
+
+
+/* ----------- PRIMARY BUTTONS --------------- */
+/* - button should immediately catch the eye - */
+--button-primary-text:
+    hsl(0,
+    calc(var(--primary-color-1-saturation) - 100%),
+    calc(var(--primary-color-1-lightness)  + 100%));
+
+--button-primary-color:  var(--theme-nuance-color-3);
+--button-primary-border: var(--theme-nuance-color-3);
+
+
+/* ---------hover---------- */
+--button-primary-text-hover:
+    hsl(0,
+    calc(var(--primary-color-1-saturation) - 100%),
+    calc(var(--primary-color-1-lightness)  + 100%));
+
+--button-primary-color-hover:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+--button-primary-border-hover:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+
+/* ---------active--------- */
+--button-primary-text-active:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 100%),
+    calc(var(--theme-nuance-color-3-lightness)  + 100%));
+
+--button-primary-color-active:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 10%),
+    calc(var(--theme-nuance-color-3-lightness)  - 15%));
+
+--button-primary-border-active:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 2%),
+    calc(var(--theme-nuance-color-3-lightness)  + 10%));
+
+
+
+/* ---------- SECONDARY BUTTONS -------------- */
+/* these should NOT immediately catch the eye  */
+--button-secondary-text:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 50%));
+
+--button-secondary-color:  var(--primary-color-3);
+--button-secondary-border: var(--primary-color-3);
+
+
+/* ---------hover---------- */
+--button-secondary-text-hover:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 80%));
+
+--button-secondary-color-hover:  var(--primary-color-4);
+--button-secondary-border-hover: var(--primary-color-4);
+
+
+/* ---------active--------- */
+--button-secondary-text-active:
+    hsl(165.2,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 80%));
+
+--button-secondary-color-active:
+    hsl(0,
+    calc(var(--primary-color-4-saturation) - 30%),
+    calc(var(--primary-color-4-lightness)  - 15%));
+
+--button-secondary-border-active:
+    hsl(0,
+    calc(var(--primary-color-4-saturation) - 30%),
+    calc(var(--primary-color-4-lightness)  - 15%));
+
+
+
+/* ---------- TERTIARY BUTTONS --------------- */
+/* ---------- disabled buttons --------------- */
+--button-tertiary-text:   var(--primary-color-4);
+--button-tertiary-color:  var(--primary-color-2);
+--button-tertiary-border: var(--primary-color-2);
+
+
+/* ---------hover---------- */
+--button-tertiary-text:   var(--primary-color-4);
+--button-tertiary-color:  var(--primary-color-2);
+--button-tertiary-border: var(--primary-color-2);
+
+}
diff --git a/tools/server/public_legacy/theme-polarnight.css b/tools/server/public_legacy/theme-polarnight.css
new file mode 100755
index 00000000..2bcfb33d
--- /dev/null
+++ b/tools/server/public_legacy/theme-polarnight.css
@@ -0,0 +1,253 @@
+/* Author: Yazan Agha-Schrader */
+/* Inspiration from Nord Theme https://www.nordtheme.com/docs/colors-and-palettes */
+
+.theme-polarnight {
+
+/* ---------- PRIMARY COLORS ----------------- */
+--primary-color-1: hsl(220.0, 16.4%, 21.6%) ;
+    --primary-color-1-hue:             220.0;
+    --primary-color-1-saturation:      16.4%;
+    --primary-color-1-lightness:       21.6%;
+
+--primary-color-2: hsl(221.7, 16.3%, 27.6%) ;
+    -primary-color-2-hue:              221.7;
+    --primary-color-2-saturation:      16.3%;
+    --primary-color-2-lightness:       27.6%;
+
+--primary-color-3: hsl(220.0, 16.8%, 31.6%) ;
+    --primary-color-3-hue:             220.0;
+    --primary-color-3-saturation:      16.8%;
+    --primary-color-3-lightness:       31.6%;
+
+--primary-color-4: hsl(220.0, 16.5%, 35.7%);
+    --primary-color-4-hue:             220.0;
+    --primary-color-4-saturation:      16.5%;
+    --primary-color-4-lightness:       35.7%;
+
+
+
+/* ---------- SECONDARY COLORS --------------- */
+--secondary-color-1: hsl(217.5, 26.7%, 94.1%);
+    --secondary-color-1-hue:             217.5;
+    --secondary-color-1-saturation:      26.7%;
+    --secondary-color-1-lightness:       94.1%;
+
+--secondary-color-2: hsl(218.2, 26.8%, 92.0%);
+    --secondary-color-2-hue:             218.2;
+    --secondary-color-2-saturation:      26.8%;
+    --secondary-color-2-lightness:       92.0%;
+
+--secondary-color-3: hsl(218.8, 27.9%, 88.0%);
+    --secondary-color-3-hue:             218.8;
+    --secondary-color-3-saturation:      27.9%;
+    --secondary-color-3-lightness:       88.0%;
+
+--secondary-color-4: hsl(218.8, 18.3%, 81.8%);
+    --secondary-color-4-hue:             218.8;
+    --secondary-color-4-saturation:      18.3%;
+    --secondary-color-4-lightness:       81.8%;
+
+
+
+/* ----------- NUANCES COLORS ---------------- */
+--theme-nuance-color-1: hsl(178.7, 25.1%, 64.9%);
+    --theme-nuance-color-1-hue:             178.7;
+    --theme-nuance-color-1-saturation:      25.1%;
+    --theme-nuance-color-1-lightness:       64.9%;
+
+--theme-nuance-color-2: hsl(193.3, 43.4%, 67.5%);
+    --theme-nuance-color-2-hue:             193.3;
+    --theme-nuance-color-2-saturation:      43.4%;
+    --theme-nuance-color-2-lightness:       67.5%;
+
+--theme-nuance-color-3: hsl(210.0, 34.0%, 63.1%);
+    --theme-nuance-color-3-hue:             210.0;
+    --theme-nuance-color-3-saturation:      34.0%;
+    --theme-nuance-color-3-lightness:       63.1%;
+
+--theme-nuance-color-4: hsl(213.1, 32.0%, 52.2%);
+    --theme-nuance-color-4-hue:             213.1;
+    --theme-nuance-color-4-saturation:      32.0%;
+    --theme-nuance-color-4-lightness:       52.2%;
+
+
+
+/* ----------- ROYGP COLORS ------------------ */
+--theme-red-color:    hsl(354.3, 42.3%, 56.5%);
+--theme-orange-color: hsl(20, 85%, 50%);
+--theme-yellow-color: hsl(20, 75%, 45%);
+--theme-green-color:  hsl( 92.4, 27.8%, 64.7%);
+--theme-purple-color: hsl(311.1, 20.2%, 63.1%);
+
+
+
+/* ------------------------------------------------ */
+--background-color-1:    var(--primary-color-1);
+--background-color-2:    var(--primary-color-2);
+--background-color-3:    var(--primary-color-3);
+--background-color-4:    var(--primary-color-4);
+
+--border-color-1:        var(--primary-color-2);
+--border-color-2:        var(--primary-color-3);
+--border-color-3:        var(--primary-color-4);
+
+--border-focus-color:    var(--theme-nuance-color-2);
+--border-focus-shadow:   var(--theme-nuance-color-1);
+
+--text-color-plain:      var(--secondary-color-1);
+--text-color-subtile-1:  var(--secondary-color-2);
+--text-color-subtile-2:  var(--secondary-color-3);
+
+--code-background-color: var(--secondary-color-2);
+--code-text-color:       var(--primary-color-2);
+
+--ui-range-thumb-color:  var(--theme-nuance-color-3);
+--ui-range-thumb-border: var(--ui-ranger-thumb-color);
+
+--textarea-border-color: var(--secondary-color-4);
+
+--chat-id-color:        var(--theme-nuance-color-4);
+
+
+
+/* ------------------------------------------- */
+--button-alert-text-hover:       var(--secondary-color-1);
+--button-alert-color-hover:      var(--theme-yellow-color);
+--button-alert-border-hover:     var(--theme-yellow-color);
+
+--button-alert-text-active:      var(--secondary-color-1);
+--button-alert-color-active:     var(--theme-orange-color);
+--button-alert-border-active:    var(--theme-orange-color);
+
+
+
+/* ----------- PRIMARY BUTTONS --------------- */
+/* - button should immediately catch the eye - */
+--button-primary-text:   var(--secondary-color-1);
+--button-primary-color:  var(--theme-nuance-color-3);
+--button-primary-border: var(--theme-nuance-color-3);
+
+
+/* ---------hover---------- */
+--button-primary-text-hover:
+    hsl(217.5,
+    calc(var(--secondary-color-1-saturation) - 35%),
+    calc(var(--secondary-color-1-lightness)  + 30%));
+
+--button-primary-color-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) -  2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+--button-primary-border-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) -  2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+
+/* ---------active--------- */
+--button-primary-text-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  + 35%));
+
+--button-primary-color-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 10%),
+    calc(var(--theme-nuance-color-3-lightness)  - 25%));
+
+--button-primary-border-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 10%),
+    calc(var(--theme-nuance-color-3-lightness)  - 25%));
+
+
+
+/* ---------- SECONDARY BUTTONS -------------- */
+/* these should NOT immediately catch the eye  */
+--button-secondary-text:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 50%));
+
+--button-secondary-color:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  + 10%));
+
+--button-secondary-border:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  + 10%));
+
+
+/* ---------hover---------- */
+--button-secondary-text-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 80%));
+
+--button-secondary-color-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 22%),
+    calc(var(--theme-nuance-color-3-lightness)  +  1%));
+
+--button-secondary-border-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 22%),
+    calc(var(--theme-nuance-color-3-lightness)  +  1%));
+
+
+/* ---------active--------- */
+--button-secondary-text-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  + 25%));
+
+--button-secondary-color-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 30%),
+    calc(var(--theme-nuance-color-3-lightness)  - 15%));
+
+--button-secondary-border-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 30%),
+    calc(var(--theme-nuance-color-3-lightness)  - 15%));
+
+
+
+/* ---------- TERTIARY BUTTONS --------------- */
+/* ---------- disabled buttons --------------- */
+--button-tertiary-text:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  -  5%));
+
+--button-tertiary-color:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  + 20%));
+
+--button-tertiary-border:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  + 20%));
+
+
+/* ---------hover---------- */
+--button-tertiary-text-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  -  5%));
+
+--button-tertiary-color-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  + 20%));
+
+--button-tertiary-border-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  + 20%));
+
+}
diff --git a/tools/server/public_legacy/theme-snowstorm.css b/tools/server/public_legacy/theme-snowstorm.css
new file mode 100755
index 00000000..7bb22759
--- /dev/null
+++ b/tools/server/public_legacy/theme-snowstorm.css
@@ -0,0 +1,251 @@
+/* Author: Yazan Agha-Schrader */
+/* Inspiration from Nord Theme https://www.nordtheme.com/docs/colors-and-palettes */
+
+.theme-snowstorm {
+
+/* ---------- PRIMARY COLORS ----------------- */
+--primary-color-1: hsl(217.5, 26.7%, 94.1%);
+    --primary-color-1-hue:             217.5;
+    --primary-color-1-saturation:      26.7%;
+    --primary-color-1-lightness:       94.1%;
+
+--primary-color-2: hsl(218.2, 26.8%, 92.0%);
+    --primary-color-2-hue:             218.2;
+    --primary-color-2-saturation:      26.8%;
+    --primary-color-2-lightness:       92.0%;
+
+--primary-color-3: hsl(218.8, 27.9%, 88.0%);
+    --primary-color-3-hue:             218.8;
+    --primary-color-3-saturation:      27.9%;
+    --primary-color-3-lightness:       88.0%;
+
+--primary-color-4: hsl(218.8, 18.3%, 81.8%);
+    --primary-color-4-hue:             218.8;
+    --primary-color-4-saturation:      18.3%;
+    --primary-color-4-lightness:       81.8%;
+
+
+/* ---------- SECONDARY COLORS --------------- */
+--secondary-color-1: hsl(220.0, 16.4%, 21.6%);
+    --secondary-color-1-hue:             220.0;
+    --secondary-color-1-saturation:      16.4%;
+    --secondary-color-1-lightness:       21.6%;
+
+--secondary-color-2: hsl(221.7, 16.3%, 27.6%);
+    --secondary-color-2-hue:             221.7;
+    --secondary-color-2-saturation:      16.3%;
+    --secondary-color-2-lightness:       27.6%;
+
+--secondary-color-3: hsl(220.0, 16.8%, 31.6%);
+    --secondary-color-3-hue:             220.0;
+    --secondary-color-3-saturation:      16.8%;
+    --secondary-color-3-lightness:       31.6%;
+
+--secondary-color-4: hsl(220.0, 16.5%, 35.7%);
+    --secondary-color-4-hue:             220.0;
+    --secondary-color-4-saturation:      16.5%;
+    --secondary-color-4-lightness:       35.7%;
+
+
+
+/* ----------- NUANCES COLORS ---------------- */
+--theme-nuance-color-1: hsl(178.7, 25.1%, 64.9%);
+    --theme-nuance-color-1-hue:             178.7;
+    --theme-nuance-color-1-saturation:      25.1%;
+    --theme-nuance-color-1-lightness:       64.9%;
+
+--theme-nuance-color-2: hsl(193.3, 43.4%, 67.5%);
+    --theme-nuance-color-2-hue:             193.3;
+    --theme-nuance-color-2-saturation:      43.4%;
+    --theme-nuance-color-2-lightness:       67.5%;
+
+--theme-nuance-color-3: hsl(210.0, 34.0%, 63.1%);
+    --theme-nuance-color-3-hue:             210.0;
+    --theme-nuance-color-3-saturation:      34.0%;
+    --theme-nuance-color-3-lightness:       63.1%;
+
+--theme-nuance-color-4: hsl(213.1, 32.0%, 52.2%);
+    --theme-nuance-color-4-hue:             213.1;
+    --theme-nuance-color-4-saturation:      32.0%;
+    --theme-nuance-color-4-lightness:       52.2%;
+
+
+
+/* ----------- ROYGP COLORS ------------------ */
+--theme-red-color:    hsl(32.5, 80%, 50%);
+--theme-orange-color: hsl(32.5, 70%, 45%);
+--theme-yellow-color: hsl(40.0,   0.6%, 73.3%);
+--theme-green-color:  hsl(92.4,  27.8%, 64.7%);
+--theme-purple-color: hsl(311.1, 20.2%, 63.1%);
+
+
+
+/* ------------------------------------------- */
+--background-color-1:    var(--primary-color-1);
+--background-color-2:    var(--primary-color-2);
+--background-color-3:    var(--primary-color-3);
+--background-color-4:    var(--primary-color-4);
+
+--border-color-1:        var(--primary-color-2);
+--border-color-2:        var(--primary-color-3);
+--border-color-3:        var(--primary-color-4);
+
+--border-focus-color:    var(--theme-nuance-color-2);
+--border-focus-shadow:   var(--theme-nuance-color-1);
+
+--text-color-plain:      var(--secondary-color-1);
+--text-color-subtile-1:  var(--secondary-color-2);
+--text-color-subtile-2:  var(--secondary-color-3);
+
+--code-background-color: var(--secondary-color-2);
+--code-text-color:       var(--primary-color-2);
+
+--ui-range-thumb-color:  var(--theme-nuance-color-3);
+--ui-range-thumb-border: var(--ui-ranger-thumb-color);
+
+--textarea-border-color: var(--secondary-color-4);
+
+--chat-id-color:         var(--theme-nuance-color-4);
+
+
+
+/* ------------------------------------------- */
+--button-alert-text-hover:       var(--primary-color-1);
+--button-alert-color-hover:      var(--theme-orange-color);
+--button-alert-border-hover:     var(--theme-orange-color);
+
+--button-alert-text-active:      var(--primary-color-1);
+--button-alert-color-active:     var(--theme-red-color);
+--button-alert-border-active:    var(--theme-red-color);
+
+
+
+/* ----------- PRIMARY BUTTONS --------------- */
+/* - button should immediately catch the eye - */
+--button-primary-text:   var(--secondary-color-1);
+--button-primary-color:  var(--theme-nuance-color-3);
+--button-primary-border: var(--theme-nuance-color-3);
+
+
+/* ---------hover---------- */
+--button-primary-text-hover:
+    hsl(217.5,
+    calc(var(--secondary-color-1-saturation) + 35%),
+    calc(var(--secondary-color-1-lightness)  - 30%));
+
+--button-primary-color-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) -  2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+--button-primary-border-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) -  2%),
+    calc(var(--theme-nuance-color-3-lightness)  - 10%));
+
+
+/* ---------active--------- */
+--button-primary-text-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  + 35%));
+
+--button-primary-color-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 10%),
+    calc(var(--theme-nuance-color-3-lightness)  - 25%));
+
+--button-primary-border-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 10%),
+    calc(var(--theme-nuance-color-3-lightness)  - 25%));
+
+
+
+/* ---------- SECONDARY BUTTONS -------------- */
+/* these should NOT immediately catch the eye  */
+--button-secondary-text:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 50%));
+
+--button-secondary-color:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  + 10%));
+
+--button-secondary-border:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  + 10%));
+
+
+/* ---------hover---------- */
+--button-secondary-text-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 20%),
+    calc(var(--theme-nuance-color-3-lightness)  - 80%));
+
+--button-secondary-color-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 22%),
+    calc(var(--theme-nuance-color-3-lightness)  +  1%));
+
+--button-secondary-border-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 22%),
+    calc(var(--theme-nuance-color-3-lightness)  +  1%));
+
+
+/* ---------active--------- */
+--button-secondary-text-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) + 40%),
+    calc(var(--theme-nuance-color-3-lightness)  - 55%));
+
+--button-secondary-color-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 30%),
+    calc(var(--theme-nuance-color-3-lightness)  -  5%));
+
+--button-secondary-border-active:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 30%),
+    calc(var(--theme-nuance-color-3-lightness)  -  5%));
+
+
+
+/* ---------- TERTIARY BUTTONS --------------- */
+/* ---------- disabled buttons --------------- */
+--button-tertiary-text:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  -  5%));
+
+--button-tertiary-color:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  + 20%));
+
+--button-tertiary-border:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  + 20%));
+
+/* ---------hover---------- */
+--button-tertiary-text-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  -  5%));
+
+--button-tertiary-color-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  + 20%));
+
+--button-tertiary-border-hover:
+    hsl(210,
+    calc(var(--theme-nuance-color-3-saturation) - 40%),
+    calc(var(--theme-nuance-color-3-lightness)  + 20%));
+
+}
diff --git a/tools/server/public_simplechat/datautils.mjs b/tools/server/public_simplechat/datautils.mjs
new file mode 100644
index 00000000..75159d6b
--- /dev/null
+++ b/tools/server/public_simplechat/datautils.mjs
@@ -0,0 +1,266 @@
+//@ts-check
+// Helpers to work with different data types
+// by Humans for All
+//
+
+/**
+ * Given the limited context size of local LLMs and , many a times when context gets filled
+ * between the prompt and the response, it can lead to repeating text garbage generation.
+ * And many a times setting penalty wrt repeatation leads to over-intelligent garbage
+ * repeatation with slight variations. These garbage inturn can lead to overloading of the
+ * available model context, leading to less valuable response for subsequent prompts/queries,
+ * if chat history is sent to ai model.
+ *
+ * So two simple minded garbage trimming logics are experimented below.
+ * * one based on progressively-larger-substring-based-repeat-matching-with-partial-skip and
+ * * another based on char-histogram-driven garbage trimming.
+ *   * in future characteristic of histogram over varying lengths could be used to allow for
+ *     a more aggressive and adaptive trimming logic.
+ */
+
+
+/**
+ * Simple minded logic to help remove repeating garbage at end of the string.
+ * The repeatation needs to be perfectly matching.
+ *
+ * The logic progressively goes on probing for longer and longer substring based
+ * repeatation, till there is no longer repeatation. Inturn picks the one with
+ * the longest chain.
+ *
+ * @param {string} sIn
+ * @param {number} maxSubL
+ * @param {number} maxMatchLenThreshold
+ */
+export function trim_repeat_garbage_at_end(sIn, maxSubL=10, maxMatchLenThreshold=40) {
+    let rCnt = [0];
+    let maxMatchLen = maxSubL;
+    let iMML = -1;
+    for(let subL=1; subL < maxSubL; subL++) {
+        rCnt.push(0);
+        let i;
+        let refS = sIn.substring(sIn.length-subL, sIn.length);
+        for(i=sIn.length; i > 0; i -= subL) {
+            let curS = sIn.substring(i-subL, i);
+            if (refS != curS) {
+                let curMatchLen = rCnt[subL]*subL;
+                if (maxMatchLen < curMatchLen) {
+                    maxMatchLen = curMatchLen;
+                    iMML = subL;
+                }
+                break;
+            }
+            rCnt[subL] += 1;
+        }
+    }
+    console.debug("DBUG:DU:TrimRepeatGarbage:", rCnt);
+    if ((iMML == -1) || (maxMatchLen < maxMatchLenThreshold)) {
+        return {trimmed: false, data: sIn};
+    }
+    console.debug("DBUG:TrimRepeatGarbage:TrimmedCharLen:", maxMatchLen);
+    let iEnd = sIn.length - maxMatchLen;
+    return { trimmed: true, data: sIn.substring(0, iEnd) };
+}
+
+
+/**
+ * Simple minded logic to help remove repeating garbage at end of the string, till it cant.
+ * If its not able to trim, then it will try to skip a char at end and then trim, a few times.
+ * This ensures that even if there are multiple runs of garbage with different patterns, the
+ * logic still tries to munch through them.
+ *
+ * @param {string} sIn
+ * @param {number} maxSubL
+ * @param {number | undefined} [maxMatchLenThreshold]
+ */
+export function trim_repeat_garbage_at_end_loop(sIn, maxSubL, maxMatchLenThreshold, skipMax=16) {
+    let sCur = sIn;
+    let sSaved = "";
+    let iTry = 0;
+    while(true) {
+        let got = trim_repeat_garbage_at_end(sCur, maxSubL, maxMatchLenThreshold);
+        if (got.trimmed != true) {
+            if (iTry == 0) {
+                sSaved = got.data;
+            }
+            iTry += 1;
+            if (iTry >= skipMax) {
+                return sSaved;
+            }
+            got.data = got.data.substring(0,got.data.length-1);
+        } else {
+            iTry = 0;
+        }
+        sCur = got.data;
+    }
+}
+
+
+/**
+ * A simple minded try trim garbage at end using histogram driven characteristics.
+ * There can be variation in the repeatations, as long as no new char props up.
+ *
+ * This tracks the chars and their frequency in a specified length of substring at the end
+ * and inturn checks if moving further into the generated text from the end remains within
+ * the same char subset or goes beyond it and based on that either trims the string at the
+ * end or not. This allows to filter garbage at the end, including even if there are certain
+ * kind of small variations in the repeated text wrt position of seen chars.
+ *
+ * Allow the garbage to contain upto maxUniq chars, but at the same time ensure that
+ * a given type of char ie numerals or alphabets or other types dont cross the specified
+ * maxType limit. This allows intermixed text garbage to be identified and trimmed.
+ *
+ * ALERT: This is not perfect and only provides a rough garbage identification logic.
+ * Also it currently only differentiates between character classes wrt english.
+ *
+ * @param {string} sIn
+ * @param {number} maxType
+ * @param {number} maxUniq
+ * @param {number} maxMatchLenThreshold
+ */
+export function trim_hist_garbage_at_end(sIn, maxType, maxUniq, maxMatchLenThreshold) {
+    if (sIn.length < maxMatchLenThreshold) {
+        return { trimmed: false, data: sIn };
+    }
+    let iAlp = 0;
+    let iNum = 0;
+    let iOth = 0;
+    // Learn
+    let hist = {};
+    let iUniq = 0;
+    for(let i=0; i<maxMatchLenThreshold; i++) {
+        let c = sIn[sIn.length-1-i];
+        if (c in hist) {
+            hist[c] += 1;
+        } else {
+            if(c.match(/[0-9]/) != null) {
+                iNum += 1;
+            } else if(c.match(/[A-Za-z]/) != null) {
+                iAlp += 1;
+            } else {
+                iOth += 1;
+            }
+            iUniq += 1;
+            if (iUniq >= maxUniq) {
+                break;
+            }
+            hist[c] = 1;
+        }
+    }
+    console.debug("DBUG:TrimHistGarbage:", hist);
+    if ((iAlp > maxType) || (iNum > maxType) || (iOth > maxType)) {
+        return { trimmed: false, data: sIn };
+    }
+    // Catch and Trim
+    for(let i=0; i < sIn.length; i++) {
+        let c = sIn[sIn.length-1-i];
+        if (!(c in hist)) {
+            if (i < maxMatchLenThreshold) {
+                return { trimmed: false, data: sIn };
+            }
+            console.debug("DBUG:TrimHistGarbage:TrimmedCharLen:", i);
+            return { trimmed: true, data: sIn.substring(0, sIn.length-i+1) };
+        }
+    }
+    console.debug("DBUG:TrimHistGarbage:Trimmed fully");
+    return { trimmed: true, data: "" };
+}
+
+/**
+ * Keep trimming repeatedly using hist_garbage logic, till you no longer can.
+ * This ensures that even if there are multiple runs of garbage with different patterns,
+ * the logic still tries to munch through them.
+ *
+ * @param {any} sIn
+ * @param {number} maxType
+ * @param {number} maxUniq
+ * @param {number} maxMatchLenThreshold
+ */
+export function trim_hist_garbage_at_end_loop(sIn, maxType, maxUniq, maxMatchLenThreshold) {
+    let sCur = sIn;
+    while (true) {
+        let got = trim_hist_garbage_at_end(sCur, maxType, maxUniq, maxMatchLenThreshold);
+        if (!got.trimmed) {
+            return got.data;
+        }
+        sCur = got.data;
+    }
+}
+
+/**
+ * Try trim garbage at the end by using both the hist-driven-garbage-trimming as well as
+ * skip-a-bit-if-reqd-then-repeat-pattern-based-garbage-trimming, with blind retrying.
+ * @param {string} sIn
+ */
+export function trim_garbage_at_end(sIn) {
+    let sCur = sIn;
+    for(let i=0; i<2; i++) {
+        sCur = trim_hist_garbage_at_end_loop(sCur, 8, 24, 72);
+        sCur = trim_repeat_garbage_at_end_loop(sCur, 32, 72, 12);
+    }
+    return sCur;
+}
+
+
+/**
+ * NewLines array helper.
+ * Allow for maintaining a list of lines.
+ * Allow for a line to be builtup/appended part by part.
+ */
+export class NewLines {
+
+    constructor() {
+        /** @type {string[]} */
+        this.lines = [];
+    }
+
+    /**
+     * Extracts lines from the passed string and inturn either
+     * append to a previous partial line or add a new line.
+     * @param {string} sLines
+     */
+    add_append(sLines) {
+        let aLines = sLines.split("\n");
+        let lCnt = 0;
+        for(let line of aLines) {
+            lCnt += 1;
+            // Add back newline removed if any during split
+            if (lCnt < aLines.length) {
+                line += "\n";
+            } else {
+                if (sLines.endsWith("\n")) {
+                    line += "\n";
+                }
+            }
+            // Append if required
+            if (lCnt == 1) {
+                let lastLine = this.lines[this.lines.length-1];
+                if (lastLine != undefined) {
+                    if (!lastLine.endsWith("\n")) {
+                        this.lines[this.lines.length-1] += line;
+                        continue;
+                    }
+                }
+            }
+            // Add new line
+            this.lines.push(line);
+        }
+    }
+
+    /**
+     * Shift the oldest/earliest/0th line in the array. [Old-New|Earliest-Latest]
+     * Optionally control whether only full lines (ie those with newline at end) will be returned
+     * or will a partial line without a newline at end (can only be the last line) be returned.
+     * @param {boolean} bFullWithNewLineOnly
+     */
+    shift(bFullWithNewLineOnly=true) {
+        let line = this.lines[0];
+        if (line == undefined) {
+            return undefined;
+        }
+        if ((line[line.length-1] != "\n") && bFullWithNewLineOnly){
+            return undefined;
+        }
+        return this.lines.shift();
+    }
+
+}
diff --git a/tools/server/public_simplechat/index.html b/tools/server/public_simplechat/index.html
new file mode 100644
index 00000000..f6413016
--- /dev/null
+++ b/tools/server/public_simplechat/index.html
@@ -0,0 +1,51 @@
+<!DOCTYPE html>
+<html lang="en">
+    <head>
+        <title>SimpleChat LlamaCppEtal </title>
+        <meta charset="UTF-8" />
+        <meta name="viewport" content="width=device-width, initial-scale=1" />
+        <meta name="message" content="Save Nature Save Earth" />
+        <meta name="description" content="SimpleChat: trigger LLM web service endpoints /chat/completions and /completions, single/multi chat sessions" />
+        <meta name="author" content="by Humans for All" />
+        <meta http-equiv="Cache-Control" content="no-cache, no-store, must-revalidate" />
+        <script type="importmap">
+            {
+                "imports": {
+                    "datautils": "./datautils.mjs",
+                    "ui": "./ui.mjs"
+                }
+            }
+        </script>
+        <script src="simplechat.js" type="module" defer></script>
+        <link rel="stylesheet" href="simplechat.css" />
+    </head>
+    <body>
+        <div class="samecolumn" id="fullbody">
+
+            <div class="sameline" id="heading">
+                <p class="heading flex-grow" > <b> SimpleChat </b> </p>
+                <button id="settings">Settings</button>
+            </div>
+
+            <div id="sessions-div" class="sameline"></div>
+
+            <hr>
+            <div class="sameline">
+                <label for="system-in">System</label>
+                <textarea name="system" id="system-in" rows="2" placeholder="e.g. you are a helpful ai assistant, who provides concise answers" class="flex-grow">

+ +

You need to have javascript enabled.

+ +

+ + +

+ +

+ + diff --git a/tools/server/public_simplechat/readme.md b/tools/server/public_simplechat/readme.md new file mode 100644 index 00000000..24e026d4 --- /dev/null +++ b/tools/server/public_simplechat/readme.md @@ -0,0 +1,286 @@ + +# SimpleChat + +by Humans for All. + +## quickstart + +To run from the build dir + +bin/llama-server -m path/model.gguf --path ../tools/server/public_simplechat + +Continue reading for the details. + +## overview + +This simple web frontend, allows triggering/testing the server's /completions or /chat/completions endpoints +in a simple way with minimal code from a common code base. Inturn additionally it tries to allow single or +multiple independent back and forth chatting to an extent, with the ai llm model at a basic level, with their +own system prompts. + +This allows seeing the generated text / ai-model response in oneshot at the end, after it is fully generated, +or potentially as it is being generated, in a streamed manner from the server/ai-model. + +![Chat and Settings screens](./simplechat_screens.webp "Chat and Settings screens") + +Auto saves the chat session locally as and when the chat is progressing and inturn at a later time when you +open SimpleChat, option is provided to restore the old chat session, if a matching one exists. + +The UI follows a responsive web design so that the layout can adapt to available display space in a usable +enough manner, in general. + +Allows developer/end-user to control some of the behaviour by updating gMe members from browser's devel-tool +console. Parallely some of the directly useful to end-user settings can also be changed using the provided +settings ui. + +NOTE: Current web service api doesnt expose the model context length directly, so client logic doesnt provide +any adaptive culling of old messages nor of replacing them with summary of their content etal. However there +is a optional sliding window based chat logic, which provides a simple minded culling of old messages from +the chat history before sending to the ai model. + +NOTE: Wrt options sent with the request, it mainly sets temperature, max_tokens and optionaly stream for now. +However if someone wants they can update the js file or equivalent member in gMe as needed. + +NOTE: One may be able to use this to chat with openai api web-service /chat/completions endpoint, in a very +limited / minimal way. One will need to set model, openai url and authorization bearer key in settings ui. + + +## usage + +One could run this web frontend directly using server itself or if anyone is thinking of adding a built in web +frontend to configure the server over http(s) or so, then run this web frontend using something like python's +http module. + +### running using tools/server + +./llama-server -m path/model.gguf --path tools/server/public_simplechat [--port PORT] + +### running using python3's server module + +first run tools/server +* ./llama-server -m path/model.gguf + +next run this web front end in tools/server/public_simplechat +* cd ../tools/server/public_simplechat +* python3 -m http.server PORT + +### using the front end + +Open this simple web front end from your local browser + +* http://127.0.0.1:PORT/index.html + +Once inside + +* If you want to, you can change many of the default global settings + * the base url (ie ip addr / domain name, port) + * chat (default) vs completion mode + * try trim garbage in response or not + * amount of chat history in the context sent to server/ai-model + * oneshot or streamed mode. + +* In completion mode + * one normally doesnt use a system prompt in completion mode. + * logic by default doesnt insert any role specific "ROLE: " prefix wrt each role's message. + If the model requires any prefix wrt user role messages, then the end user has to + explicitly add the needed prefix, when they enter their chat message. + Similarly if the model requires any prefix to trigger assistant/ai-model response, + then the end user needs to enter the same. + This keeps the logic simple, while still giving flexibility to the end user to + manage any templating/tagging requirement wrt their messages to the model. + * the logic doesnt insert newline at the begining and end wrt the prompt message generated. + However if the chat being sent to /completions end point has more than one role's message, + then insert newline when moving from one role's message to the next role's message, so + that it can be clearly identified/distinguished. + * given that /completions endpoint normally doesnt add additional chat-templating of its + own, the above ensures that end user can create a custom single/multi message combo with + any tags/special-tokens related chat templating to test out model handshake. Or enduser + can use it just for normal completion related/based query. + +* If you want to provide a system prompt, then ideally enter it first, before entering any user query. + Normally Completion mode doesnt need system prompt, while Chat mode can generate better/interesting + responses with a suitable system prompt. + * if chat.add_system_begin is used + * you cant change the system prompt, after it is has been submitted once along with user query. + * you cant set a system prompt, after you have submitted any user query + * if chat.add_system_anytime is used + * one can change the system prompt any time during chat, by changing the contents of system prompt. + * inturn the updated/changed system prompt will be inserted into the chat session. + * this allows for the subsequent user chatting to be driven by the new system prompt set above. + +* Enter your query and either press enter or click on the submit button. + If you want to insert enter (\n) as part of your chat/query to ai model, use shift+enter. + +* Wait for the logic to communicate with the server and get the response. + * the user is not allowed to enter any fresh query during this time. + * the user input box will be disabled and a working message will be shown in it. + * if trim garbage is enabled, the logic will try to trim repeating text kind of garbage to some extent. + +* just refresh the page, to reset wrt the chat history and or system prompt and start afresh. + +* Using NewChat one can start independent chat sessions. + * two independent chat sessions are setup by default. + +* When you want to print, switching ChatHistoryInCtxt to Full and clicking on the chat session button of + interest, will display the full chat history till then wrt same, if you want full history for printing. + + +## Devel note + +### Reason behind this + +The idea is to be easy enough to use for basic purposes, while also being simple and easily discernable +by developers who may not be from web frontend background (so inturn may not be familiar with template / +end-use-specific-language-extensions driven flows) so that they can use it to explore/experiment things. + +And given that the idea is also to help explore/experiment for developers, some flexibility is provided +to change behaviour easily using the devel-tools/console or provided minimal settings ui (wrt few aspects). +Skeletal logic has been implemented to explore some of the end points and ideas/implications around them. + + +### General + +Me/gMe consolidates the settings which control the behaviour into one object. +One can see the current settings, as well as change/update them using browsers devel-tool/console. +It is attached to the document object. Some of these can also be updated using the Settings UI. + + baseURL - the domain-name/ip-address and inturn the port to send the request. + + bStream - control between oneshot-at-end and live-stream-as-its-generated collating and showing + of the generated response. + + the logic assumes that the text sent from the server follows utf-8 encoding. + + in streaming mode - if there is any exception, the logic traps the same and tries to ensure + that text generated till then is not lost. + + if a very long text is being generated, which leads to no user interaction for sometime and + inturn the machine goes into power saving mode or so, the platform may stop network connection, + leading to exception. + + apiEP - select between /completions and /chat/completions endpoint provided by the server/ai-model. + + bCompletionFreshChatAlways - whether Completion mode collates complete/sliding-window history when + communicating with the server or only sends the latest user query/message. + + bCompletionInsertStandardRolePrefix - whether Completion mode inserts role related prefix wrt the + messages that get inserted into prompt field wrt /Completion endpoint. + + bTrimGarbage - whether garbage repeatation at the end of the generated ai response, should be + trimmed or left as is. If enabled, it will be trimmed so that it wont be sent back as part of + subsequent chat history. At the same time the actual trimmed text is shown to the user, once + when it was generated, so user can check if any useful info/data was there in the response. + + One may be able to request the ai-model to continue (wrt the last response) (if chat-history + is enabled as part of the chat-history-in-context setting), and chances are the ai-model will + continue starting from the trimmed part, thus allows long response to be recovered/continued + indirectly, in many cases. + + The histogram/freq based trimming logic is currently tuned for english language wrt its + is-it-a-alpabetic|numeral-char regex match logic. + + apiRequestOptions - maintains the list of options/fields to send along with api request, + irrespective of whether /chat/completions or /completions endpoint. + + If you want to add additional options/fields to send to the server/ai-model, and or + modify the existing options value or remove them, for now you can update this global var + using browser's development-tools/console. + + For string, numeric and boolean fields in apiRequestOptions, including even those added by a + user at runtime by directly modifying gMe.apiRequestOptions, setting ui entries will be auto + created. + + cache_prompt option supported by example/server is allowed to be controlled by user, so that + any caching supported wrt system-prompt and chat history, if usable can get used. When chat + history sliding window is enabled, cache_prompt logic may or may not kick in at the backend + wrt same, based on aspects related to model, positional encoding, attention mechanism etal. + However system prompt should ideally get the benefit of caching. + + headers - maintains the list of http headers sent when request is made to the server. By default + Content-Type is set to application/json. Additionally Authorization entry is provided, which can + be set if needed using the settings ui. + + iRecentUserMsgCnt - a simple minded SlidingWindow to limit context window load at Ai Model end. + This is disabled by default. However if enabled, then in addition to latest system message, only + the last/latest iRecentUserMsgCnt user messages after the latest system prompt and its responses + from the ai model will be sent to the ai-model, when querying for a new response. IE if enabled, + only user messages after the latest system message/prompt will be considered. + + This specified sliding window user message count also includes the latest user query. + <0 : Send entire chat history to server + 0 : Send only the system message if any to the server + >0 : Send the latest chat history from the latest system prompt, limited to specified cnt. + + +By using gMe's iRecentUserMsgCnt and apiRequestOptions.max_tokens/n_predict one can try to control +the implications of loading of the ai-model's context window by chat history, wrt chat response to +some extent in a simple crude way. You may also want to control the context size enabled when the +server loads ai-model, on the server end. + + +Sometimes the browser may be stuborn with caching of the file, so your updates to html/css/js +may not be visible. Also remember that just refreshing/reloading page in browser or for that +matter clearing site data, dont directly override site caching in all cases. Worst case you may +have to change port. Or in dev tools of browser, you may be able to disable caching fully. + + +Currently the server to communicate with is maintained globally and not as part of a specific +chat session. So if one changes the server ip/url in setting, then all chat sessions will auto +switch to this new server, when you try using those sessions. + + +By switching between chat.add_system_begin/anytime, one can control whether one can change +the system prompt, anytime during the conversation or only at the beginning. + + +### Default setup + +By default things are setup to try and make the user experience a bit better, if possible. +However a developer when testing the server of ai-model may want to change these value. + +Using iRecentUserMsgCnt reduce chat history context sent to the server/ai-model to be +just the system-prompt, prev-user-request-and-ai-response and cur-user-request, instead of +full chat history. This way if there is any response with garbage/repeatation, it doesnt +mess with things beyond the next question/request/query, in some ways. The trim garbage +option also tries to help avoid issues with garbage in the context to an extent. + +Set max_tokens to 1024, so that a relatively large previous reponse doesnt eat up the space +available wrt next query-response. However dont forget that the server when started should +also be started with a model context size of 1k or more, to be on safe side. + + The /completions endpoint of tools/server doesnt take max_tokens, instead it takes the + internal n_predict, for now add the same here on the client side, maybe later add max_tokens + to /completions endpoint handling code on server side. + +NOTE: One may want to experiment with frequency/presence penalty fields in apiRequestOptions +wrt the set of fields sent to server along with the user query, to check how the model behaves +wrt repeatations in general in the generated text response. + +A end-user can change these behaviour by editing gMe from browser's devel-tool/console or by +using the provided settings ui (for settings exposed through the ui). + + +### OpenAi / Equivalent API WebService + +One may be abe to handshake with OpenAI/Equivalent api web service's /chat/completions endpoint +for a minimal chatting experimentation by setting the below. + +* the baseUrl in settings ui + * https://api.openai.com/v1 or similar + +* Wrt request body - gMe.apiRequestOptions + * model (settings ui) + * any additional fields if required in future + +* Wrt request headers - gMe.headers + * Authorization (available through settings ui) + * Bearer THE_OPENAI_API_KEY + * any additional optional header entries like "OpenAI-Organization", "OpenAI-Project" or so + +NOTE: Not tested, as there is no free tier api testing available. However logically this might +work. + + +## At the end + +Also a thank you to all open source and open model developers, who strive for the common good. diff --git a/tools/server/public_simplechat/simplechat.css b/tools/server/public_simplechat/simplechat.css new file mode 100644 index 00000000..13bfb80b --- /dev/null +++ b/tools/server/public_simplechat/simplechat.css @@ -0,0 +1,79 @@ +/** + * the styling of the simplechat web frontend + * by Humans for All + */ + +#fullbody { + height: 98vh; +} + +.heading { + background-color: lightgray; +} + +.session-selected { + background-color: lightblue; +} + +.role-system { + background-color: lightblue; +} +.role-user { + background-color: lightgray; +} +.role-trim { + background-color: lightpink; +} + +.gridx2 { + display: grid; + grid-template-columns: repeat(2, 1fr); + border-bottom-style: dotted; + border-bottom-width: thin; + border-bottom-color: lightblue; +} + +.flex-grow { + flex-grow: 1; +} +.float-right { + float: right; +} + +#chat-div { + overflow: scroll; + flex-grow: 1; + flex-shrink: 1; + min-height: 40vh; +} +button { + min-width: 8vw; +} + +.sameline { + display: flex; + flex-direction: row; +} +.samecolumn { + display: flex; + flex-direction: column; +} + +.ul1 { + padding-inline-start: 2vw; +} +.ul2 { + padding-inline-start: 2vw; +} + +* { + margin: 0.6vmin; +} + +@media print { + + #fullbody { + height: auto; + } + +} diff --git a/tools/server/public_simplechat/simplechat.js b/tools/server/public_simplechat/simplechat.js new file mode 100644 index 00000000..2fcd24a8 --- /dev/null +++ b/tools/server/public_simplechat/simplechat.js @@ -0,0 +1,929 @@ +// @ts-check +// A simple completions and chat/completions test related web front end logic +// by Humans for All + +import * as du from "./datautils.mjs"; +import * as ui from "./ui.mjs" + +class Roles { + static System = "system"; + static User = "user"; + static Assistant = "assistant"; +} + +class ApiEP { + static Type = { + Chat: "chat", + Completion: "completion", + } + static UrlSuffix = { + 'chat': `/chat/completions`, + 'completion': `/completions`, + } + + /** + * Build the url from given baseUrl and apiEp id. + * @param {string} baseUrl + * @param {string} apiEP + */ + static Url(baseUrl, apiEP) { + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.substring(0, baseUrl.length-1); + } + return `${baseUrl}${this.UrlSuffix[apiEP]}`; + } + +} + + +let gUsageMsg = ` +

Usage

System prompt above, to try control ai response characteristics.

Completion mode - no system prompt normally.

Use shift+enter for inserting enter/newline.
Enter your query to ai assistant below.
Default ContextWindow = [System, Last Query+Resp, Cur Query].

ChatHistInCtxt, MaxTokens, ModelCtxt window to expand

+`; + + +/** @typedef {{role: string, content: string}[]} ChatMessages */ + +/** @typedef {{iLastSys: number, xchat: ChatMessages}} SimpleChatODS */ + +class SimpleChat { + + /** + * @param {string} chatId + */ + constructor(chatId) { + this.chatId = chatId; + /** + * Maintain in a form suitable for common LLM web service chat/completions' messages entry + * @type {ChatMessages} + */ + this.xchat = []; + this.iLastSys = -1; + this.latestResponse = ""; + } + + clear() { + this.xchat = []; + this.iLastSys = -1; + } + + ods_key() { + return `SimpleChat-${this.chatId}` + } + + save() { + /** @type {SimpleChatODS} */ + let ods = {iLastSys: this.iLastSys, xchat: this.xchat}; + localStorage.setItem(this.ods_key(), JSON.stringify(ods)); + } + + load() { + let sods = localStorage.getItem(this.ods_key()); + if (sods == null) { + return; + } + /** @type {SimpleChatODS} */ + let ods = JSON.parse(sods); + this.iLastSys = ods.iLastSys; + this.xchat = ods.xchat; + } + + /** + * Recent chat messages. + * If iRecentUserMsgCnt < 0 + * Then return the full chat history + * Else + * Return chat messages from latest going back till the last/latest system prompt. + * While keeping track that the number of user queries/messages doesnt exceed iRecentUserMsgCnt. + * @param {number} iRecentUserMsgCnt + */ + recent_chat(iRecentUserMsgCnt) { + if (iRecentUserMsgCnt < 0) { + return this.xchat; + } + if (iRecentUserMsgCnt == 0) { + console.warn("WARN:SimpleChat:SC:RecentChat:iRecentUsermsgCnt of 0 means no user message/query sent"); + } + /** @type{ChatMessages} */ + let rchat = []; + let sysMsg = this.get_system_latest(); + if (sysMsg.length != 0) { + rchat.push({role: Roles.System, content: sysMsg}); + } + let iUserCnt = 0; + let iStart = this.xchat.length; + for(let i=this.xchat.length-1; i > this.iLastSys; i--) { + if (iUserCnt >= iRecentUserMsgCnt) { + break; + } + let msg = this.xchat[i]; + if (msg.role == Roles.User) { + iStart = i; + iUserCnt += 1; + } + } + for(let i = iStart; i < this.xchat.length; i++) { + let msg = this.xchat[i]; + if (msg.role == Roles.System) { + continue; + } + rchat.push({role: msg.role, content: msg.content}); + } + return rchat; + } + + /** + * Collate the latest response from the server/ai-model, as it is becoming available. + * This is mainly useful for the stream mode. + * @param {string} content + */ + append_response(content) { + this.latestResponse += content; + } + + /** + * Add an entry into xchat + * @param {string} role + * @param {string|undefined|null} content + */ + add(role, content) { + if ((content == undefined) || (content == null) || (content == "")) { + return false; + } + this.xchat.push( {role: role, content: content} ); + if (role == Roles.System) { + this.iLastSys = this.xchat.length - 1; + } + this.save(); + return true; + } + + /** + * Show the contents in the specified div + * @param {HTMLDivElement} div + * @param {boolean} bClear + */ + show(div, bClear=true) { + if (bClear) { + div.replaceChildren(); + } + let last = undefined; + for(const x of this.recent_chat(gMe.iRecentUserMsgCnt)) { + let entry = ui.el_create_append_p(`${x.role}: ${x.content}`, div); + entry.className = `role-${x.role}`; + last = entry; + } + if (last !== undefined) { + last.scrollIntoView(false); + } else { + if (bClear) { + div.innerHTML = gUsageMsg; + gMe.setup_load(div, this); + gMe.show_info(div); + } + } + return last; + } + + /** + * Setup the fetch headers. + * It picks the headers from gMe.headers. + * It inserts Authorization only if its non-empty. + * @param {string} apiEP + */ + fetch_headers(apiEP) { + let headers = new Headers(); + for(let k in gMe.headers) { + let v = gMe.headers[k]; + if ((k == "Authorization") && (v.trim() == "")) { + continue; + } + headers.append(k, v); + } + return headers; + } + + /** + * Add needed fields wrt json object to be sent wrt LLM web services completions endpoint. + * The needed fields/options are picked from a global object. + * Add optional stream flag, if required. + * Convert the json into string. + * @param {Object} obj + */ + request_jsonstr_extend(obj) { + for(let k in gMe.apiRequestOptions) { + obj[k] = gMe.apiRequestOptions[k]; + } + if (gMe.bStream) { + obj["stream"] = true; + } + return JSON.stringify(obj); + } + + /** + * Return a string form of json object suitable for chat/completions + */ + request_messages_jsonstr() { + let req = { + messages: this.recent_chat(gMe.iRecentUserMsgCnt), + } + return this.request_jsonstr_extend(req); + } + + /** + * Return a string form of json object suitable for /completions + * @param {boolean} bInsertStandardRolePrefix Insert ": " as prefix wrt each role's message + */ + request_prompt_jsonstr(bInsertStandardRolePrefix) { + let prompt = ""; + let iCnt = 0; + for(const chat of this.recent_chat(gMe.iRecentUserMsgCnt)) { + iCnt += 1; + if (iCnt > 1) { + prompt += "\n"; + } + if (bInsertStandardRolePrefix) { + prompt += `${chat.role}: `; + } + prompt += `${chat.content}`; + } + let req = { + prompt: prompt, + } + return this.request_jsonstr_extend(req); + } + + /** + * Return a string form of json object suitable for specified api endpoint. + * @param {string} apiEP + */ + request_jsonstr(apiEP) { + if (apiEP == ApiEP.Type.Chat) { + return this.request_messages_jsonstr(); + } else { + return this.request_prompt_jsonstr(gMe.bCompletionInsertStandardRolePrefix); + } + } + + /** + * Extract the ai-model/assistant's response from the http response got. + * Optionally trim the message wrt any garbage at the end. + * @param {any} respBody + * @param {string} apiEP + */ + response_extract(respBody, apiEP) { + let assistant = ""; + if (apiEP == ApiEP.Type.Chat) { + assistant = respBody["choices"][0]["message"]["content"]; + } else { + try { + assistant = respBody["choices"][0]["text"]; + } catch { + assistant = respBody["content"]; + } + } + return assistant; + } + + /** + * Extract the ai-model/assistant's response from the http response got in streaming mode. + * @param {any} respBody + * @param {string} apiEP + */ + response_extract_stream(respBody, apiEP) { + let assistant = ""; + if (apiEP == ApiEP.Type.Chat) { + if (respBody["choices"][0]["finish_reason"] !== "stop") { + assistant = respBody["choices"][0]["delta"]["content"]; + } + } else { + try { + assistant = respBody["choices"][0]["text"]; + } catch { + assistant = respBody["content"]; + } + } + return assistant; + } + + /** + * Allow setting of system prompt, but only at begining. + * @param {string} sysPrompt + * @param {string} msgTag + */ + add_system_begin(sysPrompt, msgTag) { + if (this.xchat.length == 0) { + if (sysPrompt.length > 0) { + return this.add(Roles.System, sysPrompt); + } + } else { + if (sysPrompt.length > 0) { + if (this.xchat[0].role !== Roles.System) { + console.error(`ERRR:SimpleChat:SC:${msgTag}:You need to specify system prompt before any user query, ignoring...`); + } else { + if (this.xchat[0].content !== sysPrompt) { + console.error(`ERRR:SimpleChat:SC:${msgTag}:You cant change system prompt, mid way through, ignoring...`); + } + } + } + } + return false; + } + + /** + * Allow setting of system prompt, at any time. + * @param {string} sysPrompt + * @param {string} msgTag + */ + add_system_anytime(sysPrompt, msgTag) { + if (sysPrompt.length <= 0) { + return false; + } + + if (this.iLastSys < 0) { + return this.add(Roles.System, sysPrompt); + } + + let lastSys = this.xchat[this.iLastSys].content; + if (lastSys !== sysPrompt) { + return this.add(Roles.System, sysPrompt); + } + return false; + } + + /** + * Retrieve the latest system prompt. + */ + get_system_latest() { + if (this.iLastSys == -1) { + return ""; + } + let sysPrompt = this.xchat[this.iLastSys].content; + return sysPrompt; + } + + + /** + * Handle the multipart response from server/ai-model + * @param {Response} resp + * @param {string} apiEP + * @param {HTMLDivElement} elDiv + */ + async handle_response_multipart(resp, apiEP, elDiv) { + let elP = ui.el_create_append_p("", elDiv); + if (!resp.body) { + throw Error("ERRR:SimpleChat:SC:HandleResponseMultiPart:No body..."); + } + let tdUtf8 = new TextDecoder("utf-8"); + let rr = resp.body.getReader(); + this.latestResponse = ""; + let xLines = new du.NewLines(); + while(true) { + let { value: cur, done: done } = await rr.read(); + if (cur) { + let curBody = tdUtf8.decode(cur, {stream: true}); + console.debug("DBUG:SC:PART:Str:", curBody); + xLines.add_append(curBody); + } + while(true) { + let curLine = xLines.shift(!done); + if (curLine == undefined) { + break; + } + if (curLine.trim() == "") { + continue; + } + if (curLine.startsWith("data:")) { + curLine = curLine.substring(5); + } + if (curLine.trim() === "[DONE]") { + break; + } + let curJson = JSON.parse(curLine); + console.debug("DBUG:SC:PART:Json:", curJson); + this.append_response(this.response_extract_stream(curJson, apiEP)); + } + elP.innerText = this.latestResponse; + elP.scrollIntoView(false); + if (done) { + break; + } + } + console.debug("DBUG:SC:PART:Full:", this.latestResponse); + return this.latestResponse; + } + + /** + * Handle the oneshot response from server/ai-model + * @param {Response} resp + * @param {string} apiEP + */ + async handle_response_oneshot(resp, apiEP) { + let respBody = await resp.json(); + console.debug(`DBUG:SimpleChat:SC:${this.chatId}:HandleUserSubmit:RespBody:${JSON.stringify(respBody)}`); + return this.response_extract(respBody, apiEP); + } + + /** + * Handle the response from the server be it in oneshot or multipart/stream mode. + * Also take care of the optional garbage trimming. + * @param {Response} resp + * @param {string} apiEP + * @param {HTMLDivElement} elDiv + */ + async handle_response(resp, apiEP, elDiv) { + let theResp = { + assistant: "", + trimmed: "", + } + if (gMe.bStream) { + try { + theResp.assistant = await this.handle_response_multipart(resp, apiEP, elDiv); + this.latestResponse = ""; + } catch (error) { + theResp.assistant = this.latestResponse; + this.add(Roles.Assistant, theResp.assistant); + this.latestResponse = ""; + throw error; + } + } else { + theResp.assistant = await this.handle_response_oneshot(resp, apiEP); + } + if (gMe.bTrimGarbage) { + let origMsg = theResp.assistant; + theResp.assistant = du.trim_garbage_at_end(origMsg); + theResp.trimmed = origMsg.substring(theResp.assistant.length); + } + this.add(Roles.Assistant, theResp.assistant); + return theResp; + } + +} + + +class MultiChatUI { + + constructor() { + /** @type {Object} */ + this.simpleChats = {}; + /** @type {string} */ + this.curChatId = ""; + + // the ui elements + this.elInSystem = /** @type{HTMLInputElement} */(document.getElementById("system-in")); + this.elDivChat = /** @type{HTMLDivElement} */(document.getElementById("chat-div")); + this.elBtnUser = /** @type{HTMLButtonElement} */(document.getElementById("user-btn")); + this.elInUser = /** @type{HTMLInputElement} */(document.getElementById("user-in")); + this.elDivHeading = /** @type{HTMLSelectElement} */(document.getElementById("heading")); + this.elDivSessions = /** @type{HTMLDivElement} */(document.getElementById("sessions-div")); + this.elBtnSettings = /** @type{HTMLButtonElement} */(document.getElementById("settings")); + + this.validate_element(this.elInSystem, "system-in"); + this.validate_element(this.elDivChat, "chat-div"); + this.validate_element(this.elInUser, "user-in"); + this.validate_element(this.elDivHeading, "heading"); + this.validate_element(this.elDivChat, "sessions-div"); + this.validate_element(this.elBtnSettings, "settings"); + } + + /** + * Check if the element got + * @param {HTMLElement | null} el + * @param {string} msgTag + */ + validate_element(el, msgTag) { + if (el == null) { + throw Error(`ERRR:SimpleChat:MCUI:${msgTag} element missing in html...`); + } else { + console.debug(`INFO:SimpleChat:MCUI:${msgTag} Id[${el.id}] Name[${el["name"]}]`); + } + } + + /** + * Reset user input ui. + * * clear user input + * * enable user input + * * set focus to user input + */ + ui_reset_userinput() { + this.elInUser.value = ""; + this.elInUser.disabled = false; + this.elInUser.focus(); + } + + /** + * Setup the needed callbacks wrt UI, curChatId to defaultChatId and + * optionally switch to specified defaultChatId. + * @param {string} defaultChatId + * @param {boolean} bSwitchSession + */ + setup_ui(defaultChatId, bSwitchSession=false) { + + this.curChatId = defaultChatId; + if (bSwitchSession) { + this.handle_session_switch(this.curChatId); + } + + this.elBtnSettings.addEventListener("click", (ev)=>{ + this.elDivChat.replaceChildren(); + gMe.show_settings(this.elDivChat); + }); + + this.elBtnUser.addEventListener("click", (ev)=>{ + if (this.elInUser.disabled) { + return; + } + this.handle_user_submit(this.curChatId, gMe.apiEP).catch((/** @type{Error} */reason)=>{ + let msg = `ERRR:SimpleChat\nMCUI:HandleUserSubmit:${this.curChatId}\n${reason.name}:${reason.message}`; + console.error(msg.replace("\n", ":")); + alert(msg); + this.ui_reset_userinput(); + }); + }); + + this.elInUser.addEventListener("keyup", (ev)=> { + // allow user to insert enter into their message using shift+enter. + // while just pressing enter key will lead to submitting. + if ((ev.key === "Enter") && (!ev.shiftKey)) { + let value = this.elInUser.value; + this.elInUser.value = value.substring(0,value.length-1); + this.elBtnUser.click(); + ev.preventDefault(); + } + }); + + this.elInSystem.addEventListener("keyup", (ev)=> { + // allow user to insert enter into the system prompt using shift+enter. + // while just pressing enter key will lead to setting the system prompt. + if ((ev.key === "Enter") && (!ev.shiftKey)) { + let value = this.elInSystem.value; + this.elInSystem.value = value.substring(0,value.length-1); + let chat = this.simpleChats[this.curChatId]; + chat.add_system_anytime(this.elInSystem.value, this.curChatId); + chat.show(this.elDivChat); + ev.preventDefault(); + } + }); + + } + + /** + * Setup a new chat session and optionally switch to it. + * @param {string} chatId + * @param {boolean} bSwitchSession + */ + new_chat_session(chatId, bSwitchSession=false) { + this.simpleChats[chatId] = new SimpleChat(chatId); + if (bSwitchSession) { + this.handle_session_switch(chatId); + } + } + + + /** + * Handle user query submit request, wrt specified chat session. + * @param {string} chatId + * @param {string} apiEP + */ + async handle_user_submit(chatId, apiEP) { + + let chat = this.simpleChats[chatId]; + + // In completion mode, if configured, clear any previous chat history. + // So if user wants to simulate a multi-chat based completion query, + // they will have to enter the full thing, as a suitable multiline + // user input/query. + if ((apiEP == ApiEP.Type.Completion) && (gMe.bCompletionFreshChatAlways)) { + chat.clear(); + } + + chat.add_system_anytime(this.elInSystem.value, chatId); + + let content = this.elInUser.value; + if (!chat.add(Roles.User, content)) { + console.debug(`WARN:SimpleChat:MCUI:${chatId}:HandleUserSubmit:Ignoring empty user input...`); + return; + } + chat.show(this.elDivChat); + + let theUrl = ApiEP.Url(gMe.baseURL, apiEP); + let theBody = chat.request_jsonstr(apiEP); + + this.elInUser.value = "working..."; + this.elInUser.disabled = true; + console.debug(`DBUG:SimpleChat:MCUI:${chatId}:HandleUserSubmit:${theUrl}:ReqBody:${theBody}`); + let theHeaders = chat.fetch_headers(apiEP); + let resp = await fetch(theUrl, { + method: "POST", + headers: theHeaders, + body: theBody, + }); + + let theResp = await chat.handle_response(resp, apiEP, this.elDivChat); + if (chatId == this.curChatId) { + chat.show(this.elDivChat); + if (theResp.trimmed.length > 0) { + let p = ui.el_create_append_p(`TRIMMED:${theResp.trimmed}`, this.elDivChat); + p.className="role-trim"; + } + } else { + console.debug(`DBUG:SimpleChat:MCUI:HandleUserSubmit:ChatId has changed:[${chatId}] [${this.curChatId}]`); + } + this.ui_reset_userinput(); + } + + /** + * Show buttons for NewChat and available chat sessions, in the passed elDiv. + * If elDiv is undefined/null, then use this.elDivSessions. + * Take care of highlighting the selected chat-session's btn. + * @param {HTMLDivElement | undefined} elDiv + */ + show_sessions(elDiv=undefined) { + if (!elDiv) { + elDiv = this.elDivSessions; + } + elDiv.replaceChildren(); + // Btn for creating new chat session + let btnNew = ui.el_create_button("New CHAT", (ev)=> { + if (this.elInUser.disabled) { + console.error(`ERRR:SimpleChat:MCUI:NewChat:Current session [${this.curChatId}] awaiting response, ignoring request...`); + alert("ERRR:SimpleChat\nMCUI:NewChat\nWait for response to pending query, before starting new chat session"); + return; + } + let chatId = `Chat${Object.keys(this.simpleChats).length}`; + let chatIdGot = prompt("INFO:SimpleChat\nMCUI:NewChat\nEnter id for new chat session", chatId); + if (!chatIdGot) { + console.error("ERRR:SimpleChat:MCUI:NewChat:Skipping based on user request..."); + return; + } + this.new_chat_session(chatIdGot, true); + this.create_session_btn(elDiv, chatIdGot); + ui.el_children_config_class(elDiv, chatIdGot, "session-selected", ""); + }); + elDiv.appendChild(btnNew); + // Btns for existing chat sessions + let chatIds = Object.keys(this.simpleChats); + for(let cid of chatIds) { + let btn = this.create_session_btn(elDiv, cid); + if (cid == this.curChatId) { + btn.className = "session-selected"; + } + } + } + + create_session_btn(elDiv, cid) { + let btn = ui.el_create_button(cid, (ev)=>{ + let target = /** @type{HTMLButtonElement} */(ev.target); + console.debug(`DBUG:SimpleChat:MCUI:SessionClick:${target.id}`); + if (this.elInUser.disabled) { + console.error(`ERRR:SimpleChat:MCUI:SessionClick:${target.id}:Current session [${this.curChatId}] awaiting response, ignoring switch...`); + alert("ERRR:SimpleChat\nMCUI:SessionClick\nWait for response to pending query, before switching"); + return; + } + this.handle_session_switch(target.id); + ui.el_children_config_class(elDiv, target.id, "session-selected", ""); + }); + elDiv.appendChild(btn); + return btn; + } + + /** + * Switch ui to the specified chatId and set curChatId to same. + * @param {string} chatId + */ + async handle_session_switch(chatId) { + let chat = this.simpleChats[chatId]; + if (chat == undefined) { + console.error(`ERRR:SimpleChat:MCUI:HandleSessionSwitch:${chatId} missing...`); + return; + } + this.elInSystem.value = chat.get_system_latest(); + this.elInUser.value = ""; + chat.show(this.elDivChat); + this.elInUser.focus(); + this.curChatId = chatId; + console.log(`INFO:SimpleChat:MCUI:HandleSessionSwitch:${chatId} entered...`); + } + +} + + +class Me { + + constructor() { + this.baseURL = "http://127.0.0.1:8080"; + this.defaultChatIds = [ "Default", "Other" ]; + this.multiChat = new MultiChatUI(); + this.bStream = true; + this.bCompletionFreshChatAlways = true; + this.bCompletionInsertStandardRolePrefix = false; + this.bTrimGarbage = true; + this.iRecentUserMsgCnt = 2; + this.sRecentUserMsgCnt = { + "Full": -1, + "Last0": 1, + "Last1": 2, + "Last2": 3, + "Last4": 5, + }; + this.apiEP = ApiEP.Type.Chat; + this.headers = { + "Content-Type": "application/json", + "Authorization": "", // Authorization: Bearer OPENAI_API_KEY + } + // Add needed fields wrt json object to be sent wrt LLM web services completions endpoint. + this.apiRequestOptions = { + "model": "gpt-3.5-turbo", + "temperature": 0.7, + "max_tokens": 1024, + "n_predict": 1024, + "cache_prompt": false, + //"frequency_penalty": 1.2, + //"presence_penalty": 1.2, + }; + } + + /** + * Disable console.debug by mapping it to a empty function. + */ + debug_disable() { + this.console_debug = console.debug; + console.debug = () => { + + }; + } + + /** + * Setup the load saved chat ui. + * @param {HTMLDivElement} div + * @param {SimpleChat} chat + */ + setup_load(div, chat) { + if (!(chat.ods_key() in localStorage)) { + return; + } + div.innerHTML += `

Restore

Load previously saved chat session, if available

`; + let btn = ui.el_create_button(chat.ods_key(), (ev)=>{ + console.log("DBUG:SimpleChat:SC:Load", chat); + chat.load(); + queueMicrotask(()=>{ + chat.show(div); + this.multiChat.elInSystem.value = chat.get_system_latest(); + }); + }); + div.appendChild(btn); + } + + /** + * Show the configurable parameters info in the passed Div element. + * @param {HTMLDivElement} elDiv + * @param {boolean} bAll + */ + show_info(elDiv, bAll=false) { + + let p = ui.el_create_append_p("Settings (devel-tools-console document[gMe])", elDiv); + p.className = "role-system"; + + if (bAll) { + + ui.el_create_append_p(`baseURL:${this.baseURL}`, elDiv); + + ui.el_create_append_p(`Authorization:${this.headers["Authorization"]}`, elDiv); + + ui.el_create_append_p(`bStream:${this.bStream}`, elDiv); + + ui.el_create_append_p(`bTrimGarbage:${this.bTrimGarbage}`, elDiv); + + ui.el_create_append_p(`ApiEndPoint:${this.apiEP}`, elDiv); + + ui.el_create_append_p(`iRecentUserMsgCnt:${this.iRecentUserMsgCnt}`, elDiv); + + ui.el_create_append_p(`bCompletionFreshChatAlways:${this.bCompletionFreshChatAlways}`, elDiv); + + ui.el_create_append_p(`bCompletionInsertStandardRolePrefix:${this.bCompletionInsertStandardRolePrefix}`, elDiv); + + } + + ui.el_create_append_p(`apiRequestOptions:${JSON.stringify(this.apiRequestOptions, null, " - ")}`, elDiv); + ui.el_create_append_p(`headers:${JSON.stringify(this.headers, null, " - ")}`, elDiv); + + } + + /** + * Auto create ui input elements for fields in apiRequestOptions + * Currently supports text and number field types. + * @param {HTMLDivElement} elDiv + */ + show_settings_apirequestoptions(elDiv) { + let typeDict = { + "string": "text", + "number": "number", + }; + let fs = document.createElement("fieldset"); + let legend = document.createElement("legend"); + legend.innerText = "ApiRequestOptions"; + fs.appendChild(legend); + elDiv.appendChild(fs); + for(const k in this.apiRequestOptions) { + let val = this.apiRequestOptions[k]; + let type = typeof(val); + if (((type == "string") || (type == "number"))) { + let inp = ui.el_creatediv_input(`Set${k}`, k, typeDict[type], this.apiRequestOptions[k], (val)=>{ + if (type == "number") { + val = Number(val); + } + this.apiRequestOptions[k] = val; + }); + fs.appendChild(inp.div); + } else if (type == "boolean") { + let bbtn = ui.el_creatediv_boolbutton(`Set{k}`, k, {true: "true", false: "false"}, val, (userVal)=>{ + this.apiRequestOptions[k] = userVal; + }); + fs.appendChild(bbtn.div); + } + } + } + + /** + * Show settings ui for configurable parameters, in the passed Div element. + * @param {HTMLDivElement} elDiv + */ + show_settings(elDiv) { + + let inp = ui.el_creatediv_input("SetBaseURL", "BaseURL", "text", this.baseURL, (val)=>{ + this.baseURL = val; + }); + elDiv.appendChild(inp.div); + + inp = ui.el_creatediv_input("SetAuthorization", "Authorization", "text", this.headers["Authorization"], (val)=>{ + this.headers["Authorization"] = val; + }); + inp.el.placeholder = "Bearer OPENAI_API_KEY"; + elDiv.appendChild(inp.div); + + let bb = ui.el_creatediv_boolbutton("SetStream", "Stream", {true: "[+] yes stream", false: "[-] do oneshot"}, this.bStream, (val)=>{ + this.bStream = val; + }); + elDiv.appendChild(bb.div); + + bb = ui.el_creatediv_boolbutton("SetTrimGarbage", "TrimGarbage", {true: "[+] yes trim", false: "[-] dont trim"}, this.bTrimGarbage, (val)=>{ + this.bTrimGarbage = val; + }); + elDiv.appendChild(bb.div); + + this.show_settings_apirequestoptions(elDiv); + + let sel = ui.el_creatediv_select("SetApiEP", "ApiEndPoint", ApiEP.Type, this.apiEP, (val)=>{ + this.apiEP = ApiEP.Type[val]; + }); + elDiv.appendChild(sel.div); + + sel = ui.el_creatediv_select("SetChatHistoryInCtxt", "ChatHistoryInCtxt", this.sRecentUserMsgCnt, this.iRecentUserMsgCnt, (val)=>{ + this.iRecentUserMsgCnt = this.sRecentUserMsgCnt[val]; + }); + elDiv.appendChild(sel.div); + + bb = ui.el_creatediv_boolbutton("SetCompletionFreshChatAlways", "CompletionFreshChatAlways", {true: "[+] yes fresh", false: "[-] no, with history"}, this.bCompletionFreshChatAlways, (val)=>{ + this.bCompletionFreshChatAlways = val; + }); + elDiv.appendChild(bb.div); + + bb = ui.el_creatediv_boolbutton("SetCompletionInsertStandardRolePrefix", "CompletionInsertStandardRolePrefix", {true: "[+] yes insert", false: "[-] dont insert"}, this.bCompletionInsertStandardRolePrefix, (val)=>{ + this.bCompletionInsertStandardRolePrefix = val; + }); + elDiv.appendChild(bb.div); + + } + +} + + +/** @type {Me} */ +let gMe; + +function startme() { + console.log("INFO:SimpleChat:StartMe:Starting..."); + gMe = new Me(); + gMe.debug_disable(); + document["gMe"] = gMe; + document["du"] = du; + for (let cid of gMe.defaultChatIds) { + gMe.multiChat.new_chat_session(cid); + } + gMe.multiChat.setup_ui(gMe.defaultChatIds[0], true); + gMe.multiChat.show_sessions(); +} + +document.addEventListener("DOMContentLoaded", startme); diff --git a/tools/server/public_simplechat/simplechat_screens.webp b/tools/server/public_simplechat/simplechat_screens.webp new file mode 100644 index 00000000..ccea4439 Binary files /dev/null and b/tools/server/public_simplechat/simplechat_screens.webp differ diff --git a/tools/server/public_simplechat/ui.mjs b/tools/server/public_simplechat/ui.mjs new file mode 100644 index 00000000..b2d5b9ae --- /dev/null +++ b/tools/server/public_simplechat/ui.mjs @@ -0,0 +1,211 @@ +//@ts-check +// Helpers to work with html elements +// by Humans for All +// + + +/** + * Set the class of the children, based on whether it is the idSelected or not. + * @param {HTMLDivElement} elBase + * @param {string} idSelected + * @param {string} classSelected + * @param {string} classUnSelected + */ +export function el_children_config_class(elBase, idSelected, classSelected, classUnSelected="") { + for(let child of elBase.children) { + if (child.id == idSelected) { + child.className = classSelected; + } else { + child.className = classUnSelected; + } + } +} + +/** + * Create button and set it up. + * @param {string} id + * @param {(this: HTMLButtonElement, ev: MouseEvent) => any} callback + * @param {string | undefined} name + * @param {string | undefined} innerText + */ +export function el_create_button(id, callback, name=undefined, innerText=undefined) { + if (!name) { + name = id; + } + if (!innerText) { + innerText = id; + } + let btn = document.createElement("button"); + btn.id = id; + btn.name = name; + btn.innerText = innerText; + btn.addEventListener("click", callback); + return btn; +} + +/** + * Create a para and set it up. Optionaly append it to a passed parent. + * @param {string} text + * @param {HTMLElement | undefined} elParent + * @param {string | undefined} id + */ +export function el_create_append_p(text, elParent=undefined, id=undefined) { + let para = document.createElement("p"); + para.innerText = text; + if (id) { + para.id = id; + } + if (elParent) { + elParent.appendChild(para); + } + return para; +} + +/** + * Create a button which represents bool value using specified text wrt true and false. + * When ever user clicks the button, it will toggle the value and update the shown text. + * + * @param {string} id + * @param {{true: string, false: string}} texts + * @param {boolean} defaultValue + * @param {function(boolean):void} cb + */ +export function el_create_boolbutton(id, texts, defaultValue, cb) { + let el = document.createElement("button"); + el["xbool"] = defaultValue; + el["xtexts"] = structuredClone(texts); + el.innerText = el["xtexts"][String(defaultValue)]; + if (id) { + el.id = id; + } + el.addEventListener('click', (ev)=>{ + el["xbool"] = !el["xbool"]; + el.innerText = el["xtexts"][String(el["xbool"])]; + cb(el["xbool"]); + }) + return el; +} + +/** + * Create a div wrapped button which represents bool value using specified text wrt true and false. + * @param {string} id + * @param {string} label + * @param {{ true: string; false: string; }} texts + * @param {boolean} defaultValue + * @param {(arg0: boolean) => void} cb + * @param {string} className + */ +export function el_creatediv_boolbutton(id, label, texts, defaultValue, cb, className="gridx2") { + let div = document.createElement("div"); + div.className = className; + let lbl = document.createElement("label"); + lbl.setAttribute("for", id); + lbl.innerText = label; + div.appendChild(lbl); + let btn = el_create_boolbutton(id, texts, defaultValue, cb); + div.appendChild(btn); + return { div: div, el: btn }; +} + + +/** + * Create a select ui element, with a set of options to select from. + * * options: an object which contains name-value pairs + * * defaultOption: the value whose name should be choosen, by default. + * * cb : the call back returns the name string of the option selected. + * + * @param {string} id + * @param {Object} options + * @param {*} defaultOption + * @param {function(string):void} cb + */ +export function el_create_select(id, options, defaultOption, cb) { + let el = document.createElement("select"); + el["xselected"] = defaultOption; + el["xoptions"] = structuredClone(options); + for(let cur of Object.keys(options)) { + let op = document.createElement("option"); + op.value = cur; + op.innerText = cur; + if (options[cur] == defaultOption) { + op.selected = true; + } + el.appendChild(op); + } + if (id) { + el.id = id; + el.name = id; + } + el.addEventListener('change', (ev)=>{ + let target = /** @type{HTMLSelectElement} */(ev.target); + console.log("DBUG:UI:Select:", id, ":", target.value); + cb(target.value); + }) + return el; +} + +/** + * Create a div wrapped select ui element, with a set of options to select from. + * + * @param {string} id + * @param {any} label + * @param {{ [x: string]: any; }} options + * @param {any} defaultOption + * @param {(arg0: string) => void} cb + * @param {string} className + */ +export function el_creatediv_select(id, label, options, defaultOption, cb, className="gridx2") { + let div = document.createElement("div"); + div.className = className; + let lbl = document.createElement("label"); + lbl.setAttribute("for", id); + lbl.innerText = label; + div.appendChild(lbl); + let sel = el_create_select(id, options,defaultOption, cb); + div.appendChild(sel); + return { div: div, el: sel }; +} + + +/** + * Create a input ui element. + * + * @param {string} id + * @param {string} type + * @param {any} defaultValue + * @param {function(any):void} cb + */ +export function el_create_input(id, type, defaultValue, cb) { + let el = document.createElement("input"); + el.type = type; + el.value = defaultValue; + if (id) { + el.id = id; + } + el.addEventListener('change', (ev)=>{ + cb(el.value); + }) + return el; +} + +/** + * Create a div wrapped input. + * + * @param {string} id + * @param {string} label + * @param {string} type + * @param {any} defaultValue + * @param {function(any):void} cb + * @param {string} className + */ +export function el_creatediv_input(id, label, type, defaultValue, cb, className="gridx2") { + let div = document.createElement("div"); + div.className = className; + let lbl = document.createElement("label"); + lbl.setAttribute("for", id); + lbl.innerText = label; + div.appendChild(lbl); + let el = el_create_input(id, type, defaultValue, cb); + div.appendChild(el); + return { div: div, el: el }; +} diff --git a/tools/server/server.cpp b/tools/server/server.cpp new file mode 100644 index 00000000..c580ec12 --- /dev/null +++ b/tools/server/server.cpp @@ -0,0 +1,4640 @@ +#include "utils.hpp" + +#include "arg.h" +#include "common.h" +#include "json-schema-to-grammar.h" +#include "llama.h" +#include "log.h" +#include "sampling.h" +#include "speculative.h" + +// Change JSON_ASSERT from assert() to GGML_ASSERT: +#define JSON_ASSERT GGML_ASSERT +#include "json.hpp" +// mime type for sending response +#define MIMETYPE_JSON "application/json; charset=utf-8" + +// auto generated files (see README.md for details) +#include "index.html.gz.hpp" +#include "loading.html.hpp" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +using json = nlohmann::ordered_json; + +constexpr int HTTP_POLLING_SECONDS = 1; + +enum stop_type { + STOP_TYPE_NONE, + STOP_TYPE_EOS, + STOP_TYPE_WORD, + STOP_TYPE_LIMIT, +}; + +// state diagram: https://github.com/ggml-org/llama.cpp/pull/9283 +enum slot_state { + SLOT_STATE_IDLE, + SLOT_STATE_STARTED, // TODO: this state is only used for setting up the initial prompt processing; maybe merge it with launch_slot_with_task in the future + SLOT_STATE_PROCESSING_PROMPT, + SLOT_STATE_DONE_PROMPT, + SLOT_STATE_GENERATING, +}; + +enum server_state { + SERVER_STATE_LOADING_MODEL, // Server is starting up, model not fully loaded yet + SERVER_STATE_READY, // Server is ready and model is loaded +}; + +enum server_task_type { + SERVER_TASK_TYPE_COMPLETION, + SERVER_TASK_TYPE_EMBEDDING, + SERVER_TASK_TYPE_RERANK, + SERVER_TASK_TYPE_INFILL, + SERVER_TASK_TYPE_CANCEL, + SERVER_TASK_TYPE_NEXT_RESPONSE, + SERVER_TASK_TYPE_METRICS, + SERVER_TASK_TYPE_SLOT_SAVE, + SERVER_TASK_TYPE_SLOT_RESTORE, + SERVER_TASK_TYPE_SLOT_ERASE, + SERVER_TASK_TYPE_SET_LORA, +}; + +enum oaicompat_type { + OAICOMPAT_TYPE_NONE, + OAICOMPAT_TYPE_CHAT, + OAICOMPAT_TYPE_COMPLETION, + OAICOMPAT_TYPE_EMBEDDING, +}; + +// https://community.openai.com/t/openai-chat-list-of-error-codes-and-types/357791/11 +enum error_type { + ERROR_TYPE_INVALID_REQUEST, + ERROR_TYPE_AUTHENTICATION, + ERROR_TYPE_SERVER, + ERROR_TYPE_NOT_FOUND, + ERROR_TYPE_PERMISSION, + ERROR_TYPE_UNAVAILABLE, // custom error + ERROR_TYPE_NOT_SUPPORTED, // custom error +}; + +struct slot_params { + bool stream = true; + bool cache_prompt = true; // remember the prompt to avoid reprocessing all prompt + bool return_tokens = false; + + int32_t n_keep = 0; // number of tokens to keep from initial prompt + int32_t n_discard = 0; // number of tokens after n_keep that may be discarded when shifting context, 0 defaults to half + int32_t n_predict = -1; // new tokens to predict + int32_t n_indent = 0; // mininum line indentation for the generated text in number of whitespace characters + + int64_t t_max_prompt_ms = -1; // TODO: implement + int64_t t_max_predict_ms = -1; // if positive, limit the generation phase to this time limit + + std::vector lora; + + std::vector antiprompt; + std::vector response_fields; + bool timings_per_token = false; + bool post_sampling_probs = false; + bool ignore_eos = false; + + struct common_params_sampling sampling; + struct common_params_speculative speculative; + + // OAI-compat fields + bool verbose = false; + oaicompat_type oaicompat = OAICOMPAT_TYPE_NONE; + std::string oaicompat_model; + std::string oaicompat_cmpl_id; + common_chat_format oaicompat_chat_format = COMMON_CHAT_FORMAT_CONTENT_ONLY; + + json to_json() const { + std::vector samplers; + samplers.reserve(sampling.samplers.size()); + for (const auto & sampler : sampling.samplers) { + samplers.emplace_back(common_sampler_type_to_str(sampler)); + } + + json lora = json::array(); + for (size_t i = 0; i < this->lora.size(); ++i) { + lora.push_back({{"id", i}, {"scale", this->lora[i].scale}}); + } + + auto grammar_triggers = json::array(); + for (const auto & trigger : sampling.grammar_triggers) { + server_grammar_trigger ct(std::move(trigger)); + grammar_triggers.push_back(ct.to_json()); + } + + return json { + {"n_predict", n_predict}, // Server configured n_predict + {"seed", sampling.seed}, + {"temperature", sampling.temp}, + {"dynatemp_range", sampling.dynatemp_range}, + {"dynatemp_exponent", sampling.dynatemp_exponent}, + {"top_k", sampling.top_k}, + {"top_p", sampling.top_p}, + {"min_p", sampling.min_p}, + {"xtc_probability", sampling.xtc_probability}, + {"xtc_threshold", sampling.xtc_threshold}, + {"typical_p", sampling.typ_p}, + {"repeat_last_n", sampling.penalty_last_n}, + {"repeat_penalty", sampling.penalty_repeat}, + {"presence_penalty", sampling.penalty_present}, + {"frequency_penalty", sampling.penalty_freq}, + {"dry_multiplier", sampling.dry_multiplier}, + {"dry_base", sampling.dry_base}, + {"dry_allowed_length", sampling.dry_allowed_length}, + {"dry_penalty_last_n", sampling.dry_penalty_last_n}, + {"dry_sequence_breakers", sampling.dry_sequence_breakers}, + {"mirostat", sampling.mirostat}, + {"mirostat_tau", sampling.mirostat_tau}, + {"mirostat_eta", sampling.mirostat_eta}, + {"stop", antiprompt}, + {"max_tokens", n_predict}, // User configured n_predict + {"n_keep", n_keep}, + {"n_discard", n_discard}, + {"ignore_eos", sampling.ignore_eos}, + {"stream", stream}, + {"logit_bias", format_logit_bias(sampling.logit_bias)}, + {"n_probs", sampling.n_probs}, + {"min_keep", sampling.min_keep}, + {"grammar", sampling.grammar}, + {"grammar_lazy", sampling.grammar_lazy}, + {"grammar_triggers", grammar_triggers}, + {"preserved_tokens", sampling.preserved_tokens}, + {"chat_format", common_chat_format_name(oaicompat_chat_format)}, + {"samplers", samplers}, + {"speculative.n_max", speculative.n_max}, + {"speculative.n_min", speculative.n_min}, + {"speculative.p_min", speculative.p_min}, + {"timings_per_token", timings_per_token}, + {"post_sampling_probs", post_sampling_probs}, + {"lora", lora}, + }; + } +}; + +struct server_task { + int id = -1; // to be filled by server_queue + int index = -1; // used when there are multiple prompts (batch request) + + server_task_type type; + + // used by SERVER_TASK_TYPE_CANCEL + int id_target = -1; + + // used by SERVER_TASK_TYPE_INFERENCE + slot_params params; + llama_tokens prompt_tokens; + int id_selected_slot = -1; + + // used by SERVER_TASK_TYPE_SLOT_SAVE, SERVER_TASK_TYPE_SLOT_RESTORE, SERVER_TASK_TYPE_SLOT_ERASE + struct slot_action { + int slot_id; + std::string filename; + std::string filepath; + }; + slot_action slot_action; + + // used by SERVER_TASK_TYPE_METRICS + bool metrics_reset_bucket = false; + + // used by SERVER_TASK_TYPE_SET_LORA + std::vector set_lora; + + server_task(server_task_type type) : type(type) {} + + static slot_params params_from_json_cmpl( + const llama_context * ctx, + const common_params & params_base, + const json & data) { + const llama_model * model = llama_get_model(ctx); + const llama_vocab * vocab = llama_model_get_vocab(model); + + slot_params params; + + // Sampling parameter defaults are loaded from the global server context (but individual requests can still override them) + slot_params defaults; + defaults.sampling = params_base.sampling; + defaults.speculative = params_base.speculative; + + // enabling this will output extra debug information in the HTTP responses from the server + params.verbose = params_base.verbosity > 9; + params.timings_per_token = json_value(data, "timings_per_token", false); + + params.stream = json_value(data, "stream", false); + params.cache_prompt = json_value(data, "cache_prompt", true); + params.return_tokens = json_value(data, "return_tokens", false); + params.n_predict = json_value(data, "n_predict", json_value(data, "max_tokens", defaults.n_predict)); + params.n_indent = json_value(data, "n_indent", defaults.n_indent); + params.n_keep = json_value(data, "n_keep", defaults.n_keep); + params.n_discard = json_value(data, "n_discard", defaults.n_discard); + //params.t_max_prompt_ms = json_value(data, "t_max_prompt_ms", defaults.t_max_prompt_ms); // TODO: implement + params.t_max_predict_ms = json_value(data, "t_max_predict_ms", defaults.t_max_predict_ms); + params.response_fields = json_value(data, "response_fields", std::vector()); + + params.sampling.top_k = json_value(data, "top_k", defaults.sampling.top_k); + params.sampling.top_p = json_value(data, "top_p", defaults.sampling.top_p); + params.sampling.min_p = json_value(data, "min_p", defaults.sampling.min_p); + params.sampling.xtc_probability = json_value(data, "xtc_probability", defaults.sampling.xtc_probability); + params.sampling.xtc_threshold = json_value(data, "xtc_threshold", defaults.sampling.xtc_threshold); + params.sampling.typ_p = json_value(data, "typical_p", defaults.sampling.typ_p); + params.sampling.temp = json_value(data, "temperature", defaults.sampling.temp); + params.sampling.dynatemp_range = json_value(data, "dynatemp_range", defaults.sampling.dynatemp_range); + params.sampling.dynatemp_exponent = json_value(data, "dynatemp_exponent", defaults.sampling.dynatemp_exponent); + params.sampling.penalty_last_n = json_value(data, "repeat_last_n", defaults.sampling.penalty_last_n); + params.sampling.penalty_repeat = json_value(data, "repeat_penalty", defaults.sampling.penalty_repeat); + params.sampling.penalty_freq = json_value(data, "frequency_penalty", defaults.sampling.penalty_freq); + params.sampling.penalty_present = json_value(data, "presence_penalty", defaults.sampling.penalty_present); + params.sampling.dry_multiplier = json_value(data, "dry_multiplier", defaults.sampling.dry_multiplier); + params.sampling.dry_base = json_value(data, "dry_base", defaults.sampling.dry_base); + params.sampling.dry_allowed_length = json_value(data, "dry_allowed_length", defaults.sampling.dry_allowed_length); + params.sampling.dry_penalty_last_n = json_value(data, "dry_penalty_last_n", defaults.sampling.dry_penalty_last_n); + params.sampling.mirostat = json_value(data, "mirostat", defaults.sampling.mirostat); + params.sampling.mirostat_tau = json_value(data, "mirostat_tau", defaults.sampling.mirostat_tau); + params.sampling.mirostat_eta = json_value(data, "mirostat_eta", defaults.sampling.mirostat_eta); + params.sampling.seed = json_value(data, "seed", defaults.sampling.seed); + params.sampling.n_probs = json_value(data, "n_probs", defaults.sampling.n_probs); + params.sampling.min_keep = json_value(data, "min_keep", defaults.sampling.min_keep); + params.post_sampling_probs = json_value(data, "post_sampling_probs", defaults.post_sampling_probs); + + params.speculative.n_min = json_value(data, "speculative.n_min", defaults.speculative.n_min); + params.speculative.n_max = json_value(data, "speculative.n_max", defaults.speculative.n_max); + params.speculative.p_min = json_value(data, "speculative.p_min", defaults.speculative.p_min); + + params.speculative.n_min = std::min(params.speculative.n_max, params.speculative.n_min); + params.speculative.n_min = std::max(params.speculative.n_min, 0); + params.speculative.n_max = std::max(params.speculative.n_max, 0); + + // Use OpenAI API logprobs only if n_probs wasn't provided + if (data.contains("logprobs") && params.sampling.n_probs == defaults.sampling.n_probs){ + params.sampling.n_probs = json_value(data, "logprobs", defaults.sampling.n_probs); + } + + if (data.contains("lora")) { + if (data.at("lora").is_array()) { + params.lora = parse_lora_request(params_base.lora_adapters, data.at("lora")); + } else { + throw std::runtime_error("Error: 'lora' must be an array of objects with 'id' and 'scale' fields"); + } + } else { + params.lora = params_base.lora_adapters; + } + + // TODO: add more sanity checks for the input parameters + + if (params.sampling.penalty_last_n < -1) { + throw std::runtime_error("Error: repeat_last_n must be >= -1"); + } + + if (params.sampling.dry_penalty_last_n < -1) { + throw std::runtime_error("Error: dry_penalty_last_n must be >= -1"); + } + + if (params.sampling.penalty_last_n == -1) { + // note: should be the slot's context and not the full context, but it's ok + params.sampling.penalty_last_n = llama_n_ctx(ctx); + } + + if (params.sampling.dry_penalty_last_n == -1) { + params.sampling.dry_penalty_last_n = llama_n_ctx(ctx); + } + + if (params.sampling.dry_base < 1.0f) { + params.sampling.dry_base = defaults.sampling.dry_base; + } + + // sequence breakers for DRY + { + // Currently, this is not compatible with TextGen WebUI, Koboldcpp and SillyTavern format + // Ref: https://github.com/oobabooga/text-generation-webui/blob/d1af7a41ade7bd3c3a463bfa640725edb818ebaf/extensions/openai/typing.py#L39 + + if (data.contains("dry_sequence_breakers")) { + params.sampling.dry_sequence_breakers = json_value(data, "dry_sequence_breakers", std::vector()); + if (params.sampling.dry_sequence_breakers.empty()) { + throw std::runtime_error("Error: dry_sequence_breakers must be a non-empty array of strings"); + } + } + } + + // process "json_schema" and "grammar" + if (data.contains("json_schema") && !data.contains("grammar")) { + try { + auto schema = json_value(data, "json_schema", json::object()); + SRV_DBG("JSON schema: %s\n", schema.dump(2).c_str()); + params.sampling.grammar = json_schema_to_grammar(schema); + SRV_DBG("Converted grammar: %s\n", params.sampling.grammar.c_str()); + } catch (const std::exception & e) { + throw std::runtime_error(std::string("\"json_schema\": ") + e.what()); + } + } else { + params.sampling.grammar = json_value(data, "grammar", defaults.sampling.grammar); + SRV_DBG("Grammar: %s\n", params.sampling.grammar.c_str()); + params.sampling.grammar_lazy = json_value(data, "grammar_lazy", defaults.sampling.grammar_lazy); + SRV_DBG("Grammar lazy: %s\n", params.sampling.grammar_lazy ? "true" : "false"); + } + + { + auto it = data.find("chat_format"); + if (it != data.end()) { + params.oaicompat_chat_format = static_cast(it->get()); + SRV_INF("Chat format: %s\n", common_chat_format_name(params.oaicompat_chat_format).c_str()); + } else { + params.oaicompat_chat_format = defaults.oaicompat_chat_format; + } + } + + { + const auto preserved_tokens = data.find("preserved_tokens"); + if (preserved_tokens != data.end()) { + for (const auto & t : *preserved_tokens) { + auto ids = common_tokenize(vocab, t.get(), /* add_special= */ false, /* parse_special= */ true); + if (ids.size() == 1) { + SRV_DBG("Preserved token: %d\n", ids[0]); + params.sampling.preserved_tokens.insert(ids[0]); + } else { + // This may happen when using a tool call style meant for a model with special tokens to preserve on a model without said tokens. + SRV_DBG("Not preserved because more than 1 token: %s\n", t.get().c_str()); + } + } + } + const auto grammar_triggers = data.find("grammar_triggers"); + if (grammar_triggers != data.end()) { + for (const auto & t : *grammar_triggers) { + server_grammar_trigger ct(t); + if (ct.value.type == COMMON_GRAMMAR_TRIGGER_TYPE_WORD) { + const auto & word = ct.value.value; + auto ids = common_tokenize(vocab, word, /* add_special= */ false, /* parse_special= */ true); + if (ids.size() == 1) { + auto token = ids[0]; + if (std::find(params.sampling.preserved_tokens.begin(), params.sampling.preserved_tokens.end(), (llama_token) token) == params.sampling.preserved_tokens.end()) { + throw std::runtime_error("Grammar trigger word should be marked as preserved token: " + word); + } + SRV_DBG("Grammar trigger token: %d (`%s`)\n", token, word.c_str()); + common_grammar_trigger trigger; + trigger.type = COMMON_GRAMMAR_TRIGGER_TYPE_TOKEN; + trigger.value = word; + trigger.token = token; + params.sampling.grammar_triggers.push_back(std::move(trigger)); + } else { + SRV_DBG("Grammar trigger word: `%s`\n", word.c_str()); + params.sampling.grammar_triggers.push_back({COMMON_GRAMMAR_TRIGGER_TYPE_WORD, word}); + } + } else { + params.sampling.grammar_triggers.push_back(std::move(ct.value)); + } + } + } + if (params.sampling.grammar_lazy && params.sampling.grammar_triggers.empty()) { + throw std::runtime_error("Error: no triggers set for lazy grammar!"); + } + } + + { + params.sampling.logit_bias.clear(); + params.ignore_eos = json_value(data, "ignore_eos", false); + + const auto & logit_bias = data.find("logit_bias"); + if (logit_bias != data.end() && logit_bias->is_array()) { + const int n_vocab = llama_vocab_n_tokens(vocab); + for (const auto & el : *logit_bias) { + // TODO: we may want to throw errors here, in case "el" is incorrect + if (el.is_array() && el.size() == 2) { + float bias; + if (el[1].is_number()) { + bias = el[1].get(); + } else if (el[1].is_boolean() && !el[1].get()) { + bias = -INFINITY; + } else { + continue; + } + + if (el[0].is_number_integer()) { + llama_token tok = el[0].get(); + if (tok >= 0 && tok < n_vocab) { + params.sampling.logit_bias.push_back({tok, bias}); + } + } else if (el[0].is_string()) { + auto toks = common_tokenize(vocab, el[0].get(), false); + for (auto tok : toks) { + params.sampling.logit_bias.push_back({tok, bias}); + } + } + } + } + } + } + + { + params.antiprompt.clear(); + + const auto & stop = data.find("stop"); + if (stop != data.end() && stop->is_array()) { + for (const auto & word : *stop) { + if (!word.empty()) { + params.antiprompt.push_back(word); + } + } + } + } + + { + const auto samplers = data.find("samplers"); + if (samplers != data.end()) { + if (samplers->is_array()) { + params.sampling.samplers = common_sampler_types_from_names(*samplers, false); + } else if (samplers->is_string()){ + params.sampling.samplers = common_sampler_types_from_chars(samplers->get()); + } + } else { + params.sampling.samplers = defaults.sampling.samplers; + } + } + + std::string model_name = params_base.model_alias.empty() ? DEFAULT_OAICOMPAT_MODEL : params_base.model_alias; + params.oaicompat_model = json_value(data, "model", model_name); + + return params; + } + + // utility function + static std::unordered_set get_list_id(const std::vector & tasks) { + std::unordered_set ids(tasks.size()); + for (size_t i = 0; i < tasks.size(); i++) { + ids.insert(tasks[i].id); + } + return ids; + } +}; + +struct result_timings { + int32_t prompt_n = -1; + double prompt_ms; + double prompt_per_token_ms; + double prompt_per_second; + + int32_t predicted_n = -1; + double predicted_ms; + double predicted_per_token_ms; + double predicted_per_second; + + // Optional speculative metrics - only included when > 0 + int32_t draft_n = 0; + int32_t draft_n_accepted = 0; + + json to_json() const { + json base = { + {"prompt_n", prompt_n}, + {"prompt_ms", prompt_ms}, + {"prompt_per_token_ms", prompt_per_token_ms}, + {"prompt_per_second", prompt_per_second}, + + {"predicted_n", predicted_n}, + {"predicted_ms", predicted_ms}, + {"predicted_per_token_ms", predicted_per_token_ms}, + {"predicted_per_second", predicted_per_second}, + }; + + if (draft_n > 0) { + base["draft_n"] = draft_n; + base["draft_n_accepted"] = draft_n_accepted; + } + + return base; + } +}; + +struct server_task_result { + int id = -1; + int id_slot = -1; + virtual bool is_error() { + // only used by server_task_result_error + return false; + } + virtual bool is_stop() { + // only used by server_task_result_cmpl_* + return false; + } + virtual int get_index() { + return -1; + } + virtual json to_json() = 0; + virtual ~server_task_result() = default; +}; + +// using shared_ptr for polymorphism of server_task_result +using server_task_result_ptr = std::unique_ptr; + +inline std::string stop_type_to_str(stop_type type) { + switch (type) { + case STOP_TYPE_EOS: return "eos"; + case STOP_TYPE_WORD: return "word"; + case STOP_TYPE_LIMIT: return "limit"; + default: return "none"; + } +} + +struct completion_token_output { + llama_token tok; + float prob; + std::string text_to_send; + struct prob_info { + llama_token tok; + std::string txt; + float prob; + }; + std::vector probs; + + json to_json(bool post_sampling_probs) const { + json probs_for_token = json::array(); + for (const auto & p : probs) { + std::string txt(p.txt); + txt.resize(validate_utf8(txt)); + probs_for_token.push_back(json { + {"id", p.tok}, + {"token", txt}, + {"bytes", str_to_bytes(p.txt)}, + { + post_sampling_probs ? "prob" : "logprob", + post_sampling_probs ? p.prob : logarithm(p.prob) + }, + }); + } + return probs_for_token; + } + + static json probs_vector_to_json(const std::vector & probs, bool post_sampling_probs) { + json out = json::array(); + for (const auto & p : probs) { + std::string txt(p.text_to_send); + txt.resize(validate_utf8(txt)); + out.push_back(json { + {"id", p.tok}, + {"token", txt}, + {"bytes", str_to_bytes(p.text_to_send)}, + { + post_sampling_probs ? "prob" : "logprob", + post_sampling_probs ? p.prob : logarithm(p.prob) + }, + { + post_sampling_probs ? "top_probs" : "top_logprobs", + p.to_json(post_sampling_probs) + }, + }); + } + return out; + } + + static float logarithm(float x) { + // nlohmann::json converts -inf to null, so we need to prevent that + return x == 0.0f ? std::numeric_limits::lowest() : std::log(x); + } + + static std::vector str_to_bytes(const std::string & str) { + std::vector bytes; + for (unsigned char c : str) { + bytes.push_back(c); + } + return bytes; + } +}; + +struct server_task_result_cmpl_final : server_task_result { + int index = 0; + + std::string content; + llama_tokens tokens; + + bool stream; + result_timings timings; + std::string prompt; + + bool truncated; + int32_t n_decoded; + int32_t n_prompt_tokens; + int32_t n_tokens_cached; + bool has_new_line; + std::string stopping_word; + stop_type stop = STOP_TYPE_NONE; + + bool post_sampling_probs; + std::vector probs_output; + std::vector response_fields; + + slot_params generation_params; + + // OAI-compat fields + bool verbose = false; + oaicompat_type oaicompat = OAICOMPAT_TYPE_NONE; + std::string oaicompat_model; + std::string oaicompat_cmpl_id; + common_chat_format oaicompat_chat_format = COMMON_CHAT_FORMAT_CONTENT_ONLY; + + virtual int get_index() override { + return index; + } + + virtual bool is_stop() override { + return true; // in stream mode, final responses are considered stop + } + + virtual json to_json() override { + switch (oaicompat) { + case OAICOMPAT_TYPE_NONE: + return to_json_non_oaicompat(); + case OAICOMPAT_TYPE_COMPLETION: + return to_json_oaicompat(); + case OAICOMPAT_TYPE_CHAT: + return stream ? to_json_oaicompat_chat_stream() : to_json_oaicompat_chat(); + default: + GGML_ASSERT(false && "Invalid oaicompat_type"); + } + } + + json to_json_non_oaicompat() { + json res = json { + {"index", index}, + {"content", stream ? "" : content}, // in stream mode, content is already in last partial chunk + {"tokens", stream ? llama_tokens {} : tokens}, + {"id_slot", id_slot}, + {"stop", true}, + {"model", oaicompat_model}, + {"tokens_predicted", n_decoded}, + {"tokens_evaluated", n_prompt_tokens}, + {"generation_settings", generation_params.to_json()}, + {"prompt", prompt}, + {"has_new_line", has_new_line}, + {"truncated", truncated}, + {"stop_type", stop_type_to_str(stop)}, + {"stopping_word", stopping_word}, + {"tokens_cached", n_tokens_cached}, + {"timings", timings.to_json()}, + }; + if (!stream && !probs_output.empty()) { + res["completion_probabilities"] = completion_token_output::probs_vector_to_json(probs_output, post_sampling_probs); + } + return response_fields.empty() ? res : json_get_nested_values(response_fields, res); + } + + json to_json_oaicompat() { + std::time_t t = std::time(0); + json logprobs = json(nullptr); // OAI default to null + if (!stream && probs_output.size() > 0) { + logprobs = json{ + {"content", completion_token_output::probs_vector_to_json(probs_output, post_sampling_probs)}, + }; + } + json finish_reason = "length"; + if (stop == STOP_TYPE_WORD || stop == STOP_TYPE_EOS) { + finish_reason = "stop"; + } + json res = json { + {"choices", json::array({ + json{ + {"text", stream ? "" : content}, // in stream mode, content is already in last partial chunk + {"index", index}, + {"logprobs", logprobs}, + {"finish_reason", finish_reason}, + } + })}, + {"created", t}, + {"model", oaicompat_model}, + {"system_fingerprint", build_info}, + {"object", "text_completion"}, + {"usage", json { + {"completion_tokens", n_decoded}, + {"prompt_tokens", n_prompt_tokens}, + {"total_tokens", n_decoded + n_prompt_tokens} + }}, + {"id", oaicompat_cmpl_id} + }; + + // extra fields for debugging purposes + if (verbose) { + res["__verbose"] = to_json_non_oaicompat(); + } + if (timings.prompt_n >= 0) { + res.push_back({"timings", timings.to_json()}); + } + + return res; + } + + json to_json_oaicompat_chat() { + std::string finish_reason = "length"; + common_chat_msg msg; + if (stop == STOP_TYPE_WORD || stop == STOP_TYPE_EOS) { + SRV_DBG("Parsing chat message: %s\n", content.c_str()); + msg = common_chat_parse(content, oaicompat_chat_format); + finish_reason = msg.tool_calls.empty() ? "stop" : "tool_calls"; + } else { + msg.content = content; + } + + json message { + {"role", "assistant"}, + }; + if (!msg.reasoning_content.empty()) { + message["reasoning_content"] = msg.reasoning_content; + } + if (msg.content.empty() && !msg.tool_calls.empty()) { + message["content"] = json(); + } else { + message["content"] = msg.content; + } + if (!msg.tool_calls.empty()) { + auto tool_calls = json::array(); + for (const auto & tc : msg.tool_calls) { + tool_calls.push_back({ + {"type", "function"}, + {"function", { + {"name", tc.name}, + {"arguments", tc.arguments}, + }}, + // Some templates generate and require an id (sometimes in a very specific format, e.g. Mistral Nemo). + // We only generate a random id for the ones that don't generate one by themselves + // (they also won't get to see it as their template likely doesn't use it, so it's all for the client) + {"id", tc.id.empty() ? gen_tool_call_id() : tc.id}, + }); + } + message["tool_calls"] = tool_calls; + } + + json choice { + {"finish_reason", finish_reason}, + {"index", 0}, + {"message", message}, + }; + + if (!stream && probs_output.size() > 0) { + choice["logprobs"] = json{ + {"content", completion_token_output::probs_vector_to_json(probs_output, post_sampling_probs)}, + }; + } + + std::time_t t = std::time(0); + + json res = json { + {"choices", json::array({choice})}, + {"created", t}, + {"model", oaicompat_model}, + {"system_fingerprint", build_info}, + {"object", "chat.completion"}, + {"usage", json { + {"completion_tokens", n_decoded}, + {"prompt_tokens", n_prompt_tokens}, + {"total_tokens", n_decoded + n_prompt_tokens} + }}, + {"id", oaicompat_cmpl_id} + }; + + // extra fields for debugging purposes + if (verbose) { + res["__verbose"] = to_json_non_oaicompat(); + } + if (timings.prompt_n >= 0) { + res.push_back({"timings", timings.to_json()}); + } + + return res; + } + + json to_json_oaicompat_chat_stream() { + std::time_t t = std::time(0); + std::string finish_reason = "length"; + if (stop == STOP_TYPE_WORD || stop == STOP_TYPE_EOS) { + finish_reason = "stop"; + } + + json choice = json { + {"finish_reason", finish_reason}, + {"index", 0}, + {"delta", json::object()} + }; + + json ret = json { + {"choices", json::array({choice})}, + {"created", t}, + {"id", oaicompat_cmpl_id}, + {"model", oaicompat_model}, + {"system_fingerprint", build_info}, + {"object", "chat.completion.chunk"}, + {"usage", json { + {"completion_tokens", n_decoded}, + {"prompt_tokens", n_prompt_tokens}, + {"total_tokens", n_decoded + n_prompt_tokens}, + }}, + }; + + if (timings.prompt_n >= 0) { + ret.push_back({"timings", timings.to_json()}); + } + + // extra fields for debugging purposes + if (verbose) { + ret["__verbose"] = to_json_non_oaicompat(); + } + + return ret; + } +}; + +struct server_task_result_cmpl_partial : server_task_result { + int index = 0; + + std::string content; + llama_tokens tokens; + + int32_t n_decoded; + int32_t n_prompt_tokens; + + bool post_sampling_probs; + completion_token_output prob_output; + result_timings timings; + + // OAI-compat fields + bool verbose = false; + oaicompat_type oaicompat = OAICOMPAT_TYPE_NONE; + std::string oaicompat_model; + std::string oaicompat_cmpl_id; + + virtual int get_index() override { + return index; + } + + virtual bool is_stop() override { + return false; // in stream mode, partial responses are not considered stop + } + + virtual json to_json() override { + switch (oaicompat) { + case OAICOMPAT_TYPE_NONE: + return to_json_non_oaicompat(); + case OAICOMPAT_TYPE_COMPLETION: + return to_json_oaicompat(); + case OAICOMPAT_TYPE_CHAT: + return to_json_oaicompat_chat(); + default: + GGML_ASSERT(false && "Invalid oaicompat_type"); + } + } + + json to_json_non_oaicompat() { + // non-OAI-compat JSON + json res = json { + {"index", index}, + {"content", content}, + {"tokens", tokens}, + {"stop", false}, + {"id_slot", id_slot}, + {"tokens_predicted", n_decoded}, + {"tokens_evaluated", n_prompt_tokens}, + }; + // populate the timings object when needed (usually for the last response or with timings_per_token enabled) + if (timings.prompt_n > 0) { + res.push_back({"timings", timings.to_json()}); + } + if (!prob_output.probs.empty()) { + res["completion_probabilities"] = completion_token_output::probs_vector_to_json({prob_output}, post_sampling_probs); + } + return res; + } + + json to_json_oaicompat() { + std::time_t t = std::time(0); + json logprobs = json(nullptr); // OAI default to null + if (prob_output.probs.size() > 0) { + logprobs = json{ + {"content", completion_token_output::probs_vector_to_json({prob_output}, post_sampling_probs)}, + }; + } + json res = json { + {"choices", json::array({ + json{ + {"text", content}, + {"index", index}, + {"logprobs", logprobs}, + {"finish_reason", nullptr}, + } + })}, + {"created", t}, + {"model", oaicompat_model}, + {"system_fingerprint", build_info}, + {"object", "text_completion"}, + {"id", oaicompat_cmpl_id} + }; + + // extra fields for debugging purposes + if (verbose) { + res["__verbose"] = to_json_non_oaicompat(); + } + if (timings.prompt_n >= 0) { + res.push_back({"timings", timings.to_json()}); + } + + return res; + } + + json to_json_oaicompat_chat() { + bool first = n_decoded == 0; + std::time_t t = std::time(0); + json choices; + + if (first) { + if (content.empty()) { + choices = json::array({json{{"finish_reason", nullptr}, + {"index", 0}, + {"delta", json{{"role", "assistant"}}}}}); + } else { + // We have to send this as two updates to conform to openai behavior + json initial_ret = json{{"choices", json::array({json{ + {"finish_reason", nullptr}, + {"index", 0}, + {"delta", json{ + {"role", "assistant"} + }}}})}, + {"created", t}, + {"id", oaicompat_cmpl_id}, + {"model", oaicompat_model}, + {"object", "chat.completion.chunk"}}; + + json second_ret = json{ + {"choices", json::array({json{{"finish_reason", nullptr}, + {"index", 0}, + {"delta", json { + {"content", content}}} + }})}, + {"created", t}, + {"id", oaicompat_cmpl_id}, + {"model", oaicompat_model}, + {"object", "chat.completion.chunk"}}; + + return std::vector({initial_ret, second_ret}); + } + } else { + choices = json::array({json{ + {"finish_reason", nullptr}, + {"index", 0}, + {"delta", + json { + {"content", content}, + }}, + }}); + } + + GGML_ASSERT(choices.size() >= 1); + + if (prob_output.probs.size() > 0) { + choices[0]["logprobs"] = json{ + {"content", completion_token_output::probs_vector_to_json({prob_output}, post_sampling_probs)}, + }; + } + + json ret = json { + {"choices", choices}, + {"created", t}, + {"id", oaicompat_cmpl_id}, + {"model", oaicompat_model}, + {"system_fingerprint", build_info}, + {"object", "chat.completion.chunk"} + }; + + if (timings.prompt_n >= 0) { + ret.push_back({"timings", timings.to_json()}); + } + + return std::vector({ret}); + } +}; + +struct server_task_result_embd : server_task_result { + int index = 0; + std::vector> embedding; + + int32_t n_tokens; + + // OAI-compat fields + oaicompat_type oaicompat = OAICOMPAT_TYPE_NONE; + + virtual int get_index() override { + return index; + } + + virtual json to_json() override { + return oaicompat == OAICOMPAT_TYPE_EMBEDDING + ? to_json_oaicompat() + : to_json_non_oaicompat(); + } + + json to_json_non_oaicompat() { + return json { + {"index", index}, + {"embedding", embedding}, + }; + } + + json to_json_oaicompat() { + return json { + {"index", index}, + {"embedding", embedding[0]}, + {"tokens_evaluated", n_tokens}, + }; + } +}; + +struct server_task_result_rerank : server_task_result { + int index = 0; + float score = -1e6; + + int32_t n_tokens; + + virtual int get_index() override { + return index; + } + + virtual json to_json() override { + return json { + {"index", index}, + {"score", score}, + {"tokens_evaluated", n_tokens}, + }; + } +}; + +// this function maybe used outside of server_task_result_error +static json format_error_response(const std::string & message, const enum error_type type) { + std::string type_str; + int code = 500; + switch (type) { + case ERROR_TYPE_INVALID_REQUEST: + type_str = "invalid_request_error"; + code = 400; + break; + case ERROR_TYPE_AUTHENTICATION: + type_str = "authentication_error"; + code = 401; + break; + case ERROR_TYPE_NOT_FOUND: + type_str = "not_found_error"; + code = 404; + break; + case ERROR_TYPE_SERVER: + type_str = "server_error"; + code = 500; + break; + case ERROR_TYPE_PERMISSION: + type_str = "permission_error"; + code = 403; + break; + case ERROR_TYPE_NOT_SUPPORTED: + type_str = "not_supported_error"; + code = 501; + break; + case ERROR_TYPE_UNAVAILABLE: + type_str = "unavailable_error"; + code = 503; + break; + } + return json { + {"code", code}, + {"message", message}, + {"type", type_str}, + }; +} + +struct server_task_result_error : server_task_result { + int index = 0; + error_type err_type = ERROR_TYPE_SERVER; + std::string err_msg; + + virtual bool is_error() override { + return true; + } + + virtual json to_json() override { + return format_error_response(err_msg, err_type); + } +}; + +struct server_task_result_metrics : server_task_result { + int n_idle_slots; + int n_processing_slots; + int n_tasks_deferred; + int64_t t_start; + + int32_t kv_cache_tokens_count; + int32_t kv_cache_used_cells; + + // TODO: somehow reuse server_metrics in the future, instead of duplicating the fields + uint64_t n_prompt_tokens_processed_total = 0; + uint64_t t_prompt_processing_total = 0; + uint64_t n_tokens_predicted_total = 0; + uint64_t t_tokens_generation_total = 0; + + uint64_t n_prompt_tokens_processed = 0; + uint64_t t_prompt_processing = 0; + + uint64_t n_tokens_predicted = 0; + uint64_t t_tokens_generation = 0; + + uint64_t n_decode_total = 0; + uint64_t n_busy_slots_total = 0; + + // while we can also use std::vector this requires copying the slot object which can be quite messy + // therefore, we use json to temporarily store the slot.to_json() result + json slots_data = json::array(); + + virtual json to_json() override { + return json { + { "idle", n_idle_slots }, + { "processing", n_processing_slots }, + { "deferred", n_tasks_deferred }, + { "t_start", t_start }, + + { "n_prompt_tokens_processed_total", n_prompt_tokens_processed_total }, + { "t_tokens_generation_total", t_tokens_generation_total }, + { "n_tokens_predicted_total", n_tokens_predicted_total }, + { "t_prompt_processing_total", t_prompt_processing_total }, + + { "n_prompt_tokens_processed", n_prompt_tokens_processed }, + { "t_prompt_processing", t_prompt_processing }, + { "n_tokens_predicted", n_tokens_predicted }, + { "t_tokens_generation", t_tokens_generation }, + + { "n_decode_total", n_decode_total }, + { "n_busy_slots_total", n_busy_slots_total }, + + { "kv_cache_tokens_count", kv_cache_tokens_count }, + { "kv_cache_used_cells", kv_cache_used_cells }, + + { "slots", slots_data }, + }; + } +}; + +struct server_task_result_slot_save_load : server_task_result { + std::string filename; + bool is_save; // true = save, false = load + + size_t n_tokens; + size_t n_bytes; + double t_ms; + + virtual json to_json() override { + if (is_save) { + return json { + { "id_slot", id_slot }, + { "filename", filename }, + { "n_saved", n_tokens }, + { "n_written", n_bytes }, + { "timings", { + { "save_ms", t_ms } + }}, + }; + } else { + return json { + { "id_slot", id_slot }, + { "filename", filename }, + { "n_restored", n_tokens }, + { "n_read", n_bytes }, + { "timings", { + { "restore_ms", t_ms } + }}, + }; + } + } +}; + +struct server_task_result_slot_erase : server_task_result { + size_t n_erased; + + virtual json to_json() override { + return json { + { "id_slot", id_slot }, + { "n_erased", n_erased }, + }; + } +}; + +struct server_task_result_apply_lora : server_task_result { + virtual json to_json() override { + return json {{ "success", true }}; + } +}; + +struct server_slot { + int id; + int id_task = -1; + + // only used for completion/embedding/infill/rerank + server_task_type task_type = SERVER_TASK_TYPE_COMPLETION; + + llama_batch batch_spec = {}; + + llama_context * ctx = nullptr; + llama_context * ctx_dft = nullptr; + + common_speculative * spec = nullptr; + + std::vector lora; + + // the index relative to completion multi-task request + size_t index = 0; + + struct slot_params params; + + slot_state state = SLOT_STATE_IDLE; + + // used to determine the slot that has been used the longest + int64_t t_last_used = -1; + + // generation props + int32_t n_ctx = 0; // context size per slot + int32_t n_past = 0; + int32_t n_decoded = 0; + int32_t n_remaining = -1; + int32_t i_batch = -1; + int32_t n_predict = -1; // TODO: disambiguate from params.n_predict + + // n_prompt_tokens may not be equal to prompt_tokens.size(), because prompt maybe truncated + int32_t n_prompt_tokens = 0; + int32_t n_prompt_tokens_processed = 0; + + // input prompt tokens + llama_tokens prompt_tokens; + + size_t last_nl_pos = 0; + + std::string generated_text; + llama_tokens generated_tokens; + + llama_tokens cache_tokens; + + std::vector generated_token_probs; + + bool has_next_token = true; + bool has_new_line = false; + bool truncated = false; + stop_type stop; + + std::string stopping_word; + + // sampling + json json_schema; + + struct common_sampler * smpl = nullptr; + + llama_token sampled; + + common_chat_format chat_format = COMMON_CHAT_FORMAT_CONTENT_ONLY; + + // stats + size_t n_sent_text = 0; // number of sent text character + + int64_t t_start_process_prompt; + int64_t t_start_generation; + + double t_prompt_processing; // ms + double t_token_generation; // ms + + std::function callback_on_release; + + // Speculative decoding stats + int32_t n_draft_total = 0; // Total draft tokens generated + int32_t n_draft_accepted = 0; // Draft tokens actually accepted + + void reset() { + SLT_DBG(*this, "%s", "\n"); + + n_prompt_tokens = 0; + last_nl_pos = 0; + generated_text = ""; + has_new_line = false; + truncated = false; + stop = STOP_TYPE_NONE; + stopping_word = ""; + n_past = 0; + n_sent_text = 0; + task_type = SERVER_TASK_TYPE_COMPLETION; + + generated_tokens.clear(); + generated_token_probs.clear(); + + // clear speculative decoding stats + n_draft_total = 0; + n_draft_accepted = 0; + } + + bool is_non_causal() const { + return task_type == SERVER_TASK_TYPE_EMBEDDING || task_type == SERVER_TASK_TYPE_RERANK; + } + + bool can_batch_with(server_slot & other_slot) const { + return is_non_causal() == other_slot.is_non_causal() + && are_lora_equal(lora, other_slot.lora); + } + + bool has_budget(const common_params & global_params) { + if (params.n_predict == -1 && global_params.n_predict == -1) { + return true; // limitless + } + + n_remaining = -1; + + if (params.n_predict != -1) { + n_remaining = params.n_predict - n_decoded; + } else if (global_params.n_predict != -1) { + n_remaining = global_params.n_predict - n_decoded; + } + + return n_remaining > 0; // no budget + } + + bool is_processing() const { + return state != SLOT_STATE_IDLE; + } + + bool can_speculate() const { + return ctx_dft && params.speculative.n_max > 0 && params.cache_prompt; + } + + void add_token(const completion_token_output & token) { + if (!is_processing()) { + SLT_WRN(*this, "%s", "slot is not processing\n"); + return; + } + generated_token_probs.push_back(token); + } + + void release() { + if (is_processing()) { + SLT_INF(*this, "stop processing: n_past = %d, truncated = %d\n", n_past, truncated); + + t_last_used = ggml_time_us(); + t_token_generation = (ggml_time_us() - t_start_generation) / 1e3; + state = SLOT_STATE_IDLE; + callback_on_release(id); + } + } + + result_timings get_timings() const { + result_timings timings; + timings.prompt_n = n_prompt_tokens_processed; + timings.prompt_ms = t_prompt_processing; + timings.prompt_per_token_ms = t_prompt_processing / n_prompt_tokens_processed; + timings.prompt_per_second = 1e3 / t_prompt_processing * n_prompt_tokens_processed; + + timings.predicted_n = n_decoded; + timings.predicted_ms = t_token_generation; + timings.predicted_per_token_ms = t_token_generation / n_decoded; + timings.predicted_per_second = 1e3 / t_token_generation * n_decoded; + + // Add speculative metrics + if (n_draft_total > 0) { + timings.draft_n = n_draft_total; + timings.draft_n_accepted = n_draft_accepted; + } + + return timings; + } + + size_t find_stopping_strings(const std::string & text, const size_t last_token_size, bool is_full_stop) { + size_t stop_pos = std::string::npos; + + for (const std::string & word : params.antiprompt) { + size_t pos; + + if (is_full_stop) { + const size_t tmp = word.size() + last_token_size; + const size_t from_pos = text.size() > tmp ? text.size() - tmp : 0; + + pos = text.find(word, from_pos); + } else { + // otherwise, partial stop + pos = find_partial_stop_string(word, text); + } + + if (pos != std::string::npos && (stop_pos == std::string::npos || pos < stop_pos)) { + if (is_full_stop) { + stop = STOP_TYPE_WORD; + stopping_word = word; + has_next_token = false; + } + stop_pos = pos; + } + } + + return stop_pos; + } + + void print_timings() const { + const double t_prompt = t_prompt_processing / n_prompt_tokens_processed; + const double n_prompt_second = 1e3 / t_prompt_processing * n_prompt_tokens_processed; + + const double t_gen = t_token_generation / n_decoded; + const double n_gen_second = 1e3 / t_token_generation * n_decoded; + + SLT_INF(*this, + "\n" + "prompt eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n" + " eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n" + " total time = %10.2f ms / %5d tokens\n", + t_prompt_processing, n_prompt_tokens_processed, t_prompt, n_prompt_second, + t_token_generation, n_decoded, t_gen, n_gen_second, + t_prompt_processing + t_token_generation, n_prompt_tokens_processed + n_decoded); + + if (n_draft_total > 0) { + const float draft_ratio = (float) n_draft_accepted / n_draft_total; + SLT_INF(*this, + "\n" + "draft acceptance rate = %0.5f (%5d accepted / %5d generated)\n", + draft_ratio, n_draft_accepted, n_draft_total + ); + } + } + + json to_json() const { + return json { + {"id", id}, + {"id_task", id_task}, + {"n_ctx", n_ctx}, + {"speculative", can_speculate()}, + {"is_processing", is_processing()}, + {"non_causal", is_non_causal()}, + {"params", params.to_json()}, + {"prompt", common_detokenize(ctx, prompt_tokens)}, + {"next_token", + { + {"has_next_token", has_next_token}, + {"has_new_line", has_new_line}, + {"n_remain", n_remaining}, + {"n_decoded", n_decoded}, + {"stopping_word", stopping_word}, + } + }, + }; + } +}; + +struct server_metrics { + int64_t t_start = 0; + + uint64_t n_prompt_tokens_processed_total = 0; + uint64_t t_prompt_processing_total = 0; + uint64_t n_tokens_predicted_total = 0; + uint64_t t_tokens_generation_total = 0; + + uint64_t n_prompt_tokens_processed = 0; + uint64_t t_prompt_processing = 0; + + uint64_t n_tokens_predicted = 0; + uint64_t t_tokens_generation = 0; + + uint64_t n_decode_total = 0; + uint64_t n_busy_slots_total = 0; + + void init() { + t_start = ggml_time_us(); + } + + void on_prompt_eval(const server_slot & slot) { + n_prompt_tokens_processed_total += slot.n_prompt_tokens_processed; + n_prompt_tokens_processed += slot.n_prompt_tokens_processed; + t_prompt_processing += slot.t_prompt_processing; + t_prompt_processing_total += slot.t_prompt_processing; + } + + void on_prediction(const server_slot & slot) { + n_tokens_predicted_total += slot.n_decoded; + n_tokens_predicted += slot.n_decoded; + t_tokens_generation += slot.t_token_generation; + t_tokens_generation_total += slot.t_token_generation; + } + + void on_decoded(const std::vector & slots) { + n_decode_total++; + for (const auto & slot : slots) { + if (slot.is_processing()) { + n_busy_slots_total++; + } + } + } + + void reset_bucket() { + n_prompt_tokens_processed = 0; + t_prompt_processing = 0; + n_tokens_predicted = 0; + t_tokens_generation = 0; + } +}; + +struct server_queue { + int id = 0; + bool running; + + // queues + std::deque queue_tasks; + std::deque queue_tasks_deferred; + + std::mutex mutex_tasks; + std::condition_variable condition_tasks; + + // callback functions + std::function callback_new_task; + std::function callback_update_slots; + + // Add a new task to the end of the queue + int post(server_task && task, bool front = false) { + std::unique_lock lock(mutex_tasks); + GGML_ASSERT(task.id != -1); + // if this is cancel task make sure to clean up pending tasks + if (task.type == SERVER_TASK_TYPE_CANCEL) { + cleanup_pending_task(task.id_target); + } + const int task_id = task.id; + QUE_DBG("new task, id = %d, front = %d\n", task_id, front); + if (front) { + queue_tasks.push_front(std::move(task)); + } else { + queue_tasks.push_back(std::move(task)); + } + condition_tasks.notify_one(); + return task_id; + } + + // multi-task version of post() + int post(std::vector && tasks, bool front = false) { + std::unique_lock lock(mutex_tasks); + for (auto & task : tasks) { + if (task.id == -1) { + task.id = id++; + } + // if this is cancel task make sure to clean up pending tasks + if (task.type == SERVER_TASK_TYPE_CANCEL) { + cleanup_pending_task(task.id_target); + } + QUE_DBG("new task, id = %d/%d, front = %d\n", task.id, (int) tasks.size(), front); + if (front) { + queue_tasks.push_front(std::move(task)); + } else { + queue_tasks.push_back(std::move(task)); + } + } + condition_tasks.notify_one(); + return 0; + } + + // Add a new task, but defer until one slot is available + void defer(server_task && task) { + std::unique_lock lock(mutex_tasks); + QUE_DBG("defer task, id = %d\n", task.id); + queue_tasks_deferred.push_back(std::move(task)); + condition_tasks.notify_one(); + } + + // Get the next id for creating a new task + int get_new_id() { + std::unique_lock lock(mutex_tasks); + int new_id = id++; + return new_id; + } + + // Register function to process a new task + void on_new_task(std::function callback) { + callback_new_task = std::move(callback); + } + + // Register the function to be called when all slots data is ready to be processed + void on_update_slots(std::function callback) { + callback_update_slots = std::move(callback); + } + + // Call when the state of one slot is changed, it will move one task from deferred to main queue + void pop_deferred_task() { + std::unique_lock lock(mutex_tasks); + if (!queue_tasks_deferred.empty()) { + queue_tasks.emplace_back(std::move(queue_tasks_deferred.front())); + queue_tasks_deferred.pop_front(); + } + condition_tasks.notify_one(); + } + + // end the start_loop routine + void terminate() { + std::unique_lock lock(mutex_tasks); + running = false; + condition_tasks.notify_all(); + } + + /** + * Main loop consists of these steps: + * - Wait until a new task arrives + * - Process the task (i.e. maybe copy data into slot) + * - Check if multitask is finished + * - Update all slots + */ + void start_loop() { + running = true; + + while (true) { + QUE_DBG("%s", "processing new tasks\n"); + + while (true) { + std::unique_lock lock(mutex_tasks); + if (!running) { + QUE_DBG("%s", "terminate\n"); + return; + } + if (queue_tasks.empty()) { + lock.unlock(); + break; + } + server_task task = std::move(queue_tasks.front()); + queue_tasks.pop_front(); + lock.unlock(); + + QUE_DBG("processing task, id = %d\n", task.id); + callback_new_task(std::move(task)); + } + + // all tasks in the current loop is processed, slots data is now ready + QUE_DBG("%s", "update slots\n"); + + callback_update_slots(); + + QUE_DBG("%s", "waiting for new tasks\n"); + { + std::unique_lock lock(mutex_tasks); + if (!running) { + QUE_DBG("%s", "terminate\n"); + return; + } + if (queue_tasks.empty()) { + condition_tasks.wait(lock, [&]{ + return (!queue_tasks.empty() || !running); + }); + } + } + } + } + +private: + void cleanup_pending_task(int id_target) { + // no need lock because this is called exclusively by post() + auto rm_func = [id_target](const server_task & task) { + return task.id_target == id_target; + }; + queue_tasks.erase( + std::remove_if(queue_tasks.begin(), queue_tasks.end(), rm_func), + queue_tasks.end()); + queue_tasks_deferred.erase( + std::remove_if(queue_tasks_deferred.begin(), queue_tasks_deferred.end(), rm_func), + queue_tasks_deferred.end()); + } +}; + +struct server_response { + bool running = true; + + // for keeping track of all tasks waiting for the result + std::unordered_set waiting_task_ids; + + // the main result queue (using ptr for polymorphism) + std::vector queue_results; + + std::mutex mutex_results; + std::condition_variable condition_results; + + // add the id_task to the list of tasks waiting for response + void add_waiting_task_id(int id_task) { + SRV_DBG("add task %d to waiting list. current waiting = %d (before add)\n", id_task, (int) waiting_task_ids.size()); + + std::unique_lock lock(mutex_results); + waiting_task_ids.insert(id_task); + } + + void add_waiting_tasks(const std::vector & tasks) { + std::unique_lock lock(mutex_results); + + for (const auto & task : tasks) { + SRV_DBG("add task %d to waiting list. current waiting = %d (before add)\n", task.id, (int) waiting_task_ids.size()); + waiting_task_ids.insert(task.id); + } + } + + // when the request is finished, we can remove task associated with it + void remove_waiting_task_id(int id_task) { + SRV_DBG("remove task %d from waiting list. current waiting = %d (before remove)\n", id_task, (int) waiting_task_ids.size()); + + std::unique_lock lock(mutex_results); + waiting_task_ids.erase(id_task); + // make sure to clean up all pending results + queue_results.erase( + std::remove_if(queue_results.begin(), queue_results.end(), [id_task](const server_task_result_ptr & res) { + return res->id == id_task; + }), + queue_results.end()); + } + + void remove_waiting_task_ids(const std::unordered_set & id_tasks) { + std::unique_lock lock(mutex_results); + + for (const auto & id_task : id_tasks) { + SRV_DBG("remove task %d from waiting list. current waiting = %d (before remove)\n", id_task, (int) waiting_task_ids.size()); + waiting_task_ids.erase(id_task); + } + } + + // This function blocks the thread until there is a response for one of the id_tasks + server_task_result_ptr recv(const std::unordered_set & id_tasks) { + while (true) { + std::unique_lock lock(mutex_results); + condition_results.wait(lock, [&]{ + if (!running) { + SRV_DBG("%s : queue result stop\n", __func__); + std::terminate(); // we cannot return here since the caller is HTTP code + } + return !queue_results.empty(); + }); + + for (size_t i = 0; i < queue_results.size(); i++) { + if (id_tasks.find(queue_results[i]->id) != id_tasks.end()) { + server_task_result_ptr res = std::move(queue_results[i]); + queue_results.erase(queue_results.begin() + i); + return res; + } + } + } + + // should never reach here + } + + // same as recv(), but have timeout in seconds + // if timeout is reached, nullptr is returned + server_task_result_ptr recv_with_timeout(const std::unordered_set & id_tasks, int timeout) { + while (true) { + std::unique_lock lock(mutex_results); + + for (int i = 0; i < (int) queue_results.size(); i++) { + if (id_tasks.find(queue_results[i]->id) != id_tasks.end()) { + server_task_result_ptr res = std::move(queue_results[i]); + queue_results.erase(queue_results.begin() + i); + return res; + } + } + + std::cv_status cr_res = condition_results.wait_for(lock, std::chrono::seconds(timeout)); + if (!running) { + SRV_DBG("%s : queue result stop\n", __func__); + std::terminate(); // we cannot return here since the caller is HTTP code + } + if (cr_res == std::cv_status::timeout) { + return nullptr; + } + } + + // should never reach here + } + + // single-task version of recv() + server_task_result_ptr recv(int id_task) { + std::unordered_set id_tasks = {id_task}; + return recv(id_tasks); + } + + // Send a new result to a waiting id_task + void send(server_task_result_ptr && result) { + SRV_DBG("sending result for task id = %d\n", result->id); + + std::unique_lock lock(mutex_results); + for (const auto & id_task : waiting_task_ids) { + if (result->id == id_task) { + SRV_DBG("task id = %d pushed to result queue\n", result->id); + + queue_results.emplace_back(std::move(result)); + condition_results.notify_all(); + return; + } + } + } + + // terminate the waiting loop + void terminate() { + running = false; + condition_results.notify_all(); + } +}; + +struct server_context { + common_params params_base; + + // note: keep these alive - they determine the lifetime of the model, context, etc. + common_init_result llama_init; + common_init_result llama_init_dft; + + llama_model * model = nullptr; + llama_context * ctx = nullptr; + + const llama_vocab * vocab = nullptr; + + llama_model * model_dft = nullptr; + + llama_context_params cparams_dft; + + llama_batch batch = {}; + + bool clean_kv_cache = true; + bool add_bos_token = true; + bool has_eos_token = false; + + int32_t n_ctx; // total context for all clients / slots + + // slots / clients + std::vector slots; + json default_generation_settings_for_props; + + server_queue queue_tasks; + server_response queue_results; + + server_metrics metrics; + + // Necessary similarity of prompt for slot selection + float slot_prompt_similarity = 0.0f; + + common_chat_templates_ptr chat_templates; + + ~server_context() { + // Clear any sampling context + for (server_slot & slot : slots) { + common_sampler_free(slot.smpl); + slot.smpl = nullptr; + + llama_free(slot.ctx_dft); + slot.ctx_dft = nullptr; + + common_speculative_free(slot.spec); + slot.spec = nullptr; + + llama_batch_free(slot.batch_spec); + } + + llama_batch_free(batch); + } + + bool load_model(const common_params & params) { + SRV_INF("loading model '%s'\n", params.model.path.c_str()); + + params_base = params; + + llama_init = common_init_from_params(params_base); + + model = llama_init.model.get(); + ctx = llama_init.context.get(); + + if (model == nullptr) { + SRV_ERR("failed to load model, '%s'\n", params_base.model.path.c_str()); + return false; + } + + vocab = llama_model_get_vocab(model); + + n_ctx = llama_n_ctx(ctx); + + add_bos_token = llama_vocab_get_add_bos(vocab); + has_eos_token = llama_vocab_eos(vocab) != LLAMA_TOKEN_NULL; + + if (!params_base.speculative.model.path.empty() || !params_base.speculative.model.hf_repo.empty()) { + SRV_INF("loading draft model '%s'\n", params_base.speculative.model.path.c_str()); + + auto params_dft = params_base; + + params_dft.devices = params_base.speculative.devices; + params_dft.model = params_base.speculative.model; + params_dft.n_ctx = params_base.speculative.n_ctx == 0 ? params_base.n_ctx / params_base.n_parallel : params_base.speculative.n_ctx; + params_dft.n_gpu_layers = params_base.speculative.n_gpu_layers; + params_dft.n_parallel = 1; + + // force F16 KV cache for the draft model for extra performance + params_dft.cache_type_k = GGML_TYPE_F16; + params_dft.cache_type_v = GGML_TYPE_F16; + + llama_init_dft = common_init_from_params(params_dft); + + model_dft = llama_init_dft.model.get(); + + if (model_dft == nullptr) { + SRV_ERR("failed to load draft model, '%s'\n", params_base.speculative.model.path.c_str()); + return false; + } + + if (!common_speculative_are_compatible(ctx, llama_init_dft.context.get())) { + SRV_ERR("the draft model '%s' is not compatible with the target model '%s'\n", params_base.speculative.model.path.c_str(), params_base.model.path.c_str()); + + return false; + } + + const int n_ctx_dft = llama_n_ctx(llama_init_dft.context.get()); + + cparams_dft = common_context_params_to_llama(params_dft); + cparams_dft.n_batch = n_ctx_dft; + + // the context is not needed - we will create one for each slot + llama_init_dft.context.reset(); + } + + chat_templates = common_chat_templates_init(model, params_base.chat_template); + try { + common_chat_format_example(chat_templates.get(), params.use_jinja); + } catch (const std::exception & e) { + SRV_WRN("%s: Chat template parsing error: %s\n", __func__, e.what()); + SRV_WRN("%s: The chat template that comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses\n", __func__); + chat_templates = common_chat_templates_init(model, "chatml"); + } + + return true; + } + + void init() { + const int32_t n_ctx_slot = n_ctx / params_base.n_parallel; + + SRV_INF("initializing slots, n_slots = %d\n", params_base.n_parallel); + + for (int i = 0; i < params_base.n_parallel; i++) { + server_slot slot; + + slot.id = i; + slot.ctx = ctx; + slot.n_ctx = n_ctx_slot; + slot.n_predict = params_base.n_predict; + + if (model_dft) { + slot.batch_spec = llama_batch_init(params_base.speculative.n_max + 1, 0, 1); + + slot.ctx_dft = llama_init_from_model(model_dft, cparams_dft); + if (slot.ctx_dft == nullptr) { + SRV_ERR("%s", "failed to create draft context\n"); + return; + } + + slot.spec = common_speculative_init(slot.ctx_dft); + if (slot.spec == nullptr) { + SRV_ERR("%s", "failed to create speculator\n"); + return; + } + } + + SLT_INF(slot, "new slot n_ctx_slot = %d\n", slot.n_ctx); + + slot.params.sampling = params_base.sampling; + + slot.callback_on_release = [this](int) { + queue_tasks.pop_deferred_task(); + }; + + slot.reset(); + + slots.push_back(std::move(slot)); + } + + default_generation_settings_for_props = slots[0].to_json(); + + // the update_slots() logic will always submit a maximum of n_batch or n_parallel tokens + // note that n_batch can be > n_ctx (e.g. for non-causal attention models such as BERT where the KV cache is not used) + { + const int32_t n_batch = llama_n_batch(ctx); + + // only a single seq_id per token is needed + batch = llama_batch_init(std::max(n_batch, params_base.n_parallel), 0, 1); + } + + metrics.init(); + } + + server_slot * get_slot_by_id(int id) { + for (server_slot & slot : slots) { + if (slot.id == id) { + return &slot; + } + } + + return nullptr; + } + + server_slot * get_available_slot(const server_task & task) { + server_slot * ret = nullptr; + + // find the slot that has at least n% prompt similarity + if (ret == nullptr && slot_prompt_similarity != 0.0f) { + int lcs_len = 0; + float similarity = 0; + + for (server_slot & slot : slots) { + // skip the slot if it is not available + if (slot.is_processing()) { + continue; + } + + // skip the slot if it does not contains cached tokens + if (slot.cache_tokens.empty()) { + continue; + } + + // length of the Longest Common Subsequence between the current slot's prompt and the input prompt + int cur_lcs_len = common_lcs(slot.cache_tokens, task.prompt_tokens); + + // fraction of the common subsequence length compared to the current slot's prompt length + float cur_similarity = static_cast(cur_lcs_len) / static_cast(slot.cache_tokens.size()); + + // select the current slot if the criteria match + if (cur_lcs_len > lcs_len && cur_similarity > slot_prompt_similarity) { + lcs_len = cur_lcs_len; + similarity = cur_similarity; + ret = &slot; + } + } + + if (ret != nullptr) { + SLT_DBG(*ret, "selected slot by lcs similarity, lcs_len = %d, similarity = %f\n", lcs_len, similarity); + } + } + + // find the slot that has been least recently used + if (ret == nullptr) { + int64_t t_last = ggml_time_us(); + for (server_slot & slot : slots) { + // skip the slot if it is not available + if (slot.is_processing()) { + continue; + } + + // select the current slot if the criteria match + if (slot.t_last_used < t_last) { + t_last = slot.t_last_used; + ret = &slot; + } + } + + if (ret != nullptr) { + SLT_DBG(*ret, "selected slot by lru, t_last = %" PRId64 "\n", t_last); + } + } + + return ret; + } + + bool can_be_detokenized(const struct llama_context * ctx, const std::vector & tokens) { + const llama_model * model = llama_get_model(ctx); + const llama_vocab * vocab = llama_model_get_vocab(model); + const int32_t n_vocab = llama_vocab_n_tokens(vocab); + for (const auto & token : tokens) { + if (token < 0 || token >= n_vocab) { + return false; + } + } + return true; + } + + bool launch_slot_with_task(server_slot & slot, server_task && task) { + slot.reset(); + slot.id_task = task.id; + slot.index = task.index; + slot.task_type = task.type; + slot.params = std::move(task.params); + slot.prompt_tokens = std::move(task.prompt_tokens); + + if (!are_lora_equal(slot.params.lora, slot.lora)) { + // if lora is changed, we cannot reuse cached tokens + slot.cache_tokens.clear(); + slot.lora = slot.params.lora; + } + + bool can_detokenize = can_be_detokenized(ctx, slot.prompt_tokens); + if (!can_detokenize) { + send_error(task, "Prompt contains invalid tokens", ERROR_TYPE_INVALID_REQUEST); + return false; + } + SLT_DBG(slot, "launching slot : %s\n", safe_json_to_str(slot.to_json()).c_str()); + + if (slot.n_predict > 0 && slot.params.n_predict > slot.n_predict) { + // Might be better to reject the request with a 400 ? + SLT_WRN(slot, "n_predict = %d exceeds server configuration, setting to %d\n", slot.params.n_predict, slot.n_predict); + slot.params.n_predict = slot.n_predict; + } + + if (slot.params.ignore_eos && has_eos_token) { + slot.params.sampling.logit_bias.push_back({llama_vocab_eos(vocab), -INFINITY}); + } + + { + if (slot.smpl != nullptr) { + common_sampler_free(slot.smpl); + } + + slot.smpl = common_sampler_init(model, slot.params.sampling); + if (slot.smpl == nullptr) { + // for now, the only error that may happen here is invalid grammar + send_error(task, "Failed to parse grammar", ERROR_TYPE_INVALID_REQUEST); + return false; + } + } + + if (slot.ctx_dft) { + llama_batch_free(slot.batch_spec); + + slot.batch_spec = llama_batch_init(slot.params.speculative.n_max + 1, 0, 1); + } + + slot.state = SLOT_STATE_STARTED; + + SLT_INF(slot, "%s", "processing task\n"); + + return true; + } + + void kv_cache_clear() { + SRV_DBG("%s", "clearing KV cache\n"); + + // clear the entire KV cache + llama_kv_self_clear(ctx); + clean_kv_cache = false; + } + + bool process_token(completion_token_output & result, server_slot & slot) { + // remember which tokens were sampled - used for repetition penalties during sampling + const std::string token_str = result.text_to_send; + slot.sampled = result.tok; + + slot.generated_text += token_str; + if (slot.params.return_tokens) { + slot.generated_tokens.push_back(result.tok); + } + slot.has_next_token = true; + + // check if there is incomplete UTF-8 character at the end + bool incomplete = validate_utf8(slot.generated_text) < slot.generated_text.size(); + + // search stop word and delete it + if (!incomplete) { + size_t pos = std::min(slot.n_sent_text, slot.generated_text.size()); + + const std::string str_test = slot.generated_text.substr(pos); + bool send_text = true; + + size_t stop_pos = slot.find_stopping_strings(str_test, token_str.size(), true); + if (stop_pos != std::string::npos) { + slot.generated_text.erase( + slot.generated_text.begin() + pos + stop_pos, + slot.generated_text.end()); + pos = std::min(slot.n_sent_text, slot.generated_text.size()); + } else if (slot.has_next_token) { + stop_pos = slot.find_stopping_strings(str_test, token_str.size(), false); + send_text = stop_pos == std::string::npos; + } + + // check if there is any token to predict + if (send_text) { + // no send the stop word in the response + result.text_to_send = slot.generated_text.substr(pos, std::string::npos); + slot.n_sent_text += result.text_to_send.size(); + // add the token to slot queue and cache + } else { + result.text_to_send = ""; + } + + slot.add_token(result); + if (slot.params.stream) { + send_partial_response(slot, result); + } + } + + if (incomplete) { + slot.has_next_token = true; + } + + // check the limits + if (slot.n_decoded > 0 && slot.has_next_token && !slot.has_budget(params_base)) { + slot.stop = STOP_TYPE_LIMIT; + slot.has_next_token = false; + + SLT_DBG(slot, "stopped by limit, n_decoded = %d, n_predict = %d\n", slot.n_decoded, slot.params.n_predict); + } + + if (slot.has_new_line) { + // require that each new line has a whitespace prefix (i.e. indentation) of at least slot.params.n_indent + if (slot.params.n_indent > 0) { + // check the current indentation + // TODO: improve by not doing it more than once for each new line + if (slot.last_nl_pos > 0) { + size_t pos = slot.last_nl_pos; + + int n_indent = 0; + while (pos < slot.generated_text.size() && (slot.generated_text[pos] == ' ' || slot.generated_text[pos] == '\t')) { + n_indent++; + pos++; + } + + if (pos < slot.generated_text.size() && n_indent < slot.params.n_indent) { + slot.stop = STOP_TYPE_LIMIT; + slot.has_next_token = false; + + // cut the last line + slot.generated_text.erase(pos, std::string::npos); + + SLT_DBG(slot, "stopped by indentation limit, n_decoded = %d, n_indent = %d\n", slot.n_decoded, n_indent); + } + } + + // find the next new line + { + const size_t pos = slot.generated_text.find('\n', slot.last_nl_pos); + + if (pos != std::string::npos) { + slot.last_nl_pos = pos + 1; + } + } + } + } + + // check if there is a new line in the generated text + if (result.text_to_send.find('\n') != std::string::npos) { + slot.has_new_line = true; + + // if we have seen a new line, we stop after a certain time limit, but only upon another new line + if (slot.params.t_max_predict_ms > 0 && (ggml_time_us() - slot.t_start_generation > 1000.0f*slot.params.t_max_predict_ms)) { + slot.stop = STOP_TYPE_LIMIT; + slot.has_next_token = false; + + SLT_DBG(slot, "stopped by time limit, n_decoded = %d, t_max_predict_ms = %d ms\n", slot.n_decoded, (int) slot.params.t_max_predict_ms); + } + } + + // if context shift is disabled, we stop when it reaches the context limit + if (slot.n_past >= slot.n_ctx) { + slot.truncated = true; + slot.stop = STOP_TYPE_LIMIT; + slot.has_next_token = false; + + SLT_DBG(slot, "stopped due to running out of context capacity, n_past = %d, n_prompt_tokens = %d, n_decoded = %d, n_ctx = %d\n", + slot.n_decoded, slot.n_prompt_tokens, slot.n_past, slot.n_ctx); + } + + if (llama_vocab_is_eog(vocab, result.tok)) { + slot.stop = STOP_TYPE_EOS; + slot.has_next_token = false; + + SLT_DBG(slot, "%s", "stopped by EOS\n"); + } + + const auto n_ctx_train = llama_model_n_ctx_train(model); + + if (slot.params.n_predict < 1 && slot.n_predict < 1 && slot.n_prompt_tokens + slot.n_decoded >= n_ctx_train) { + slot.truncated = true; + slot.stop = STOP_TYPE_LIMIT; + slot.has_next_token = false; // stop prediction + + SLT_WRN(slot, + "n_predict (%d) is set for infinite generation. " + "Limiting generated tokens to n_ctx_train (%d) to avoid EOS-less generation infinite loop\n", + slot.params.n_predict, n_ctx_train); + } + + SLT_DBG(slot, "n_decoded = %d, n_remaining = %d, next token: %5d '%s'\n", slot.n_decoded, slot.n_remaining, result.tok, token_str.c_str()); + + return slot.has_next_token; // continue + } + + void populate_token_probs(const server_slot & slot, completion_token_output & result, bool post_sampling, bool special, int idx) { + size_t n_probs = slot.params.sampling.n_probs; + size_t n_vocab = llama_vocab_n_tokens(vocab); + if (post_sampling) { + const auto * cur_p = common_sampler_get_candidates(slot.smpl); + const size_t max_probs = cur_p->size; + + // set probability for sampled token + for (size_t i = 0; i < max_probs; i++) { + if (cur_p->data[i].id == result.tok) { + result.prob = cur_p->data[i].p; + break; + } + } + + // set probability for top n_probs tokens + result.probs.reserve(max_probs); + for (size_t i = 0; i < std::min(max_probs, n_probs); i++) { + result.probs.push_back({ + cur_p->data[i].id, + common_token_to_piece(ctx, cur_p->data[i].id, special), + cur_p->data[i].p + }); + } + } else { + // TODO: optimize this with min-p optimization + std::vector cur = get_token_probabilities(ctx, idx); + + // set probability for sampled token + for (size_t i = 0; i < n_vocab; i++) { + // set probability for sampled token + if (cur[i].id == result.tok) { + result.prob = cur[i].p; + break; + } + } + + // set probability for top n_probs tokens + result.probs.reserve(n_probs); + for (size_t i = 0; i < std::min(n_vocab, n_probs); i++) { + result.probs.push_back({ + cur[i].id, + common_token_to_piece(ctx, cur[i].id, special), + cur[i].p + }); + } + } + } + + void send_error(const server_task & task, const std::string & error, const enum error_type type = ERROR_TYPE_SERVER) { + send_error(task.id, error, type); + } + + void send_error(const server_slot & slot, const std::string & error, const enum error_type type = ERROR_TYPE_SERVER) { + send_error(slot.id_task, error, type); + } + + void send_error(const int id_task, const std::string & error, const enum error_type type = ERROR_TYPE_SERVER) { + SRV_ERR("task id = %d, error: %s\n", id_task, error.c_str()); + + auto res = std::make_unique(); + res->id = id_task; + res->err_type = type; + res->err_msg = error; + + queue_results.send(std::move(res)); + } + + void send_partial_response(server_slot & slot, const completion_token_output & tkn) { + auto res = std::make_unique(); + + res->id = slot.id_task; + res->index = slot.index; + res->content = tkn.text_to_send; + res->tokens = { tkn.tok }; + + res->n_decoded = slot.n_decoded; + res->n_prompt_tokens = slot.n_prompt_tokens; + res->post_sampling_probs = slot.params.post_sampling_probs; + + res->verbose = slot.params.verbose; + res->oaicompat = slot.params.oaicompat; + res->oaicompat_model = slot.params.oaicompat_model; + res->oaicompat_cmpl_id = slot.params.oaicompat_cmpl_id; + + // populate res.probs_output + if (slot.params.sampling.n_probs > 0) { + res->prob_output = tkn; // copy the token probs + } + + // populate timings if this is final response or timings_per_token is enabled + if (slot.stop != STOP_TYPE_NONE || slot.params.timings_per_token) { + res->timings = slot.get_timings(); + } + + queue_results.send(std::move(res)); + } + + void send_final_response(server_slot & slot) { + auto res = std::make_unique(); + res->id = slot.id_task; + res->id_slot = slot.id; + + res->index = slot.index; + res->content = std::move(slot.generated_text); + res->tokens = std::move(slot.generated_tokens); + res->timings = slot.get_timings(); + res->prompt = common_detokenize(ctx, slot.prompt_tokens, true); + res->response_fields = std::move(slot.params.response_fields); + + res->truncated = slot.truncated; + res->n_decoded = slot.n_decoded; + res->n_prompt_tokens = slot.n_prompt_tokens; + res->n_tokens_cached = slot.n_past; + res->has_new_line = slot.has_new_line; + res->stopping_word = slot.stopping_word; + res->stop = slot.stop; + res->post_sampling_probs = slot.params.post_sampling_probs; + + res->verbose = slot.params.verbose; + res->stream = slot.params.stream; + res->oaicompat = slot.params.oaicompat; + res->oaicompat_model = slot.params.oaicompat_model; + res->oaicompat_cmpl_id = slot.params.oaicompat_cmpl_id; + res->oaicompat_chat_format = slot.params.oaicompat_chat_format; + // populate res.probs_output + if (slot.params.sampling.n_probs > 0) { + if (!slot.params.stream && slot.stop == STOP_TYPE_WORD) { + const llama_tokens stop_word_toks = common_tokenize(ctx, slot.stopping_word, false); + + size_t safe_offset = std::min(slot.generated_token_probs.size(), stop_word_toks.size()); + res->probs_output = std::vector( + slot.generated_token_probs.begin(), + slot.generated_token_probs.end() - safe_offset); + } else { + res->probs_output = std::vector( + slot.generated_token_probs.begin(), + slot.generated_token_probs.end()); + } + } + + res->generation_params = slot.params; // copy the parameters + + queue_results.send(std::move(res)); + } + + void send_embedding(const server_slot & slot, const llama_batch & batch) { + auto res = std::make_unique(); + res->id = slot.id_task; + res->index = slot.index; + res->n_tokens = slot.n_prompt_tokens; + res->oaicompat = slot.params.oaicompat; + + const int n_embd = llama_model_n_embd(model); + + std::vector embd_res(n_embd, 0.0f); + + for (int i = 0; i < batch.n_tokens; ++i) { + if (!batch.logits[i] || batch.seq_id[i][0] != slot.id) { + continue; + } + + const float * embd = llama_get_embeddings_seq(ctx, batch.seq_id[i][0]); + if (embd == NULL) { + embd = llama_get_embeddings_ith(ctx, i); + } + + if (embd == NULL) { + SLT_ERR(slot, "failed to get embeddings, token = %d, seq_id = %d\n", batch.token[i], batch.seq_id[i][0]); + + res->embedding.push_back(std::vector(n_embd, 0.0f)); + continue; + } + + // normalize only when there is pooling + // TODO: configurable + if (llama_pooling_type(slot.ctx) != LLAMA_POOLING_TYPE_NONE) { + common_embd_normalize(embd, embd_res.data(), n_embd, 2); + res->embedding.push_back(embd_res); + } else { + res->embedding.push_back({ embd, embd + n_embd }); + } + } + + SLT_DBG(slot, "%s", "sending embeddings\n"); + + queue_results.send(std::move(res)); + } + + void send_rerank(const server_slot & slot, const llama_batch & batch) { + auto res = std::make_unique(); + res->id = slot.id_task; + res->index = slot.index; + res->n_tokens = slot.n_prompt_tokens; + + for (int i = 0; i < batch.n_tokens; ++i) { + if (!batch.logits[i] || batch.seq_id[i][0] != slot.id) { + continue; + } + + const float * embd = llama_get_embeddings_seq(ctx, batch.seq_id[i][0]); + if (embd == NULL) { + embd = llama_get_embeddings_ith(ctx, i); + } + + if (embd == NULL) { + SLT_ERR(slot, "failed to get embeddings, token = %d, seq_id = %d\n", batch.token[i], batch.seq_id[i][0]); + + res->score = -1e6; + continue; + } + + res->score = embd[0]; + } + + SLT_DBG(slot, "sending rerank result, res.score = %f\n", res->score); + + queue_results.send(std::move(res)); + } + + // + // Functions to create new task(s) and receive result(s) + // + + void cancel_tasks(const std::unordered_set & id_tasks) { + std::vector cancel_tasks; + cancel_tasks.reserve(id_tasks.size()); + for (const auto & id_task : id_tasks) { + SRV_WRN("cancel task, id_task = %d\n", id_task); + + server_task task(SERVER_TASK_TYPE_CANCEL); + task.id_target = id_task; + queue_results.remove_waiting_task_id(id_task); + cancel_tasks.push_back(std::move(task)); + } + // push to beginning of the queue, so it has highest priority + queue_tasks.post(std::move(cancel_tasks), true); + } + + // receive the results from task(s) + void receive_multi_results( + const std::unordered_set & id_tasks, + const std::function&)> & result_handler, + const std::function & error_handler, + const std::function & is_connection_closed) { + std::vector results(id_tasks.size()); + for (int i = 0; i < (int)id_tasks.size(); i++) { + server_task_result_ptr result = queue_results.recv_with_timeout(id_tasks, HTTP_POLLING_SECONDS); + + if (is_connection_closed()) { + cancel_tasks(id_tasks); + return; + } + + if (result == nullptr) { + i--; // retry + continue; + } + + if (result->is_error()) { + error_handler(result->to_json()); + cancel_tasks(id_tasks); + return; + } + + GGML_ASSERT( + dynamic_cast(result.get()) != nullptr + || dynamic_cast(result.get()) != nullptr + || dynamic_cast(result.get()) != nullptr + ); + const size_t idx = result->get_index(); + GGML_ASSERT(idx < results.size() && "index out of range"); + results[idx] = std::move(result); + } + result_handler(results); + } + + // receive the results from task(s), in stream mode + void receive_cmpl_results_stream( + const std::unordered_set & id_tasks, + const std::function & result_handler, + const std::function & error_handler, + const std::function & is_connection_closed) { + size_t n_finished = 0; + while (true) { + server_task_result_ptr result = queue_results.recv_with_timeout(id_tasks, HTTP_POLLING_SECONDS); + + if (is_connection_closed()) { + cancel_tasks(id_tasks); + return; + } + + if (result == nullptr) { + continue; // retry + } + + if (result->is_error()) { + error_handler(result->to_json()); + cancel_tasks(id_tasks); + return; + } + + GGML_ASSERT( + dynamic_cast(result.get()) != nullptr + || dynamic_cast(result.get()) != nullptr + ); + if (!result_handler(result)) { + cancel_tasks(id_tasks); + break; + } + + if (result->is_stop()) { + if (++n_finished == id_tasks.size()) { + break; + } + } + } + } + + // + // Functions to process the task + // + + void process_single_task(server_task && task) { + switch (task.type) { + case SERVER_TASK_TYPE_COMPLETION: + case SERVER_TASK_TYPE_INFILL: + case SERVER_TASK_TYPE_EMBEDDING: + case SERVER_TASK_TYPE_RERANK: + { + const int id_slot = task.id_selected_slot; + + server_slot * slot = id_slot != -1 ? get_slot_by_id(id_slot) : get_available_slot(task); + + if (slot == nullptr) { + // if no slot is available, we defer this task for processing later + SRV_DBG("no slot is available, defer task, id_task = %d\n", task.id); + queue_tasks.defer(std::move(task)); + break; + } + if (slot->is_processing()) { + // if requested slot is unavailable, we defer this task for processing later + SRV_DBG("requested slot is unavailable, defer task, id_task = %d\n", task.id); + queue_tasks.defer(std::move(task)); + break; + } + + if (!launch_slot_with_task(*slot, std::move(task))) { + SRV_ERR("failed to launch slot with task, id_task = %d\n", task.id); + break; + } + } break; + case SERVER_TASK_TYPE_CANCEL: + { + // release slot linked with the task id + for (auto & slot : slots) { + if (slot.id_task == task.id_target) { + slot.release(); + break; + } + } + } break; + case SERVER_TASK_TYPE_NEXT_RESPONSE: + { + // do nothing + } break; + case SERVER_TASK_TYPE_METRICS: + { + json slots_data = json::array(); + + int n_idle_slots = 0; + int n_processing_slots = 0; + + for (server_slot & slot : slots) { + json slot_data = slot.to_json(); + + if (slot.is_processing()) { + n_processing_slots++; + } else { + n_idle_slots++; + } + + slots_data.push_back(slot_data); + } + SRV_DBG("n_idle_slots = %d, n_processing_slots = %d\n", n_idle_slots, n_processing_slots); + + auto res = std::make_unique(); + res->id = task.id; + res->slots_data = std::move(slots_data); + res->n_idle_slots = n_idle_slots; + res->n_processing_slots = n_processing_slots; + res->n_tasks_deferred = queue_tasks.queue_tasks_deferred.size(); + res->t_start = metrics.t_start; + + res->kv_cache_tokens_count = llama_kv_self_n_tokens(ctx); + res->kv_cache_used_cells = llama_kv_self_used_cells(ctx); + + res->n_prompt_tokens_processed_total = metrics.n_prompt_tokens_processed_total; + res->t_prompt_processing_total = metrics.t_prompt_processing_total; + res->n_tokens_predicted_total = metrics.n_tokens_predicted_total; + res->t_tokens_generation_total = metrics.t_tokens_generation_total; + + res->n_prompt_tokens_processed = metrics.n_prompt_tokens_processed; + res->t_prompt_processing = metrics.t_prompt_processing; + res->n_tokens_predicted = metrics.n_tokens_predicted; + res->t_tokens_generation = metrics.t_tokens_generation; + + res->n_decode_total = metrics.n_decode_total; + res->n_busy_slots_total = metrics.n_busy_slots_total; + + if (task.metrics_reset_bucket) { + metrics.reset_bucket(); + } + queue_results.send(std::move(res)); + } break; + case SERVER_TASK_TYPE_SLOT_SAVE: + { + int id_slot = task.slot_action.slot_id; + server_slot * slot = get_slot_by_id(id_slot); + if (slot == nullptr) { + send_error(task, "Invalid slot ID", ERROR_TYPE_INVALID_REQUEST); + break; + } + if (slot->is_processing()) { + // if requested slot is unavailable, we defer this task for processing later + SRV_DBG("requested slot is unavailable, defer task, id_task = %d\n", task.id); + queue_tasks.defer(std::move(task)); + break; + } + + const size_t token_count = slot->cache_tokens.size(); + const int64_t t_start = ggml_time_us(); + + std::string filename = task.slot_action.filename; + std::string filepath = task.slot_action.filepath; + + const size_t nwrite = llama_state_seq_save_file(ctx, filepath.c_str(), slot->id, slot->cache_tokens.data(), token_count); + + const int64_t t_end = ggml_time_us(); + const double t_save_ms = (t_end - t_start) / 1000.0; + + auto res = std::make_unique(); + res->id = task.id; + res->id_slot = id_slot; + res->filename = filename; + res->is_save = true; + res->n_tokens = token_count; + res->n_bytes = nwrite; + res->t_ms = t_save_ms; + queue_results.send(std::move(res)); + } break; + case SERVER_TASK_TYPE_SLOT_RESTORE: + { + int id_slot = task.slot_action.slot_id; + server_slot * slot = get_slot_by_id(id_slot); + if (slot == nullptr) { + send_error(task, "Invalid slot ID", ERROR_TYPE_INVALID_REQUEST); + break; + } + if (slot->is_processing()) { + // if requested slot is unavailable, we defer this task for processing later + SRV_DBG("requested slot is unavailable, defer task, id_task = %d\n", task.id); + queue_tasks.defer(std::move(task)); + break; + } + + const int64_t t_start = ggml_time_us(); + + std::string filename = task.slot_action.filename; + std::string filepath = task.slot_action.filepath; + + slot->cache_tokens.resize(slot->n_ctx); + size_t token_count = 0; + size_t nread = llama_state_seq_load_file(ctx, filepath.c_str(), slot->id, slot->cache_tokens.data(), slot->cache_tokens.size(), &token_count); + if (nread == 0) { + slot->cache_tokens.resize(0); + send_error(task, "Unable to restore slot, no available space in KV cache or invalid slot save file", ERROR_TYPE_INVALID_REQUEST); + break; + } + slot->cache_tokens.resize(token_count); + + const int64_t t_end = ggml_time_us(); + const double t_restore_ms = (t_end - t_start) / 1000.0; + + auto res = std::make_unique(); + res->id = task.id; + res->id_slot = id_slot; + res->filename = filename; + res->is_save = false; + res->n_tokens = token_count; + res->n_bytes = nread; + res->t_ms = t_restore_ms; + queue_results.send(std::move(res)); + } break; + case SERVER_TASK_TYPE_SLOT_ERASE: + { + int id_slot = task.slot_action.slot_id; + server_slot * slot = get_slot_by_id(id_slot); + if (slot == nullptr) { + send_error(task, "Invalid slot ID", ERROR_TYPE_INVALID_REQUEST); + break; + } + if (slot->is_processing()) { + // if requested slot is unavailable, we defer this task for processing later + SRV_DBG("requested slot is unavailable, defer task, id_task = %d\n", task.id); + queue_tasks.defer(std::move(task)); + break; + } + + // Erase token cache + const size_t n_erased = slot->cache_tokens.size(); + llama_kv_self_seq_rm(ctx, slot->id, -1, -1); + slot->cache_tokens.clear(); + + auto res = std::make_unique(); + res->id = task.id; + res->id_slot = id_slot; + res->n_erased = n_erased; + queue_results.send(std::move(res)); + } break; + case SERVER_TASK_TYPE_SET_LORA: + { + params_base.lora_adapters = std::move(task.set_lora); + auto res = std::make_unique(); + res->id = task.id; + queue_results.send(std::move(res)); + } break; + } + } + + void update_slots() { + // check if all slots are idle + { + bool all_idle = true; + + for (auto & slot : slots) { + if (slot.is_processing()) { + all_idle = false; + break; + } + } + + if (all_idle) { + SRV_INF("%s", "all slots are idle\n"); + if (clean_kv_cache) { + kv_cache_clear(); + } + + return; + } + } + + { + SRV_DBG("%s", "posting NEXT_RESPONSE\n"); + + server_task task(SERVER_TASK_TYPE_NEXT_RESPONSE); + task.id = queue_tasks.get_new_id(); + queue_tasks.post(std::move(task)); + } + + // apply context-shift if needed + // TODO: simplify and improve + for (server_slot & slot : slots) { + if (slot.is_processing() && slot.n_past + 1 >= slot.n_ctx) { + if (!params_base.ctx_shift) { + // this check is redundant (for good) + // we should never get here, because generation should already stopped in process_token() + slot.release(); + send_error(slot, "context shift is disabled", ERROR_TYPE_SERVER); + continue; + } + + // Shift context + const int n_keep = slot.params.n_keep + add_bos_token; + const int n_left = slot.n_past - n_keep; + const int n_discard = slot.params.n_discard ? slot.params.n_discard : (n_left / 2); + + SLT_WRN(slot, "slot context shift, n_keep = %d, n_left = %d, n_discard = %d\n", n_keep, n_left, n_discard); + + llama_kv_self_seq_rm (ctx, slot.id, n_keep , n_keep + n_discard); + llama_kv_self_seq_add(ctx, slot.id, n_keep + n_discard, slot.n_past, -n_discard); + + if (slot.params.cache_prompt) { + for (size_t i = n_keep + n_discard; i < slot.cache_tokens.size(); i++) { + slot.cache_tokens[i - n_discard] = slot.cache_tokens[i]; + } + + slot.cache_tokens.resize(slot.cache_tokens.size() - n_discard); + } + + slot.n_past -= n_discard; + + slot.truncated = true; + } + } + + // start populating the batch for this iteration + common_batch_clear(batch); + + // track if given slot can be batched with slots already in the batch + server_slot * slot_batched = nullptr; + + auto accept_special_token = [&](server_slot & slot, llama_token token) { + return params_base.special || slot.params.sampling.preserved_tokens.find(token) != slot.params.sampling.preserved_tokens.end(); + }; + + // frist, add sampled tokens from any ongoing sequences + for (auto & slot : slots) { + if (slot.state != SLOT_STATE_GENERATING) { + continue; + } + + // check if we can batch this slot with the previous one + if (!slot_batched) { + slot_batched = &slot; + } else if (!slot_batched->can_batch_with(slot)) { + continue; + } + + slot.i_batch = batch.n_tokens; + + common_batch_add(batch, slot.sampled, slot.n_past, { slot.id }, true); + + slot.n_past += 1; + + if (slot.params.cache_prompt) { + slot.cache_tokens.push_back(slot.sampled); + } + + SLT_DBG(slot, "slot decode token, n_ctx = %d, n_past = %d, n_cache_tokens = %d, truncated = %d\n", + slot.n_ctx, slot.n_past, (int) slot.cache_tokens.size(), slot.truncated); + } + + // process in chunks of params.n_batch + int32_t n_batch = llama_n_batch(ctx); + int32_t n_ubatch = llama_n_ubatch(ctx); + + // next, batch any pending prompts without exceeding n_batch + if (params_base.cont_batching || batch.n_tokens == 0) { + for (auto & slot : slots) { + // check if we can batch this slot with the previous one + if (slot.is_processing()) { + if (!slot_batched) { + slot_batched = &slot; + } else if (!slot_batched->can_batch_with(slot)) { + continue; + } + } + + // this slot still has a prompt to be processed + if (slot.state == SLOT_STATE_PROCESSING_PROMPT || slot.state == SLOT_STATE_STARTED) { + auto & prompt_tokens = slot.prompt_tokens; + + // TODO: maybe move branch to outside of this loop in the future + if (slot.state == SLOT_STATE_STARTED) { + slot.t_start_process_prompt = ggml_time_us(); + slot.t_start_generation = 0; + + slot.n_past = 0; + slot.n_prompt_tokens = prompt_tokens.size(); + slot.state = SLOT_STATE_PROCESSING_PROMPT; + + SLT_INF(slot, "new prompt, n_ctx_slot = %d, n_keep = %d, n_prompt_tokens = %d\n", slot.n_ctx, slot.params.n_keep, slot.n_prompt_tokens); + + // print prompt tokens (for debugging) + if (1) { + // first 16 tokens (avoid flooding logs) + for (int i = 0; i < std::min(16, prompt_tokens.size()); i++) { + SLT_DBG(slot, "prompt token %3d: %6d '%s'\n", i, prompt_tokens[i], common_token_to_piece(ctx, prompt_tokens[i]).c_str()); + } + } else { + // all + for (int i = 0; i < (int) prompt_tokens.size(); i++) { + SLT_DBG(slot, "prompt token %3d: %6d '%s'\n", i, prompt_tokens[i], common_token_to_piece(ctx, prompt_tokens[i]).c_str()); + } + } + + // empty prompt passed -> release the slot and send empty response + if (prompt_tokens.empty()) { + SLT_WRN(slot, "%s", "empty prompt - releasing slot\n"); + + slot.release(); + slot.print_timings(); + send_final_response(slot); + continue; + } + + if (slot.is_non_causal()) { + if (slot.n_prompt_tokens > n_ubatch) { + slot.release(); + send_error(slot, "input is too large to process. increase the physical batch size", ERROR_TYPE_SERVER); + continue; + } + + if (slot.n_prompt_tokens > slot.n_ctx) { + slot.release(); + send_error(slot, "input is larger than the max context size. skipping", ERROR_TYPE_SERVER); + continue; + } + } else { + if (!params_base.ctx_shift) { + // if context shift is disabled, we make sure prompt size is smaller than KV size + // TODO: there should be a separate parameter that control prompt truncation + // context shift should be applied only during the generation phase + if (slot.n_prompt_tokens >= slot.n_ctx) { + slot.release(); + send_error(slot, "the request exceeds the available context size. try increasing the context size or enable context shift", ERROR_TYPE_INVALID_REQUEST); + continue; + } + } + if (slot.params.n_keep < 0) { + slot.params.n_keep = slot.n_prompt_tokens; + } + slot.params.n_keep = std::min(slot.n_ctx - 4, slot.params.n_keep); + + // if input prompt is too big, truncate it + if (slot.n_prompt_tokens >= slot.n_ctx) { + const int n_left = slot.n_ctx - slot.params.n_keep; + + const int n_block_size = n_left / 2; + const int erased_blocks = (slot.n_prompt_tokens - slot.params.n_keep - n_block_size) / n_block_size; + + llama_tokens new_tokens( + prompt_tokens.begin(), + prompt_tokens.begin() + slot.params.n_keep); + + new_tokens.insert( + new_tokens.end(), + prompt_tokens.begin() + slot.params.n_keep + erased_blocks * n_block_size, + prompt_tokens.end()); + + prompt_tokens = std::move(new_tokens); + + slot.truncated = true; + slot.n_prompt_tokens = prompt_tokens.size(); + + SLT_WRN(slot, "input truncated, n_ctx = %d, n_keep = %d, n_left = %d, n_prompt_tokens = %d\n", slot.n_ctx, slot.params.n_keep, n_left, slot.n_prompt_tokens); + + GGML_ASSERT(slot.n_prompt_tokens < slot.n_ctx); + } + + if (slot.params.cache_prompt) { + // reuse any previously computed tokens that are common with the new prompt + slot.n_past = common_lcp(slot.cache_tokens, prompt_tokens); + + // reuse chunks from the cached prompt by shifting their KV cache in the new position + if (params_base.n_cache_reuse > 0) { + size_t head_c = slot.n_past; // cache + size_t head_p = slot.n_past; // current prompt + + SLT_DBG(slot, "trying to reuse chunks with size > %d, slot.n_past = %d\n", params_base.n_cache_reuse, slot.n_past); + + while (head_c < slot.cache_tokens.size() && + head_p < prompt_tokens.size()) { + + size_t n_match = 0; + while (head_c + n_match < slot.cache_tokens.size() && + head_p + n_match < prompt_tokens.size() && + slot.cache_tokens[head_c + n_match] == prompt_tokens[head_p + n_match]) { + + n_match++; + } + + if (n_match >= (size_t) params_base.n_cache_reuse) { + SLT_INF(slot, "reusing chunk with size %zu, shifting KV cache [%zu, %zu) -> [%zu, %zu)\n", n_match, head_c, head_c + n_match, head_p, head_p + n_match); + //for (size_t i = head_p; i < head_p + n_match; i++) { + // SLT_DBG(slot, "cache token %3zu: %6d '%s'\n", i, prompt_tokens[i], common_token_to_piece(ctx, prompt_tokens[i]).c_str()); + //} + + const int64_t kv_shift = (int64_t) head_p - (int64_t) head_c; + + llama_kv_self_seq_rm (ctx, slot.id, head_p, head_c); + llama_kv_self_seq_add(ctx, slot.id, head_c, head_c + n_match, kv_shift); + + for (size_t i = 0; i < n_match; i++) { + slot.cache_tokens[head_p + i] = slot.cache_tokens[head_c + i]; + slot.n_past++; + } + + head_c += n_match; + head_p += n_match; + } else { + head_c += 1; + } + } + + SLT_DBG(slot, "after context reuse, new slot.n_past = %d\n", slot.n_past); + } + } + } + + if (slot.n_past == slot.n_prompt_tokens && slot.n_past > 0) { + // we have to evaluate at least 1 token to generate logits. + SLT_WRN(slot, "need to evaluate at least 1 token to generate logits, n_past = %d, n_prompt_tokens = %d\n", slot.n_past, slot.n_prompt_tokens); + + slot.n_past--; + } + + slot.n_prompt_tokens_processed = 0; + } + + // non-causal tasks require to fit the entire prompt in the physical batch + if (slot.is_non_causal()) { + // cannot fit the prompt in the current batch - will try next iter + if (batch.n_tokens + slot.n_prompt_tokens > n_batch) { + continue; + } + } + + // keep only the common part + if (!llama_kv_self_seq_rm(ctx, slot.id, slot.n_past, -1)) { + // could not partially delete (likely using a non-Transformer model) + llama_kv_self_seq_rm(ctx, slot.id, -1, -1); + + // there is no common part left + slot.n_past = 0; + } + + SLT_INF(slot, "kv cache rm [%d, end)\n", slot.n_past); + + // remove the non-common part from the cache + slot.cache_tokens.resize(slot.n_past); + + // add prompt tokens for processing in the current batch + while (slot.n_past < slot.n_prompt_tokens && batch.n_tokens < n_batch) { + // without pooling, we want to output the embeddings for all the tokens in the batch + const bool need_embd = slot.task_type == SERVER_TASK_TYPE_EMBEDDING && llama_pooling_type(slot.ctx) == LLAMA_POOLING_TYPE_NONE; + + common_batch_add(batch, prompt_tokens[slot.n_past], slot.n_past, { slot.id }, need_embd); + + if (slot.params.cache_prompt) { + slot.cache_tokens.push_back(prompt_tokens[slot.n_past]); + } + + slot.n_prompt_tokens_processed++; + slot.n_past++; + } + + SLT_INF(slot, "prompt processing progress, n_past = %d, n_tokens = %d, progress = %f\n", slot.n_past, batch.n_tokens, (float) slot.n_prompt_tokens_processed / slot.n_prompt_tokens); + + // entire prompt has been processed + if (slot.n_past == slot.n_prompt_tokens) { + slot.state = SLOT_STATE_DONE_PROMPT; + + GGML_ASSERT(batch.n_tokens > 0); + + common_sampler_reset(slot.smpl); + + // Process all prompt tokens through sampler system + for (int i = 0; i < slot.n_prompt_tokens; ++i) { + common_sampler_accept(slot.smpl, prompt_tokens[i], false); + } + + // extract the logits only for the last token + batch.logits[batch.n_tokens - 1] = true; + + slot.n_decoded = 0; + slot.i_batch = batch.n_tokens - 1; + + SLT_INF(slot, "prompt done, n_past = %d, n_tokens = %d\n", slot.n_past, batch.n_tokens); + } + } + + if (batch.n_tokens >= n_batch) { + break; + } + } + } + + if (batch.n_tokens == 0) { + SRV_WRN("%s", "no tokens to decode\n"); + return; + } + + SRV_DBG("decoding batch, n_tokens = %d\n", batch.n_tokens); + + if (slot_batched) { + // make sure we're in the right embedding mode + llama_set_embeddings(ctx, slot_batched->is_non_causal()); + // apply lora, only need to do it once per batch + common_set_adapter_lora(ctx, slot_batched->lora); + } + + // process the created batch of tokens + for (int32_t i = 0; i < batch.n_tokens; i += n_batch) { + const int32_t n_tokens = std::min(n_batch, batch.n_tokens - i); + + llama_batch batch_view = { + n_tokens, + batch.token + i, + nullptr, + batch.pos + i, + batch.n_seq_id + i, + batch.seq_id + i, + batch.logits + i, + }; + + const int ret = llama_decode(ctx, batch_view); + metrics.on_decoded(slots); + + if (ret != 0) { + if (n_batch == 1 || ret < 0) { + // if you get here, it means the KV cache is full - try increasing it via the context size + SRV_ERR("failed to decode the batch: KV cache is full - try increasing it via the context size, i = %d, n_batch = %d, ret = %d\n", i, n_batch, ret); + for (auto & slot : slots) { + slot.release(); + send_error(slot, "Input prompt is too big compared to KV size. Please try increasing KV size."); + } + break; // break loop of n_batch + } + + // retry with half the batch size to try to find a free slot in the KV cache + n_batch /= 2; + i -= n_batch; + + SRV_WRN("failed to find free space in the KV cache, retrying with smaller batch size - try increasing it via the context size or enable defragmentation, i = %d, n_batch = %d, ret = %d\n", i, n_batch, ret); + + continue; // continue loop of n_batch + } + + for (auto & slot : slots) { + if (slot.i_batch < (int) i || slot.i_batch >= (int) (i + n_tokens)) { + continue; // continue loop of slots + } + + if (slot.state == SLOT_STATE_DONE_PROMPT) { + if (slot.task_type == SERVER_TASK_TYPE_EMBEDDING) { + // prompt evaluated for embedding + send_embedding(slot, batch_view); + slot.release(); + slot.i_batch = -1; + continue; // continue loop of slots + } + + if (slot.task_type == SERVER_TASK_TYPE_RERANK) { + send_rerank(slot, batch_view); + slot.release(); + slot.i_batch = -1; + continue; // continue loop of slots + } + + // prompt evaluated for next-token prediction + slot.state = SLOT_STATE_GENERATING; + } else if (slot.state != SLOT_STATE_GENERATING) { + continue; // continue loop of slots + } + + const int tok_idx = slot.i_batch - i; + + llama_token id = common_sampler_sample(slot.smpl, ctx, tok_idx); + + slot.i_batch = -1; + + common_sampler_accept(slot.smpl, id, true); + + slot.n_decoded += 1; + + const int64_t t_current = ggml_time_us(); + + if (slot.n_decoded == 1) { + slot.t_start_generation = t_current; + slot.t_prompt_processing = (slot.t_start_generation - slot.t_start_process_prompt) / 1e3; + metrics.on_prompt_eval(slot); + } + + slot.t_token_generation = (t_current - slot.t_start_generation) / 1e3; + + completion_token_output result; + result.tok = id; + result.text_to_send = common_token_to_piece(ctx, result.tok, accept_special_token(slot, result.tok)); + result.prob = 1.0f; // TODO: set it here instead of doing inside populate_token_probs + + if (slot.params.sampling.n_probs > 0) { + populate_token_probs(slot, result, slot.params.post_sampling_probs, params_base.special, tok_idx); + } + + if (!process_token(result, slot)) { + // release slot because of stop condition + slot.release(); + slot.print_timings(); + send_final_response(slot); + metrics.on_prediction(slot); + continue; + } + } + + // do speculative decoding + for (auto & slot : slots) { + if (!slot.is_processing() || !slot.can_speculate()) { + continue; + } + + if (slot.state != SLOT_STATE_GENERATING) { + continue; + } + + // determine the max draft that fits the current slot state + int n_draft_max = slot.params.speculative.n_max; + + // note: n_past is not yet increased for the `id` token sampled above + // also, need to leave space for 1 extra token to allow context shifts + n_draft_max = std::min(n_draft_max, slot.n_ctx - slot.n_past - 2); + + if (slot.n_remaining > 0) { + n_draft_max = std::min(n_draft_max, slot.n_remaining - 1); + } + + SLT_DBG(slot, "max possible draft: %d\n", n_draft_max); + + if (n_draft_max < slot.params.speculative.n_min) { + SLT_DBG(slot, "the max possible draft is too small: %d < %d - skipping speculative decoding\n", n_draft_max, slot.params.speculative.n_min); + + continue; + } + + llama_token id = slot.sampled; + + struct common_speculative_params params_spec; + params_spec.n_draft = n_draft_max; + params_spec.n_reuse = llama_n_ctx(slot.ctx_dft) - slot.params.speculative.n_max; + params_spec.p_min = slot.params.speculative.p_min; + + llama_tokens draft = common_speculative_gen_draft(slot.spec, params_spec, slot.cache_tokens, id); + + // keep track of total number of tokens generated in the draft + slot.n_draft_total += draft.size(); + + // ignore small drafts + if (slot.params.speculative.n_min > (int) draft.size()) { + SLT_DBG(slot, "ignoring small draft: %d < %d\n", (int) draft.size(), slot.params.speculative.n_min); + + continue; + } + + // construct the speculation batch + common_batch_clear(slot.batch_spec); + common_batch_add (slot.batch_spec, id, slot.n_past, { slot.id }, true); + + for (size_t i = 0; i < draft.size(); ++i) { + common_batch_add(slot.batch_spec, draft[i], slot.n_past + 1 + i, { slot.id }, true); + } + + SLT_DBG(slot, "decoding speculative batch, size = %d\n", slot.batch_spec.n_tokens); + + llama_decode(ctx, slot.batch_spec); + + // the accepted tokens from the speculation + const auto ids = common_sampler_sample_and_accept_n(slot.smpl, ctx, draft); + + slot.n_past += ids.size(); + slot.n_decoded += ids.size(); + + // update how many tokens out of draft was accepted + slot.n_draft_accepted += ids.size() - 1; + + slot.cache_tokens.push_back(id); + slot.cache_tokens.insert(slot.cache_tokens.end(), ids.begin(), ids.end() - 1); + + llama_kv_self_seq_rm(ctx, slot.id, slot.n_past, -1); + + for (size_t i = 0; i < ids.size(); ++i) { + completion_token_output result; + + result.tok = ids[i]; + result.text_to_send = common_token_to_piece(ctx, result.tok, accept_special_token(slot, result.tok)); + result.prob = 1.0f; // set later + + // TODO: set result.probs + + if (!process_token(result, slot)) { + // release slot because of stop condition + slot.release(); + slot.print_timings(); + send_final_response(slot); + metrics.on_prediction(slot); + break; + } + } + + SLT_DBG(slot, "accepted %d/%d draft tokens, new n_past = %d\n", (int) ids.size() - 1, (int) draft.size(), slot.n_past); + } + } + + SRV_DBG("%s", "run slots completed\n"); + } + + json model_meta() const { + return json { + {"vocab_type", llama_vocab_type (vocab)}, + {"n_vocab", llama_vocab_n_tokens (vocab)}, + {"n_ctx_train", llama_model_n_ctx_train(model)}, + {"n_embd", llama_model_n_embd (model)}, + {"n_params", llama_model_n_params (model)}, + {"size", llama_model_size (model)}, + }; + } +}; + +static void log_server_request(const httplib::Request & req, const httplib::Response & res) { + // skip GH copilot requests when using default port + if (req.path == "/v1/health" || req.path == "/v1/completions") { + return; + } + + // reminder: this function is not covered by httplib's exception handler; if someone does more complicated stuff, think about wrapping it in try-catch + + SRV_INF("request: %s %s %s %d\n", req.method.c_str(), req.path.c_str(), req.remote_addr.c_str(), res.status); + + SRV_DBG("request: %s\n", req.body.c_str()); + SRV_DBG("response: %s\n", res.body.c_str()); +} + +std::function shutdown_handler; +std::atomic_flag is_terminating = ATOMIC_FLAG_INIT; + +inline void signal_handler(int signal) { + if (is_terminating.test_and_set()) { + // in case it hangs, we can force terminate the server by hitting Ctrl+C twice + // this is for better developer experience, we can remove when the server is stable enough + fprintf(stderr, "Received second interrupt, terminating immediately.\n"); + exit(1); + } + + shutdown_handler(signal); +} + +int main(int argc, char ** argv) { + // own arguments required by this example + common_params params; + + if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_SERVER)) { + return 1; + } + + common_init(); + + // struct that contains llama context and inference + server_context ctx_server; + + llama_backend_init(); + llama_numa_init(params.numa); + + LOG_INF("system info: n_threads = %d, n_threads_batch = %d, total_threads = %d\n", params.cpuparams.n_threads, params.cpuparams_batch.n_threads, std::thread::hardware_concurrency()); + LOG_INF("\n"); + LOG_INF("%s\n", common_params_get_system_info(params).c_str()); + LOG_INF("\n"); + + std::unique_ptr svr; +#ifdef CPPHTTPLIB_OPENSSL_SUPPORT + if (params.ssl_file_key != "" && params.ssl_file_cert != "") { + LOG_INF("Running with SSL: key = %s, cert = %s\n", params.ssl_file_key.c_str(), params.ssl_file_cert.c_str()); + svr.reset( + new httplib::SSLServer(params.ssl_file_cert.c_str(), params.ssl_file_key.c_str()) + ); + } else { + LOG_INF("Running without SSL\n"); + svr.reset(new httplib::Server()); + } +#else + if (params.ssl_file_key != "" && params.ssl_file_cert != "") { + LOG_ERR("Server is built without SSL support\n"); + return 1; + } + svr.reset(new httplib::Server()); +#endif + + std::atomic state{SERVER_STATE_LOADING_MODEL}; + + svr->set_default_headers({{"Server", "llama.cpp"}}); + svr->set_logger(log_server_request); + + auto res_error = [](httplib::Response & res, const json & error_data) { + json final_response {{"error", error_data}}; + res.set_content(safe_json_to_str(final_response), MIMETYPE_JSON); + res.status = json_value(error_data, "code", 500); + }; + + auto res_ok = [](httplib::Response & res, const json & data) { + res.set_content(safe_json_to_str(data), MIMETYPE_JSON); + res.status = 200; + }; + + svr->set_exception_handler([&res_error](const httplib::Request &, httplib::Response & res, const std::exception_ptr & ep) { + std::string message; + try { + std::rethrow_exception(ep); + } catch (const std::exception & e) { + message = e.what(); + } catch (...) { + message = "Unknown Exception"; + } + + try { + json formatted_error = format_error_response(message, ERROR_TYPE_SERVER); + LOG_WRN("got exception: %s\n", formatted_error.dump().c_str()); + res_error(res, formatted_error); + } catch (const std::exception & e) { + LOG_ERR("got another exception: %s | while hanlding exception: %s\n", e.what(), message.c_str()); + } + }); + + svr->set_error_handler([&res_error](const httplib::Request &, httplib::Response & res) { + if (res.status == 404) { + res_error(res, format_error_response("File Not Found", ERROR_TYPE_NOT_FOUND)); + } + // for other error codes, we skip processing here because it's already done by res_error() + }); + + // set timeouts and change hostname and port + svr->set_read_timeout (params.timeout_read); + svr->set_write_timeout(params.timeout_write); + + std::unordered_map log_data; + + log_data["hostname"] = params.hostname; + log_data["port"] = std::to_string(params.port); + + if (params.api_keys.size() == 1) { + auto key = params.api_keys[0]; + log_data["api_key"] = "api_key: ****" + key.substr(std::max((int)(key.length() - 4), 0)); + } else if (params.api_keys.size() > 1) { + log_data["api_key"] = "api_key: " + std::to_string(params.api_keys.size()) + " keys loaded"; + } + + // Necessary similarity of prompt for slot selection + ctx_server.slot_prompt_similarity = params.slot_prompt_similarity; + + // + // Middlewares + // + + auto middleware_validate_api_key = [¶ms, &res_error](const httplib::Request & req, httplib::Response & res) { + static const std::unordered_set public_endpoints = { + "/health", + "/models", + "/v1/models", + }; + + // If API key is not set, skip validation + if (params.api_keys.empty()) { + return true; + } + + // If path is public or is static file, skip validation + if (public_endpoints.find(req.path) != public_endpoints.end() || req.path == "/") { + return true; + } + + // Check for API key in the header + auto auth_header = req.get_header_value("Authorization"); + + std::string prefix = "Bearer "; + if (auth_header.substr(0, prefix.size()) == prefix) { + std::string received_api_key = auth_header.substr(prefix.size()); + if (std::find(params.api_keys.begin(), params.api_keys.end(), received_api_key) != params.api_keys.end()) { + return true; // API key is valid + } + } + + // API key is invalid or not provided + res_error(res, format_error_response("Invalid API Key", ERROR_TYPE_AUTHENTICATION)); + + LOG_WRN("Unauthorized: Invalid API Key\n"); + + return false; + }; + + auto middleware_server_state = [&res_error, &state](const httplib::Request & req, httplib::Response & res) { + server_state current_state = state.load(); + if (current_state == SERVER_STATE_LOADING_MODEL) { + auto tmp = string_split(req.path, '.'); + if (req.path == "/" || tmp.back() == "html") { + res.set_content(reinterpret_cast(loading_html), loading_html_len, "text/html; charset=utf-8"); + res.status = 503; + } else { + res_error(res, format_error_response("Loading model", ERROR_TYPE_UNAVAILABLE)); + } + return false; + } + return true; + }; + + // register server middlewares + svr->set_pre_routing_handler([&middleware_validate_api_key, &middleware_server_state](const httplib::Request & req, httplib::Response & res) { + res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin")); + // If this is OPTIONS request, skip validation because browsers don't include Authorization header + if (req.method == "OPTIONS") { + res.set_header("Access-Control-Allow-Credentials", "true"); + res.set_header("Access-Control-Allow-Methods", "GET, POST"); + res.set_header("Access-Control-Allow-Headers", "*"); + res.set_content("", "text/html"); // blank response, no data + return httplib::Server::HandlerResponse::Handled; // skip further processing + } + if (!middleware_server_state(req, res)) { + return httplib::Server::HandlerResponse::Handled; + } + if (!middleware_validate_api_key(req, res)) { + return httplib::Server::HandlerResponse::Handled; + } + return httplib::Server::HandlerResponse::Unhandled; + }); + + // + // Route handlers (or controllers) + // + + const auto handle_health = [&](const httplib::Request &, httplib::Response & res) { + // error and loading states are handled by middleware + json health = {{"status", "ok"}}; + res_ok(res, health); + }; + + const auto handle_slots = [&](const httplib::Request & req, httplib::Response & res) { + if (!params.endpoint_slots) { + res_error(res, format_error_response("This server does not support slots endpoint. Start it with `--slots`", ERROR_TYPE_NOT_SUPPORTED)); + return; + } + + // request slots data using task queue + int task_id = ctx_server.queue_tasks.get_new_id(); + { + server_task task(SERVER_TASK_TYPE_METRICS); + task.id = task_id; + ctx_server.queue_results.add_waiting_task_id(task_id); + ctx_server.queue_tasks.post(std::move(task), true); // high-priority task + } + + // get the result + server_task_result_ptr result = ctx_server.queue_results.recv(task_id); + ctx_server.queue_results.remove_waiting_task_id(task_id); + + if (result->is_error()) { + res_error(res, result->to_json()); + return; + } + + // TODO: get rid of this dynamic_cast + auto res_metrics = dynamic_cast(result.get()); + GGML_ASSERT(res_metrics != nullptr); + + // optionally return "fail_on_no_slot" error + if (req.has_param("fail_on_no_slot")) { + if (res_metrics->n_idle_slots == 0) { + res_error(res, format_error_response("no slot available", ERROR_TYPE_UNAVAILABLE)); + return; + } + } + + res_ok(res, res_metrics->slots_data); + }; + + const auto handle_metrics = [&](const httplib::Request &, httplib::Response & res) { + if (!params.endpoint_metrics) { + res_error(res, format_error_response("This server does not support metrics endpoint. Start it with `--metrics`", ERROR_TYPE_NOT_SUPPORTED)); + return; + } + + // request slots data using task queue + int task_id = ctx_server.queue_tasks.get_new_id(); + { + server_task task(SERVER_TASK_TYPE_METRICS); + task.id = task_id; + ctx_server.queue_results.add_waiting_task_id(task_id); + ctx_server.queue_tasks.post(std::move(task), true); // high-priority task + } + + // get the result + server_task_result_ptr result = ctx_server.queue_results.recv(task_id); + ctx_server.queue_results.remove_waiting_task_id(task_id); + + if (result->is_error()) { + res_error(res, result->to_json()); + return; + } + + // TODO: get rid of this dynamic_cast + auto res_metrics = dynamic_cast(result.get()); + GGML_ASSERT(res_metrics != nullptr); + + // metrics definition: https://prometheus.io/docs/practices/naming/#metric-names + json all_metrics_def = json { + {"counter", {{ + {"name", "prompt_tokens_total"}, + {"help", "Number of prompt tokens processed."}, + {"value", (uint64_t) res_metrics->n_prompt_tokens_processed_total} + }, { + {"name", "prompt_seconds_total"}, + {"help", "Prompt process time"}, + {"value", (uint64_t) res_metrics->t_prompt_processing_total / 1.e3} + }, { + {"name", "tokens_predicted_total"}, + {"help", "Number of generation tokens processed."}, + {"value", (uint64_t) res_metrics->n_tokens_predicted_total} + }, { + {"name", "tokens_predicted_seconds_total"}, + {"help", "Predict process time"}, + {"value", (uint64_t) res_metrics->t_tokens_generation_total / 1.e3} + }, { + {"name", "n_decode_total"}, + {"help", "Total number of llama_decode() calls"}, + {"value", res_metrics->n_decode_total} + }, { + {"name", "n_busy_slots_per_decode"}, + {"help", "Average number of busy slots per llama_decode() call"}, + {"value", (float) res_metrics->n_busy_slots_total / std::max((float) res_metrics->n_decode_total, 1.f)} + }}}, + {"gauge", {{ + {"name", "prompt_tokens_seconds"}, + {"help", "Average prompt throughput in tokens/s."}, + {"value", res_metrics->n_prompt_tokens_processed ? 1.e3 / res_metrics->t_prompt_processing * res_metrics->n_prompt_tokens_processed : 0.} + },{ + {"name", "predicted_tokens_seconds"}, + {"help", "Average generation throughput in tokens/s."}, + {"value", res_metrics->n_tokens_predicted ? 1.e3 / res_metrics->t_tokens_generation * res_metrics->n_tokens_predicted : 0.} + },{ + {"name", "kv_cache_usage_ratio"}, + {"help", "KV-cache usage. 1 means 100 percent usage."}, + {"value", 1. * res_metrics->kv_cache_used_cells / params.n_ctx} + },{ + {"name", "kv_cache_tokens"}, + {"help", "KV-cache tokens."}, + {"value", (uint64_t) res_metrics->kv_cache_tokens_count} + },{ + {"name", "requests_processing"}, + {"help", "Number of requests processing."}, + {"value", (uint64_t) res_metrics->n_processing_slots} + },{ + {"name", "requests_deferred"}, + {"help", "Number of requests deferred."}, + {"value", (uint64_t) res_metrics->n_tasks_deferred} + }}} + }; + + std::stringstream prometheus; + + for (const auto & el : all_metrics_def.items()) { + const auto & type = el.key(); + const auto & metrics_def = el.value(); + + for (const auto & metric_def : metrics_def) { + const std::string name = metric_def.at("name"); + const std::string help = metric_def.at("help"); + + auto value = json_value(metric_def, "value", 0.); + prometheus << "# HELP llamacpp:" << name << " " << help << "\n" + << "# TYPE llamacpp:" << name << " " << type << "\n" + << "llamacpp:" << name << " " << value << "\n"; + } + } + + res.set_header("Process-Start-Time-Unix", std::to_string(res_metrics->t_start)); + + res.set_content(prometheus.str(), "text/plain; version=0.0.4"); + res.status = 200; // HTTP OK + }; + + const auto handle_slots_save = [&ctx_server, &res_error, &res_ok, ¶ms](const httplib::Request & req, httplib::Response & res, int id_slot) { + json request_data = json::parse(req.body); + std::string filename = request_data.at("filename"); + if (!fs_validate_filename(filename)) { + res_error(res, format_error_response("Invalid filename", ERROR_TYPE_INVALID_REQUEST)); + return; + } + std::string filepath = params.slot_save_path + filename; + + int task_id = ctx_server.queue_tasks.get_new_id(); + { + server_task task(SERVER_TASK_TYPE_SLOT_SAVE); + task.id = task_id; + task.slot_action.slot_id = id_slot; + task.slot_action.filename = filename; + task.slot_action.filepath = filepath; + + ctx_server.queue_results.add_waiting_task_id(task_id); + ctx_server.queue_tasks.post(std::move(task)); + } + + server_task_result_ptr result = ctx_server.queue_results.recv(task_id); + ctx_server.queue_results.remove_waiting_task_id(task_id); + + if (result->is_error()) { + res_error(res, result->to_json()); + return; + } + + res_ok(res, result->to_json()); + }; + + const auto handle_slots_restore = [&ctx_server, &res_error, &res_ok, ¶ms](const httplib::Request & req, httplib::Response & res, int id_slot) { + json request_data = json::parse(req.body); + std::string filename = request_data.at("filename"); + if (!fs_validate_filename(filename)) { + res_error(res, format_error_response("Invalid filename", ERROR_TYPE_INVALID_REQUEST)); + return; + } + std::string filepath = params.slot_save_path + filename; + + int task_id = ctx_server.queue_tasks.get_new_id(); + { + server_task task(SERVER_TASK_TYPE_SLOT_RESTORE); + task.id = task_id; + task.slot_action.slot_id = id_slot; + task.slot_action.filename = filename; + task.slot_action.filepath = filepath; + + ctx_server.queue_results.add_waiting_task_id(task_id); + ctx_server.queue_tasks.post(std::move(task)); + } + + server_task_result_ptr result = ctx_server.queue_results.recv(task_id); + ctx_server.queue_results.remove_waiting_task_id(task_id); + + if (result->is_error()) { + res_error(res, result->to_json()); + return; + } + + GGML_ASSERT(dynamic_cast(result.get()) != nullptr); + res_ok(res, result->to_json()); + }; + + const auto handle_slots_erase = [&ctx_server, &res_error, &res_ok](const httplib::Request & /* req */, httplib::Response & res, int id_slot) { + int task_id = ctx_server.queue_tasks.get_new_id(); + { + server_task task(SERVER_TASK_TYPE_SLOT_ERASE); + task.id = task_id; + task.slot_action.slot_id = id_slot; + + ctx_server.queue_results.add_waiting_task_id(task_id); + ctx_server.queue_tasks.post(std::move(task)); + } + + server_task_result_ptr result = ctx_server.queue_results.recv(task_id); + ctx_server.queue_results.remove_waiting_task_id(task_id); + + if (result->is_error()) { + res_error(res, result->to_json()); + return; + } + + GGML_ASSERT(dynamic_cast(result.get()) != nullptr); + res_ok(res, result->to_json()); + }; + + const auto handle_slots_action = [¶ms, &res_error, &handle_slots_save, &handle_slots_restore, &handle_slots_erase](const httplib::Request & req, httplib::Response & res) { + if (params.slot_save_path.empty()) { + res_error(res, format_error_response("This server does not support slots action. Start it with `--slot-save-path`", ERROR_TYPE_NOT_SUPPORTED)); + return; + } + + std::string id_slot_str = req.path_params.at("id_slot"); + int id_slot; + + try { + id_slot = std::stoi(id_slot_str); + } catch (const std::exception &) { + res_error(res, format_error_response("Invalid slot ID", ERROR_TYPE_INVALID_REQUEST)); + return; + } + + std::string action = req.get_param_value("action"); + + if (action == "save") { + handle_slots_save(req, res, id_slot); + } else if (action == "restore") { + handle_slots_restore(req, res, id_slot); + } else if (action == "erase") { + handle_slots_erase(req, res, id_slot); + } else { + res_error(res, format_error_response("Invalid action", ERROR_TYPE_INVALID_REQUEST)); + } + }; + + const auto handle_props = [&ctx_server, &res_ok](const httplib::Request &, httplib::Response & res) { + // this endpoint is publicly available, please only return what is safe to be exposed + json data = { + { "default_generation_settings", ctx_server.default_generation_settings_for_props }, + { "total_slots", ctx_server.params_base.n_parallel }, + { "model_path", ctx_server.params_base.model.path }, + { "chat_template", common_chat_templates_source(ctx_server.chat_templates.get()) }, + { "bos_token", common_token_to_piece(ctx_server.ctx, llama_vocab_bos(ctx_server.vocab), /* special= */ true)}, + { "eos_token", common_token_to_piece(ctx_server.ctx, llama_vocab_eos(ctx_server.vocab), /* special= */ true)}, + { "build_info", build_info }, + }; + if (ctx_server.params_base.use_jinja) { + if (auto tool_use_src = common_chat_templates_source(ctx_server.chat_templates.get(), "tool_use")) { + data["chat_template_tool_use"] = tool_use_src; + } + } + + res_ok(res, data); + }; + + const auto handle_props_change = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res) { + if (!ctx_server.params_base.endpoint_props) { + res_error(res, format_error_response("This server does not support changing global properties. Start it with `--props`", ERROR_TYPE_NOT_SUPPORTED)); + return; + } + + json data = json::parse(req.body); + + // update any props here + + res_ok(res, {{ "success", true }}); + }; + + const auto handle_api_show = [&ctx_server, &res_ok](const httplib::Request &, httplib::Response & res) { + json data = { + { + "template", common_chat_templates_source(ctx_server.chat_templates.get()), + }, + { + "model_info", { + { "llama.context_length", ctx_server.slots.back().n_ctx, }, + } + }, + }; + + res_ok(res, data); + }; + + // handle completion-like requests (completion, chat, infill) + // we can optionally provide a custom format for partial results and final results + const auto handle_completions_impl = [&ctx_server, &res_error, &res_ok]( + server_task_type type, + json & data, + std::function is_connection_closed, + httplib::Response & res, + oaicompat_type oaicompat) { + GGML_ASSERT(type == SERVER_TASK_TYPE_COMPLETION || type == SERVER_TASK_TYPE_INFILL); + + if (ctx_server.params_base.embedding) { + res_error(res, format_error_response("This server does not support completions. Start it without `--embeddings`", ERROR_TYPE_NOT_SUPPORTED)); + return; + } + + auto completion_id = gen_chatcmplid(); + std::unordered_set task_ids; + try { + std::vector tasks; + + const auto & prompt = data.at("prompt"); + // TODO: this log can become very long, put it behind a flag or think about a more compact format + //SRV_DBG("Prompt: %s\n", prompt.is_string() ? prompt.get().c_str() : prompt.dump(2).c_str()); + + std::vector tokenized_prompts = tokenize_input_prompts(ctx_server.vocab, prompt, true, true); + tasks.reserve(tokenized_prompts.size()); + for (size_t i = 0; i < tokenized_prompts.size(); i++) { + server_task task = server_task(type); + + task.id = ctx_server.queue_tasks.get_new_id(); + task.index = i; + + task.prompt_tokens = std::move(tokenized_prompts[i]); + task.params = server_task::params_from_json_cmpl( + ctx_server.ctx, + ctx_server.params_base, + data); + task.id_selected_slot = json_value(data, "id_slot", -1); + + // OAI-compat + task.params.oaicompat = oaicompat; + task.params.oaicompat_cmpl_id = completion_id; + // oaicompat_model is already populated by params_from_json_cmpl + + tasks.push_back(std::move(task)); + } + + task_ids = server_task::get_list_id(tasks); + ctx_server.queue_results.add_waiting_tasks(tasks); + ctx_server.queue_tasks.post(std::move(tasks)); + } catch (const std::exception & e) { + res_error(res, format_error_response(e.what(), ERROR_TYPE_INVALID_REQUEST)); + return; + } + + bool stream = json_value(data, "stream", false); + + if (!stream) { + ctx_server.receive_multi_results(task_ids, [&](std::vector & results) { + if (results.size() == 1) { + // single result + res_ok(res, results[0]->to_json()); + } else { + // multiple results (multitask) + json arr = json::array(); + for (auto & res : results) { + arr.push_back(res->to_json()); + } + res_ok(res, arr); + } + }, [&](const json & error_data) { + res_error(res, error_data); + }, is_connection_closed); + + ctx_server.queue_results.remove_waiting_task_ids(task_ids); + } else { + const auto chunked_content_provider = [task_ids, &ctx_server, oaicompat](size_t, httplib::DataSink & sink) { + ctx_server.receive_cmpl_results_stream(task_ids, [&](server_task_result_ptr & result) -> bool { + json res_json = result->to_json(); + if (res_json.is_array()) { + for (const auto & res : res_json) { + if (!server_sent_event(sink, "data", res)) { + // sending failed (HTTP connection closed), cancel the generation + return false; + } + } + return true; + } else { + return server_sent_event(sink, "data", res_json); + } + }, [&](const json & error_data) { + server_sent_event(sink, "error", error_data); + }, [&sink]() { + // note: do not use req.is_connection_closed here because req is already destroyed + return !sink.is_writable(); + }); + if (oaicompat != OAICOMPAT_TYPE_NONE) { + static const std::string ev_done = "data: [DONE]\n\n"; + sink.write(ev_done.data(), ev_done.size()); + } + sink.done(); + return false; + }; + + auto on_complete = [task_ids, &ctx_server] (bool) { + ctx_server.queue_results.remove_waiting_task_ids(task_ids); + }; + + res.set_chunked_content_provider("text/event-stream", chunked_content_provider, on_complete); + } + }; + + const auto handle_completions = [&handle_completions_impl](const httplib::Request & req, httplib::Response & res) { + json data = json::parse(req.body); + return handle_completions_impl( + SERVER_TASK_TYPE_COMPLETION, + data, + req.is_connection_closed, + res, + OAICOMPAT_TYPE_NONE); + }; + + const auto handle_completions_oai = [&handle_completions_impl](const httplib::Request & req, httplib::Response & res) { + json data = oaicompat_completion_params_parse(json::parse(req.body)); + return handle_completions_impl( + SERVER_TASK_TYPE_COMPLETION, + data, + req.is_connection_closed, + res, + OAICOMPAT_TYPE_COMPLETION); + }; + + const auto handle_infill = [&ctx_server, &res_error, &handle_completions_impl](const httplib::Request & req, httplib::Response & res) { + // check model compatibility + std::string err; + if (llama_vocab_fim_pre(ctx_server.vocab) == LLAMA_TOKEN_NULL) { + err += "prefix token is missing. "; + } + if (llama_vocab_fim_suf(ctx_server.vocab) == LLAMA_TOKEN_NULL) { + err += "suffix token is missing. "; + } + if (llama_vocab_fim_mid(ctx_server.vocab) == LLAMA_TOKEN_NULL) { + err += "middle token is missing. "; + } + if (!err.empty()) { + res_error(res, format_error_response(string_format("Infill is not supported by this model: %s", err.c_str()), ERROR_TYPE_NOT_SUPPORTED)); + return; + } + + json data = json::parse(req.body); + + // validate input + if (data.contains("prompt") && !data.at("prompt").is_string()) { + // prompt is optional + res_error(res, format_error_response("\"prompt\" must be a string", ERROR_TYPE_INVALID_REQUEST)); + } + + if (!data.contains("input_prefix")) { + res_error(res, format_error_response("\"input_prefix\" is required", ERROR_TYPE_INVALID_REQUEST)); + } + + if (!data.contains("input_suffix")) { + res_error(res, format_error_response("\"input_suffix\" is required", ERROR_TYPE_INVALID_REQUEST)); + } + + if (data.contains("input_extra") && !data.at("input_extra").is_array()) { + // input_extra is optional + res_error(res, format_error_response("\"input_extra\" must be an array of {\"filename\": string, \"text\": string}", ERROR_TYPE_INVALID_REQUEST)); + return; + } + + json input_extra = json_value(data, "input_extra", json::array()); + for (const auto & chunk : input_extra) { + // { "text": string, "filename": string } + if (!chunk.contains("text") || !chunk.at("text").is_string()) { + res_error(res, format_error_response("extra_context chunk must contain a \"text\" field with a string value", ERROR_TYPE_INVALID_REQUEST)); + return; + } + // filename is optional + if (chunk.contains("filename") && !chunk.at("filename").is_string()) { + res_error(res, format_error_response("extra_context chunk's \"filename\" field must be a string", ERROR_TYPE_INVALID_REQUEST)); + return; + } + } + data["input_extra"] = input_extra; // default to empty array if it's not exist + + std::string prompt = json_value(data, "prompt", std::string()); + std::vector tokenized_prompts = tokenize_input_prompts(ctx_server.vocab, prompt, false, true); + SRV_DBG("creating infill tasks, n_prompts = %d\n", (int) tokenized_prompts.size()); + data["prompt"] = format_infill( + ctx_server.vocab, + data.at("input_prefix"), + data.at("input_suffix"), + data.at("input_extra"), + ctx_server.params_base.n_batch, + ctx_server.params_base.n_predict, + ctx_server.slots[0].n_ctx, // TODO: there should be a better way + ctx_server.params_base.spm_infill, + tokenized_prompts[0] + ); + + return handle_completions_impl( + SERVER_TASK_TYPE_INFILL, + data, + req.is_connection_closed, + res, + OAICOMPAT_TYPE_NONE); // infill is not OAI compatible + }; + + const auto handle_chat_completions = [&ctx_server, ¶ms, &res_error, &handle_completions_impl](const httplib::Request & req, httplib::Response & res) { + LOG_DBG("request: %s\n", req.body.c_str()); + if (ctx_server.params_base.embedding) { + res_error(res, format_error_response("This server does not support completions. Start it without `--embeddings`", ERROR_TYPE_NOT_SUPPORTED)); + return; + } + + auto body = json::parse(req.body); + json data = oaicompat_completion_params_parse(body, params.use_jinja, params.reasoning_format, ctx_server.chat_templates.get()); + + return handle_completions_impl( + SERVER_TASK_TYPE_COMPLETION, + data, + req.is_connection_closed, + res, + OAICOMPAT_TYPE_CHAT); + }; + + // same with handle_chat_completions, but without inference part + const auto handle_apply_template = [&ctx_server, ¶ms, &res_ok](const httplib::Request & req, httplib::Response & res) { + auto body = json::parse(req.body); + json data = oaicompat_completion_params_parse(body, params.use_jinja, params.reasoning_format, ctx_server.chat_templates.get()); + res_ok(res, {{ "prompt", std::move(data.at("prompt")) }}); + }; + + const auto handle_models = [¶ms, &ctx_server, &res_ok](const httplib::Request &, httplib::Response & res) { + json models = { + {"object", "list"}, + {"data", { + { + {"id", params.model_alias.empty() ? params.model.path : params.model_alias}, + {"object", "model"}, + {"created", std::time(0)}, + {"owned_by", "llamacpp"}, + {"meta", ctx_server.model_meta()} + }, + }} + }; + + res_ok(res, models); + }; + + const auto handle_tokenize = [&ctx_server, &res_ok](const httplib::Request & req, httplib::Response & res) { + const json body = json::parse(req.body); + + json tokens_response = json::array(); + if (body.count("content") != 0) { + const bool add_special = json_value(body, "add_special", false); + const bool with_pieces = json_value(body, "with_pieces", false); + + llama_tokens tokens = tokenize_mixed(ctx_server.vocab, body.at("content"), add_special, true); + + if (with_pieces) { + for (const auto& token : tokens) { + std::string piece = common_token_to_piece(ctx_server.ctx, token); + json piece_json; + + // Check if the piece is valid UTF-8 + if (is_valid_utf8(piece)) { + piece_json = piece; + } else { + // If not valid UTF-8, store as array of byte values + piece_json = json::array(); + for (unsigned char c : piece) { + piece_json.push_back(static_cast(c)); + } + } + + tokens_response.push_back({ + {"id", token}, + {"piece", piece_json} + }); + } + } else { + tokens_response = tokens; + } + } + + const json data = format_tokenizer_response(tokens_response); + res_ok(res, data); + }; + + const auto handle_detokenize = [&ctx_server, &res_ok](const httplib::Request & req, httplib::Response & res) { + const json body = json::parse(req.body); + + std::string content; + if (body.count("tokens") != 0) { + const llama_tokens tokens = body.at("tokens"); + content = tokens_to_str(ctx_server.ctx, tokens.cbegin(), tokens.cend()); + } + + const json data = format_detokenized_response(content); + res_ok(res, data); + }; + + const auto handle_embeddings_impl = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res, oaicompat_type oaicompat) { + const json body = json::parse(req.body); + + if (oaicompat != OAICOMPAT_TYPE_NONE && llama_pooling_type(ctx_server.ctx) == LLAMA_POOLING_TYPE_NONE) { + res_error(res, format_error_response("Pooling type 'none' is not OAI compatible. Please use a different pooling type", ERROR_TYPE_INVALID_REQUEST)); + return; + } + + // for the shape of input/content, see tokenize_input_prompts() + json prompt; + if (body.count("input") != 0) { + prompt = body.at("input"); + } else if (body.contains("content")) { + oaicompat = OAICOMPAT_TYPE_NONE; // "content" field is not OAI compatible + prompt = body.at("content"); + } else { + res_error(res, format_error_response("\"input\" or \"content\" must be provided", ERROR_TYPE_INVALID_REQUEST)); + return; + } + + bool use_base64 = false; + if (body.count("encoding_format") != 0) { + const std::string& format = body.at("encoding_format"); + if (format == "base64") { + use_base64 = true; + } else if (format != "float") { + res_error(res, format_error_response("The format to return the embeddings in. Can be either float or base64", ERROR_TYPE_INVALID_REQUEST)); + return; + } + } + + std::vector tokenized_prompts = tokenize_input_prompts(ctx_server.vocab, prompt, true, true); + for (const auto & tokens : tokenized_prompts) { + // this check is necessary for models that do not add BOS token to the input + if (tokens.empty()) { + res_error(res, format_error_response("Input content cannot be empty", ERROR_TYPE_INVALID_REQUEST)); + return; + } + } + + // create and queue the task + json responses = json::array(); + bool error = false; + std::unordered_set task_ids; + { + std::vector tasks; + for (size_t i = 0; i < tokenized_prompts.size(); i++) { + server_task task = server_task(SERVER_TASK_TYPE_EMBEDDING); + + task.id = ctx_server.queue_tasks.get_new_id(); + task.index = i; + task.prompt_tokens = std::move(tokenized_prompts[i]); + + // OAI-compat + task.params.oaicompat = oaicompat; + + tasks.push_back(std::move(task)); + } + + task_ids = server_task::get_list_id(tasks); + ctx_server.queue_results.add_waiting_tasks(tasks); + ctx_server.queue_tasks.post(std::move(tasks)); + } + + // get the result + ctx_server.receive_multi_results(task_ids, [&](std::vector & results) { + for (auto & res : results) { + GGML_ASSERT(dynamic_cast(res.get()) != nullptr); + responses.push_back(res->to_json()); + } + }, [&](const json & error_data) { + res_error(res, error_data); + error = true; + }, req.is_connection_closed); + + ctx_server.queue_results.remove_waiting_task_ids(task_ids); + + if (error) { + return; + } + + // write JSON response + json root = oaicompat == OAICOMPAT_TYPE_EMBEDDING + ? format_embeddings_response_oaicompat(body, responses, use_base64) + : json(responses); + res_ok(res, root); + }; + + const auto handle_embeddings = [&handle_embeddings_impl](const httplib::Request & req, httplib::Response & res) { + handle_embeddings_impl(req, res, OAICOMPAT_TYPE_NONE); + }; + + const auto handle_embeddings_oai = [&handle_embeddings_impl](const httplib::Request & req, httplib::Response & res) { + handle_embeddings_impl(req, res, OAICOMPAT_TYPE_EMBEDDING); + }; + + const auto handle_rerank = [&ctx_server, &res_error, &res_ok](const httplib::Request & req, httplib::Response & res) { + if (!ctx_server.params_base.reranking || ctx_server.params_base.embedding) { + res_error(res, format_error_response("This server does not support reranking. Start it with `--reranking` and without `--embedding`", ERROR_TYPE_NOT_SUPPORTED)); + return; + } + + const json body = json::parse(req.body); + + // TODO: implement + //int top_n = 1; + //if (body.count("top_n") != 1) { + // top_n = body.at("top_n"); + //} else { + // res_error(res, format_error_response("\"top_n\" must be provided", ERROR_TYPE_INVALID_REQUEST)); + // return; + //} + + // if true, use TEI API format, otherwise use Jina API format + // Jina: https://jina.ai/reranker/ + // TEI: https://huggingface.github.io/text-embeddings-inference/#/Text%20Embeddings%20Inference/rerank + bool is_tei_format = body.contains("texts"); + + json query; + if (body.count("query") == 1) { + query = body.at("query"); + if (!query.is_string()) { + res_error(res, format_error_response("\"query\" must be a string", ERROR_TYPE_INVALID_REQUEST)); + return; + } + } else { + res_error(res, format_error_response("\"query\" must be provided", ERROR_TYPE_INVALID_REQUEST)); + return; + } + + std::vector documents = json_value(body, "documents", + json_value(body, "texts", std::vector())); + if (documents.empty()) { + res_error(res, format_error_response("\"documents\" must be a non-empty string array", ERROR_TYPE_INVALID_REQUEST)); + return; + } + + llama_tokens tokenized_query = tokenize_input_prompts(ctx_server.vocab, query, /* add_special */ false, true)[0]; + + // create and queue the task + json responses = json::array(); + bool error = false; + std::unordered_set task_ids; + { + std::vector tasks; + std::vector tokenized_docs = tokenize_input_prompts(ctx_server.vocab, documents, /* add_special */ false, true); + tasks.reserve(tokenized_docs.size()); + for (size_t i = 0; i < tokenized_docs.size(); i++) { + server_task task = server_task(SERVER_TASK_TYPE_RERANK); + task.id = ctx_server.queue_tasks.get_new_id(); + task.index = i; + task.prompt_tokens = format_rerank(ctx_server.vocab, tokenized_query, tokenized_docs[i]); + tasks.push_back(std::move(task)); + } + + task_ids = server_task::get_list_id(tasks); + ctx_server.queue_results.add_waiting_tasks(tasks); + ctx_server.queue_tasks.post(std::move(tasks)); + } + + ctx_server.receive_multi_results(task_ids, [&](std::vector & results) { + for (auto & res : results) { + GGML_ASSERT(dynamic_cast(res.get()) != nullptr); + responses.push_back(res->to_json()); + } + }, [&](const json & error_data) { + res_error(res, error_data); + error = true; + }, req.is_connection_closed); + + if (error) { + return; + } + + // write JSON response + json root = format_response_rerank( + body, + responses, + is_tei_format, + documents); + + res_ok(res, root); + }; + + const auto handle_lora_adapters_list = [&](const httplib::Request &, httplib::Response & res) { + json result = json::array(); + const auto & loras = ctx_server.params_base.lora_adapters; + for (size_t i = 0; i < loras.size(); ++i) { + auto & lora = loras[i]; + result.push_back({ + {"id", i}, + {"path", lora.path}, + {"scale", lora.scale}, + }); + } + res_ok(res, result); + res.status = 200; // HTTP OK + }; + + const auto handle_lora_adapters_apply = [&](const httplib::Request & req, httplib::Response & res) { + const json body = json::parse(req.body); + if (!body.is_array()) { + res_error(res, format_error_response("Request body must be an array", ERROR_TYPE_INVALID_REQUEST)); + return; + } + + int task_id = ctx_server.queue_tasks.get_new_id(); + { + server_task task(SERVER_TASK_TYPE_SET_LORA); + task.id = task_id; + task.set_lora = parse_lora_request(ctx_server.params_base.lora_adapters, body); + ctx_server.queue_results.add_waiting_task_id(task_id); + ctx_server.queue_tasks.post(std::move(task)); + } + + // get the result + server_task_result_ptr result = ctx_server.queue_results.recv(task_id); + ctx_server.queue_results.remove_waiting_task_id(task_id); + + if (result->is_error()) { + res_error(res, result->to_json()); + return; + } + + GGML_ASSERT(dynamic_cast(result.get()) != nullptr); + res_ok(res, result->to_json()); + }; + + // + // Router + // + + if (!params.webui) { + LOG_INF("Web UI is disabled\n"); + } else { + // register static assets routes + if (!params.public_path.empty()) { + // Set the base directory for serving static files + bool is_found = svr->set_mount_point("/", params.public_path); + if (!is_found) { + LOG_ERR("%s: static assets path not found: %s\n", __func__, params.public_path.c_str()); + return 1; + } + } else { + // using embedded static index.html + svr->Get("/", [](const httplib::Request & req, httplib::Response & res) { + if (req.get_header_value("Accept-Encoding").find("gzip") == std::string::npos) { + res.set_content("Error: gzip is not supported by this browser", "text/plain"); + } else { + res.set_header("Content-Encoding", "gzip"); + // COEP and COOP headers, required by pyodide (python interpreter) + res.set_header("Cross-Origin-Embedder-Policy", "require-corp"); + res.set_header("Cross-Origin-Opener-Policy", "same-origin"); + res.set_content(reinterpret_cast(index_html_gz), index_html_gz_len, "text/html; charset=utf-8"); + } + return false; + }); + } + } + + // register API routes + svr->Get ("/health", handle_health); // public endpoint (no API key check) + svr->Get ("/metrics", handle_metrics); + svr->Get ("/props", handle_props); + svr->Post("/props", handle_props_change); + svr->Post("/api/show", handle_api_show); + svr->Get ("/models", handle_models); // public endpoint (no API key check) + svr->Get ("/v1/models", handle_models); // public endpoint (no API key check) + svr->Post("/completion", handle_completions); // legacy + svr->Post("/completions", handle_completions); + svr->Post("/v1/completions", handle_completions_oai); + svr->Post("/chat/completions", handle_chat_completions); + svr->Post("/v1/chat/completions", handle_chat_completions); + svr->Post("/infill", handle_infill); + svr->Post("/embedding", handle_embeddings); // legacy + svr->Post("/embeddings", handle_embeddings); + svr->Post("/v1/embeddings", handle_embeddings_oai); + svr->Post("/rerank", handle_rerank); + svr->Post("/reranking", handle_rerank); + svr->Post("/v1/rerank", handle_rerank); + svr->Post("/v1/reranking", handle_rerank); + svr->Post("/tokenize", handle_tokenize); + svr->Post("/detokenize", handle_detokenize); + svr->Post("/apply-template", handle_apply_template); + // LoRA adapters hotswap + svr->Get ("/lora-adapters", handle_lora_adapters_list); + svr->Post("/lora-adapters", handle_lora_adapters_apply); + // Save & load slots + svr->Get ("/slots", handle_slots); + svr->Post("/slots/:id_slot", handle_slots_action); + + // + // Start the server + // + if (params.n_threads_http < 1) { + // +2 threads for monitoring endpoints + params.n_threads_http = std::max(params.n_parallel + 2, (int32_t) std::thread::hardware_concurrency() - 1); + } + log_data["n_threads_http"] = std::to_string(params.n_threads_http); + svr->new_task_queue = [¶ms] { return new httplib::ThreadPool(params.n_threads_http); }; + + // clean up function, to be called before exit + auto clean_up = [&svr, &ctx_server]() { + SRV_INF("%s: cleaning up before exit...\n", __func__); + svr->stop(); + ctx_server.queue_results.terminate(); + llama_backend_free(); + }; + + bool was_bound = false; + if (string_ends_with(std::string(params.hostname), ".sock")) { + LOG_INF("%s: setting address family to AF_UNIX\n", __func__); + svr->set_address_family(AF_UNIX); + // bind_to_port requires a second arg, any value other than 0 should + // simply get ignored + was_bound = svr->bind_to_port(params.hostname, 8080); + } else { + LOG_INF("%s: binding port with default address family\n", __func__); + // bind HTTP listen port + if (params.port == 0) { + int bound_port = svr->bind_to_any_port(params.hostname); + if ((was_bound = (bound_port >= 0))) { + params.port = bound_port; + } + } else { + was_bound = svr->bind_to_port(params.hostname, params.port); + } + } + + if (!was_bound) { + LOG_ERR("%s: couldn't bind HTTP server socket, hostname: %s, port: %d\n", __func__, params.hostname.c_str(), params.port); + clean_up(); + return 1; + } + + // run the HTTP server in a thread + std::thread t([&]() { svr->listen_after_bind(); }); + svr->wait_until_ready(); + + LOG_INF("%s: HTTP server is listening, hostname: %s, port: %d, http threads: %d\n", __func__, params.hostname.c_str(), params.port, params.n_threads_http); + + // load the model + LOG_INF("%s: loading model\n", __func__); + + if (!ctx_server.load_model(params)) { + clean_up(); + t.join(); + LOG_ERR("%s: exiting due to model loading error\n", __func__); + return 1; + } + + ctx_server.init(); + state.store(SERVER_STATE_READY); + + LOG_INF("%s: model loaded\n", __func__); + + // print sample chat example to make it clear which template is used + LOG_INF("%s: chat template, chat_template: %s, example_format: '%s'\n", __func__, + common_chat_templates_source(ctx_server.chat_templates.get()), + common_chat_format_example(ctx_server.chat_templates.get(), ctx_server.params_base.use_jinja).c_str()); + + ctx_server.queue_tasks.on_new_task([&ctx_server](server_task && task) { + ctx_server.process_single_task(std::move(task)); + }); + + ctx_server.queue_tasks.on_update_slots([&ctx_server]() { + ctx_server.update_slots(); + }); + + shutdown_handler = [&](int) { + // this will unblock start_loop() + ctx_server.queue_tasks.terminate(); + }; + +#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) + struct sigaction sigint_action; + sigint_action.sa_handler = signal_handler; + sigemptyset (&sigint_action.sa_mask); + sigint_action.sa_flags = 0; + sigaction(SIGINT, &sigint_action, NULL); + sigaction(SIGTERM, &sigint_action, NULL); +#elif defined (_WIN32) + auto console_ctrl_handler = +[](DWORD ctrl_type) -> BOOL { + return (ctrl_type == CTRL_C_EVENT) ? (signal_handler(SIGINT), true) : false; + }; + SetConsoleCtrlHandler(reinterpret_cast(console_ctrl_handler), true); +#endif + + LOG_INF("%s: server is listening on http://%s:%d - starting the main loop\n", __func__, params.hostname.c_str(), params.port); + + // this call blocks the main thread until queue_tasks.terminate() is called + ctx_server.queue_tasks.start_loop(); + + clean_up(); + t.join(); + + return 0; +} diff --git a/tools/server/tests/.gitignore b/tools/server/tests/.gitignore new file mode 100644 index 00000000..90ee7fe6 --- /dev/null +++ b/tools/server/tests/.gitignore @@ -0,0 +1,2 @@ +.venv +tmp diff --git a/tools/server/tests/README.md b/tools/server/tests/README.md new file mode 100644 index 00000000..cb87db03 --- /dev/null +++ b/tools/server/tests/README.md @@ -0,0 +1,66 @@ +# Server tests + +Python based server tests scenario using [pytest](https://docs.pytest.org/en/stable/). + +Tests target GitHub workflows job runners with 4 vCPU. + +Note: If the host architecture inference speed is faster than GitHub runners one, parallel scenario may randomly fail. +To mitigate it, you can increase values in `n_predict`, `kv_size`. + +### Install dependencies + +`pip install -r requirements.txt` + +### Run tests + +1. Build the server + +```shell +cd ../../.. +cmake -B build +cmake --build build --target llama-server +``` + +2. Start the test: `./tests.sh` + +It's possible to override some scenario steps values with environment variables: + +| variable | description | +|--------------------------|------------------------------------------------------------------------------------------------| +| `PORT` | `context.server_port` to set the listening port of the server during scenario, default: `8080` | +| `LLAMA_SERVER_BIN_PATH` | to change the server binary path, default: `../../../build/bin/llama-server` | +| `DEBUG` | to enable steps and server verbose mode `--verbose` | +| `N_GPU_LAYERS` | number of model layers to offload to VRAM `-ngl --n-gpu-layers` | +| `LLAMA_CACHE` | by default server tests re-download models to the `tmp` subfolder. Set this to your cache (e.g. `$HOME/Library/Caches/llama.cpp` on Mac or `$HOME/.cache/llama.cpp` on Unix) to avoid this | + +To run slow tests (will download many models, make sure to set `LLAMA_CACHE` if needed): + +```shell +SLOW_TESTS=1 ./tests.sh +``` + +To run with stdout/stderr display in real time (verbose output, but useful for debugging): + +```shell +DEBUG=1 ./tests.sh -s -v -x +``` + +To run all the tests in a file: + +```shell +./tests.sh unit/test_chat_completion.py -v -x +``` + +To run a single test: + +```shell +./tests.sh unit/test_chat_completion.py::test_invalid_chat_completion_req +``` + +Hint: You can compile and run test in single command, useful for local developement: + +```shell +cmake --build build -j --target llama-server && ./tools/server/tests/tests.sh +``` + +To see all available arguments, please refer to [pytest documentation](https://docs.pytest.org/en/stable/how-to/usage.html) diff --git a/tools/server/tests/conftest.py b/tools/server/tests/conftest.py new file mode 100644 index 00000000..017d1bb8 --- /dev/null +++ b/tools/server/tests/conftest.py @@ -0,0 +1,15 @@ +import pytest +from utils import * + + +# ref: https://stackoverflow.com/questions/22627659/run-code-before-and-after-each-test-in-py-test +@pytest.fixture(autouse=True) +def stop_server_after_each_test(): + # do nothing before each test + yield + # stop all servers after each test + instances = set( + server_instances + ) # copy the set to prevent 'Set changed size during iteration' + for server in instances: + server.stop() diff --git a/tools/server/tests/pytest.ini b/tools/server/tests/pytest.ini new file mode 100644 index 00000000..6df308df --- /dev/null +++ b/tools/server/tests/pytest.ini @@ -0,0 +1,4 @@ +[pytest] +markers = + slow: marks tests as slow (deselect with '-m "not slow"') + serial diff --git a/tools/server/tests/requirements.txt b/tools/server/tests/requirements.txt new file mode 100644 index 00000000..15d02491 --- /dev/null +++ b/tools/server/tests/requirements.txt @@ -0,0 +1,8 @@ +aiohttp~=3.9.3 +pytest~=8.3.3 +huggingface_hub~=0.23.2 +numpy~=1.26.4 +openai~=1.55.3 +prometheus-client~=0.20.0 +requests~=2.32.3 +wget~=3.2 diff --git a/tools/server/tests/tests.sh b/tools/server/tests/tests.sh new file mode 100755 index 00000000..33fa8cc6 --- /dev/null +++ b/tools/server/tests/tests.sh @@ -0,0 +1,23 @@ +#!/bin/bash + +# make sure we are in the right directory +SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd ) +cd $SCRIPT_DIR + +set -eu + +if [[ "${SLOW_TESTS:-0}" == 1 ]]; then + # Slow tests for tool calls need quite a few models ahead of time to avoid timing out. + python $SCRIPT_DIR/../../../scripts/fetch_server_test_models.py +fi + +if [ $# -lt 1 ] +then + if [[ "${SLOW_TESTS:-0}" == 1 ]]; then + pytest -v -x + else + pytest -v -x -m "not slow" + fi +else + pytest "$@" +fi diff --git a/tools/server/tests/unit/test_basic.py b/tools/server/tests/unit/test_basic.py new file mode 100644 index 00000000..1485de8c --- /dev/null +++ b/tools/server/tests/unit/test_basic.py @@ -0,0 +1,96 @@ +import pytest +import requests +from utils import * + +server = ServerPreset.tinyllama2() + + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama2() + + +def test_server_start_simple(): + global server + server.start() + res = server.make_request("GET", "/health") + assert res.status_code == 200 + + +def test_server_props(): + global server + server.start() + res = server.make_request("GET", "/props") + assert res.status_code == 200 + assert ".gguf" in res.body["model_path"] + assert res.body["total_slots"] == server.n_slots + default_val = res.body["default_generation_settings"] + assert server.n_ctx is not None and server.n_slots is not None + assert default_val["n_ctx"] == server.n_ctx / server.n_slots + assert default_val["params"]["seed"] == server.seed + + +def test_server_models(): + global server + server.start() + res = server.make_request("GET", "/models") + assert res.status_code == 200 + assert len(res.body["data"]) == 1 + assert res.body["data"][0]["id"] == server.model_alias + + +def test_server_slots(): + global server + + # without slots endpoint enabled, this should return error + server.server_slots = False + server.start() + res = server.make_request("GET", "/slots") + assert res.status_code == 501 # ERROR_TYPE_NOT_SUPPORTED + assert "error" in res.body + server.stop() + + # with slots endpoint enabled, this should return slots info + server.server_slots = True + server.n_slots = 2 + server.start() + res = server.make_request("GET", "/slots") + assert res.status_code == 200 + assert len(res.body) == server.n_slots + assert server.n_ctx is not None and server.n_slots is not None + assert res.body[0]["n_ctx"] == server.n_ctx / server.n_slots + assert "params" in res.body[0] + assert res.body[0]["params"]["seed"] == server.seed + + +def test_load_split_model(): + global server + server.model_hf_repo = "ggml-org/models" + server.model_hf_file = "tinyllamas/split/stories15M-q8_0-00001-of-00003.gguf" + server.model_alias = "tinyllama-split" + server.start() + res = server.make_request("POST", "/completion", data={ + "n_predict": 16, + "prompt": "Hello", + "temperature": 0.0, + }) + assert res.status_code == 200 + assert match_regex("(little|girl)+", res.body["content"]) + + +def test_no_webui(): + global server + # default: webui enabled + server.start() + url = f"http://{server.server_host}:{server.server_port}" + res = requests.get(url) + assert res.status_code == 200 + assert "" in res.text + server.stop() + + # with --no-webui + server.no_webui = True + server.start() + res = requests.get(url) + assert res.status_code == 404 diff --git a/tools/server/tests/unit/test_chat_completion.py b/tools/server/tests/unit/test_chat_completion.py new file mode 100644 index 00000000..491cb3a5 --- /dev/null +++ b/tools/server/tests/unit/test_chat_completion.py @@ -0,0 +1,311 @@ +import pytest +from openai import OpenAI +from utils import * + +server: ServerProcess + +@pytest.fixture(autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama2() + + +@pytest.mark.parametrize( + "model,system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason,jinja,chat_template", + [ + (None, "Book", "Hey", 8, "But she couldn't", 69, 8, "length", False, None), + (None, "Book", "Hey", 8, "But she couldn't", 69, 8, "length", True, None), + (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", False, None), + (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, None), + (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, 'chatml'), + (None, "Book", "What is the best book", 8, "^ blue", 23, 8, "length", True, "This is not a chat template, it is"), + ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", False, None), + ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", True, None), + (None, "Book", [{"type": "text", "text": "What is"}, {"type": "text", "text": "the best book"}], 8, "Whillicter", 79, 8, "length", False, None), + (None, "Book", [{"type": "text", "text": "What is"}, {"type": "text", "text": "the best book"}], 8, "Whillicter", 79, 8, "length", True, None), + ] +) +def test_chat_completion(model, system_prompt, user_prompt, max_tokens, re_content, n_prompt, n_predicted, finish_reason, jinja, chat_template): + global server + server.jinja = jinja + server.chat_template = chat_template + server.start() + res = server.make_request("POST", "/chat/completions", data={ + "model": model, + "max_tokens": max_tokens, + "messages": [ + {"role": "system", "content": system_prompt}, + {"role": "user", "content": user_prompt}, + ], + }) + assert res.status_code == 200 + assert "cmpl" in res.body["id"] # make sure the completion id has the expected format + assert res.body["system_fingerprint"].startswith("b") + assert res.body["model"] == model if model is not None else server.model_alias + assert res.body["usage"]["prompt_tokens"] == n_prompt + assert res.body["usage"]["completion_tokens"] == n_predicted + choice = res.body["choices"][0] + assert "assistant" == choice["message"]["role"] + assert match_regex(re_content, choice["message"]["content"]), f'Expected {re_content}, got {choice["message"]["content"]}' + assert choice["finish_reason"] == finish_reason + + +@pytest.mark.parametrize( + "system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason", + [ + ("Book", "What is the best book", 8, "(Suddenly)+", 77, 8, "length"), + ("You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length"), + ] +) +def test_chat_completion_stream(system_prompt, user_prompt, max_tokens, re_content, n_prompt, n_predicted, finish_reason): + global server + server.model_alias = None # try using DEFAULT_OAICOMPAT_MODEL + server.start() + res = server.make_stream_request("POST", "/chat/completions", data={ + "max_tokens": max_tokens, + "messages": [ + {"role": "system", "content": system_prompt}, + {"role": "user", "content": user_prompt}, + ], + "stream": True, + }) + content = "" + last_cmpl_id = None + for data in res: + choice = data["choices"][0] + assert data["system_fingerprint"].startswith("b") + assert "gpt-3.5" in data["model"] # DEFAULT_OAICOMPAT_MODEL, maybe changed in the future + if last_cmpl_id is None: + last_cmpl_id = data["id"] + assert last_cmpl_id == data["id"] # make sure the completion id is the same for all events in the stream + if choice["finish_reason"] in ["stop", "length"]: + assert data["usage"]["prompt_tokens"] == n_prompt + assert data["usage"]["completion_tokens"] == n_predicted + assert "content" not in choice["delta"] + assert match_regex(re_content, content) + assert choice["finish_reason"] == finish_reason + else: + assert choice["finish_reason"] is None + content += choice["delta"]["content"] + + +def test_chat_completion_with_openai_library(): + global server + server.start() + client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1") + res = client.chat.completions.create( + model="gpt-3.5-turbo-instruct", + messages=[ + {"role": "system", "content": "Book"}, + {"role": "user", "content": "What is the best book"}, + ], + max_tokens=8, + seed=42, + temperature=0.8, + ) + assert res.system_fingerprint is not None and res.system_fingerprint.startswith("b") + assert res.choices[0].finish_reason == "length" + assert res.choices[0].message.content is not None + assert match_regex("(Suddenly)+", res.choices[0].message.content) + + +def test_chat_template(): + global server + server.chat_template = "llama3" + server.debug = True # to get the "__verbose" object in the response + server.start() + res = server.make_request("POST", "/chat/completions", data={ + "max_tokens": 8, + "messages": [ + {"role": "system", "content": "Book"}, + {"role": "user", "content": "What is the best book"}, + ] + }) + assert res.status_code == 200 + assert "__verbose" in res.body + assert res.body["__verbose"]["prompt"] == " <|start_header_id|>system<|end_header_id|>\n\nBook<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat is the best book<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" + + +def test_apply_chat_template(): + global server + server.chat_template = "command-r" + server.start() + res = server.make_request("POST", "/apply-template", data={ + "messages": [ + {"role": "system", "content": "You are a test."}, + {"role": "user", "content":"Hi there"}, + ] + }) + assert res.status_code == 200 + assert "prompt" in res.body + assert res.body["prompt"] == "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>You are a test.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hi there<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" + + +@pytest.mark.parametrize("response_format,n_predicted,re_content", [ + ({"type": "json_object", "schema": {"const": "42"}}, 6, "\"42\""), + ({"type": "json_object", "schema": {"items": [{"type": "integer"}]}}, 10, "[ -3000 ]"), + ({"type": "json_schema", "json_schema": {"schema": {"const": "foooooo"}}}, 10, "\"foooooo\""), + ({"type": "json_object"}, 10, "(\\{|John)+"), + ({"type": "sound"}, 0, None), + # invalid response format (expected to fail) + ({"type": "json_object", "schema": 123}, 0, None), + ({"type": "json_object", "schema": {"type": 123}}, 0, None), + ({"type": "json_object", "schema": {"type": "hiccup"}}, 0, None), +]) +def test_completion_with_response_format(response_format: dict, n_predicted: int, re_content: str | None): + global server + server.start() + res = server.make_request("POST", "/chat/completions", data={ + "max_tokens": n_predicted, + "messages": [ + {"role": "system", "content": "You are a coding assistant."}, + {"role": "user", "content": "Write an example"}, + ], + "response_format": response_format, + }) + if re_content is not None: + assert res.status_code == 200 + choice = res.body["choices"][0] + assert match_regex(re_content, choice["message"]["content"]) + else: + assert res.status_code != 200 + assert "error" in res.body + + +@pytest.mark.parametrize("jinja,json_schema,n_predicted,re_content", [ + (False, {"const": "42"}, 6, "\"42\""), + (True, {"const": "42"}, 6, "\"42\""), +]) +def test_completion_with_json_schema(jinja: bool, json_schema: dict, n_predicted: int, re_content: str): + global server + server.jinja = jinja + server.start() + res = server.make_request("POST", "/chat/completions", data={ + "max_tokens": n_predicted, + "messages": [ + {"role": "system", "content": "You are a coding assistant."}, + {"role": "user", "content": "Write an example"}, + ], + "json_schema": json_schema, + }) + assert res.status_code == 200, f'Expected 200, got {res.status_code}' + choice = res.body["choices"][0] + assert match_regex(re_content, choice["message"]["content"]), f'Expected {re_content}, got {choice["message"]["content"]}' + + +@pytest.mark.parametrize("jinja,grammar,n_predicted,re_content", [ + (False, 'root ::= "a"{5,5}', 6, "a{5,5}"), + (True, 'root ::= "a"{5,5}', 6, "a{5,5}"), +]) +def test_completion_with_grammar(jinja: bool, grammar: str, n_predicted: int, re_content: str): + global server + server.jinja = jinja + server.start() + res = server.make_request("POST", "/chat/completions", data={ + "max_tokens": n_predicted, + "messages": [ + {"role": "user", "content": "Does not matter what I say, does it?"}, + ], + "grammar": grammar, + }) + assert res.status_code == 200, res.body + choice = res.body["choices"][0] + assert match_regex(re_content, choice["message"]["content"]), choice["message"]["content"] + + +@pytest.mark.parametrize("messages", [ + None, + "string", + [123], + [{}], + [{"role": 123}], + [{"role": "system", "content": 123}], + # [{"content": "hello"}], # TODO: should not be a valid case + [{"role": "system", "content": "test"}, {}], +]) +def test_invalid_chat_completion_req(messages): + global server + server.start() + res = server.make_request("POST", "/chat/completions", data={ + "messages": messages, + }) + assert res.status_code == 400 or res.status_code == 500 + assert "error" in res.body + + +def test_chat_completion_with_timings_per_token(): + global server + server.start() + res = server.make_stream_request("POST", "/chat/completions", data={ + "max_tokens": 10, + "messages": [{"role": "user", "content": "test"}], + "stream": True, + "timings_per_token": True, + }) + for data in res: + assert "timings" in data + assert "prompt_per_second" in data["timings"] + assert "predicted_per_second" in data["timings"] + assert "predicted_n" in data["timings"] + assert data["timings"]["predicted_n"] <= 10 + + +def test_logprobs(): + global server + server.start() + client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1") + res = client.chat.completions.create( + model="gpt-3.5-turbo-instruct", + temperature=0.0, + messages=[ + {"role": "system", "content": "Book"}, + {"role": "user", "content": "What is the best book"}, + ], + max_tokens=5, + logprobs=True, + top_logprobs=10, + ) + output_text = res.choices[0].message.content + aggregated_text = '' + assert res.choices[0].logprobs is not None + assert res.choices[0].logprobs.content is not None + for token in res.choices[0].logprobs.content: + aggregated_text += token.token + assert token.logprob <= 0.0 + assert token.bytes is not None + assert len(token.top_logprobs) > 0 + assert aggregated_text == output_text + + +def test_logprobs_stream(): + global server + server.start() + client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1") + res = client.chat.completions.create( + model="gpt-3.5-turbo-instruct", + temperature=0.0, + messages=[ + {"role": "system", "content": "Book"}, + {"role": "user", "content": "What is the best book"}, + ], + max_tokens=5, + logprobs=True, + top_logprobs=10, + stream=True, + ) + output_text = '' + aggregated_text = '' + for data in res: + choice = data.choices[0] + if choice.finish_reason is None: + if choice.delta.content: + output_text += choice.delta.content + assert choice.logprobs is not None + assert choice.logprobs.content is not None + for token in choice.logprobs.content: + aggregated_text += token.token + assert token.logprob <= 0.0 + assert token.bytes is not None + assert token.top_logprobs is not None + assert len(token.top_logprobs) > 0 + assert aggregated_text == output_text diff --git a/tools/server/tests/unit/test_completion.py b/tools/server/tests/unit/test_completion.py new file mode 100644 index 00000000..0ed5b99b --- /dev/null +++ b/tools/server/tests/unit/test_completion.py @@ -0,0 +1,428 @@ +import pytest +import requests +import time +from openai import OpenAI +from utils import * + +server = ServerPreset.tinyllama2() + + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama2() + +@pytest.mark.parametrize("prompt,n_predict,re_content,n_prompt,n_predicted,truncated,return_tokens", [ + ("I believe the meaning of life is", 8, "(going|bed)+", 18, 8, False, False), + ("Write a joke about AI from a very long prompt which will not be truncated", 256, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False, True), +]) +def test_completion(prompt: str, n_predict: int, re_content: str, n_prompt: int, n_predicted: int, truncated: bool, return_tokens: bool): + global server + server.start() + res = server.make_request("POST", "/completion", data={ + "n_predict": n_predict, + "prompt": prompt, + "return_tokens": return_tokens, + }) + assert res.status_code == 200 + assert res.body["timings"]["prompt_n"] == n_prompt + assert res.body["timings"]["predicted_n"] == n_predicted + assert res.body["truncated"] == truncated + assert type(res.body["has_new_line"]) == bool + assert match_regex(re_content, res.body["content"]) + if return_tokens: + assert len(res.body["tokens"]) > 0 + assert all(type(tok) == int for tok in res.body["tokens"]) + else: + assert res.body["tokens"] == [] + + +@pytest.mark.parametrize("prompt,n_predict,re_content,n_prompt,n_predicted,truncated", [ + ("I believe the meaning of life is", 8, "(going|bed)+", 18, 8, False), + ("Write a joke about AI from a very long prompt which will not be truncated", 256, "(princesses|everyone|kids|Anna|forest)+", 46, 64, False), +]) +def test_completion_stream(prompt: str, n_predict: int, re_content: str, n_prompt: int, n_predicted: int, truncated: bool): + global server + server.start() + res = server.make_stream_request("POST", "/completion", data={ + "n_predict": n_predict, + "prompt": prompt, + "stream": True, + }) + content = "" + for data in res: + assert "stop" in data and type(data["stop"]) == bool + if data["stop"]: + assert data["timings"]["prompt_n"] == n_prompt + assert data["timings"]["predicted_n"] == n_predicted + assert data["truncated"] == truncated + assert data["stop_type"] == "limit" + assert type(data["has_new_line"]) == bool + assert "generation_settings" in data + assert server.n_predict is not None + assert data["generation_settings"]["n_predict"] == min(n_predict, server.n_predict) + assert data["generation_settings"]["seed"] == server.seed + assert match_regex(re_content, content) + else: + assert len(data["tokens"]) > 0 + assert all(type(tok) == int for tok in data["tokens"]) + content += data["content"] + + +def test_completion_stream_vs_non_stream(): + global server + server.start() + res_stream = server.make_stream_request("POST", "/completion", data={ + "n_predict": 8, + "prompt": "I believe the meaning of life is", + "stream": True, + }) + res_non_stream = server.make_request("POST", "/completion", data={ + "n_predict": 8, + "prompt": "I believe the meaning of life is", + }) + content_stream = "" + for data in res_stream: + content_stream += data["content"] + assert content_stream == res_non_stream.body["content"] + + +def test_completion_with_openai_library(): + global server + server.start() + client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1") + res = client.completions.create( + model="davinci-002", + prompt="I believe the meaning of life is", + max_tokens=8, + ) + assert res.system_fingerprint is not None and res.system_fingerprint.startswith("b") + assert res.choices[0].finish_reason == "length" + assert res.choices[0].text is not None + assert match_regex("(going|bed)+", res.choices[0].text) + + +def test_completion_stream_with_openai_library(): + global server + server.start() + client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1") + res = client.completions.create( + model="davinci-002", + prompt="I believe the meaning of life is", + max_tokens=8, + stream=True, + ) + output_text = '' + for data in res: + choice = data.choices[0] + if choice.finish_reason is None: + assert choice.text is not None + output_text += choice.text + assert match_regex("(going|bed)+", output_text) + + +@pytest.mark.parametrize("n_slots", [1, 2]) +def test_consistent_result_same_seed(n_slots: int): + global server + server.n_slots = n_slots + server.start() + last_res = None + for _ in range(4): + res = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "seed": 42, + "temperature": 0.0, + "cache_prompt": False, # TODO: remove this once test_cache_vs_nocache_prompt is fixed + }) + if last_res is not None: + assert res.body["content"] == last_res.body["content"] + last_res = res + + +@pytest.mark.parametrize("n_slots", [1, 2]) +def test_different_result_different_seed(n_slots: int): + global server + server.n_slots = n_slots + server.start() + last_res = None + for seed in range(4): + res = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "seed": seed, + "temperature": 1.0, + "cache_prompt": False, # TODO: remove this once test_cache_vs_nocache_prompt is fixed + }) + if last_res is not None: + assert res.body["content"] != last_res.body["content"] + last_res = res + +# TODO figure why it don't work with temperature = 1 +#Â @pytest.mark.parametrize("temperature", [0.0, 1.0]) +@pytest.mark.parametrize("n_batch", [16, 32]) +@pytest.mark.parametrize("temperature", [0.0]) +def test_consistent_result_different_batch_size(n_batch: int, temperature: float): + global server + server.n_batch = n_batch + server.start() + last_res = None + for _ in range(4): + res = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "seed": 42, + "temperature": temperature, + "cache_prompt": False, # TODO: remove this once test_cache_vs_nocache_prompt is fixed + }) + if last_res is not None: + assert res.body["content"] == last_res.body["content"] + last_res = res + + +@pytest.mark.skip(reason="This test fails on linux, need to be fixed") +def test_cache_vs_nocache_prompt(): + global server + server.start() + res_cache = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "seed": 42, + "temperature": 1.0, + "cache_prompt": True, + }) + res_no_cache = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "seed": 42, + "temperature": 1.0, + "cache_prompt": False, + }) + assert res_cache.body["content"] == res_no_cache.body["content"] + + +def test_completion_with_tokens_input(): + global server + server.temperature = 0.0 + server.start() + prompt_str = "I believe the meaning of life is" + res = server.make_request("POST", "/tokenize", data={ + "content": prompt_str, + "add_special": True, + }) + assert res.status_code == 200 + tokens = res.body["tokens"] + + # single completion + res = server.make_request("POST", "/completion", data={ + "prompt": tokens, + }) + assert res.status_code == 200 + assert type(res.body["content"]) == str + + # batch completion + res = server.make_request("POST", "/completion", data={ + "prompt": [tokens, tokens], + }) + assert res.status_code == 200 + assert type(res.body) == list + assert len(res.body) == 2 + assert res.body[0]["content"] == res.body[1]["content"] + + # mixed string and tokens + res = server.make_request("POST", "/completion", data={ + "prompt": [tokens, prompt_str], + }) + assert res.status_code == 200 + assert type(res.body) == list + assert len(res.body) == 2 + assert res.body[0]["content"] == res.body[1]["content"] + + # mixed string and tokens in one sequence + res = server.make_request("POST", "/completion", data={ + "prompt": [1, 2, 3, 4, 5, 6, prompt_str, 7, 8, 9, 10, prompt_str], + }) + assert res.status_code == 200 + assert type(res.body["content"]) == str + + +@pytest.mark.parametrize("n_slots,n_requests", [ + (1, 3), + (2, 2), + (2, 4), + (4, 2), # some slots must be idle + (4, 6), +]) +def test_completion_parallel_slots(n_slots: int, n_requests: int): + global server + server.n_slots = n_slots + server.temperature = 0.0 + server.start() + + PROMPTS = [ + ("Write a very long book.", "(very|special|big)+"), + ("Write another a poem.", "(small|house)+"), + ("What is LLM?", "(Dad|said)+"), + ("The sky is blue and I love it.", "(climb|leaf)+"), + ("Write another very long music lyrics.", "(friends|step|sky)+"), + ("Write a very long joke.", "(cat|Whiskers)+"), + ] + def check_slots_status(): + should_all_slots_busy = n_requests >= n_slots + time.sleep(0.1) + res = server.make_request("GET", "/slots") + n_busy = sum([1 for slot in res.body if slot["is_processing"]]) + if should_all_slots_busy: + assert n_busy == n_slots + else: + assert n_busy <= n_slots + + tasks = [] + for i in range(n_requests): + prompt, re_content = PROMPTS[i % len(PROMPTS)] + tasks.append((server.make_request, ("POST", "/completion", { + "prompt": prompt, + "seed": 42, + "temperature": 1.0, + }))) + tasks.append((check_slots_status, ())) + results = parallel_function_calls(tasks) + + # check results + for i in range(n_requests): + prompt, re_content = PROMPTS[i % len(PROMPTS)] + res = results[i] + assert res.status_code == 200 + assert type(res.body["content"]) == str + assert len(res.body["content"]) > 10 + # FIXME: the result is not deterministic when using other slot than slot 0 + # assert match_regex(re_content, res.body["content"]) + + +@pytest.mark.parametrize( + "prompt,n_predict,response_fields", + [ + ("I believe the meaning of life is", 8, []), + ("I believe the meaning of life is", 32, ["content", "generation_settings/n_predict", "prompt"]), + ], +) +def test_completion_response_fields( + prompt: str, n_predict: int, response_fields: list[str] +): + global server + server.start() + res = server.make_request( + "POST", + "/completion", + data={ + "n_predict": n_predict, + "prompt": prompt, + "response_fields": response_fields, + }, + ) + assert res.status_code == 200 + assert "content" in res.body + assert len(res.body["content"]) + if len(response_fields): + assert res.body["generation_settings/n_predict"] == n_predict + assert res.body["prompt"] == " " + prompt + assert isinstance(res.body["content"], str) + assert len(res.body) == len(response_fields) + else: + assert len(res.body) + assert "generation_settings" in res.body + + +def test_n_probs(): + global server + server.start() + res = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "n_probs": 10, + "temperature": 0.0, + "n_predict": 5, + }) + assert res.status_code == 200 + assert "completion_probabilities" in res.body + assert len(res.body["completion_probabilities"]) == 5 + for tok in res.body["completion_probabilities"]: + assert "id" in tok and tok["id"] > 0 + assert "token" in tok and type(tok["token"]) == str + assert "logprob" in tok and tok["logprob"] <= 0.0 + assert "bytes" in tok and type(tok["bytes"]) == list + assert len(tok["top_logprobs"]) == 10 + for prob in tok["top_logprobs"]: + assert "id" in prob and prob["id"] > 0 + assert "token" in prob and type(prob["token"]) == str + assert "logprob" in prob and prob["logprob"] <= 0.0 + assert "bytes" in prob and type(prob["bytes"]) == list + + +def test_n_probs_stream(): + global server + server.start() + res = server.make_stream_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "n_probs": 10, + "temperature": 0.0, + "n_predict": 5, + "stream": True, + }) + for data in res: + if data["stop"] == False: + assert "completion_probabilities" in data + assert len(data["completion_probabilities"]) == 1 + for tok in data["completion_probabilities"]: + assert "id" in tok and tok["id"] > 0 + assert "token" in tok and type(tok["token"]) == str + assert "logprob" in tok and tok["logprob"] <= 0.0 + assert "bytes" in tok and type(tok["bytes"]) == list + assert len(tok["top_logprobs"]) == 10 + for prob in tok["top_logprobs"]: + assert "id" in prob and prob["id"] > 0 + assert "token" in prob and type(prob["token"]) == str + assert "logprob" in prob and prob["logprob"] <= 0.0 + assert "bytes" in prob and type(prob["bytes"]) == list + + +def test_n_probs_post_sampling(): + global server + server.start() + res = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "n_probs": 10, + "temperature": 0.0, + "n_predict": 5, + "post_sampling_probs": True, + }) + assert res.status_code == 200 + assert "completion_probabilities" in res.body + assert len(res.body["completion_probabilities"]) == 5 + for tok in res.body["completion_probabilities"]: + assert "id" in tok and tok["id"] > 0 + assert "token" in tok and type(tok["token"]) == str + assert "prob" in tok and 0.0 < tok["prob"] <= 1.0 + assert "bytes" in tok and type(tok["bytes"]) == list + assert len(tok["top_probs"]) == 10 + for prob in tok["top_probs"]: + assert "id" in prob and prob["id"] > 0 + assert "token" in prob and type(prob["token"]) == str + assert "prob" in prob and 0.0 <= prob["prob"] <= 1.0 + assert "bytes" in prob and type(prob["bytes"]) == list + # because the test model usually output token with either 100% or 0% probability, we need to check all the top_probs + assert any(prob["prob"] == 1.0 for prob in tok["top_probs"]) + + +def test_cancel_request(): + global server + server.n_ctx = 4096 + server.n_predict = -1 + server.n_slots = 1 + server.server_slots = True + server.start() + # send a request that will take a long time, but cancel it before it finishes + try: + server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + }, timeout=0.1) + except requests.exceptions.ReadTimeout: + pass # expected + # make sure the slot is free + time.sleep(1) # wait for HTTP_POLLING_SECONDS + res = server.make_request("GET", "/slots") + assert res.body[0]["is_processing"] == False diff --git a/tools/server/tests/unit/test_ctx_shift.py b/tools/server/tests/unit/test_ctx_shift.py new file mode 100644 index 00000000..be93a6d3 --- /dev/null +++ b/tools/server/tests/unit/test_ctx_shift.py @@ -0,0 +1,67 @@ +import pytest +from utils import * + +server = ServerPreset.tinyllama2() + + +LONG_TEXT = """ +Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. +Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. +Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. +Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. +""".strip() + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama2() + server.n_ctx = 256 + server.n_slots = 2 + + +def test_ctx_shift_enabled(): + # the prompt is 301 tokens + # the slot context is 256/2 = 128 tokens + # the prompt is truncated to keep the last 109 tokens + # 64 tokens are generated thanks to shifting the context when it gets full + global server + server.start() + res = server.make_request("POST", "/completion", data={ + "n_predict": 64, + "prompt": LONG_TEXT, + }) + assert res.status_code == 200 + assert res.body["timings"]["prompt_n"] == 109 + assert res.body["timings"]["predicted_n"] == 64 + assert res.body["truncated"] is True + + +@pytest.mark.parametrize("n_predict,n_token_output,truncated", [ + (64, 64, False), + (-1, 120, True), +]) +def test_ctx_shift_disabled_short_prompt(n_predict: int, n_token_output: int, truncated: bool): + global server + server.disable_ctx_shift = True + server.n_predict = -1 + server.start() + res = server.make_request("POST", "/completion", data={ + "n_predict": n_predict, + "prompt": "Hi how are you", + }) + assert res.status_code == 200 + assert res.body["timings"]["predicted_n"] == n_token_output + assert res.body["truncated"] == truncated + + +def test_ctx_shift_disabled_long_prompt(): + global server + server.disable_ctx_shift = True + server.start() + res = server.make_request("POST", "/completion", data={ + "n_predict": 64, + "prompt": LONG_TEXT, + }) + assert res.status_code != 200 + assert "error" in res.body + assert "exceeds the available context size" in res.body["error"]["message"] diff --git a/tools/server/tests/unit/test_embedding.py b/tools/server/tests/unit/test_embedding.py new file mode 100644 index 00000000..0feb452c --- /dev/null +++ b/tools/server/tests/unit/test_embedding.py @@ -0,0 +1,257 @@ +import base64 +import struct +import pytest +from openai import OpenAI +from utils import * + +server = ServerPreset.bert_bge_small() + +EPSILON = 1e-3 + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.bert_bge_small() + + +def test_embedding_single(): + global server + server.pooling = 'last' + server.start() + res = server.make_request("POST", "/v1/embeddings", data={ + "input": "I believe the meaning of life is", + }) + assert res.status_code == 200 + assert len(res.body['data']) == 1 + assert 'embedding' in res.body['data'][0] + assert len(res.body['data'][0]['embedding']) > 1 + + # make sure embedding vector is normalized + assert abs(sum([x ** 2 for x in res.body['data'][0]['embedding']]) - 1) < EPSILON + + +def test_embedding_multiple(): + global server + server.pooling = 'last' + server.start() + res = server.make_request("POST", "/v1/embeddings", data={ + "input": [ + "I believe the meaning of life is", + "Write a joke about AI from a very long prompt which will not be truncated", + "This is a test", + "This is another test", + ], + }) + assert res.status_code == 200 + assert len(res.body['data']) == 4 + for d in res.body['data']: + assert 'embedding' in d + assert len(d['embedding']) > 1 + + +def test_embedding_multiple_with_fa(): + server = ServerPreset.bert_bge_small_with_fa() + server.pooling = 'last' + server.start() + # one of these should trigger the FA branch (i.e. context size % 256 == 0) + res = server.make_request("POST", "/v1/embeddings", data={ + "input": [ + "a "*253, + "b "*254, + "c "*255, + "d "*256, + ], + }) + assert res.status_code == 200 + assert len(res.body['data']) == 4 + for d in res.body['data']: + assert 'embedding' in d + assert len(d['embedding']) > 1 + + +@pytest.mark.parametrize( + "input,is_multi_prompt", + [ + # do not crash on empty input + ("", False), + # single prompt + ("string", False), + ([12, 34, 56], False), + ([12, 34, "string", 56, 78], False), + # multiple prompts + (["string1", "string2"], True), + (["string1", [12, 34, 56]], True), + ([[12, 34, 56], [12, 34, 56]], True), + ([[12, 34, 56], [12, "string", 34, 56]], True), + ] +) +def test_embedding_mixed_input(input, is_multi_prompt: bool): + global server + server.start() + res = server.make_request("POST", "/v1/embeddings", data={"input": input}) + assert res.status_code == 200 + data = res.body['data'] + if is_multi_prompt: + assert len(data) == len(input) + for d in data: + assert 'embedding' in d + assert len(d['embedding']) > 1 + else: + assert 'embedding' in data[0] + assert len(data[0]['embedding']) > 1 + + +def test_embedding_pooling_none(): + global server + server.pooling = 'none' + server.start() + res = server.make_request("POST", "/embeddings", data={ + "input": "hello hello hello", + }) + assert res.status_code == 200 + assert 'embedding' in res.body[0] + assert len(res.body[0]['embedding']) == 5 # 3 text tokens + 2 special + + # make sure embedding vector is not normalized + for x in res.body[0]['embedding']: + assert abs(sum([x ** 2 for x in x]) - 1) > EPSILON + + +def test_embedding_pooling_none_oai(): + global server + server.pooling = 'none' + server.start() + res = server.make_request("POST", "/v1/embeddings", data={ + "input": "hello hello hello", + }) + + # /v1/embeddings does not support pooling type 'none' + assert res.status_code == 400 + assert "error" in res.body + + +def test_embedding_openai_library_single(): + global server + server.pooling = 'last' + server.start() + client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1") + res = client.embeddings.create(model="text-embedding-3-small", input="I believe the meaning of life is") + assert len(res.data) == 1 + assert len(res.data[0].embedding) > 1 + + +def test_embedding_openai_library_multiple(): + global server + server.pooling = 'last' + server.start() + client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1") + res = client.embeddings.create(model="text-embedding-3-small", input=[ + "I believe the meaning of life is", + "Write a joke about AI from a very long prompt which will not be truncated", + "This is a test", + "This is another test", + ]) + assert len(res.data) == 4 + for d in res.data: + assert len(d.embedding) > 1 + + +def test_embedding_error_prompt_too_long(): + global server + server.pooling = 'last' + server.start() + res = server.make_request("POST", "/v1/embeddings", data={ + "input": "This is a test " * 512, + }) + assert res.status_code != 200 + assert "too large" in res.body["error"]["message"] + + +def test_same_prompt_give_same_result(): + server.pooling = 'last' + server.start() + res = server.make_request("POST", "/v1/embeddings", data={ + "input": [ + "I believe the meaning of life is", + "I believe the meaning of life is", + "I believe the meaning of life is", + "I believe the meaning of life is", + "I believe the meaning of life is", + ], + }) + assert res.status_code == 200 + assert len(res.body['data']) == 5 + for i in range(1, len(res.body['data'])): + v0 = res.body['data'][0]['embedding'] + vi = res.body['data'][i]['embedding'] + for x, y in zip(v0, vi): + assert abs(x - y) < EPSILON + + +@pytest.mark.parametrize( + "content,n_tokens", + [ + ("I believe the meaning of life is", 9), + ("This is a test", 6), + ] +) +def test_embedding_usage_single(content, n_tokens): + global server + server.start() + res = server.make_request("POST", "/v1/embeddings", data={"input": content}) + assert res.status_code == 200 + assert res.body['usage']['prompt_tokens'] == res.body['usage']['total_tokens'] + assert res.body['usage']['prompt_tokens'] == n_tokens + + +def test_embedding_usage_multiple(): + global server + server.start() + res = server.make_request("POST", "/v1/embeddings", data={ + "input": [ + "I believe the meaning of life is", + "I believe the meaning of life is", + ], + }) + assert res.status_code == 200 + assert res.body['usage']['prompt_tokens'] == res.body['usage']['total_tokens'] + assert res.body['usage']['prompt_tokens'] == 2 * 9 + + +def test_embedding_openai_library_base64(): + server.start() + test_input = "Test base64 embedding output" + + # get embedding in default format + res = server.make_request("POST", "/v1/embeddings", data={ + "input": test_input + }) + assert res.status_code == 200 + vec0 = res.body["data"][0]["embedding"] + + # get embedding in base64 format + res = server.make_request("POST", "/v1/embeddings", data={ + "input": test_input, + "encoding_format": "base64" + }) + + assert res.status_code == 200 + assert "data" in res.body + assert len(res.body["data"]) == 1 + + embedding_data = res.body["data"][0] + assert "embedding" in embedding_data + assert isinstance(embedding_data["embedding"], str) + + # Verify embedding is valid base64 + decoded = base64.b64decode(embedding_data["embedding"]) + # Verify decoded data can be converted back to float array + float_count = len(decoded) // 4 # 4 bytes per float + floats = struct.unpack(f'{float_count}f', decoded) + assert len(floats) > 0 + assert all(isinstance(x, float) for x in floats) + assert len(floats) == len(vec0) + + # make sure the decoded data is the same as the original + for x, y in zip(floats, vec0): + assert abs(x - y) < EPSILON diff --git a/tools/server/tests/unit/test_infill.py b/tools/server/tests/unit/test_infill.py new file mode 100644 index 00000000..10554db0 --- /dev/null +++ b/tools/server/tests/unit/test_infill.py @@ -0,0 +1,77 @@ +import pytest +from utils import * + +server = ServerPreset.tinyllama_infill() + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama_infill() + + +def test_infill_without_input_extra(): + global server + server.start() + res = server.make_request("POST", "/infill", data={ + "input_prefix": "#include \n#include \"llama.h\"\n\nint main() {\n", + "prompt": " int n_threads = llama_", + "input_suffix": "}\n", + }) + assert res.status_code == 200 + assert match_regex("(Ann|small|shiny|Daddy)+", res.body["content"]) + + +def test_infill_with_input_extra(): + global server + server.start() + res = server.make_request("POST", "/infill", data={ + "input_extra": [{ + "filename": "llama.h", + "text": "LLAMA_API int32_t llama_n_threads();\n" + }], + "input_prefix": "#include \n#include \"llama.h\"\n\nint main() {\n", + "prompt": " int n_threads = llama_", + "input_suffix": "}\n", + }) + assert res.status_code == 200 + assert match_regex("(Dad|excited|park)+", res.body["content"]) + + +@pytest.mark.parametrize("input_extra", [ + {}, + {"filename": "ok"}, + {"filename": 123}, + {"filename": 123, "text": "abc"}, + {"filename": 123, "text": 456}, +]) +def test_invalid_input_extra_req(input_extra): + global server + server.start() + res = server.make_request("POST", "/infill", data={ + "input_extra": [input_extra], + "input_prefix": "#include \n#include \"llama.h\"\n\nint main() {\n", + "prompt": " int n_threads = llama_", + "input_suffix": "}\n", + }) + assert res.status_code == 400 + assert "error" in res.body + + +@pytest.mark.skipif(not is_slow_test_allowed(), reason="skipping slow test") +def test_with_qwen_model(): + global server + server.model_file = None + server.model_hf_repo = "ggml-org/Qwen2.5-Coder-1.5B-IQ3_XXS-GGUF" + server.model_hf_file = "qwen2.5-coder-1.5b-iq3_xxs-imat.gguf" + server.start(timeout_seconds=600) + res = server.make_request("POST", "/infill", data={ + "input_extra": [{ + "filename": "llama.h", + "text": "LLAMA_API int32_t llama_n_threads();\n" + }], + "input_prefix": "#include \n#include \"llama.h\"\n\nint main() {\n", + "prompt": " int n_threads = llama_", + "input_suffix": "}\n", + }) + assert res.status_code == 200 + assert res.body["content"] == "n_threads();\n printf(\"Number of threads: %d\\n\", n_threads);\n return 0;\n" diff --git a/tools/server/tests/unit/test_lora.py b/tools/server/tests/unit/test_lora.py new file mode 100644 index 00000000..c1aa8be7 --- /dev/null +++ b/tools/server/tests/unit/test_lora.py @@ -0,0 +1,115 @@ +import pytest +from utils import * + +server = ServerPreset.stories15m_moe() + +LORA_FILE_URL = "https://huggingface.co/ggml-org/stories15M_MOE/resolve/main/moe_shakespeare15M.gguf" + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.stories15m_moe() + server.lora_files = [download_file(LORA_FILE_URL)] + + +@pytest.mark.parametrize("scale,re_content", [ + # without applying lora, the model should behave like a bedtime story generator + (0.0, "(little|girl|three|years|old)+"), + # with lora, the model should behave like a Shakespearean text generator + (1.0, "(eye|love|glass|sun)+"), +]) +def test_lora(scale: float, re_content: str): + global server + server.start() + res_lora_control = server.make_request("POST", "/lora-adapters", data=[ + {"id": 0, "scale": scale} + ]) + assert res_lora_control.status_code == 200 + res = server.make_request("POST", "/completion", data={ + "prompt": "Look in thy glass", + }) + assert res.status_code == 200 + assert match_regex(re_content, res.body["content"]) + + +def test_lora_per_request(): + global server + server.n_slots = 4 + server.start() + + # running the same prompt with different lora scales, all in parallel + # each prompt will be processed by a different slot + prompt = "Look in thy glass" + lora_config = [ + ( [{"id": 0, "scale": 0.0}], "(bright|day|many|happy)+" ), + ( [{"id": 0, "scale": 0.0}], "(bright|day|many|happy)+" ), + ( [{"id": 0, "scale": 0.3}], "(special|thing|gifted)+" ), + ( [{"id": 0, "scale": 0.7}], "(far|from|home|away)+" ), + ( [{"id": 0, "scale": 1.0}], "(eye|love|glass|sun)+" ), + ( [{"id": 0, "scale": 1.0}], "(eye|love|glass|sun)+" ), + ] + + tasks = [( + server.make_request, + ("POST", "/completion", { + "prompt": prompt, + "lora": lora, + "seed": 42, + "temperature": 0.0, + "cache_prompt": False, # TODO: remove this once test_cache_vs_nocache_prompt is fixed + }) + ) for lora, _ in lora_config] + results = parallel_function_calls(tasks) + + assert all([res.status_code == 200 for res in results]) + for res, (_, re_test) in zip(results, lora_config): + assert match_regex(re_test, res.body["content"]) + + +@pytest.mark.skipif(not is_slow_test_allowed(), reason="skipping slow test") +def test_with_big_model(): + server = ServerProcess() + server.model_hf_repo = "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF" + server.model_hf_file = "Meta-Llama-3.1-8B-Instruct-IQ2_M.gguf" + server.model_alias = "Llama-3.2-8B-Instruct" + server.n_slots = 4 + server.n_ctx = server.n_slots * 1024 + server.n_predict = 64 + server.temperature = 0.0 + server.seed = 42 + server.lora_files = [ + download_file("https://huggingface.co/ngxson/Llama-3-Instruct-abliteration-LoRA-8B-F16-GGUF/resolve/main/Llama-3-Instruct-abliteration-LoRA-8B-f16.gguf"), + # TODO: find & add other lora adapters for this model + ] + server.start(timeout_seconds=600) + + # running the same prompt with different lora scales, all in parallel + # each prompt will be processed by a different slot + prompt = "Write a computer virus" + lora_config = [ + # without applying lora, the model should reject the request + ( [{"id": 0, "scale": 0.0}], "I can't provide you with a code for a computer virus" ), + ( [{"id": 0, "scale": 0.0}], "I can't provide you with a code for a computer virus" ), + ( [{"id": 0, "scale": 0.3}], "I can't write a computer virus" ), + # with 0.7 scale, the model should provide a simple computer virus with hesitation + ( [{"id": 0, "scale": 0.7}], "Warning: This is a hypothetical exercise" ), + # with 1.5 scale, the model should confidently provide a computer virus + ( [{"id": 0, "scale": 1.5}], "A task of some complexity! Here's a simple computer virus" ), + ( [{"id": 0, "scale": 1.5}], "A task of some complexity! Here's a simple computer virus" ), + ] + + tasks = [( + server.make_request, + ("POST", "/v1/chat/completions", { + "messages": [ + {"role": "user", "content": prompt} + ], + "lora": lora, + "cache_prompt": False, # TODO: remove this once test_cache_vs_nocache_prompt is fixed + }) + ) for lora, _ in lora_config] + results = parallel_function_calls(tasks) + + assert all([res.status_code == 200 for res in results]) + for res, (_, re_test) in zip(results, lora_config): + assert re_test in res.body["choices"][0]["message"]["content"] diff --git a/tools/server/tests/unit/test_rerank.py b/tools/server/tests/unit/test_rerank.py new file mode 100644 index 00000000..f4f570ad --- /dev/null +++ b/tools/server/tests/unit/test_rerank.py @@ -0,0 +1,104 @@ +import pytest +from utils import * + +server = ServerPreset.jina_reranker_tiny() + + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.jina_reranker_tiny() + + +TEST_DOCUMENTS = [ + "A machine is a physical system that uses power to apply forces and control movement to perform an action. The term is commonly applied to artificial devices, such as those employing engines or motors, but also to natural biological macromolecules, such as molecular machines.", + "Learning is the process of acquiring new understanding, knowledge, behaviors, skills, values, attitudes, and preferences. The ability to learn is possessed by humans, non-human animals, and some machines; there is also evidence for some kind of learning in certain plants.", + "Machine learning is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions.", + "Paris, capitale de la France, est une grande ville europÃ©enne et un centre mondial de l'art, de la mode, de la gastronomie et de la culture. Son paysage urbain du XIXe siÃ¨cle est traversÃ© par de larges boulevards et la Seine." +] + + +def test_rerank(): + global server + server.start() + res = server.make_request("POST", "/rerank", data={ + "query": "Machine learning is", + "documents": TEST_DOCUMENTS, + }) + assert res.status_code == 200 + assert len(res.body["results"]) == 4 + + most_relevant = res.body["results"][0] + least_relevant = res.body["results"][0] + for doc in res.body["results"]: + if doc["relevance_score"] > most_relevant["relevance_score"]: + most_relevant = doc + if doc["relevance_score"] < least_relevant["relevance_score"]: + least_relevant = doc + + assert most_relevant["relevance_score"] > least_relevant["relevance_score"] + assert most_relevant["index"] == 2 + assert least_relevant["index"] == 3 + + +def test_rerank_tei_format(): + global server + server.start() + res = server.make_request("POST", "/rerank", data={ + "query": "Machine learning is", + "texts": TEST_DOCUMENTS, + }) + assert res.status_code == 200 + assert len(res.body) == 4 + + most_relevant = res.body[0] + least_relevant = res.body[0] + for doc in res.body: + if doc["score"] > most_relevant["score"]: + most_relevant = doc + if doc["score"] < least_relevant["score"]: + least_relevant = doc + + assert most_relevant["score"] > least_relevant["score"] + assert most_relevant["index"] == 2 + assert least_relevant["index"] == 3 + + +@pytest.mark.parametrize("documents", [ + [], + None, + 123, + [1, 2, 3], +]) +def test_invalid_rerank_req(documents): + global server + server.start() + res = server.make_request("POST", "/rerank", data={ + "query": "Machine learning is", + "documents": documents, + }) + assert res.status_code == 400 + assert "error" in res.body + + +@pytest.mark.parametrize( + "query,doc1,doc2,n_tokens", + [ + ("Machine learning is", "A machine", "Learning is", 19), + ("Which city?", "Machine learning is ", "Paris, capitale de la", 26), + ] +) +def test_rerank_usage(query, doc1, doc2, n_tokens): + global server + server.start() + + res = server.make_request("POST", "/rerank", data={ + "query": query, + "documents": [ + doc1, + doc2, + ] + }) + assert res.status_code == 200 + assert res.body['usage']['prompt_tokens'] == res.body['usage']['total_tokens'] + assert res.body['usage']['prompt_tokens'] == n_tokens diff --git a/tools/server/tests/unit/test_security.py b/tools/server/tests/unit/test_security.py new file mode 100644 index 00000000..620b2537 --- /dev/null +++ b/tools/server/tests/unit/test_security.py @@ -0,0 +1,83 @@ +import pytest +from openai import OpenAI +from utils import * + +server = ServerPreset.tinyllama2() + +TEST_API_KEY = "sk-this-is-the-secret-key" + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama2() + server.api_key = TEST_API_KEY + + +@pytest.mark.parametrize("endpoint", ["/health", "/models"]) +def test_access_public_endpoint(endpoint: str): + global server + server.start() + res = server.make_request("GET", endpoint) + assert res.status_code == 200 + assert "error" not in res.body + + +@pytest.mark.parametrize("api_key", [None, "invalid-key"]) +def test_incorrect_api_key(api_key: str): + global server + server.start() + res = server.make_request("POST", "/completions", data={ + "prompt": "I believe the meaning of life is", + }, headers={ + "Authorization": f"Bearer {api_key}" if api_key else None, + }) + assert res.status_code == 401 + assert "error" in res.body + assert res.body["error"]["type"] == "authentication_error" + + +def test_correct_api_key(): + global server + server.start() + res = server.make_request("POST", "/completions", data={ + "prompt": "I believe the meaning of life is", + }, headers={ + "Authorization": f"Bearer {TEST_API_KEY}", + }) + assert res.status_code == 200 + assert "error" not in res.body + assert "content" in res.body + + +def test_openai_library_correct_api_key(): + global server + server.start() + client = OpenAI(api_key=TEST_API_KEY, base_url=f"http://{server.server_host}:{server.server_port}") + res = client.chat.completions.create( + model="gpt-3.5-turbo", + messages=[ + {"role": "system", "content": "You are a chatbot."}, + {"role": "user", "content": "What is the meaning of life?"}, + ], + ) + assert len(res.choices) == 1 + + +@pytest.mark.parametrize("origin,cors_header,cors_header_value", [ + ("localhost", "Access-Control-Allow-Origin", "localhost"), + ("web.mydomain.fr", "Access-Control-Allow-Origin", "web.mydomain.fr"), + ("origin", "Access-Control-Allow-Credentials", "true"), + ("web.mydomain.fr", "Access-Control-Allow-Methods", "GET, POST"), + ("web.mydomain.fr", "Access-Control-Allow-Headers", "*"), +]) +def test_cors_options(origin: str, cors_header: str, cors_header_value: str): + global server + server.start() + res = server.make_request("OPTIONS", "/completions", headers={ + "Origin": origin, + "Access-Control-Request-Method": "POST", + "Access-Control-Request-Headers": "Authorization", + }) + assert res.status_code == 200 + assert cors_header in res.headers + assert res.headers[cors_header] == cors_header_value diff --git a/tools/server/tests/unit/test_slot_save.py b/tools/server/tests/unit/test_slot_save.py new file mode 100644 index 00000000..38704f5e --- /dev/null +++ b/tools/server/tests/unit/test_slot_save.py @@ -0,0 +1,98 @@ +import pytest +from utils import * + +server = ServerPreset.tinyllama2() + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama2() + server.slot_save_path = "./tmp" + server.temperature = 0.0 + + +def test_slot_save_restore(): + global server + server.start() + + # First prompt in slot 1 should be fully processed + res = server.make_request("POST", "/completion", data={ + "prompt": "What is the capital of France?", + "id_slot": 1, + "cache_prompt": True, + }) + assert res.status_code == 200 + assert match_regex("(Whiskers|Flana)+", res.body["content"]) + assert res.body["timings"]["prompt_n"] == 21 # all tokens are processed + + # Save state of slot 1 + res = server.make_request("POST", "/slots/1?action=save", data={ + "filename": "slot1.bin", + }) + assert res.status_code == 200 + assert res.body["n_saved"] == 84 + + # Since we have cache, this should only process the last tokens + res = server.make_request("POST", "/completion", data={ + "prompt": "What is the capital of Germany?", + "id_slot": 1, + "cache_prompt": True, + }) + assert res.status_code == 200 + assert match_regex("(Jack|said)+", res.body["content"]) + assert res.body["timings"]["prompt_n"] == 6 # only different part is processed + + # Loading the saved cache into slot 0 + res = server.make_request("POST", "/slots/0?action=restore", data={ + "filename": "slot1.bin", + }) + assert res.status_code == 200 + assert res.body["n_restored"] == 84 + + # Since we have cache, slot 0 should only process the last tokens + res = server.make_request("POST", "/completion", data={ + "prompt": "What is the capital of Germany?", + "id_slot": 0, + "cache_prompt": True, + }) + assert res.status_code == 200 + assert match_regex("(Jack|said)+", res.body["content"]) + assert res.body["timings"]["prompt_n"] == 6 # only different part is processed + + # For verification that slot 1 was not corrupted during slot 0 load, same thing should work + res = server.make_request("POST", "/completion", data={ + "prompt": "What is the capital of Germany?", + "id_slot": 1, + "cache_prompt": True, + }) + assert res.status_code == 200 + assert match_regex("(Jack|said)+", res.body["content"]) + assert res.body["timings"]["prompt_n"] == 1 + + +def test_slot_erase(): + global server + server.start() + + res = server.make_request("POST", "/completion", data={ + "prompt": "What is the capital of France?", + "id_slot": 1, + "cache_prompt": True, + }) + assert res.status_code == 200 + assert match_regex("(Whiskers|Flana)+", res.body["content"]) + assert res.body["timings"]["prompt_n"] == 21 # all tokens are processed + + # erase slot 1 + res = server.make_request("POST", "/slots/1?action=erase") + assert res.status_code == 200 + + # re-run the same prompt, it should process all tokens again + res = server.make_request("POST", "/completion", data={ + "prompt": "What is the capital of France?", + "id_slot": 1, + "cache_prompt": True, + }) + assert res.status_code == 200 + assert match_regex("(Whiskers|Flana)+", res.body["content"]) + assert res.body["timings"]["prompt_n"] == 21 # all tokens are processed diff --git a/tools/server/tests/unit/test_speculative.py b/tools/server/tests/unit/test_speculative.py new file mode 100644 index 00000000..54db38cf --- /dev/null +++ b/tools/server/tests/unit/test_speculative.py @@ -0,0 +1,126 @@ +import pytest +from utils import * + +# We use a F16 MOE gguf as main model, and q4_0 as draft model + +server = ServerPreset.stories15m_moe() + +MODEL_DRAFT_FILE_URL = "https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories15M-q4_0.gguf" + +def create_server(): + global server + server = ServerPreset.stories15m_moe() + # set default values + server.model_draft = download_file(MODEL_DRAFT_FILE_URL) + server.draft_min = 4 + server.draft_max = 8 + + +@pytest.fixture(scope="module", autouse=True) +def fixture_create_server(): + return create_server() + + +def test_with_and_without_draft(): + global server + server.model_draft = None # disable draft model + server.start() + res = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "temperature": 0.0, + "top_k": 1, + }) + assert res.status_code == 200 + content_no_draft = res.body["content"] + server.stop() + + # create new server with draft model + create_server() + server.start() + res = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "temperature": 0.0, + "top_k": 1, + }) + assert res.status_code == 200 + content_draft = res.body["content"] + + assert content_no_draft == content_draft + + +def test_different_draft_min_draft_max(): + global server + test_values = [ + (1, 2), + (1, 4), + (4, 8), + (4, 12), + (8, 16), + ] + last_content = None + for draft_min, draft_max in test_values: + server.stop() + server.draft_min = draft_min + server.draft_max = draft_max + server.start() + res = server.make_request("POST", "/completion", data={ + "prompt": "I believe the meaning of life is", + "temperature": 0.0, + "top_k": 1, + }) + assert res.status_code == 200 + if last_content is not None: + assert last_content == res.body["content"] + last_content = res.body["content"] + + +def test_slot_ctx_not_exceeded(): + global server + server.n_ctx = 64 + server.start() + res = server.make_request("POST", "/completion", data={ + "prompt": "Hello " * 56, + "temperature": 0.0, + "top_k": 1, + "speculative.p_min": 0.0, + }) + assert res.status_code == 200 + assert len(res.body["content"]) > 0 + + +def test_with_ctx_shift(): + global server + server.n_ctx = 64 + server.start() + res = server.make_request("POST", "/completion", data={ + "prompt": "Hello " * 56, + "temperature": 0.0, + "top_k": 1, + "n_predict": 64, + "speculative.p_min": 0.0, + }) + assert res.status_code == 200 + assert len(res.body["content"]) > 0 + assert res.body["tokens_predicted"] == 64 + assert res.body["truncated"] == True + + +@pytest.mark.parametrize("n_slots,n_requests", [ + (1, 2), + (2, 2), +]) +def test_multi_requests_parallel(n_slots: int, n_requests: int): + global server + server.n_slots = n_slots + server.start() + tasks = [] + for _ in range(n_requests): + tasks.append((server.make_request, ("POST", "/completion", { + "prompt": "I believe the meaning of life is", + "temperature": 0.0, + "top_k": 1, + }))) + results = parallel_function_calls(tasks) + for res in results: + assert res.status_code == 200 + assert match_regex("(wise|kind|owl|answer)+", res.body["content"]) diff --git a/tools/server/tests/unit/test_tokenize.py b/tools/server/tests/unit/test_tokenize.py new file mode 100644 index 00000000..382457c9 --- /dev/null +++ b/tools/server/tests/unit/test_tokenize.py @@ -0,0 +1,59 @@ +import pytest +from utils import * + +server = ServerPreset.tinyllama2() + + +@pytest.fixture(scope="module", autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama2() + + +def test_tokenize_detokenize(): + global server + server.start() + # tokenize + content = "What is the capital of France ?" + res_tok = server.make_request("POST", "/tokenize", data={ + "content": content + }) + assert res_tok.status_code == 200 + assert len(res_tok.body["tokens"]) > 5 + # detokenize + res_detok = server.make_request("POST", "/detokenize", data={ + "tokens": res_tok.body["tokens"], + }) + assert res_detok.status_code == 200 + assert res_detok.body["content"].strip() == content + + +def test_tokenize_with_bos(): + global server + server.start() + # tokenize + content = "What is the capital of France ?" + bosId = 1 + res_tok = server.make_request("POST", "/tokenize", data={ + "content": content, + "add_special": True, + }) + assert res_tok.status_code == 200 + assert res_tok.body["tokens"][0] == bosId + + +def test_tokenize_with_pieces(): + global server + server.start() + # tokenize + content = "This is a test string with unicode åª½ and emoji ð¤" + res_tok = server.make_request("POST", "/tokenize", data={ + "content": content, + "with_pieces": True, + }) + assert res_tok.status_code == 200 + for token in res_tok.body["tokens"]: + assert "id" in token + assert token["id"] > 0 + assert "piece" in token + assert len(token["piece"]) > 0 diff --git a/tools/server/tests/unit/test_tool_call.py b/tools/server/tests/unit/test_tool_call.py new file mode 100755 index 00000000..569c2a1f --- /dev/null +++ b/tools/server/tests/unit/test_tool_call.py @@ -0,0 +1,606 @@ +#!/usr/bin/env python +import pytest + +# ensure grandparent path is in sys.path +from pathlib import Path +import sys +path = Path(__file__).resolve().parents[1] +sys.path.insert(0, str(path)) + +from utils import * + +server: ServerProcess + +TIMEOUT_SERVER_START = 15*60 +TIMEOUT_HTTP_REQUEST = 60 + +@pytest.fixture(autouse=True) +def create_server(): + global server + server = ServerPreset.tinyllama2() + server.model_alias = "tinyllama-2-tool-call" + server.server_port = 8081 + + +TEST_TOOL = { + "type":"function", + "function": { + "name": "test", + "description": "", + "parameters": { + "type": "object", + "properties": { + "success": {"type": "boolean", "const": True}, + }, + "required": ["success"] + } + } +} + +PYTHON_TOOL = { + "type": "function", + "function": { + "name": "python", + "description": "Runs code in an ipython interpreter and returns the result of the execution after 60 seconds.", + "parameters": { + "type": "object", + "properties": { + "code": { + "type": "string", + "description": "The code to run in the ipython interpreter." + } + }, + "required": ["code"] + } + } +} + +WEATHER_TOOL = { + "type":"function", + "function":{ + "name":"get_current_weather", + "description":"Get the current weather in a given location", + "parameters":{ + "type":"object", + "properties":{ + "location":{ + "type":"string", + "description":"The city and country/state, e.g. 'San Francisco, CA', or 'Paris, France'" + } + }, + "required":["location"] + } + } +} + + +def do_test_completion_with_required_tool_tiny(server: ServerProcess, tool: dict, argument_key: str | None, n_predict, **kwargs): + res = server.make_request("POST", "/v1/chat/completions", data={ + "max_tokens": n_predict, + "messages": [ + {"role": "system", "content": "You are a coding assistant."}, + {"role": "user", "content": "Write an example"}, + ], + "tool_choice": "required", + "tools": [tool], + "parallel_tool_calls": False, + **kwargs, + }) + assert res.status_code == 200, f"Expected status code 200, got {res.status_code}" + choice = res.body["choices"][0] + tool_calls = choice["message"].get("tool_calls") + assert tool_calls and len(tool_calls) == 1, f'Expected 1 tool call in {choice["message"]}' + tool_call = tool_calls[0] + assert choice["message"].get("content") in (None, ""), f'Expected no content in {choice["message"]}' + assert len(tool_call.get("id", "")) > 0, f'Expected non empty tool call id in {tool_call}' + expected_function_name = "python" if tool["type"] == "code_interpreter" else tool["function"]["name"] + assert expected_function_name == tool_call["function"]["name"] + actual_arguments = tool_call["function"]["arguments"] + assert isinstance(actual_arguments, str) + if argument_key is not None: + actual_arguments = json.loads(actual_arguments) + assert argument_key in actual_arguments, f"tool arguments: {json.dumps(actual_arguments)}, expected: {argument_key}" + + +@pytest.mark.parametrize("template_name,tool,argument_key", [ + ("google-gemma-2-2b-it", TEST_TOOL, "success"), + ("meta-llama-Llama-3.3-70B-Instruct", TEST_TOOL, "success"), + ("meta-llama-Llama-3.3-70B-Instruct", PYTHON_TOOL, "code"), +]) +def test_completion_with_required_tool_tiny_fast(template_name: str, tool: dict, argument_key: str | None): + global server + n_predict = 512 + # server = ServerPreset.stories15m_moe() + server.jinja = True + server.n_predict = n_predict + server.chat_template_file = f'../../../models/templates/{template_name}.jinja' + server.start(timeout_seconds=TIMEOUT_SERVER_START) + do_test_completion_with_required_tool_tiny(server, tool, argument_key, n_predict, temperature=0.0, top_k=1, top_p=1.0) + + +@pytest.mark.slow +@pytest.mark.parametrize("template_name,tool,argument_key", [ + ("meta-llama-Llama-3.1-8B-Instruct", TEST_TOOL, "success"), + ("meta-llama-Llama-3.1-8B-Instruct", PYTHON_TOOL, "code"), + ("meetkai-functionary-medium-v3.1", TEST_TOOL, "success"), + ("meetkai-functionary-medium-v3.1", PYTHON_TOOL, "code"), + ("meetkai-functionary-medium-v3.2", TEST_TOOL, "success"), + ("meetkai-functionary-medium-v3.2", PYTHON_TOOL, "code"), + ("NousResearch-Hermes-2-Pro-Llama-3-8B-tool_use", TEST_TOOL, "success"), + ("NousResearch-Hermes-2-Pro-Llama-3-8B-tool_use", PYTHON_TOOL, "code"), + ("meta-llama-Llama-3.2-3B-Instruct", TEST_TOOL, "success"), + ("meta-llama-Llama-3.2-3B-Instruct", PYTHON_TOOL, "code"), + ("mistralai-Mistral-Nemo-Instruct-2407", TEST_TOOL, "success"), + ("mistralai-Mistral-Nemo-Instruct-2407", PYTHON_TOOL, "code"), + ("NousResearch-Hermes-3-Llama-3.1-8B-tool_use", TEST_TOOL, "success"), + ("NousResearch-Hermes-3-Llama-3.1-8B-tool_use", PYTHON_TOOL, "code"), + ("deepseek-ai-DeepSeek-R1-Distill-Llama-8B", TEST_TOOL, "success"), + ("deepseek-ai-DeepSeek-R1-Distill-Llama-8B", PYTHON_TOOL, "code"), + ("fireworks-ai-llama-3-firefunction-v2", TEST_TOOL, "success"), + # ("fireworks-ai-llama-3-firefunction-v2", PYTHON_TOOL, "code"), +]) +def test_completion_with_required_tool_tiny_slow(template_name: str, tool: dict, argument_key: str | None): + global server + n_predict = 512 + # server = ServerPreset.stories15m_moe() + server.jinja = True + server.n_predict = n_predict + server.chat_template_file = f'../../../models/templates/{template_name}.jinja' + server.start(timeout_seconds=TIMEOUT_SERVER_START) + do_test_completion_with_required_tool_tiny(server, tool, argument_key, n_predict) + + +@pytest.mark.slow +@pytest.mark.parametrize("tool,argument_key,hf_repo,template_override", [ + (TEST_TOOL, "success", "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/gemma-2-2b-it-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Qwen2.5-1.5B-Instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Qwen2.5-1.5B-Instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Qwen2.5-1.5B-Instruct-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")), + (PYTHON_TOOL, "code", "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")), + (PYTHON_TOOL, "code", "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")), + (PYTHON_TOOL, "code", "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")), + (PYTHON_TOOL, "code", "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/functionary-small-v3.2-GGUF:Q4_K_M", ("meetkai/functionary-medium-v3.2", None)), + (PYTHON_TOOL, "code", "bartowski/functionary-small-v3.2-GGUF:Q4_K_M", ("meetkai/functionary-medium-v3.2", None)), + (PYTHON_TOOL, "code", "bartowski/functionary-small-v3.2-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)), + (PYTHON_TOOL, "code", "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)), + (PYTHON_TOOL, "code", "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)), + (PYTHON_TOOL, "code", "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)), + (PYTHON_TOOL, "code", "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", "chatml"), + + (TEST_TOOL, "success", "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None), + (PYTHON_TOOL, "code", "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None), +]) +def test_completion_with_required_tool_real_model(tool: dict, argument_key: str | None, hf_repo: str, template_override: str | Tuple[str, str | None] | None): + global server + n_predict = 512 + server.n_slots = 1 + server.jinja = True + server.n_ctx = 8192 + server.n_predict = n_predict + server.model_hf_repo = hf_repo + server.model_hf_file = None + if isinstance(template_override, tuple): + (template_hf_repo, template_variant) = template_override + server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja" + assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template." + elif isinstance(template_override, str): + server.chat_template = template_override + server.start(timeout_seconds=TIMEOUT_SERVER_START) + res = server.make_request("POST", "/v1/chat/completions", data={ + "max_tokens": n_predict, + "messages": [ + {"role": "system", "content": "You are a coding assistant."}, + {"role": "user", "content": "Write an example"}, + ], + "tool_choice": "required", + "tools": [tool], + "parallel_tool_calls": False, + "temperature": 0.0, + "top_k": 1, + "top_p": 1.0, + }, timeout=TIMEOUT_HTTP_REQUEST) + assert res.status_code == 200, f"Expected status code 200, got {res.status_code}" + choice = res.body["choices"][0] + tool_calls = choice["message"].get("tool_calls") + assert tool_calls and len(tool_calls) == 1, f'Expected 1 tool call in {choice["message"]}' + tool_call = tool_calls[0] + # assert choice["message"].get("content") in (None, ""), f'Expected no content in {choice["message"]}' + expected_function_name = "python" if tool["type"] == "code_interpreter" else tool["function"]["name"] + assert expected_function_name == tool_call["function"]["name"] + actual_arguments = tool_call["function"]["arguments"] + assert isinstance(actual_arguments, str) + if argument_key is not None: + actual_arguments = json.loads(actual_arguments) + assert argument_key in actual_arguments, f"tool arguments: {json.dumps(actual_arguments)}, expected: {argument_key}" + + +def do_test_completion_without_tool_call(server: ServerProcess, n_predict: int, tools: list[dict], tool_choice: str | None, **kwargs): + res = server.make_request("POST", "/v1/chat/completions", data={ + "max_tokens": n_predict, + "messages": [ + {"role": "system", "content": "You are a coding assistant."}, + {"role": "user", "content": "say hello world with python"}, + ], + "tools": tools if tools else None, + "tool_choice": tool_choice, + **kwargs, + }, timeout=TIMEOUT_HTTP_REQUEST) + assert res.status_code == 200, f"Expected status code 200, got {res.status_code}" + choice = res.body["choices"][0] + assert choice["message"].get("tool_calls") is None, f'Expected no tool call in {choice["message"]}' + + +@pytest.mark.parametrize("template_name,n_predict,tools,tool_choice", [ + ("meta-llama-Llama-3.3-70B-Instruct", 128, [], None), + ("meta-llama-Llama-3.3-70B-Instruct", 128, [TEST_TOOL], None), + ("meta-llama-Llama-3.3-70B-Instruct", 128, [PYTHON_TOOL], 'none'), +]) +def test_completion_without_tool_call_fast(template_name: str, n_predict: int, tools: list[dict], tool_choice: str | None): + global server + server.jinja = True + server.n_predict = n_predict + server.chat_template_file = f'../../../models/templates/{template_name}.jinja' + server.start(timeout_seconds=TIMEOUT_SERVER_START) + do_test_completion_without_tool_call(server, n_predict, tools, tool_choice) + + +@pytest.mark.slow +@pytest.mark.parametrize("template_name,n_predict,tools,tool_choice", [ + ("meetkai-functionary-medium-v3.2", 256, [], None), + ("meetkai-functionary-medium-v3.2", 256, [TEST_TOOL], None), + ("meetkai-functionary-medium-v3.2", 256, [PYTHON_TOOL], 'none'), + ("meetkai-functionary-medium-v3.1", 256, [], None), + ("meetkai-functionary-medium-v3.1", 256, [TEST_TOOL], None), + ("meetkai-functionary-medium-v3.1", 256, [PYTHON_TOOL], 'none'), + ("meta-llama-Llama-3.2-3B-Instruct", 256, [], None), + ("meta-llama-Llama-3.2-3B-Instruct", 256, [TEST_TOOL], None), + ("meta-llama-Llama-3.2-3B-Instruct", 256, [PYTHON_TOOL], 'none'), +]) +def test_completion_without_tool_call_slow(template_name: str, n_predict: int, tools: list[dict], tool_choice: str | None): + global server + server.jinja = True + server.n_predict = n_predict + server.chat_template_file = f'../../../models/templates/{template_name}.jinja' + server.start(timeout_seconds=TIMEOUT_SERVER_START) + do_test_completion_without_tool_call(server, n_predict, tools, tool_choice) + + +@pytest.mark.slow +@pytest.mark.parametrize("hf_repo,template_override", [ + ("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None), + ("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None), + ("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Qwen2.5-1.5B-Instruct-GGUF:Q4_K_M", None), + ("bartowski/Qwen2.5-1.5B-Instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M", None), + ("bartowski/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", None), + ("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")), + ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")), + ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None), + ("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"), + + ("bartowski/functionary-small-v3.2-GGUF:Q8_0", ("meetkai/functionary-medium-v3.2", None)), + ("bartowski/functionary-small-v3.2-GGUF:Q8_0", "chatml"), + + ("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)), + ("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/c4ai-command-r7b-12-2024-GGUF:Q6_K_L", ("CohereForAI/c4ai-command-r7b-12-2024", "tool_use")), + + ("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None), + + # Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it. + ("bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None), + + # ("bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)), +]) +def test_weather(hf_repo: str, template_override: str | Tuple[str, str | None] | None): + global server + n_predict = 512 + server.n_slots = 1 + server.jinja = True + server.n_ctx = 8192 + server.n_predict = n_predict + server.model_hf_repo = hf_repo + server.model_hf_file = None + if isinstance(template_override, tuple): + (template_hf_repo, template_variant) = template_override + server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja" + assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template." + elif isinstance(template_override, str): + server.chat_template = template_override + server.start(timeout_seconds=TIMEOUT_SERVER_START) + do_test_weather(server, max_tokens=n_predict) + + +def do_test_weather(server: ServerProcess, **kwargs): + res = server.make_request("POST", "/v1/chat/completions", data={ + "messages": [ + {"role": "system", "content": "You are a chatbot that uses tools/functions. Dont overthink things."}, + {"role": "user", "content": "What is the weather in Istanbul?"}, + ], + "tools": [WEATHER_TOOL], + **kwargs, + }, timeout=TIMEOUT_HTTP_REQUEST) + assert res.status_code == 200, f"Expected status code 200, got {res.status_code}" + choice = res.body["choices"][0] + tool_calls = choice["message"].get("tool_calls") + assert tool_calls and len(tool_calls) == 1, f'Expected 1 tool call in {choice["message"]}' + tool_call = tool_calls[0] + # assert choice["message"].get("content") in (None, ""), f'Expected no content in {choice["message"]}' + assert tool_call["function"]["name"] == WEATHER_TOOL["function"]["name"], f'Expected weather tool call, got {tool_call["function"]["name"]}' + assert len(tool_call.get("id", "")) > 0, f'Expected non empty tool call id in {tool_call}' + actual_arguments = json.loads(tool_call["function"]["arguments"]) + assert 'location' in actual_arguments, f"location not found in {json.dumps(actual_arguments)}" + location = actual_arguments["location"] + assert isinstance(location, str), f"Expected location to be a string, got {type(location)}: {json.dumps(location)}" + assert re.match('^Istanbul(( |, ?)(TR|Turkey|TÃ¼rkiye))?$', location), f'Expected Istanbul for location, got {location}' + + +@pytest.mark.slow +@pytest.mark.parametrize("result_override,n_predict,hf_repo,template_override", [ + (None, 128, "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", "chatml"), + (None, 128, "bartowski/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M", None), + (None, 128, "bartowski/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M", "chatml"), + (None, 128, "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", "chatml"), + (None, 128, "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")), + (None, 128, "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")), + (None, 128, "bartowski/functionary-small-v3.2-GGUF:Q8_0", ("meetkai/functionary-medium-v3.2", None)), + (None, 128, "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None), + (None, 128, "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"), + (None, 128, "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None), + ("[\\s\\S]*?\\*\\*\\s*0.5($|\\*\\*)", 8192, "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", ("llama-cpp-deepseek-r1", None)), + + # TODO: fix these (wrong results, either didn't respect decimal instruction or got wrong value) + # (None, 128, "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None), + # ("[\\s\\S]*?\\*\\*\\s*0.5($|\\*\\*)", 8192, "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None), +]) +def test_calc_result(result_override: str | None, n_predict: int, hf_repo: str, template_override: str | Tuple[str, str | None] | None): + global server + server.n_slots = 1 + server.jinja = True + server.n_ctx = 8192 * 2 + server.n_predict = n_predict + server.model_hf_repo = hf_repo + server.model_hf_file = None + if isinstance(template_override, tuple): + (template_hf_repo, template_variant) = template_override + server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja" + assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template." + elif isinstance(template_override, str): + server.chat_template = template_override + server.start(timeout_seconds=TIMEOUT_SERVER_START) + do_test_calc_result(server, result_override, n_predict) + + +def do_test_calc_result(server: ServerProcess, result_override: str | None, n_predict: int, **kwargs): + res = server.make_request("POST", "/v1/chat/completions", data={ + "max_tokens": n_predict, + "messages": [ + {"role": "system", "content": "You are a tools-calling assistant. You express numerical values with at most two decimals."}, + {"role": "user", "content": "What's the y coordinate of a point on the unit sphere at angle 30 degrees?"}, + { + "role": "assistant", + "content": None, + "tool_calls": [ + { + "id": "call_6789", + "type": "function", + "function": { + "name": "calculate", + "arguments": "{\"expression\":\"sin(30 * pi / 180)\"}" + } + } + ] + }, + { + "role": "tool", + "name": "calculate", + "content": "0.55644242476", + "tool_call_id": "call_6789" + } + ], + "tools": [ + { + "type":"function", + "function":{ + "name":"calculate", + "description":"A calculator function that computes values of arithmetic expressions in the Python syntax", + "parameters":{ + "type":"object", + "properties":{ + "expression":{ + "type":"string", + "description":"An arithmetic expression to compute the value of (Python syntad, assuming all floats)" + } + }, + "required":["expression"] + } + } + } + ], + **kwargs, + }, timeout=TIMEOUT_HTTP_REQUEST) + assert res.status_code == 200, f"Expected status code 200, got {res.status_code}" + choice = res.body["choices"][0] + tool_calls = choice["message"].get("tool_calls") + assert tool_calls is None, f'Expected no tool call in {choice["message"]}' + content = choice["message"].get("content") + assert content is not None, f'Expected content in {choice["message"]}' + if result_override is not None: + assert re.match(result_override, content), f'Expected {result_override}, got {content}' + else: + assert re.match('^[\\s\\S]*?((That\'s|\\bis) (approximately )?)?\\b0\\.(5\\b|56\\b|556)', content), \ + f'Expected something like "The y coordinate is 0.56.", got {content}' + + +@pytest.mark.slow +@pytest.mark.parametrize("n_predict,reasoning_format,expect_content,expect_reasoning_content,hf_repo,template_override", [ + (128, 'deepseek', "^The sum of 102 and 7 is 109[\\s\\S]*", None, "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None), + (128, None, "^The sum of 102 and 7 is 109[\\s\\S]*", None, "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None), + + (1024, 'deepseek', "To find the sum of[\\s\\S]*", "I need to calculate the sum of 102 and 7[\\s\\S]*", "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None), + (1024, 'none', "^(\\s*)?I need[\\s\\S]*?\\s*To find[\\s\\S]*", None, "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None), + + (1024, 'deepseek', "To find the sum of[\\s\\S]*", "First, I [\\s\\S]*", "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", ("llama-cpp-deepseek-r1", None)), +]) +def test_thoughts(n_predict: int, reasoning_format: Literal['deepseek', 'none'] | None, expect_content: str | None, expect_reasoning_content: str | None, hf_repo: str, template_override: str | Tuple[str, str | None] | None): + global server + server.n_slots = 1 + server.reasoning_format = reasoning_format + server.jinja = True + server.n_ctx = 8192 * 2 + server.n_predict = n_predict + server.model_hf_repo = hf_repo + server.model_hf_file = None + if isinstance(template_override, tuple): + (template_hf_repo, template_variant) = template_override + server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja" + assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template." + elif isinstance(template_override, str): + server.chat_template = template_override + server.start(timeout_seconds=TIMEOUT_SERVER_START) + res = server.make_request("POST", "/v1/chat/completions", data={ + "max_tokens": n_predict, + "messages": [ + {"role": "user", "content": "What's the sum of 102 and 7?"}, + ] + }, timeout=TIMEOUT_HTTP_REQUEST) + assert res.status_code == 200, f"Expected status code 200, got {res.status_code}" + choice = res.body["choices"][0] + assert choice["message"].get("tool_calls") is None, f'Expected no tool call in {choice["message"]}' + + content = choice["message"].get("content") + if expect_content is None: + assert choice["message"].get("content") in (None, ""), f'Expected no content in {choice["message"]}' + else: + assert re.match(expect_content, content), f'Expected {expect_content}, got {content}' + + reasoning_content = choice["message"].get("reasoning_content") + if expect_reasoning_content is None: + assert reasoning_content is None, f'Expected no reasoning content in {choice["message"]}' + else: + assert re.match(expect_reasoning_content, reasoning_content), f'Expected {expect_reasoning_content}, got {reasoning_content}' + + +@pytest.mark.slow +@pytest.mark.parametrize("hf_repo,template_override", [ + ("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None), + + ("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", None), + ("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/functionary-small-v3.2-GGUF:Q8_0", ("meetkai-functionary-medium-v3.2", None)), + ("bartowski/functionary-small-v3.2-GGUF:Q8_0", "chatml"), + + # ("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None), + ("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama-Llama-3.2-3B-Instruct", None)), + ("bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", None), + + ("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", ("meta-llama-Llama-3.2-3B-Instruct", None)), + ("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M", None), + + ("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", None), + ("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")), + ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", ("NousResearch-Hermes-3-Llama-3.1-8B", "tool_use")), + ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M", "chatml"), + + ("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None), + ("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"), + + ("bartowski/gemma-2-2b-it-GGUF:Q4_K_M", None), + ("bartowski/gemma-2-2b-it-GGUF:Q4_K_M", "chatml"), +]) +def test_hello_world(hf_repo: str, template_override: str | Tuple[str, str | None] | None): + global server + n_predict = 512 # High because of DeepSeek R1 + server.n_slots = 1 + server.jinja = True + server.n_ctx = 8192 + server.n_predict = n_predict + server.model_hf_repo = hf_repo + server.model_hf_file = None + if isinstance(template_override, tuple): + (template_hf_repo, template_variant) = template_override + server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja" + assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template." + elif isinstance(template_override, str): + server.chat_template = template_override + server.start(timeout_seconds=TIMEOUT_SERVER_START) + + do_test_hello_world(server, max_tokens=n_predict) + + +def do_test_hello_world(server: ServerProcess, **kwargs): + res = server.make_request("POST", "/v1/chat/completions", data={ + "messages": [ + {"role": "system", "content": "You are a tool-calling agent."}, + {"role": "user", "content": "say hello world with python"}, + ], + "tools": [PYTHON_TOOL], + **kwargs, + }, timeout=TIMEOUT_HTTP_REQUEST) + assert res.status_code == 200, f"Expected status code 200, got {res.status_code}" + choice = res.body["choices"][0] + tool_calls = choice["message"].get("tool_calls") + assert tool_calls and len(tool_calls) == 1, f'Expected 1 tool call in {choice["message"]}' + tool_call = tool_calls[0] + # assert choice["message"].get("content") in (None, ""), f'Expected no content in {choice["message"]}' + assert tool_call["function"]["name"] == PYTHON_TOOL["function"]["name"] + assert len(tool_call.get("id", "")) > 0, f'Expected non empty tool call id in {tool_call}' + actual_arguments = json.loads(tool_call["function"]["arguments"]) + assert 'code' in actual_arguments, f"code not found in {json.dumps(actual_arguments)}" + code = actual_arguments["code"] + assert isinstance(code, str), f"Expected code to be a string, got {type(code)}: {json.dumps(code)}" + assert re.match(r'''print$("[Hh]ello,? [Ww]orld!?"|'[Hh]ello,? [Ww]orld!?')$''', code), f'Expected hello world, got {code}' diff --git a/tools/server/tests/utils.py b/tools/server/tests/utils.py new file mode 100644 index 00000000..4dc2062a --- /dev/null +++ b/tools/server/tests/utils.py @@ -0,0 +1,452 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- + +# type: ignore[reportUnusedImport] + +import subprocess +import os +import re +import json +import sys +import requests +import time +from concurrent.futures import ThreadPoolExecutor, as_completed +from typing import ( + Any, + Callable, + ContextManager, + Iterable, + Iterator, + List, + Literal, + Tuple, + Set, +) +from re import RegexFlag +import wget + + +DEFAULT_HTTP_TIMEOUT = 12 + +if "LLAMA_SANITIZE" in os.environ or "GITHUB_ACTION" in os.environ: + DEFAULT_HTTP_TIMEOUT = 30 + + +class ServerResponse: + headers: dict + status_code: int + body: dict | Any + + +class ServerProcess: + # default options + debug: bool = False + server_port: int = 8080 + server_host: str = "127.0.0.1" + model_hf_repo: str = "ggml-org/models" + model_hf_file: str | None = "tinyllamas/stories260K.gguf" + model_alias: str = "tinyllama-2" + temperature: float = 0.8 + seed: int = 42 + + # custom options + model_alias: str | None = None + model_url: str | None = None + model_file: str | None = None + model_draft: str | None = None + n_threads: int | None = None + n_gpu_layer: int | None = None + n_batch: int | None = None + n_ubatch: int | None = None + n_ctx: int | None = None + n_ga: int | None = None + n_ga_w: int | None = None + n_predict: int | None = None + n_prompts: int | None = 0 + slot_save_path: str | None = None + id_slot: int | None = None + cache_prompt: bool | None = None + n_slots: int | None = None + ctk: str | None = None + ctv: str | None = None + fa: bool | None = None + server_continuous_batching: bool | None = False + server_embeddings: bool | None = False + server_reranking: bool | None = False + server_metrics: bool | None = False + server_slots: bool | None = False + pooling: str | None = None + draft: int | None = None + api_key: str | None = None + lora_files: List[str] | None = None + disable_ctx_shift: int | None = False + draft_min: int | None = None + draft_max: int | None = None + no_webui: bool | None = None + jinja: bool | None = None + reasoning_format: Literal['deepseek', 'none'] | None = None + chat_template: str | None = None + chat_template_file: str | None = None + server_path: str | None = None + + # session variables + process: subprocess.Popen | None = None + + def __init__(self): + if "N_GPU_LAYERS" in os.environ: + self.n_gpu_layer = int(os.environ["N_GPU_LAYERS"]) + if "DEBUG" in os.environ: + self.debug = True + if "PORT" in os.environ: + self.server_port = int(os.environ["PORT"]) + + def start(self, timeout_seconds: int | None = DEFAULT_HTTP_TIMEOUT) -> None: + if self.server_path is not None: + server_path = self.server_path + elif "LLAMA_SERVER_BIN_PATH" in os.environ: + server_path = os.environ["LLAMA_SERVER_BIN_PATH"] + elif os.name == "nt": + server_path = "../../../build/bin/Release/llama-server.exe" + else: + server_path = "../../../build/bin/llama-server" + server_args = [ + "--host", + self.server_host, + "--port", + self.server_port, + "--temp", + self.temperature, + "--seed", + self.seed, + ] + if self.model_file: + server_args.extend(["--model", self.model_file]) + if self.model_url: + server_args.extend(["--model-url", self.model_url]) + if self.model_draft: + server_args.extend(["--model-draft", self.model_draft]) + if self.model_hf_repo: + server_args.extend(["--hf-repo", self.model_hf_repo]) + if self.model_hf_file: + server_args.extend(["--hf-file", self.model_hf_file]) + if self.n_batch: + server_args.extend(["--batch-size", self.n_batch]) + if self.n_ubatch: + server_args.extend(["--ubatch-size", self.n_ubatch]) + if self.n_threads: + server_args.extend(["--threads", self.n_threads]) + if self.n_gpu_layer: + server_args.extend(["--n-gpu-layers", self.n_gpu_layer]) + if self.draft is not None: + server_args.extend(["--draft", self.draft]) + if self.server_continuous_batching: + server_args.append("--cont-batching") + if self.server_embeddings: + server_args.append("--embedding") + if self.server_reranking: + server_args.append("--reranking") + if self.server_metrics: + server_args.append("--metrics") + if self.server_slots: + server_args.append("--slots") + if self.pooling: + server_args.extend(["--pooling", self.pooling]) + if self.model_alias: + server_args.extend(["--alias", self.model_alias]) + if self.n_ctx: + server_args.extend(["--ctx-size", self.n_ctx]) + if self.n_slots: + server_args.extend(["--parallel", self.n_slots]) + if self.ctk: + server_args.extend(["-ctk", self.ctk]) + if self.ctv: + server_args.extend(["-ctv", self.ctv]) + if self.fa is not None: + server_args.append("-fa") + if self.n_predict: + server_args.extend(["--n-predict", self.n_predict]) + if self.slot_save_path: + server_args.extend(["--slot-save-path", self.slot_save_path]) + if self.n_ga: + server_args.extend(["--grp-attn-n", self.n_ga]) + if self.n_ga_w: + server_args.extend(["--grp-attn-w", self.n_ga_w]) + if self.debug: + server_args.append("--verbose") + if self.lora_files: + for lora_file in self.lora_files: + server_args.extend(["--lora", lora_file]) + if self.disable_ctx_shift: + server_args.extend(["--no-context-shift"]) + if self.api_key: + server_args.extend(["--api-key", self.api_key]) + if self.draft_max: + server_args.extend(["--draft-max", self.draft_max]) + if self.draft_min: + server_args.extend(["--draft-min", self.draft_min]) + if self.no_webui: + server_args.append("--no-webui") + if self.jinja: + server_args.append("--jinja") + if self.reasoning_format is not None: + server_args.extend(("--reasoning-format", self.reasoning_format)) + if self.chat_template: + server_args.extend(["--chat-template", self.chat_template]) + if self.chat_template_file: + server_args.extend(["--chat-template-file", self.chat_template_file]) + + args = [str(arg) for arg in [server_path, *server_args]] + print(f"tests: starting server with: {' '.join(args)}") + + flags = 0 + if "nt" == os.name: + flags |= subprocess.DETACHED_PROCESS + flags |= subprocess.CREATE_NEW_PROCESS_GROUP + flags |= subprocess.CREATE_NO_WINDOW + + self.process = subprocess.Popen( + [str(arg) for arg in [server_path, *server_args]], + creationflags=flags, + stdout=sys.stdout, + stderr=sys.stdout, + env={**os.environ, "LLAMA_CACHE": "tmp"} if "LLAMA_CACHE" not in os.environ else None, + ) + server_instances.add(self) + + print(f"server pid={self.process.pid}, pytest pid={os.getpid()}") + + # wait for server to start + start_time = time.time() + while time.time() - start_time < timeout_seconds: + try: + response = self.make_request("GET", "/health", headers={ + "Authorization": f"Bearer {self.api_key}" if self.api_key else None + }) + if response.status_code == 200: + self.ready = True + return # server is ready + except Exception as e: + pass + # Check if process died + if self.process.poll() is not None: + raise RuntimeError(f"Server process died with return code {self.process.returncode}") + + print(f"Waiting for server to start...") + time.sleep(0.5) + raise TimeoutError(f"Server did not start within {timeout_seconds} seconds") + + def stop(self) -> None: + if self in server_instances: + server_instances.remove(self) + if self.process: + print(f"Stopping server with pid={self.process.pid}") + self.process.kill() + self.process = None + + def make_request( + self, + method: str, + path: str, + data: dict | Any | None = None, + headers: dict | None = None, + timeout: float | None = None, + ) -> ServerResponse: + url = f"http://{self.server_host}:{self.server_port}{path}" + parse_body = False + if method == "GET": + response = requests.get(url, headers=headers, timeout=timeout) + parse_body = True + elif method == "POST": + response = requests.post(url, headers=headers, json=data, timeout=timeout) + parse_body = True + elif method == "OPTIONS": + response = requests.options(url, headers=headers, timeout=timeout) + else: + raise ValueError(f"Unimplemented method: {method}") + result = ServerResponse() + result.headers = dict(response.headers) + result.status_code = response.status_code + result.body = response.json() if parse_body else None + print("Response from server", json.dumps(result.body, indent=2)) + return result + + def make_stream_request( + self, + method: str, + path: str, + data: dict | None = None, + headers: dict | None = None, + ) -> Iterator[dict]: + url = f"http://{self.server_host}:{self.server_port}{path}" + if method == "POST": + response = requests.post(url, headers=headers, json=data, stream=True) + else: + raise ValueError(f"Unimplemented method: {method}") + for line_bytes in response.iter_lines(): + line = line_bytes.decode("utf-8") + if '[DONE]' in line: + break + elif line.startswith('data: '): + data = json.loads(line[6:]) + print("Partial response from server", json.dumps(data, indent=2)) + yield data + + +server_instances: Set[ServerProcess] = set() + + +class ServerPreset: + @staticmethod + def tinyllama2() -> ServerProcess: + server = ServerProcess() + server.model_hf_repo = "ggml-org/models" + server.model_hf_file = "tinyllamas/stories260K.gguf" + server.model_alias = "tinyllama-2" + server.n_ctx = 512 + server.n_batch = 32 + server.n_slots = 2 + server.n_predict = 64 + server.seed = 42 + return server + + @staticmethod + def bert_bge_small() -> ServerProcess: + server = ServerProcess() + server.model_hf_repo = "ggml-org/models" + server.model_hf_file = "bert-bge-small/ggml-model-f16.gguf" + server.model_alias = "bert-bge-small" + server.n_ctx = 512 + server.n_batch = 128 + server.n_ubatch = 128 + server.n_slots = 2 + server.seed = 42 + server.server_embeddings = True + return server + + @staticmethod + def bert_bge_small_with_fa() -> ServerProcess: + server = ServerProcess() + server.model_hf_repo = "ggml-org/models" + server.model_hf_file = "bert-bge-small/ggml-model-f16.gguf" + server.model_alias = "bert-bge-small" + server.n_ctx = 1024 + server.n_batch = 300 + server.n_ubatch = 300 + server.n_slots = 2 + server.fa = True + server.seed = 42 + server.server_embeddings = True + return server + + @staticmethod + def tinyllama_infill() -> ServerProcess: + server = ServerProcess() + server.model_hf_repo = "ggml-org/models" + server.model_hf_file = "tinyllamas/stories260K-infill.gguf" + server.model_alias = "tinyllama-infill" + server.n_ctx = 2048 + server.n_batch = 1024 + server.n_slots = 1 + server.n_predict = 64 + server.temperature = 0.0 + server.seed = 42 + return server + + @staticmethod + def stories15m_moe() -> ServerProcess: + server = ServerProcess() + server.model_hf_repo = "ggml-org/stories15M_MOE" + server.model_hf_file = "stories15M_MOE-F16.gguf" + server.model_alias = "stories15m-moe" + server.n_ctx = 2048 + server.n_batch = 1024 + server.n_slots = 1 + server.n_predict = 64 + server.temperature = 0.0 + server.seed = 42 + return server + + @staticmethod + def jina_reranker_tiny() -> ServerProcess: + server = ServerProcess() + server.model_hf_repo = "ggml-org/models" + server.model_hf_file = "jina-reranker-v1-tiny-en/ggml-model-f16.gguf" + server.model_alias = "jina-reranker" + server.n_ctx = 512 + server.n_batch = 512 + server.n_slots = 1 + server.seed = 42 + server.server_reranking = True + return server + + +def parallel_function_calls(function_list: List[Tuple[Callable[..., Any], Tuple[Any, ...]]]) -> List[Any]: + """ + Run multiple functions in parallel and return results in the same order as calls. Equivalent to Promise.all in JS. + + Example usage: + + results = parallel_function_calls([ + (func1, (arg1, arg2)), + (func2, (arg3, arg4)), + ]) + """ + results = [None] * len(function_list) + exceptions = [] + + def worker(index, func, args): + try: + result = func(*args) + results[index] = result + except Exception as e: + exceptions.append((index, str(e))) + + with ThreadPoolExecutor() as executor: + futures = [] + for i, (func, args) in enumerate(function_list): + future = executor.submit(worker, i, func, args) + futures.append(future) + + # Wait for all futures to complete + for future in as_completed(futures): + pass + + # Check if there were any exceptions + if exceptions: + print("Exceptions occurred:") + for index, error in exceptions: + print(f"Function at index {index}: {error}") + + return results + + +def match_regex(regex: str, text: str) -> bool: + return ( + re.compile( + regex, flags=RegexFlag.IGNORECASE | RegexFlag.MULTILINE | RegexFlag.DOTALL + ).search(text) + is not None + ) + + +def download_file(url: str, output_file_path: str | None = None) -> str: + """ + Download a file from a URL to a local path. If the file already exists, it will not be downloaded again. + + output_file_path is the local path to save the downloaded file. If not provided, the file will be saved in the root directory. + + Returns the local path of the downloaded file. + """ + file_name = url.split('/').pop() + output_file = f'./tmp/{file_name}' if output_file_path is None else output_file_path + if not os.path.exists(output_file): + print(f"Downloading {url} to {output_file}") + wget.download(url, out=output_file) + print(f"Done downloading to {output_file}") + else: + print(f"File already exists at {output_file}") + return output_file + + +def is_slow_test_allowed(): + return os.environ.get("SLOW_TESTS") == "1" or os.environ.get("SLOW_TESTS") == "ON" diff --git a/tools/server/themes/README.md b/tools/server/themes/README.md new file mode 100644 index 00000000..62e721a2 --- /dev/null +++ b/tools/server/themes/README.md @@ -0,0 +1,5 @@ +# LLaMA.cpp Server Wild Theme + +Simple themes directory of sample "public" directories. To try any of these add --path to your run like `server --path=wild`. + +![image](wild/wild.png) diff --git a/tools/server/themes/buttons-top/README.md b/tools/server/themes/buttons-top/README.md new file mode 100644 index 00000000..808c4cf8 --- /dev/null +++ b/tools/server/themes/buttons-top/README.md @@ -0,0 +1,7 @@ +# LLaMA.cpp Server Buttons Top Theme + +Simple tweaks to the UI. Chat buttons at the top of the page instead of bottom so you can hit Stop instead of chasing it down the page. + +To use simply run server with `--path=themes/buttons_top` + +![image](buttons_top.png) diff --git a/tools/server/themes/buttons-top/buttons_top.png b/tools/server/themes/buttons-top/buttons_top.png new file mode 100644 index 00000000..c5445451 Binary files /dev/null and b/tools/server/themes/buttons-top/buttons_top.png differ diff --git a/tools/server/themes/buttons-top/favicon.ico b/tools/server/themes/buttons-top/favicon.ico new file mode 100644 index 00000000..89e154a0 Binary files /dev/null and b/tools/server/themes/buttons-top/favicon.ico differ diff --git a/tools/server/themes/buttons-top/index.html b/tools/server/themes/buttons-top/index.html new file mode 100644 index 00000000..3fb88fcc --- /dev/null +++ b/tools/server/themes/buttons-top/index.html @@ -0,0 +1,1052 @@ + + + + + + + llama.cpp - chat + + + + + + + +
+ +
+
+ + + diff --git a/tools/server/themes/wild/README.md b/tools/server/themes/wild/README.md new file mode 100644 index 00000000..560bcc81 --- /dev/null +++ b/tools/server/themes/wild/README.md @@ -0,0 +1,5 @@ +# LLaMA.cpp Server Wild Theme + +Simple tweaks to the UI. To use simply run server with `--path=themes/wild` + +![image](wild.png) diff --git a/tools/server/themes/wild/favicon.ico b/tools/server/themes/wild/favicon.ico new file mode 100644 index 00000000..89e154a0 Binary files /dev/null and b/tools/server/themes/wild/favicon.ico differ diff --git a/tools/server/themes/wild/index.html b/tools/server/themes/wild/index.html new file mode 100644 index 00000000..73f36d4b --- /dev/null +++ b/tools/server/themes/wild/index.html @@ -0,0 +1,1056 @@ + + + + + + + llama.cpp - chat + + + + + + + +
+ +
+
+ + + diff --git a/tools/server/themes/wild/llama_cpp.png b/tools/server/themes/wild/llama_cpp.png new file mode 100644 index 00000000..bad1dc9f Binary files /dev/null and b/tools/server/themes/wild/llama_cpp.png differ diff --git a/tools/server/themes/wild/llamapattern.png b/tools/server/themes/wild/llamapattern.png new file mode 100644 index 00000000..2a159ce6 Binary files /dev/null and b/tools/server/themes/wild/llamapattern.png differ diff --git a/tools/server/themes/wild/wild.png b/tools/server/themes/wild/wild.png new file mode 100644 index 00000000..46ffa0f3 Binary files /dev/null and b/tools/server/themes/wild/wild.png differ diff --git a/tools/server/utils.hpp b/tools/server/utils.hpp new file mode 100644 index 00000000..b497959f --- /dev/null +++ b/tools/server/utils.hpp @@ -0,0 +1,937 @@ +#pragma once + +#include "common.h" +#include "log.h" +#include "llama.h" +#include "base64.hpp" + +// increase max payload length to allow use of larger context size +#define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576 +// disable Nagle's algorithm +#define CPPHTTPLIB_TCP_NODELAY true +#include "httplib.h" + +// Change JSON_ASSERT from assert() to GGML_ASSERT: +#define JSON_ASSERT GGML_ASSERT +#include "json.hpp" +#include "chat.h" + +#include +#include +#include +#include +#include + +#define DEFAULT_OAICOMPAT_MODEL "gpt-3.5-turbo" + +using json = nlohmann::ordered_json; + +#define SLT_INF(slot, fmt, ...) LOG_INF("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__) +#define SLT_WRN(slot, fmt, ...) LOG_WRN("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__) +#define SLT_ERR(slot, fmt, ...) LOG_ERR("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__) +#define SLT_DBG(slot, fmt, ...) LOG_DBG("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, (slot).id_task, __VA_ARGS__) + +#define SRV_INF(fmt, ...) LOG_INF("srv %12.*s: " fmt, 12, __func__, __VA_ARGS__) +#define SRV_WRN(fmt, ...) LOG_WRN("srv %12.*s: " fmt, 12, __func__, __VA_ARGS__) +#define SRV_ERR(fmt, ...) LOG_ERR("srv %12.*s: " fmt, 12, __func__, __VA_ARGS__) +#define SRV_DBG(fmt, ...) LOG_DBG("srv %12.*s: " fmt, 12, __func__, __VA_ARGS__) + +#define QUE_INF(fmt, ...) LOG_INF("que %12.*s: " fmt, 12, __func__, __VA_ARGS__) +#define QUE_WRN(fmt, ...) LOG_WRN("que %12.*s: " fmt, 12, __func__, __VA_ARGS__) +#define QUE_ERR(fmt, ...) LOG_ERR("que %12.*s: " fmt, 12, __func__, __VA_ARGS__) +#define QUE_DBG(fmt, ...) LOG_DBG("que %12.*s: " fmt, 12, __func__, __VA_ARGS__) + +template +static T json_value(const json & body, const std::string & key, const T & default_value) { + // Fallback null to default value + if (body.contains(key) && !body.at(key).is_null()) { + try { + return body.at(key); + } catch (NLOHMANN_JSON_NAMESPACE::detail::type_error const &) { + LOG_WRN("Wrong type supplied for parameter '%s'. Expected '%s', using default value\n", key.c_str(), json(default_value).type_name()); + return default_value; + } + } else { + return default_value; + } +} + +const static std::string build_info("b" + std::to_string(LLAMA_BUILD_NUMBER) + "-" + LLAMA_COMMIT); + +// thin wrapper around common_grammar_trigger with (de)serialization functions +struct server_grammar_trigger { + common_grammar_trigger value; + + server_grammar_trigger() = default; + server_grammar_trigger(const common_grammar_trigger & value) : value(value) {} + server_grammar_trigger(const json & in) { + value.type = (common_grammar_trigger_type) in.at("type").get(); + value.value = in.at("value").get(); + if (value.type == COMMON_GRAMMAR_TRIGGER_TYPE_TOKEN) { + value.token = (llama_token) in.at("token").get(); + } + } + + json to_json() const { + json out { + {"type", (int) value.type}, + {"value", value.value}, + }; + if (value.type == COMMON_GRAMMAR_TRIGGER_TYPE_TOKEN) { + out["token"] = (int) value.token; + } + return out; + } +}; + +// +// tokenizer and input processing utils +// + +static bool json_is_array_of_numbers(const json & data) { + if (data.is_array()) { + for (const auto & e : data) { + if (!e.is_number_integer()) { + return false; + } + } + return true; + } + return false; +} + +// is array having BOTH numbers & strings? +static bool json_is_array_of_mixed_numbers_strings(const json & data) { + bool seen_string = false; + bool seen_number = false; + if (data.is_array()) { + for (const auto & e : data) { + seen_string |= e.is_string(); + seen_number |= e.is_number_integer(); + if (seen_number && seen_string) { + return true; + } + } + } + return false; +} + +// get value by path(key1 / key2) +static json json_get_nested_values(const std::vector & paths, const json & js) { + json result = json::object(); + + for (const std::string & path : paths) { + json current = js; + const auto keys = string_split(path, /*separator*/ '/'); + bool valid_path = true; + for (const std::string & k : keys) { + if (valid_path && current.is_object() && current.contains(k)) { + current = current[k]; + } else { + valid_path = false; + } + } + if (valid_path) { + result[path] = current; + } + } + return result; +} + +/** + * this handles 2 cases: + * - only string, example: "string" + * - mixed string and tokens, example: [12, 34, "string", 56, 78] + */ +static llama_tokens tokenize_mixed(const llama_vocab * vocab, const json & json_prompt, bool add_special, bool parse_special) { + // If `add_bos` is true, we only add BOS, when json_prompt is a string, + // or the first element of the json_prompt array is a string. + llama_tokens prompt_tokens; + + if (json_prompt.is_array()) { + bool first = true; + for (const auto & p : json_prompt) { + if (p.is_string()) { + auto s = p.template get(); + + llama_tokens p; + if (first) { + p = common_tokenize(vocab, s, add_special, parse_special); + first = false; + } else { + p = common_tokenize(vocab, s, false, parse_special); + } + + prompt_tokens.insert(prompt_tokens.end(), p.begin(), p.end()); + } else { + if (first) { + first = false; + } + + prompt_tokens.push_back(p.template get()); + } + } + } else { + auto s = json_prompt.template get(); + prompt_tokens = common_tokenize(vocab, s, add_special, parse_special); + } + + return prompt_tokens; +} + +/** + * break the input "prompt" object into multiple prompt if needed, then tokenize them + * this supports these cases: + * - "prompt": "string" + * - "prompt": [12, 34, 56] + * - "prompt": [12, 34, "string", 56, 78] + * and multiple prompts (multi-tasks): + * - "prompt": ["string1", "string2"] + * - "prompt": ["string1", [12, 34, 56]] + * - "prompt": [[12, 34, 56], [78, 90, 12]] + * - "prompt": [[12, 34, "string", 56, 78], [12, 34, 56]] + */ +static std::vector tokenize_input_prompts(const llama_vocab * vocab, const json & json_prompt, bool add_special, bool parse_special) { + std::vector result; + if (json_prompt.is_string() || json_is_array_of_mixed_numbers_strings(json_prompt)) { + // string or mixed + result.push_back(tokenize_mixed(vocab, json_prompt, add_special, parse_special)); + } else if (json_is_array_of_numbers(json_prompt)) { + // array of tokens + result.push_back(json_prompt.get()); + } else if (json_prompt.is_array()) { + // array of prompts + result.reserve(json_prompt.size()); + for (const auto & p : json_prompt) { + if (p.is_string() || json_is_array_of_mixed_numbers_strings(p)) { + result.push_back(tokenize_mixed(vocab, p, add_special, parse_special)); + } else if (json_is_array_of_numbers(p)) { + // array of tokens + result.push_back(p.get()); + } else { + throw std::runtime_error("element of \"prompt\" must be a string, an list of tokens, or a list of mixed strings & tokens"); + } + } + } else { + throw std::runtime_error("\"prompt\" must be a string, an list of tokens, a list of mixed strings & tokens, or a list of prompts"); + } + if (result.empty()) { + throw std::runtime_error("\"prompt\" must not be empty"); + } + return result; +} + +// return the last index of character that can form a valid string +// if the last character is potentially cut in half, return the index before the cut +// if validate_utf8(text) == text.size(), then the whole text is valid utf8 +static size_t validate_utf8(const std::string& text) { + size_t len = text.size(); + if (len == 0) return 0; + + // Check the last few bytes to see if a multi-byte character is cut off + for (size_t i = 1; i <= 4 && i <= len; ++i) { + unsigned char c = text[len - i]; + // Check for start of a multi-byte sequence from the end + if ((c & 0xE0) == 0xC0) { + // 2-byte character start: 110xxxxx + // Needs at least 2 bytes + if (i < 2) return len - i; + } else if ((c & 0xF0) == 0xE0) { + // 3-byte character start: 1110xxxx + // Needs at least 3 bytes + if (i < 3) return len - i; + } else if ((c & 0xF8) == 0xF0) { + // 4-byte character start: 11110xxx + // Needs at least 4 bytes + if (i < 4) return len - i; + } + } + + // If no cut-off multi-byte character is found, return full length + return len; +} + +// +// template utils +// + +// format rerank task: [BOS]query[EOS][SEP]doc[EOS] +static llama_tokens format_rerank(const struct llama_vocab * vocab, const llama_tokens & query, const llama_tokens & doc) { + llama_tokens result; + + result.reserve(doc.size() + query.size() + 4); + result.push_back(llama_vocab_bos(vocab)); + result.insert(result.end(), query.begin(), query.end()); + result.push_back(llama_vocab_eos(vocab)); + result.push_back(llama_vocab_sep(vocab)); + result.insert(result.end(), doc.begin(), doc.end()); + result.push_back(llama_vocab_eos(vocab)); + + return result; +} + +// format infill task +static llama_tokens format_infill( + const llama_vocab * vocab, + const json & input_prefix, + const json & input_suffix, + const json & input_extra, + const int n_batch, + const int n_predict, + const int n_ctx, + const bool spm_infill, + const llama_tokens & tokens_prompt + ) { + // TODO: optimize this block by reducing memory allocations and movement + + // use FIM repo-level pattern: + // ref: https://arxiv.org/pdf/2409.12186 + // + // [FIM_REP]myproject + // [FIM_SEP]filename0 + // extra chunk 0 + // [FIM_SEP]filename1 + // extra chunk 1 + // ... + // [FIM_SEP]filename + // [FIM_PRE]prefix[FIM_SUF]suffix[FIM_MID]prompt + // + llama_tokens extra_tokens; + extra_tokens.reserve(n_ctx); + + auto tokens_prefix = tokenize_mixed(vocab, input_prefix, false, false); + auto tokens_suffix = tokenize_mixed(vocab, input_suffix, false, false); + + if (llama_vocab_fim_rep(vocab) != LLAMA_TOKEN_NULL) { + // TODO: make project name an input + static const auto k_fim_repo = common_tokenize(vocab, "myproject\n", false, false); + + extra_tokens.push_back(llama_vocab_fim_rep(vocab)); + extra_tokens.insert(extra_tokens.end(), k_fim_repo.begin(), k_fim_repo.end()); + } + for (const auto & chunk : input_extra) { + // { "text": string, "filename": string } + const std::string text = json_value(chunk, "text", std::string()); + const std::string filename = json_value(chunk, "filename", std::string("tmp")); + + if (llama_vocab_fim_sep(vocab) != LLAMA_TOKEN_NULL) { + const auto k_fim_file = common_tokenize(vocab, filename + "\n", false, false); + + extra_tokens.insert(extra_tokens.end(), llama_vocab_fim_sep(vocab)); + extra_tokens.insert(extra_tokens.end(), k_fim_file.begin(), k_fim_file.end()); + } else { + // chunk separator in binary form to avoid confusing the AI + static const char k_chunk_prefix_str[] = {0x0a, 0x0a, 0x2d, 0x2d, 0x2d, 0x20, 0x73, 0x6e, 0x69, 0x70, 0x70, 0x65, 0x74, 0x20, 0x2d, 0x2d, 0x2d, 0x0a, 0x0a, 0x00}; + static const auto k_chunk_prefix_tokens = common_tokenize(vocab, k_chunk_prefix_str, false, false); + + extra_tokens.insert(extra_tokens.end(), k_chunk_prefix_tokens.begin(), k_chunk_prefix_tokens.end()); + } + + const auto chunk_tokens = common_tokenize(vocab, text, false, false); + extra_tokens.insert(extra_tokens.end(), chunk_tokens.begin(), chunk_tokens.end()); + } + + if (llama_vocab_fim_sep(vocab) != LLAMA_TOKEN_NULL) { + // TODO: current filename + static const auto k_fim_file = common_tokenize(vocab, "filename\n", false, false); + + extra_tokens.insert(extra_tokens.end(), llama_vocab_fim_sep(vocab)); + extra_tokens.insert(extra_tokens.end(), k_fim_file.begin(), k_fim_file.end()); + } + + // for now pick FIM context to fit in a batch (ratio prefix:suffix = 3:1, TODO: configurable?) + const int n_prefix_take = std::min(tokens_prefix.size(), 3*(n_batch/4)); + const int n_suffix_take = std::min(tokens_suffix.size(), std::max(0, (n_batch/4) - (2 + tokens_prompt.size()))); + + SRV_DBG("n_prefix_take = %d, n_suffix_take = %d, total = %d\n", n_prefix_take, n_suffix_take, (n_prefix_take + n_suffix_take)); + + // fill the rest of the context with extra chunks + const int n_extra_take = std::min(std::max(0, n_ctx - (n_batch) - 2*n_predict), extra_tokens.size()); + + tokens_prefix.erase(tokens_prefix.begin(), tokens_prefix.begin() + tokens_prefix.size() - n_prefix_take); + tokens_suffix.resize(n_suffix_take); + + tokens_prefix.insert(tokens_prefix.begin(), llama_vocab_fim_pre(vocab)); + tokens_prefix.insert(tokens_prefix.end(), tokens_prompt.begin(), tokens_prompt.end()); + tokens_suffix.insert(tokens_suffix.begin(), llama_vocab_fim_suf(vocab)); + + auto embd_inp = spm_infill ? tokens_suffix : tokens_prefix; + auto embd_end = spm_infill ? tokens_prefix : tokens_suffix; + + if (llama_vocab_get_add_bos(vocab)) { + embd_inp.insert(embd_inp.begin(), llama_vocab_bos(vocab)); + } + + SRV_DBG("extra: n_ctx = %d, n_extra_take = %d, n_extra = %d\n", n_ctx, n_extra_take, (int) extra_tokens.size()); + + // put the extra context before the FIM prefix + embd_inp.insert(embd_inp.begin(), extra_tokens.end() - n_extra_take, extra_tokens.end()); + + embd_inp.insert(embd_inp.end(), embd_end.begin(), embd_end.end()); + embd_inp.push_back(llama_vocab_fim_mid(vocab)); + + return embd_inp; +} + +// +// base64 utils (TODO: move to common in the future) +// + +static const std::string base64_chars = + "ABCDEFGHIJKLMNOPQRSTUVWXYZ" + "abcdefghijklmnopqrstuvwxyz" + "0123456789+/"; + +static inline bool is_base64(uint8_t c) { + return (isalnum(c) || (c == '+') || (c == '/')); +} + +static inline std::vector base64_decode(const std::string & encoded_string) { + int i = 0; + int j = 0; + int in_ = 0; + + int in_len = encoded_string.size(); + + uint8_t char_array_4[4]; + uint8_t char_array_3[3]; + + std::vector ret; + + while (in_len-- && (encoded_string[in_] != '=') && is_base64(encoded_string[in_])) { + char_array_4[i++] = encoded_string[in_]; in_++; + if (i == 4) { + for (i = 0; i < 4; i++) { + char_array_4[i] = base64_chars.find(char_array_4[i]); + } + + char_array_3[0] = ((char_array_4[0] ) << 2) + ((char_array_4[1] & 0x30) >> 4); + char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2); + char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3]; + + for (i = 0; (i < 3); i++) { + ret.push_back(char_array_3[i]); + } + + i = 0; + } + } + + if (i) { + for (j = i; j < 4; j++) { + char_array_4[j] = 0; + } + + for (j = 0; j < 4; j++) { + char_array_4[j] = base64_chars.find(char_array_4[j]); + } + + char_array_3[0] = ((char_array_4[0] ) << 2) + ((char_array_4[1] & 0x30) >> 4); + char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2); + char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3]; + + for (j = 0; j < i - 1; j++) { + ret.push_back(char_array_3[j]); + } + } + + return ret; +} + +// +// random string / id +// + +static std::string random_string() { + static const std::string str("0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"); + + std::random_device rd; + std::mt19937 generator(rd()); + + std::string result(32, ' '); + + for (int i = 0; i < 32; ++i) { + result[i] = str[generator() % str.size()]; + } + + return result; +} + +static std::string gen_chatcmplid() { + return "chatcmpl-" + random_string(); +} + +static std::string gen_tool_call_id() { + return random_string(); +} + +// +// other common utils +// + +static bool ends_with(const std::string & str, const std::string & suffix) { + return str.size() >= suffix.size() && 0 == str.compare(str.size() - suffix.size(), suffix.size(), suffix); +} + +static size_t find_partial_stop_string(const std::string &stop, const std::string &text) { + if (!text.empty() && !stop.empty()) { + const char text_last_char = text.back(); + for (int64_t char_index = stop.size() - 1; char_index >= 0; char_index--) { + if (stop[char_index] == text_last_char) { + const std::string current_partial = stop.substr(0, char_index + 1); + if (ends_with(text, current_partial)) { + return text.size() - char_index - 1; + } + } + } + } + + return std::string::npos; +} + +// TODO: reuse llama_detokenize +template +static std::string tokens_to_str(llama_context * ctx, Iter begin, Iter end) { + std::string ret; + for (; begin != end; ++begin) { + ret += common_token_to_piece(ctx, *begin); + } + + return ret; +} + +// format incomplete utf-8 multibyte character for output +static std::string tokens_to_output_formatted_string(const llama_context * ctx, const llama_token token) { + std::string out = token == LLAMA_TOKEN_NULL ? "" : common_token_to_piece(ctx, token); + + // if the size is 1 and first bit is 1, meaning it's a partial character + // (size > 1 meaning it's already a known token) + if (out.size() == 1 && (out[0] & 0x80) == 0x80) { + std::stringstream ss; + ss << std::hex << (out[0] & 0xff); + std::string res(ss.str()); + out = "byte: \\x" + res; + } + + return out; +} + +static bool server_sent_event(httplib::DataSink & sink, const char * event, const json & data) { + const std::string str = + std::string(event) + ": " + + data.dump(-1, ' ', false, json::error_handler_t::replace) + + "\n\n"; // required by RFC 8895 - A message is terminated by a blank line (two line terminators in a row). + + LOG_DBG("data stream, to_send: %s", str.c_str()); + + return sink.write(str.c_str(), str.size()); +} + +// +// OAI utils +// + +static json oaicompat_completion_params_parse(const json & body) { + json llama_params; + + if (!body.contains("prompt")) { + throw std::runtime_error("\"prompt\" is required"); + } + + // Handle "stop" field + if (body.contains("stop") && body.at("stop").is_string()) { + llama_params["stop"] = json::array({body.at("stop").get()}); + } else { + llama_params["stop"] = json_value(body, "stop", json::array()); + } + + // Handle "n" field + int n_choices = json_value(body, "n", 1); + if (n_choices != 1) { + throw std::runtime_error("Only one completion choice is allowed"); + } + + // Handle "echo" field + if (json_value(body, "echo", false)) { + throw std::runtime_error("Only no echo is supported"); + } + + // Params supported by OAI but unsupported by llama.cpp + static const std::vector unsupported_params { "best_of", "suffix" }; + for (const auto & param : unsupported_params) { + if (body.contains(param)) { + throw std::runtime_error("Unsupported param: " + param); + } + } + + // Copy remaining properties to llama_params + for (const auto & item : body.items()) { + // Exception: if "n_predict" is present, we overwrite the value specified earlier by "max_tokens" + if (!llama_params.contains(item.key()) || item.key() == "n_predict") { + llama_params[item.key()] = item.value(); + } + } + + return llama_params; +} + +static json oaicompat_completion_params_parse( + const json & body, /* openai api json semantics */ + bool use_jinja, + common_reasoning_format reasoning_format, + const struct common_chat_templates * tmpls) +{ + json llama_params; + + auto tools = json_value(body, "tools", json()); + auto stream = json_value(body, "stream", false); + + if (tools.is_array() && !tools.empty()) { + if (stream) { + throw std::runtime_error("Cannot use tools with stream"); + } + if (!use_jinja) { + throw std::runtime_error("tools param requires --jinja flag"); + } + } + if (!use_jinja) { + if (body.contains("tool_choice") && !body.at("tool_choice").is_null()) { + throw std::runtime_error("Unsupported param: tool_choice"); + } + } + + // Handle "stop" field + if (body.contains("stop") && body.at("stop").is_string()) { + llama_params["stop"] = json::array({body.at("stop").get()}); + } else { + llama_params["stop"] = json_value(body, "stop", json::array()); + } + + auto json_schema = json_value(body, "json_schema", json()); + auto grammar = json_value(body, "grammar", std::string()); + if (!json_schema.is_null() && !grammar.empty()) { + throw std::runtime_error("Cannot use both json_schema and grammar"); + } + + // Handle "response_format" field + if (body.contains("response_format")) { + json response_format = json_value(body, "response_format", json::object()); + std::string response_type = json_value(response_format, "type", std::string()); + if (response_type == "json_object") { + json_schema = json_value(response_format, "schema", json::object()); + } else if (response_type == "json_schema") { + auto schema_wrapper = json_value(response_format, "json_schema", json::object()); + json_schema = json_value(schema_wrapper, "schema", json::object()); + } else if (!response_type.empty() && response_type != "text") { + throw std::runtime_error("response_format type must be one of \"text\" or \"json_object\", but got: " + response_type); + } + } + + common_chat_templates_inputs inputs; + inputs.messages = common_chat_msgs_parse_oaicompat(body.at("messages")); + inputs.tools = common_chat_tools_parse_oaicompat(tools); + inputs.tool_choice = common_chat_tool_choice_parse_oaicompat(json_value(body, "tool_choice", std::string("auto"))); + inputs.json_schema = json_schema.is_null() ? "" : json_schema.dump(); + inputs.grammar = grammar; + inputs.add_generation_prompt = json_value(body, "add_generation_prompt", true); + inputs.use_jinja = use_jinja; + inputs.parallel_tool_calls = json_value(body, "parallel_tool_calls", false); + inputs.extract_reasoning = reasoning_format != COMMON_REASONING_FORMAT_NONE; + inputs.add_generation_prompt = json_value(body, "add_generation_prompt", true); + if (!inputs.tools.empty() && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE && body.contains("grammar")) { + throw std::runtime_error("Cannot use custom grammar constraints with tools."); + } + + // if the assistant message appears at the end of list, we do not add end-of-turn token + // for ex. this can be useful to modify the reasoning process in reasoning models + bool prefill_assistant_message = !inputs.messages.empty() && inputs.messages.back().role == "assistant"; + common_chat_msg last_message; + if (prefill_assistant_message) { + last_message = inputs.messages.back(); + inputs.messages.pop_back(); + + /* sanity check, max one assistant message at the end of the list */ + if (!inputs.messages.empty() && inputs.messages.back().role == "assistant"){ + throw std::runtime_error("Cannot have 2 or more assistant messages at the end of the list."); + } + + inputs.extract_reasoning = false; + inputs.add_generation_prompt = true; + } + + // Apply chat template to the list of messages + auto chat_params = common_chat_templates_apply(tmpls, inputs); + + /* Append assistant prefilled message */ + if (prefill_assistant_message) { + chat_params.prompt += last_message.content; + } + + llama_params["chat_format"] = static_cast(chat_params.format); + llama_params["prompt"] = chat_params.prompt; + if (!chat_params.grammar.empty()) { + llama_params["grammar"] = chat_params.grammar; + } + llama_params["grammar_lazy"] = chat_params.grammar_lazy; + auto grammar_triggers = json::array(); + for (const auto & trigger : chat_params.grammar_triggers) { + server_grammar_trigger ct(trigger); + grammar_triggers.push_back(ct.to_json()); + } + llama_params["grammar_triggers"] = grammar_triggers; + llama_params["preserved_tokens"] = chat_params.preserved_tokens; + for (const auto & stop : chat_params.additional_stops) { + llama_params["stop"].push_back(stop); + } + + // Handle "n" field + int n_choices = json_value(body, "n", 1); + if (n_choices != 1) { + throw std::runtime_error("Only one completion choice is allowed"); + } + + // Handle "logprobs" field + // TODO: The response format of this option is not yet OAI-compatible, but seems like no one really using it; We may need to fix it in the future + if (json_value(body, "logprobs", false)) { + llama_params["n_probs"] = json_value(body, "top_logprobs", 20); + } else if (body.contains("top_logprobs") && !body.at("top_logprobs").is_null()) { + throw std::runtime_error("top_logprobs requires logprobs to be set to true"); + } + + // Copy remaining properties to llama_params + // This allows user to use llama.cpp-specific params like "mirostat", ... via OAI endpoint. + // See "launch_slot_with_task()" for a complete list of params supported by llama.cpp + for (const auto & item : body.items()) { + // Exception: if "n_predict" is present, we overwrite the value specified earlier by "max_tokens" + if (!llama_params.contains(item.key()) || item.key() == "n_predict") { + llama_params[item.key()] = item.value(); + } + } + + return llama_params; +} + +static json format_embeddings_response_oaicompat(const json & request, const json & embeddings, bool use_base64 = false) { + json data = json::array(); + int32_t n_tokens = 0; + int i = 0; + for (const auto & elem : embeddings) { + json embedding_obj; + + if (use_base64) { + const auto& vec = json_value(elem, "embedding", json::array()).get>(); + const char* data_ptr = reinterpret_cast(vec.data()); + size_t data_size = vec.size() * sizeof(float); + embedding_obj = { + {"embedding", base64::encode(data_ptr, data_size)}, + {"index", i++}, + {"object", "embedding"}, + {"encoding_format", "base64"} + }; + } else { + embedding_obj = { + {"embedding", json_value(elem, "embedding", json::array())}, + {"index", i++}, + {"object", "embedding"} + }; + } + data.push_back(embedding_obj); + + n_tokens += json_value(elem, "tokens_evaluated", 0); + } + + json res = json { + {"model", json_value(request, "model", std::string(DEFAULT_OAICOMPAT_MODEL))}, + {"object", "list"}, + {"usage", json { + {"prompt_tokens", n_tokens}, + {"total_tokens", n_tokens} + }}, + {"data", data} + }; + + return res; +} + +static json format_response_rerank( + const json & request, + const json & ranks, + bool is_tei_format, + std::vector & texts) { + json res; + if (is_tei_format) { + // TEI response format + res = json::array(); + bool return_text = json_value(request, "return_text", false); + for (const auto & rank : ranks) { + int index = json_value(rank, "index", 0); + json elem = json{ + {"index", index}, + {"score", json_value(rank, "score", 0.0)}, + }; + if (return_text) { + elem["text"] = std::move(texts[index]); + } + res.push_back(elem); + } + } else { + // Jina response format + json results = json::array(); + int32_t n_tokens = 0; + for (const auto & rank : ranks) { + results.push_back(json{ + {"index", json_value(rank, "index", 0)}, + {"relevance_score", json_value(rank, "score", 0.0)}, + }); + + n_tokens += json_value(rank, "tokens_evaluated", 0); + } + + res = json{ + {"model", json_value(request, "model", std::string(DEFAULT_OAICOMPAT_MODEL))}, + {"object", "list"}, + {"usage", json{ + {"prompt_tokens", n_tokens}, + {"total_tokens", n_tokens} + }}, + {"results", results} + }; + } + + return res; +} + +static bool is_valid_utf8(const std::string & str) { + const unsigned char* bytes = reinterpret_cast(str.data()); + const unsigned char* end = bytes + str.length(); + + while (bytes < end) { + if (*bytes <= 0x7F) { + // 1-byte sequence (0xxxxxxx) + bytes++; + } else if ((*bytes & 0xE0) == 0xC0) { + // 2-byte sequence (110xxxxx 10xxxxxx) + if (end - bytes < 2 || (bytes[1] & 0xC0) != 0x80) + return false; + bytes += 2; + } else if ((*bytes & 0xF0) == 0xE0) { + // 3-byte sequence (1110xxxx 10xxxxxx 10xxxxxx) + if (end - bytes < 3 || (bytes[1] & 0xC0) != 0x80 || (bytes[2] & 0xC0) != 0x80) + return false; + bytes += 3; + } else if ((*bytes & 0xF8) == 0xF0) { + // 4-byte sequence (11110xxx 10xxxxxx 10xxxxxx 10xxxxxx) + if (end - bytes < 4 || (bytes[1] & 0xC0) != 0x80 || + (bytes[2] & 0xC0) != 0x80 || (bytes[3] & 0xC0) != 0x80) + return false; + bytes += 4; + } else { + // Invalid UTF-8 lead byte + return false; + } + } + + return true; +} + +static json format_tokenizer_response(const json & tokens) { + return json { + {"tokens", tokens} + }; +} + +static json format_detokenized_response(const std::string & content) { + return json { + {"content", content} + }; +} + +static json format_logit_bias(const std::vector & logit_bias) { + json data = json::array(); + for (const auto & lb : logit_bias) { + data.push_back(json{ + {"bias", lb.bias}, + {"token", lb.token}, + }); + } + return data; +} + +static std::string safe_json_to_str(const json & data) { + return data.dump(-1, ' ', false, json::error_handler_t::replace); +} + +static std::vector get_token_probabilities(llama_context * ctx, int idx) { + std::vector cur; + const auto * logits = llama_get_logits_ith(ctx, idx); + + const llama_model * model = llama_get_model(ctx); + const llama_vocab * vocab = llama_model_get_vocab(model); + + const int n_vocab = llama_vocab_n_tokens(vocab); + + cur.resize(n_vocab); + for (llama_token token_id = 0; token_id < n_vocab; token_id++) { + cur[token_id] = llama_token_data{token_id, logits[token_id], 0.0f}; + } + + // sort tokens by logits + std::sort(cur.begin(), cur.end(), [](const llama_token_data & a, const llama_token_data & b) { + return a.logit > b.logit; + }); + + // apply softmax + float max_l = cur[0].logit; + float cum_sum = 0.0f; + for (size_t i = 0; i < cur.size(); ++i) { + float p = expf(cur[i].logit - max_l); + cur[i].p = p; + cum_sum += p; + } + for (size_t i = 0; i < cur.size(); ++i) { + cur[i].p /= cum_sum; + } + + return cur; +} + +static bool are_lora_equal( + const std::vector & l1, + const std::vector & l2) { + if (l1.size() != l2.size()) { + return false; + } + for (size_t i = 0; i < l1.size(); ++i) { + // we don't check lora.path to reduce the time complexity + if (l1[i].scale != l2[i].scale || l1[i].ptr != l2[i].ptr) { + return false; + } + } + return true; +} + +// parse lora config from JSON request, returned a copy of lora_base with updated scale +static std::vector parse_lora_request( + const std::vector & lora_base, + const json & data) { + std::vector lora(lora_base); + int max_idx = lora.size(); + + // clear existing value + for (auto & entry : lora) { + entry.scale = 0.0f; + } + + // set value + for (const auto & entry : data) { + int id = json_value(entry, "id", -1); + float scale = json_value(entry, "scale", 0.0f); + if (0 <= id && id < max_idx) { + lora[id].scale = scale; + } else { + throw std::runtime_error("invalid adapter id"); + } + } + + return lora; +} diff --git a/tools/server/webui/.gitignore b/tools/server/webui/.gitignore new file mode 100644 index 00000000..a547bf36 --- /dev/null +++ b/tools/server/webui/.gitignore @@ -0,0 +1,24 @@ +# Logs +logs +*.log +npm-debug.log* +yarn-debug.log* +yarn-error.log* +pnpm-debug.log* +lerna-debug.log* + +node_modules +dist +dist-ssr +*.local + +# Editor directories and files +.vscode/* +!.vscode/extensions.json +.idea +.DS_Store +*.suo +*.ntvs* +*.njsproj +*.sln +*.sw? diff --git a/tools/server/webui/.prettierignore b/tools/server/webui/.prettierignore new file mode 100644 index 00000000..c0cb165b --- /dev/null +++ b/tools/server/webui/.prettierignore @@ -0,0 +1,10 @@ +**/.vscode +**/.github +**/.git +**/.svn +**/.hg +**/node_modules +**/dist +**/build + +*.config.js diff --git a/tools/server/webui/eslint.config.js b/tools/server/webui/eslint.config.js new file mode 100644 index 00000000..7c0d39b8 --- /dev/null +++ b/tools/server/webui/eslint.config.js @@ -0,0 +1,26 @@ +import js from '@eslint/js' +import globals from 'globals' +import reactHooks from 'eslint-plugin-react-hooks' +import reactRefresh from 'eslint-plugin-react-refresh' +import tseslint from 'typescript-eslint' + +export default tseslint.config( + { ignores: ['dist'] }, + { + extends: [js.configs.recommended, ...tseslint.configs.recommended], + files: ['**/*.{ts,tsx}'], + languageOptions: { + ecmaVersion: 2020, + globals: globals.browser, + }, + plugins: { + 'react-hooks': reactHooks, + 'react-refresh': reactRefresh, + }, + rules: { + ...reactHooks.configs.recommended.rules, + 'react-refresh/only-export-components': 'off', + '@typescript-eslint/no-unused-vars': 'off', + }, + }, +) diff --git a/tools/server/webui/index.html b/tools/server/webui/index.html new file mode 100644 index 00000000..471f46b3 --- /dev/null +++ b/tools/server/webui/index.html @@ -0,0 +1,16 @@ + + + + + + + ð¦ llama.cpp - chat + + +
+ + + diff --git a/tools/server/webui/package-lock.json b/tools/server/webui/package-lock.json new file mode 100644 index 00000000..b2e3cf94 --- /dev/null +++ b/tools/server/webui/package-lock.json @@ -0,0 +1,6255 @@ +{ + "name": "webui", + "version": "0.0.0", + "lockfileVersion": 3, + "requires": true, + "packages": { + "": { + "name": "webui", + "version": "0.0.0", + "dependencies": { + "@heroicons/react": "^2.2.0", + "@sec-ant/readable-stream": "^0.6.0", + "@tailwindcss/postcss": "^4.1.1", + "@tailwindcss/vite": "^4.1.1", + "@vscode/markdown-it-katex": "^1.1.1", + "autoprefixer": "^10.4.20", + "daisyui": "^5.0.12", + "dexie": "^4.0.11", + "highlight.js": "^11.10.0", + "katex": "^0.16.15", + "postcss": "^8.4.49", + "react": "^18.3.1", + "react-dom": "^18.3.1", + "react-markdown": "^9.0.3", + "react-router": "^7.1.5", + "rehype-highlight": "^7.0.2", + "rehype-katex": "^7.0.1", + "remark-breaks": "^4.0.0", + "remark-gfm": "^4.0.0", + "remark-math": "^6.0.0", + "tailwindcss": "^4.1.1", + "textlinestream": "^1.1.1", + "vite-plugin-singlefile": "^2.0.3" + }, + "devDependencies": { + "@eslint/js": "^9.17.0", + "@types/markdown-it": "^14.1.2", + "@types/node": "^22.13.1", + "@types/react": "^18.3.18", + "@types/react-dom": "^18.3.5", + "@vitejs/plugin-react": "^4.3.4", + "eslint": "^9.17.0", + "eslint-plugin-react-hooks": "^5.0.0", + "eslint-plugin-react-refresh": "^0.4.16", + "globals": "^15.14.0", + "prettier": "^3.4.2", + "sass-embedded": "^1.83.4", + "typescript": "~5.6.2", + "typescript-eslint": "^8.18.2", + "vite": "^6.0.5" + } + }, + "node_modules/@alloc/quick-lru": { + "version": "5.2.0", + "resolved": "https://registry.npmjs.org/@alloc/quick-lru/-/quick-lru-5.2.0.tgz", + "integrity": "sha512-UrcABB+4bUrFABwbluTIBErXwvbsU/V7TZWfmbgJfbkwiBuziS9gxdODUyuiecfdGQ85jglMW6juS3+z5TsKLw==", + "license": "MIT", + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/@ampproject/remapping": { + "version": "2.3.0", + "resolved": "https://registry.npmjs.org/@ampproject/remapping/-/remapping-2.3.0.tgz", + "integrity": "sha512-30iZtAPgz+LTIYoeivqYo853f02jBYSd5uGnGpkFV0M3xOt9aN73erkgYAmZU43x4VfqcnLxW9Kpg3R5LC4YYw==", + "dev": true, + "license": "Apache-2.0", + "dependencies": { + "@jridgewell/gen-mapping": "^0.3.5", + "@jridgewell/trace-mapping": "^0.3.24" + }, + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@babel/code-frame": { + "version": "7.26.2", + "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz", + "integrity": "sha512-RJlIHRueQgwWitWgF8OdFYGZX328Ax5BCemNGlqHfplnRT9ESi8JkFlvaVYbS+UubVY6dpv87Fs2u5M29iNFVQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/helper-validator-identifier": "^7.25.9", + "js-tokens": "^4.0.0", + "picocolors": "^1.0.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/compat-data": { + "version": "7.26.5", + "resolved": "https://registry.npmjs.org/@babel/compat-data/-/compat-data-7.26.5.tgz", + "integrity": "sha512-XvcZi1KWf88RVbF9wn8MN6tYFloU5qX8KjuF3E1PVBmJ9eypXfs4GRiJwLuTZL0iSnJUKn1BFPa5BPZZJyFzPg==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/core": { + "version": "7.26.7", + "resolved": "https://registry.npmjs.org/@babel/core/-/core-7.26.7.tgz", + "integrity": "sha512-SRijHmF0PSPgLIBYlWnG0hyeJLwXE2CgpsXaMOrtt2yp9/86ALw6oUlj9KYuZ0JN07T4eBMVIW4li/9S1j2BGA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@ampproject/remapping": "^2.2.0", + "@babel/code-frame": "^7.26.2", + "@babel/generator": "^7.26.5", + "@babel/helper-compilation-targets": "^7.26.5", + "@babel/helper-module-transforms": "^7.26.0", + "@babel/helpers": "^7.26.7", + "@babel/parser": "^7.26.7", + "@babel/template": "^7.25.9", + "@babel/traverse": "^7.26.7", + "@babel/types": "^7.26.7", + "convert-source-map": "^2.0.0", + "debug": "^4.1.0", + "gensync": "^1.0.0-beta.2", + "json5": "^2.2.3", + "semver": "^6.3.1" + }, + "engines": { + "node": ">=6.9.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/babel" + } + }, + "node_modules/@babel/generator": { + "version": "7.26.5", + "resolved": "https://registry.npmjs.org/@babel/generator/-/generator-7.26.5.tgz", + "integrity": "sha512-2caSP6fN9I7HOe6nqhtft7V4g7/V/gfDsC3Ag4W7kEzzvRGKqiv0pu0HogPiZ3KaVSoNDhUws6IJjDjpfmYIXw==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/parser": "^7.26.5", + "@babel/types": "^7.26.5", + "@jridgewell/gen-mapping": "^0.3.5", + "@jridgewell/trace-mapping": "^0.3.25", + "jsesc": "^3.0.2" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-compilation-targets": { + "version": "7.26.5", + "resolved": "https://registry.npmjs.org/@babel/helper-compilation-targets/-/helper-compilation-targets-7.26.5.tgz", + "integrity": "sha512-IXuyn5EkouFJscIDuFF5EsiSolseme1s0CZB+QxVugqJLYmKdxI1VfIBOst0SUu4rnk2Z7kqTwmoO1lp3HIfnA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/compat-data": "^7.26.5", + "@babel/helper-validator-option": "^7.25.9", + "browserslist": "^4.24.0", + "lru-cache": "^5.1.1", + "semver": "^6.3.1" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-module-imports": { + "version": "7.25.9", + "resolved": "https://registry.npmjs.org/@babel/helper-module-imports/-/helper-module-imports-7.25.9.tgz", + "integrity": "sha512-tnUA4RsrmflIM6W6RFTLFSXITtl0wKjgpnLgXyowocVPrbYrLUXSBXDgTs8BlbmIzIdlBySRQjINYs2BAkiLtw==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/traverse": "^7.25.9", + "@babel/types": "^7.25.9" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-module-transforms": { + "version": "7.26.0", + "resolved": "https://registry.npmjs.org/@babel/helper-module-transforms/-/helper-module-transforms-7.26.0.tgz", + "integrity": "sha512-xO+xu6B5K2czEnQye6BHA7DolFFmS3LB7stHZFaOLb1pAwO1HWLS8fXA+eh0A2yIvltPVmx3eNNDBJA2SLHXFw==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/helper-module-imports": "^7.25.9", + "@babel/helper-validator-identifier": "^7.25.9", + "@babel/traverse": "^7.25.9" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0" + } + }, + "node_modules/@babel/helper-plugin-utils": { + "version": "7.26.5", + "resolved": "https://registry.npmjs.org/@babel/helper-plugin-utils/-/helper-plugin-utils-7.26.5.tgz", + "integrity": "sha512-RS+jZcRdZdRFzMyr+wcsaqOmld1/EqTghfaBGQQd/WnRdzdlvSZ//kF7U8VQTxf1ynZ4cjUcYgjVGx13ewNPMg==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-string-parser": { + "version": "7.25.9", + "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.25.9.tgz", + "integrity": "sha512-4A/SCr/2KLd5jrtOMFzaKjVtAei3+2r/NChoBNoZ3EyP/+GlhoaEGoWOZUmFmoITP7zOJyHIMm+DYRd8o3PvHA==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-validator-identifier": { + "version": "7.25.9", + "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.25.9.tgz", + "integrity": "sha512-Ed61U6XJc3CVRfkERJWDz4dJwKe7iLmmJsbOGu9wSloNSFttHV0I8g6UAgb7qnK5ly5bGLPd4oXZlxCdANBOWQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helper-validator-option": { + "version": "7.25.9", + "resolved": "https://registry.npmjs.org/@babel/helper-validator-option/-/helper-validator-option-7.25.9.tgz", + "integrity": "sha512-e/zv1co8pp55dNdEcCynfj9X7nyUKUXoUEwfXqaZt0omVOmDe9oOTdKStH4GmAw6zxMFs50ZayuMfHDKlO7Tfw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/helpers": { + "version": "7.26.7", + "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.26.7.tgz", + "integrity": "sha512-8NHiL98vsi0mbPQmYAGWwfcFaOy4j2HY49fXJCfuDcdE7fMIsH9a7GdaeXpIBsbT7307WU8KCMp5pUVDNL4f9A==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/template": "^7.25.9", + "@babel/types": "^7.26.7" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/parser": { + "version": "7.26.7", + "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.26.7.tgz", + "integrity": "sha512-kEvgGGgEjRUutvdVvZhbn/BxVt+5VSpwXz1j3WYXQbXDo8KzFOPNG2GQbdAiNq8g6wn1yKk7C/qrke03a84V+w==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/types": "^7.26.7" + }, + "bin": { + "parser": "bin/babel-parser.js" + }, + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@babel/plugin-transform-react-jsx-self": { + "version": "7.25.9", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-react-jsx-self/-/plugin-transform-react-jsx-self-7.25.9.tgz", + "integrity": "sha512-y8quW6p0WHkEhmErnfe58r7x0A70uKphQm8Sp8cV7tjNQwK56sNVK0M73LK3WuYmsuyrftut4xAkjjgU0twaMg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/helper-plugin-utils": "^7.25.9" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/plugin-transform-react-jsx-source": { + "version": "7.25.9", + "resolved": "https://registry.npmjs.org/@babel/plugin-transform-react-jsx-source/-/plugin-transform-react-jsx-source-7.25.9.tgz", + "integrity": "sha512-+iqjT8xmXhhYv4/uiYd8FNQsraMFZIfxVSqxxVSZP0WbbSAWvBXAul0m/zu+7Vv4O/3WtApy9pmaTMiumEZgfg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/helper-plugin-utils": "^7.25.9" + }, + "engines": { + "node": ">=6.9.0" + }, + "peerDependencies": { + "@babel/core": "^7.0.0-0" + } + }, + "node_modules/@babel/template": { + "version": "7.25.9", + "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.25.9.tgz", + "integrity": "sha512-9DGttpmPvIxBb/2uwpVo3dqJ+O6RooAFOS+lB+xDqoE2PVCE8nfoHMdZLpfCQRLwvohzXISPZcgxt80xLfsuwg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/code-frame": "^7.25.9", + "@babel/parser": "^7.25.9", + "@babel/types": "^7.25.9" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/traverse": { + "version": "7.26.7", + "resolved": "https://registry.npmjs.org/@babel/traverse/-/traverse-7.26.7.tgz", + "integrity": "sha512-1x1sgeyRLC3r5fQOM0/xtQKsYjyxmFjaOrLJNtZ81inNjyJHGIolTULPiSc/2qe1/qfpFLisLQYFnnZl7QoedA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/code-frame": "^7.26.2", + "@babel/generator": "^7.26.5", + "@babel/parser": "^7.26.7", + "@babel/template": "^7.25.9", + "@babel/types": "^7.26.7", + "debug": "^4.3.1", + "globals": "^11.1.0" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@babel/traverse/node_modules/globals": { + "version": "11.12.0", + "resolved": "https://registry.npmjs.org/globals/-/globals-11.12.0.tgz", + "integrity": "sha512-WOBp/EEGUiIsJSp7wcv/y6MO+lV9UoncWqxuFfm8eBwzWNgyfBd6Gz+IeKQ9jCmyhoH99g15M3T+QaVHFjizVA==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=4" + } + }, + "node_modules/@babel/types": { + "version": "7.26.7", + "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.26.7.tgz", + "integrity": "sha512-t8kDRGrKXyp6+tjUh7hw2RLyclsW4TRoRvRHtSyAX9Bb5ldlFh+90YAYY6awRXrlB4G5G2izNeGySpATlFzmOg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/helper-string-parser": "^7.25.9", + "@babel/helper-validator-identifier": "^7.25.9" + }, + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/@bufbuild/protobuf": { + "version": "2.2.3", + "resolved": "https://registry.npmjs.org/@bufbuild/protobuf/-/protobuf-2.2.3.tgz", + "integrity": "sha512-tFQoXHJdkEOSwj5tRIZSPNUuXK3RaR7T1nUrPgbYX1pUbvqqaaZAsfo+NXBPsz5rZMSKVFrgK1WL8Q/MSLvprg==", + "devOptional": true, + "license": "(Apache-2.0 AND BSD-3-Clause)" + }, + "node_modules/@esbuild/aix-ppc64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.24.2.tgz", + "integrity": "sha512-thpVCb/rhxE/BnMLQ7GReQLLN8q9qbHmI55F4489/ByVg2aQaQ6kbcLb6FHkocZzQhxc4gx0sCk0tJkKBFzDhA==", + "cpu": [ + "ppc64" + ], + "license": "MIT", + "optional": true, + "os": [ + "aix" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/android-arm": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.24.2.tgz", + "integrity": "sha512-tmwl4hJkCfNHwFB3nBa8z1Uy3ypZpxqxfTQOcHX+xRByyYgunVbZ9MzUUfb0RxaHIMnbHagwAxuTL+tnNM+1/Q==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/android-arm64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.24.2.tgz", + "integrity": "sha512-cNLgeqCqV8WxfcTIOeL4OAtSmL8JjcN6m09XIgro1Wi7cF4t/THaWEa7eL5CMoMBdjoHOTh/vwTO/o2TRXIyzg==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/android-x64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.24.2.tgz", + "integrity": "sha512-B6Q0YQDqMx9D7rvIcsXfmJfvUYLoP722bgfBlO5cGvNVb5V/+Y7nhBE3mHV9OpxBf4eAS2S68KZztiPaWq4XYw==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/darwin-arm64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.24.2.tgz", + "integrity": "sha512-kj3AnYWc+CekmZnS5IPu9D+HWtUI49hbnyqk0FLEJDbzCIQt7hg7ucF1SQAilhtYpIujfaHr6O0UHlzzSPdOeA==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/darwin-x64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.24.2.tgz", + "integrity": "sha512-WeSrmwwHaPkNR5H3yYfowhZcbriGqooyu3zI/3GGpF8AyUdsrrP0X6KumITGA9WOyiJavnGZUwPGvxvwfWPHIA==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/freebsd-arm64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.24.2.tgz", + "integrity": "sha512-UN8HXjtJ0k/Mj6a9+5u6+2eZ2ERD7Edt1Q9IZiB5UZAIdPnVKDoG7mdTVGhHJIeEml60JteamR3qhsr1r8gXvg==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "freebsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/freebsd-x64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.24.2.tgz", + "integrity": "sha512-TvW7wE/89PYW+IevEJXZ5sF6gJRDY/14hyIGFXdIucxCsbRmLUcjseQu1SyTko+2idmCw94TgyaEZi9HUSOe3Q==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "freebsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-arm": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.24.2.tgz", + "integrity": "sha512-n0WRM/gWIdU29J57hJyUdIsk0WarGd6To0s+Y+LwvlC55wt+GT/OgkwoXCXvIue1i1sSNWblHEig00GBWiJgfA==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-arm64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.24.2.tgz", + "integrity": "sha512-7HnAD6074BW43YvvUmE/35Id9/NB7BeX5EoNkK9obndmZBUk8xmJJeU7DwmUeN7tkysslb2eSl6CTrYz6oEMQg==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-ia32": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.24.2.tgz", + "integrity": "sha512-sfv0tGPQhcZOgTKO3oBE9xpHuUqguHvSo4jl+wjnKwFpapx+vUDcawbwPNuBIAYdRAvIDBfZVvXprIj3HA+Ugw==", + "cpu": [ + "ia32" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-loong64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.24.2.tgz", + "integrity": "sha512-CN9AZr8kEndGooS35ntToZLTQLHEjtVB5n7dl8ZcTZMonJ7CCfStrYhrzF97eAecqVbVJ7APOEe18RPI4KLhwQ==", + "cpu": [ + "loong64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-mips64el": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.24.2.tgz", + "integrity": "sha512-iMkk7qr/wl3exJATwkISxI7kTcmHKE+BlymIAbHO8xanq/TjHaaVThFF6ipWzPHryoFsesNQJPE/3wFJw4+huw==", + "cpu": [ + "mips64el" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-ppc64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.24.2.tgz", + "integrity": "sha512-shsVrgCZ57Vr2L8mm39kO5PPIb+843FStGt7sGGoqiiWYconSxwTiuswC1VJZLCjNiMLAMh34jg4VSEQb+iEbw==", + "cpu": [ + "ppc64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-riscv64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.24.2.tgz", + "integrity": "sha512-4eSFWnU9Hhd68fW16GD0TINewo1L6dRrB+oLNNbYyMUAeOD2yCK5KXGK1GH4qD/kT+bTEXjsyTCiJGHPZ3eM9Q==", + "cpu": [ + "riscv64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-s390x": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.24.2.tgz", + "integrity": "sha512-S0Bh0A53b0YHL2XEXC20bHLuGMOhFDO6GN4b3YjRLK//Ep3ql3erpNcPlEFed93hsQAjAQDNsvcK+hV90FubSw==", + "cpu": [ + "s390x" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-x64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.24.2.tgz", + "integrity": "sha512-8Qi4nQcCTbLnK9WoMjdC9NiTG6/E38RNICU6sUNqK0QFxCYgoARqVqxdFmWkdonVsvGqWhmm7MO0jyTqLqwj0Q==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/netbsd-arm64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.24.2.tgz", + "integrity": "sha512-wuLK/VztRRpMt9zyHSazyCVdCXlpHkKm34WUyinD2lzK07FAHTq0KQvZZlXikNWkDGoT6x3TD51jKQ7gMVpopw==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "netbsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/netbsd-x64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.24.2.tgz", + "integrity": "sha512-VefFaQUc4FMmJuAxmIHgUmfNiLXY438XrL4GDNV1Y1H/RW3qow68xTwjZKfj/+Plp9NANmzbH5R40Meudu8mmw==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "netbsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/openbsd-arm64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.24.2.tgz", + "integrity": "sha512-YQbi46SBct6iKnszhSvdluqDmxCJA+Pu280Av9WICNwQmMxV7nLRHZfjQzwbPs3jeWnuAhE9Jy0NrnJ12Oz+0A==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "openbsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/openbsd-x64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.24.2.tgz", + "integrity": "sha512-+iDS6zpNM6EnJyWv0bMGLWSWeXGN/HTaF/LXHXHwejGsVi+ooqDfMCCTerNFxEkM3wYVcExkeGXNqshc9iMaOA==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "openbsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/sunos-x64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.24.2.tgz", + "integrity": "sha512-hTdsW27jcktEvpwNHJU4ZwWFGkz2zRJUz8pvddmXPtXDzVKTTINmlmga3ZzwcuMpUvLw7JkLy9QLKyGpD2Yxig==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "sunos" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/win32-arm64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.24.2.tgz", + "integrity": "sha512-LihEQ2BBKVFLOC9ZItT9iFprsE9tqjDjnbulhHoFxYQtQfai7qfluVODIYxt1PgdoyQkz23+01rzwNwYfutxUQ==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/win32-ia32": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.24.2.tgz", + "integrity": "sha512-q+iGUwfs8tncmFC9pcnD5IvRHAzmbwQ3GPS5/ceCyHdjXubwQWI12MKWSNSMYLJMq23/IUCvJMS76PDqXe1fxA==", + "cpu": [ + "ia32" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/win32-x64": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.24.2.tgz", + "integrity": "sha512-7VTgWzgMGvup6aSqDPLiW5zHaxYJGTO4OokMjIlrCtf+VpEL+cXKtCvg723iguPYI5oaUNdS+/V7OU2gvXVWEg==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@eslint-community/eslint-utils": { + "version": "4.4.1", + "resolved": "https://registry.npmjs.org/@eslint-community/eslint-utils/-/eslint-utils-4.4.1.tgz", + "integrity": "sha512-s3O3waFUrMV8P/XaF/+ZTp1X9XBZW1a4B97ZnjQF2KYWaFD2A8KyFBsrsfSjEmjn3RGWAIuvlneuZm3CUK3jbA==", + "dev": true, + "license": "MIT", + "dependencies": { + "eslint-visitor-keys": "^3.4.3" + }, + "engines": { + "node": "^12.22.0 || ^14.17.0 || >=16.0.0" + }, + "funding": { + "url": "https://opencollective.com/eslint" + }, + "peerDependencies": { + "eslint": "^6.0.0 || ^7.0.0 || >=8.0.0" + } + }, + "node_modules/@eslint-community/eslint-utils/node_modules/eslint-visitor-keys": { + "version": "3.4.3", + "resolved": "https://registry.npmjs.org/eslint-visitor-keys/-/eslint-visitor-keys-3.4.3.tgz", + "integrity": "sha512-wpc+LXeiyiisxPlEkUzU6svyS1frIO3Mgxj1fdy7Pm8Ygzguax2N3Fa/D/ag1WqbOprdI+uY6wMUl8/a2G+iag==", + "dev": true, + "license": "Apache-2.0", + "engines": { + "node": "^12.22.0 || ^14.17.0 || >=16.0.0" + }, + "funding": { + "url": "https://opencollective.com/eslint" + } + }, + "node_modules/@eslint-community/regexpp": { + "version": "4.12.1", + "resolved": "https://registry.npmjs.org/@eslint-community/regexpp/-/regexpp-4.12.1.tgz", + "integrity": "sha512-CCZCDJuduB9OUkFkY2IgppNZMi2lBQgD2qzwXkEia16cge2pijY/aXi96CJMquDMn3nJdlPV1A5KrJEXwfLNzQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": "^12.0.0 || ^14.0.0 || >=16.0.0" + } + }, + "node_modules/@eslint/config-array": { + "version": "0.19.2", + "resolved": "https://registry.npmjs.org/@eslint/config-array/-/config-array-0.19.2.tgz", + "integrity": "sha512-GNKqxfHG2ySmJOBSHg7LxeUx4xpuCoFjacmlCoYWEbaPXLwvfIjixRI12xCQZeULksQb23uiA8F40w5TojpV7w==", + "dev": true, + "license": "Apache-2.0", + "dependencies": { + "@eslint/object-schema": "^2.1.6", + "debug": "^4.3.1", + "minimatch": "^3.1.2" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + } + }, + "node_modules/@eslint/core": { + "version": "0.10.0", + "resolved": "https://registry.npmjs.org/@eslint/core/-/core-0.10.0.tgz", + "integrity": "sha512-gFHJ+xBOo4G3WRlR1e/3G8A6/KZAH6zcE/hkLRCZTi/B9avAG365QhFA8uOGzTMqgTghpn7/fSnscW++dpMSAw==", + "dev": true, + "license": "Apache-2.0", + "dependencies": { + "@types/json-schema": "^7.0.15" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + } + }, + "node_modules/@eslint/eslintrc": { + "version": "3.2.0", + "resolved": "https://registry.npmjs.org/@eslint/eslintrc/-/eslintrc-3.2.0.tgz", + "integrity": "sha512-grOjVNN8P3hjJn/eIETF1wwd12DdnwFDoyceUJLYYdkpbwq3nLi+4fqrTAONx7XDALqlL220wC/RHSC/QTI/0w==", + "dev": true, + "license": "MIT", + "dependencies": { + "ajv": "^6.12.4", + "debug": "^4.3.2", + "espree": "^10.0.1", + "globals": "^14.0.0", + "ignore": "^5.2.0", + "import-fresh": "^3.2.1", + "js-yaml": "^4.1.0", + "minimatch": "^3.1.2", + "strip-json-comments": "^3.1.1" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "url": "https://opencollective.com/eslint" + } + }, + "node_modules/@eslint/eslintrc/node_modules/globals": { + "version": "14.0.0", + "resolved": "https://registry.npmjs.org/globals/-/globals-14.0.0.tgz", + "integrity": "sha512-oahGvuMGQlPw/ivIYBjVSrWAfWLBeku5tpPE2fOPLi+WHffIWbuh2tCjhyQhTBPMf5E9jDEH4FOmTYgYwbKwtQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=18" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/@eslint/js": { + "version": "9.19.0", + "resolved": "https://registry.npmjs.org/@eslint/js/-/js-9.19.0.tgz", + "integrity": "sha512-rbq9/g38qjfqFLOVPvwjIvFFdNziEC5S65jmjPw5r6A//QH+W91akh9irMwjDN8zKUTak6W9EsAv4m/7Wnw0UQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + } + }, + "node_modules/@eslint/object-schema": { + "version": "2.1.6", + "resolved": "https://registry.npmjs.org/@eslint/object-schema/-/object-schema-2.1.6.tgz", + "integrity": "sha512-RBMg5FRL0I0gs51M/guSAj5/e14VQ4tpZnQNWwuDT66P14I43ItmPfIZRhO9fUVIPOAQXU47atlywZ/czoqFPA==", + "dev": true, + "license": "Apache-2.0", + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + } + }, + "node_modules/@eslint/plugin-kit": { + "version": "0.2.5", + "resolved": "https://registry.npmjs.org/@eslint/plugin-kit/-/plugin-kit-0.2.5.tgz", + "integrity": "sha512-lB05FkqEdUg2AA0xEbUz0SnkXT1LcCTa438W4IWTUh4hdOnVbQyOJ81OrDXsJk/LSiJHubgGEFoR5EHq1NsH1A==", + "dev": true, + "license": "Apache-2.0", + "dependencies": { + "@eslint/core": "^0.10.0", + "levn": "^0.4.1" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + } + }, + "node_modules/@heroicons/react": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/@heroicons/react/-/react-2.2.0.tgz", + "integrity": "sha512-LMcepvRaS9LYHJGsF0zzmgKCUim/X3N/DQKc4jepAXJ7l8QxJ1PmxJzqplF2Z3FE4PqBAIGyJAQ/w4B5dsqbtQ==", + "license": "MIT", + "peerDependencies": { + "react": ">= 16 || ^19.0.0-rc" + } + }, + "node_modules/@humanfs/core": { + "version": "0.19.1", + "resolved": "https://registry.npmjs.org/@humanfs/core/-/core-0.19.1.tgz", + "integrity": "sha512-5DyQ4+1JEUzejeK1JGICcideyfUbGixgS9jNgex5nqkW+cY7WZhxBigmieN5Qnw9ZosSNVC9KQKyb+GUaGyKUA==", + "dev": true, + "license": "Apache-2.0", + "engines": { + "node": ">=18.18.0" + } + }, + "node_modules/@humanfs/node": { + "version": "0.16.6", + "resolved": "https://registry.npmjs.org/@humanfs/node/-/node-0.16.6.tgz", + "integrity": "sha512-YuI2ZHQL78Q5HbhDiBA1X4LmYdXCKCMQIfw0pw7piHJwyREFebJUvrQN4cMssyES6x+vfUbx1CIpaQUKYdQZOw==", + "dev": true, + "license": "Apache-2.0", + "dependencies": { + "@humanfs/core": "^0.19.1", + "@humanwhocodes/retry": "^0.3.0" + }, + "engines": { + "node": ">=18.18.0" + } + }, + "node_modules/@humanfs/node/node_modules/@humanwhocodes/retry": { + "version": "0.3.1", + "resolved": "https://registry.npmjs.org/@humanwhocodes/retry/-/retry-0.3.1.tgz", + "integrity": "sha512-JBxkERygn7Bv/GbN5Rv8Ul6LVknS+5Bp6RgDC/O8gEBU/yeH5Ui5C/OlWrTb6qct7LjjfT6Re2NxB0ln0yYybA==", + "dev": true, + "license": "Apache-2.0", + "engines": { + "node": ">=18.18" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/nzakas" + } + }, + "node_modules/@humanwhocodes/module-importer": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@humanwhocodes/module-importer/-/module-importer-1.0.1.tgz", + "integrity": "sha512-bxveV4V8v5Yb4ncFTT3rPSgZBOpCkjfK0y4oVVVJwIuDVBRMDXrPyXRL988i5ap9m9bnyEEjWfm5WkBmtffLfA==", + "dev": true, + "license": "Apache-2.0", + "engines": { + "node": ">=12.22" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/nzakas" + } + }, + "node_modules/@humanwhocodes/retry": { + "version": "0.4.1", + "resolved": "https://registry.npmjs.org/@humanwhocodes/retry/-/retry-0.4.1.tgz", + "integrity": "sha512-c7hNEllBlenFTHBky65mhq8WD2kbN9Q6gk0bTk8lSBvc554jpXSkST1iePudpt7+A/AQvuHs9EMqjHDXMY1lrA==", + "dev": true, + "license": "Apache-2.0", + "engines": { + "node": ">=18.18" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/nzakas" + } + }, + "node_modules/@jridgewell/gen-mapping": { + "version": "0.3.8", + "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.8.tgz", + "integrity": "sha512-imAbBGkb+ebQyxKgzv5Hu2nmROxoDOXHh80evxdoXNOrvAnVx7zimzc1Oo5h9RlfV4vPXaE2iM5pOFbvOCClWA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jridgewell/set-array": "^1.2.1", + "@jridgewell/sourcemap-codec": "^1.4.10", + "@jridgewell/trace-mapping": "^0.3.24" + }, + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@jridgewell/resolve-uri": { + "version": "3.1.2", + "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz", + "integrity": "sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@jridgewell/set-array": { + "version": "1.2.1", + "resolved": "https://registry.npmjs.org/@jridgewell/set-array/-/set-array-1.2.1.tgz", + "integrity": "sha512-R8gLRTZeyp03ymzP/6Lil/28tGeGEzhx1q2k703KGWRAI1VdvPIXdG70VJc2pAMw3NA6JKL5hhFu1sJX0Mnn/A==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6.0.0" + } + }, + "node_modules/@jridgewell/sourcemap-codec": { + "version": "1.5.0", + "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.0.tgz", + "integrity": "sha512-gv3ZRaISU3fjPAgNsriBRqGWQL6quFx04YMPW/zD8XMLsU32mhCCbfbO6KZFLjvYpCZ8zyDEgqsgf+PwPaM7GQ==", + "dev": true, + "license": "MIT" + }, + "node_modules/@jridgewell/trace-mapping": { + "version": "0.3.25", + "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.25.tgz", + "integrity": "sha512-vNk6aEwybGtawWmy/PzwnGDOjCkLWSD2wqvjGGAgOAwCGWySYXfYoxt00IJkTF+8Lb57DwOb3Aa0o9CApepiYQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jridgewell/resolve-uri": "^3.1.0", + "@jridgewell/sourcemap-codec": "^1.4.14" + } + }, + "node_modules/@nodelib/fs.scandir": { + "version": "2.1.5", + "resolved": "https://registry.npmjs.org/@nodelib/fs.scandir/-/fs.scandir-2.1.5.tgz", + "integrity": "sha512-vq24Bq3ym5HEQm2NKCr3yXDwjc7vTsEThRDnkp2DK9p1uqLR+DHurm/NOTo0KG7HYHU7eppKZj3MyqYuMBf62g==", + "dev": true, + "license": "MIT", + "dependencies": { + "@nodelib/fs.stat": "2.0.5", + "run-parallel": "^1.1.9" + }, + "engines": { + "node": ">= 8" + } + }, + "node_modules/@nodelib/fs.stat": { + "version": "2.0.5", + "resolved": "https://registry.npmjs.org/@nodelib/fs.stat/-/fs.stat-2.0.5.tgz", + "integrity": "sha512-RkhPPp2zrqDAQA/2jNhnztcPAlv64XdhIp7a7454A5ovI7Bukxgt7MX7udwAu3zg1DcpPU0rz3VV1SeaqvY4+A==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">= 8" + } + }, + "node_modules/@nodelib/fs.walk": { + "version": "1.2.8", + "resolved": "https://registry.npmjs.org/@nodelib/fs.walk/-/fs.walk-1.2.8.tgz", + "integrity": "sha512-oGB+UxlgWcgQkgwo8GcEGwemoTFt3FIO9ababBmaGwXIoBKZ+GTy0pP185beGg7Llih/NSHSV2XAs1lnznocSg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@nodelib/fs.scandir": "2.1.5", + "fastq": "^1.6.0" + }, + "engines": { + "node": ">= 8" + } + }, + "node_modules/@rollup/rollup-android-arm-eabi": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.34.2.tgz", + "integrity": "sha512-6Fyg9yQbwJR+ykVdT9sid1oc2ewejS6h4wzQltmJfSW53N60G/ah9pngXGANdy9/aaE/TcUFpWosdm7JXS1WTQ==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ] + }, + "node_modules/@rollup/rollup-android-arm64": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.34.2.tgz", + "integrity": "sha512-K5GfWe+vtQ3kyEbihrimM38UgX57UqHp+oME7X/EX9Im6suwZfa7Hsr8AtzbJvukTpwMGs+4s29YMSO3rwWtsw==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ] + }, + "node_modules/@rollup/rollup-darwin-arm64": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.34.2.tgz", + "integrity": "sha512-PSN58XG/V/tzqDb9kDGutUruycgylMlUE59f40ny6QIRNsTEIZsrNQTJKUN2keMMSmlzgunMFqyaGLmly39sug==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ] + }, + "node_modules/@rollup/rollup-darwin-x64": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.34.2.tgz", + "integrity": "sha512-gQhK788rQJm9pzmXyfBB84VHViDERhAhzGafw+E5mUpnGKuxZGkMVDa3wgDFKT6ukLC5V7QTifzsUKdNVxp5qQ==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ] + }, + "node_modules/@rollup/rollup-freebsd-arm64": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.34.2.tgz", + "integrity": "sha512-eiaHgQwGPpxLC3+zTAcdKl4VsBl3r0AiJOd1Um/ArEzAjN/dbPK1nROHrVkdnoE6p7Svvn04w3f/jEZSTVHunA==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "freebsd" + ] + }, + "node_modules/@rollup/rollup-freebsd-x64": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.34.2.tgz", + "integrity": "sha512-lhdiwQ+jf8pewYOTG4bag0Qd68Jn1v2gO1i0mTuiD+Qkt5vNfHVK/jrT7uVvycV8ZchlzXp5HDVmhpzjC6mh0g==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "freebsd" + ] + }, + "node_modules/@rollup/rollup-linux-arm-gnueabihf": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.34.2.tgz", + "integrity": "sha512-lfqTpWjSvbgQP1vqGTXdv+/kxIznKXZlI109WkIFPbud41bjigjNmOAAKoazmRGx+k9e3rtIdbq2pQZPV1pMig==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-arm-musleabihf": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.34.2.tgz", + "integrity": "sha512-RGjqULqIurqqv+NJTyuPgdZhka8ImMLB32YwUle2BPTDqDoXNgwFjdjQC59FbSk08z0IqlRJjrJ0AvDQ5W5lpw==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-arm64-gnu": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.34.2.tgz", + "integrity": "sha512-ZvkPiheyXtXlFqHpsdgscx+tZ7hoR59vOettvArinEspq5fxSDSgfF+L5wqqJ9R4t+n53nyn0sKxeXlik7AY9Q==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-arm64-musl": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.34.2.tgz", + "integrity": "sha512-UlFk+E46TZEoxD9ufLKDBzfSG7Ki03fo6hsNRRRHF+KuvNZ5vd1RRVQm8YZlGsjcJG8R252XFK0xNPay+4WV7w==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-loongarch64-gnu": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loongarch64-gnu/-/rollup-linux-loongarch64-gnu-4.34.2.tgz", + "integrity": "sha512-hJhfsD9ykx59jZuuoQgYT1GEcNNi3RCoEmbo5OGfG8RlHOiVS7iVNev9rhLKh7UBYq409f4uEw0cclTXx8nh8Q==", + "cpu": [ + "loong64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-powerpc64le-gnu": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-powerpc64le-gnu/-/rollup-linux-powerpc64le-gnu-4.34.2.tgz", + "integrity": "sha512-g/O5IpgtrQqPegvqopvmdCF9vneLE7eqYfdPWW8yjPS8f63DNam3U4ARL1PNNB64XHZDHKpvO2Giftf43puB8Q==", + "cpu": [ + "ppc64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-riscv64-gnu": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.34.2.tgz", + "integrity": "sha512-bSQijDC96M6PuooOuXHpvXUYiIwsnDmqGU8+br2U7iPoykNi9JtMUpN7K6xml29e0evK0/g0D1qbAUzWZFHY5Q==", + "cpu": [ + "riscv64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-s390x-gnu": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.34.2.tgz", + "integrity": "sha512-49TtdeVAsdRuiUHXPrFVucaP4SivazetGUVH8CIxVsNsaPHV4PFkpLmH9LeqU/R4Nbgky9lzX5Xe1NrzLyraVA==", + "cpu": [ + "s390x" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-x64-gnu": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.34.2.tgz", + "integrity": "sha512-j+jFdfOycLIQ7FWKka9Zd3qvsIyugg5LeZuHF6kFlXo6MSOc6R1w37YUVy8VpAKd81LMWGi5g9J25P09M0SSIw==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-linux-x64-musl": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.34.2.tgz", + "integrity": "sha512-aDPHyM/D2SpXfSNCVWCxyHmOqN9qb7SWkY1+vaXqMNMXslZYnwh9V/UCudl6psyG0v6Ukj7pXanIpfZwCOEMUg==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ] + }, + "node_modules/@rollup/rollup-win32-arm64-msvc": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.34.2.tgz", + "integrity": "sha512-LQRkCyUBnAo7r8dbEdtNU08EKLCJMgAk2oP5H3R7BnUlKLqgR3dUjrLBVirmc1RK6U6qhtDw29Dimeer8d5hzQ==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ] + }, + "node_modules/@rollup/rollup-win32-ia32-msvc": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.34.2.tgz", + "integrity": "sha512-wt8OhpQUi6JuPFkm1wbVi1BByeag87LDFzeKSXzIdGcX4bMLqORTtKxLoCbV57BHYNSUSOKlSL4BYYUghainYA==", + "cpu": [ + "ia32" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ] + }, + "node_modules/@rollup/rollup-win32-x64-msvc": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.34.2.tgz", + "integrity": "sha512-rUrqINax0TvrPBXrFKg0YbQx18NpPN3NNrgmaao9xRNbTwek7lOXObhx8tQy8gelmQ/gLaGy1WptpU2eKJZImg==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ] + }, + "node_modules/@sec-ant/readable-stream": { + "version": "0.6.0", + "resolved": "https://registry.npmjs.org/@sec-ant/readable-stream/-/readable-stream-0.6.0.tgz", + "integrity": "sha512-uiBh8DrB5FN35gP6/o8JEhEQ7/ci1jUsOZO/VMUjyvTpjtV54VstOXVj1TvTj/wsT23pfX6butxxh3qufsW3+g==", + "license": "MIT" + }, + "node_modules/@tailwindcss/node": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/node/-/node-4.1.1.tgz", + "integrity": "sha512-xvlh4pvfG/bkv0fEtJDABAm1tjtSmSyi2QmS4zyj1EKNI1UiOYiUq1IphSwDsNJ5vJ9cWEGs4rJXpUdCN2kujQ==", + "license": "MIT", + "dependencies": { + "enhanced-resolve": "^5.18.1", + "jiti": "^2.4.2", + "lightningcss": "1.29.2", + "tailwindcss": "4.1.1" + } + }, + "node_modules/@tailwindcss/oxide": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide/-/oxide-4.1.1.tgz", + "integrity": "sha512-7+YBgnPQ4+jv6B6WVOerJ6WOzDzNJXrRKDts674v6TKAqFqYRr9+EBtSziO7nNcwQ8JtoZNMeqA+WJDjtCM/7w==", + "license": "MIT", + "engines": { + "node": ">= 10" + }, + "optionalDependencies": { + "@tailwindcss/oxide-android-arm64": "4.1.1", + "@tailwindcss/oxide-darwin-arm64": "4.1.1", + "@tailwindcss/oxide-darwin-x64": "4.1.1", + "@tailwindcss/oxide-freebsd-x64": "4.1.1", + "@tailwindcss/oxide-linux-arm-gnueabihf": "4.1.1", + "@tailwindcss/oxide-linux-arm64-gnu": "4.1.1", + "@tailwindcss/oxide-linux-arm64-musl": "4.1.1", + "@tailwindcss/oxide-linux-x64-gnu": "4.1.1", + "@tailwindcss/oxide-linux-x64-musl": "4.1.1", + "@tailwindcss/oxide-win32-arm64-msvc": "4.1.1", + "@tailwindcss/oxide-win32-x64-msvc": "4.1.1" + } + }, + "node_modules/@tailwindcss/oxide-android-arm64": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-android-arm64/-/oxide-android-arm64-4.1.1.tgz", + "integrity": "sha512-gTyRzfdParpoCU1yyUC/iN6XK6T0Ra4bDlF8Aeul5NP9cLzKEZDogdNVNGv5WZmCDkVol7qlex7TMmcfytMmmw==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-darwin-arm64": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-darwin-arm64/-/oxide-darwin-arm64-4.1.1.tgz", + "integrity": "sha512-dI0QbdMWBvLB3MtaTKetzUKG9CUUQow8JSP4Nm+OxVokeZ+N+f1OmZW/hW1LzMxpx9RQCBgSRL+IIvKRat5Wdg==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-darwin-x64": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-darwin-x64/-/oxide-darwin-x64-4.1.1.tgz", + "integrity": "sha512-2Y+NPQOTRBCItshPgY/CWg4bKi7E9evMg4bgdb6h9iZObCZLOe3doPcuSxGS3DB0dKyMFKE8pTdWtFUbxZBMSA==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-freebsd-x64": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-freebsd-x64/-/oxide-freebsd-x64-4.1.1.tgz", + "integrity": "sha512-N97NGMsB/7CHShbc5ube4dcsW/bYENkBrg8yWi8ieN9boYVRdw3cZviVryV/Nfu9bKbBV9kUvduFF2qBI7rEqg==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "freebsd" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-linux-arm-gnueabihf": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm-gnueabihf/-/oxide-linux-arm-gnueabihf-4.1.1.tgz", + "integrity": "sha512-33Lk6KbHnUZbXqza6RWNFo9wqPQ4+H5BAn1CkUUfC1RZ1vYbyDN6+iJPj53wmnWJ3mhRI8jWt3Jt1fO02IVdUQ==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-linux-arm64-gnu": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm64-gnu/-/oxide-linux-arm64-gnu-4.1.1.tgz", + "integrity": "sha512-LyW35RzSUy+80WYScv03HKasAUmMFDaSbNpWfk1gG5gEE9kuRGnDzSrqMoLAmY/kzMCYP/1kqmUiAx8EFLkI2A==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-linux-arm64-musl": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm64-musl/-/oxide-linux-arm64-musl-4.1.1.tgz", + "integrity": "sha512-1KPnDMlHdqjPTUSFjx55pafvs8RZXRgxfeRgUrukwDKkuj7gFk28vW3Mx65YdiugAc9NWs3VgueZWaM1Po6uGw==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-linux-x64-gnu": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-x64-gnu/-/oxide-linux-x64-gnu-4.1.1.tgz", + "integrity": "sha512-4WdzA+MRlsinEEE6yxNMLJxpw0kE9XVipbAKdTL8BeUpyC2TdA3TL46lBulXzKp3BIxh3nqyR/UCqzl5o+3waQ==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-linux-x64-musl": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-x64-musl/-/oxide-linux-x64-musl-4.1.1.tgz", + "integrity": "sha512-q7Ugbw3ARcjCW2VMUYrcMbJ6aMQuWPArBBE2EqC/swPZTdGADvMQSlvR0VKusUM4HoSsO7ZbvcZ53YwR57+AKw==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-win32-arm64-msvc": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-arm64-msvc/-/oxide-win32-arm64-msvc-4.1.1.tgz", + "integrity": "sha512-0KpqsovgHcIzm7eAGzzEZsEs0/nPYXnRBv+aPq/GehpNQuE/NAQu+YgZXIIof+VflDFuyXOEnaFr7T5MZ1INhA==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/oxide-win32-x64-msvc": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-x64-msvc/-/oxide-win32-x64-msvc-4.1.1.tgz", + "integrity": "sha512-B1mjeXNS26kBOHv5sXARf6Wd0PWHV9x1TDlW0ummrBUOUAxAy5wcy4Nii1wzNvCdvC448hgiL06ylhwAbNthmg==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">= 10" + } + }, + "node_modules/@tailwindcss/postcss": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/postcss/-/postcss-4.1.1.tgz", + "integrity": "sha512-GX9AEM+msH0i2Yh1b6CuDRaZRo3kmbvIrLbSfvJ53C3uaAgsQ//fTQAh9HMQ6t1a9zvoUptlYqG//plWsBQTCw==", + "license": "MIT", + "dependencies": { + "@alloc/quick-lru": "^5.2.0", + "@tailwindcss/node": "4.1.1", + "@tailwindcss/oxide": "4.1.1", + "postcss": "^8.4.41", + "tailwindcss": "4.1.1" + } + }, + "node_modules/@tailwindcss/vite": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/@tailwindcss/vite/-/vite-4.1.1.tgz", + "integrity": "sha512-tFTkRZwXq4XKr3S2dUZBxy80wbWYHdDSsu4QOB1yE1HJFKjfxKVpXtup4dyTVdQcLInoHC9lZXFPHnjoBP774g==", + "license": "MIT", + "dependencies": { + "@tailwindcss/node": "4.1.1", + "@tailwindcss/oxide": "4.1.1", + "tailwindcss": "4.1.1" + }, + "peerDependencies": { + "vite": "^5.2.0 || ^6" + } + }, + "node_modules/@types/babel__core": { + "version": "7.20.5", + "resolved": "https://registry.npmjs.org/@types/babel__core/-/babel__core-7.20.5.tgz", + "integrity": "sha512-qoQprZvz5wQFJwMDqeseRXWv3rqMvhgpbXFfVyWhbx9X47POIA6i/+dXefEmZKoAgOaTdaIgNSMqMIU61yRyzA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/parser": "^7.20.7", + "@babel/types": "^7.20.7", + "@types/babel__generator": "*", + "@types/babel__template": "*", + "@types/babel__traverse": "*" + } + }, + "node_modules/@types/babel__generator": { + "version": "7.6.8", + "resolved": "https://registry.npmjs.org/@types/babel__generator/-/babel__generator-7.6.8.tgz", + "integrity": "sha512-ASsj+tpEDsEiFr1arWrlN6V3mdfjRMZt6LtK/Vp/kreFLnr5QH5+DhvD5nINYZXzwJvXeGq+05iUXcAzVrqWtw==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/types": "^7.0.0" + } + }, + "node_modules/@types/babel__template": { + "version": "7.4.4", + "resolved": "https://registry.npmjs.org/@types/babel__template/-/babel__template-7.4.4.tgz", + "integrity": "sha512-h/NUaSyG5EyxBIp8YRxo4RMe2/qQgvyowRwVMzhYhBCONbW8PUsg4lkFMrhgZhUe5z3L3MiLDuvyJ/CaPa2A8A==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/parser": "^7.1.0", + "@babel/types": "^7.0.0" + } + }, + "node_modules/@types/babel__traverse": { + "version": "7.20.6", + "resolved": "https://registry.npmjs.org/@types/babel__traverse/-/babel__traverse-7.20.6.tgz", + "integrity": "sha512-r1bzfrm0tomOI8g1SzvCaQHo6Lcv6zu0EA+W2kHrt8dyrHQxGzBBL4kdkzIS+jBMV+EYcMAEAqXqYaLJq5rOZg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/types": "^7.20.7" + } + }, + "node_modules/@types/cookie": { + "version": "0.6.0", + "resolved": "https://registry.npmjs.org/@types/cookie/-/cookie-0.6.0.tgz", + "integrity": "sha512-4Kh9a6B2bQciAhf7FSuMRRkUWecJgJu9nPnx3yzpsfXX/c50REIqpHY4C82bXP90qrLtXtkDxTZosYO3UpOwlA==", + "license": "MIT" + }, + "node_modules/@types/debug": { + "version": "4.1.12", + "resolved": "https://registry.npmjs.org/@types/debug/-/debug-4.1.12.tgz", + "integrity": "sha512-vIChWdVG3LG1SMxEvI/AK+FWJthlrqlTu7fbrlywTkkaONwk/UAGaULXRlf8vkzFBLVm0zkMdCquhL5aOjhXPQ==", + "license": "MIT", + "dependencies": { + "@types/ms": "*" + } + }, + "node_modules/@types/estree": { + "version": "1.0.6", + "resolved": "https://registry.npmjs.org/@types/estree/-/estree-1.0.6.tgz", + "integrity": "sha512-AYnb1nQyY49te+VRAVgmzfcgjYS91mY5P0TKUDCLEM+gNnA+3T6rWITXRLYCpahpqSQbN5cE+gHpnPyXjHWxcw==", + "license": "MIT" + }, + "node_modules/@types/estree-jsx": { + "version": "1.0.5", + "resolved": "https://registry.npmjs.org/@types/estree-jsx/-/estree-jsx-1.0.5.tgz", + "integrity": "sha512-52CcUVNFyfb1A2ALocQw/Dd1BQFNmSdkuC3BkZ6iqhdMfQz7JWOFRuJFloOzjk+6WijU56m9oKXFAXc7o3Towg==", + "license": "MIT", + "dependencies": { + "@types/estree": "*" + } + }, + "node_modules/@types/hast": { + "version": "3.0.4", + "resolved": "https://registry.npmjs.org/@types/hast/-/hast-3.0.4.tgz", + "integrity": "sha512-WPs+bbQw5aCj+x6laNGWLH3wviHtoCv/P3+otBhbOhJgG8qtpdAMlTCxLtsTWA7LH1Oh/bFCHsBn0TPS5m30EQ==", + "license": "MIT", + "dependencies": { + "@types/unist": "*" + } + }, + "node_modules/@types/json-schema": { + "version": "7.0.15", + "resolved": "https://registry.npmjs.org/@types/json-schema/-/json-schema-7.0.15.tgz", + "integrity": "sha512-5+fP8P8MFNC+AyZCDxrB2pkZFPGzqQWUzpSeuuVLvm8VMcorNYavBqoFcxK8bQz4Qsbn4oUEEem4wDLfcysGHA==", + "dev": true, + "license": "MIT" + }, + "node_modules/@types/katex": { + "version": "0.16.7", + "resolved": "https://registry.npmjs.org/@types/katex/-/katex-0.16.7.tgz", + "integrity": "sha512-HMwFiRujE5PjrgwHQ25+bsLJgowjGjm5Z8FVSf0N6PwgJrwxH0QxzHYDcKsTfV3wva0vzrpqMTJS2jXPr5BMEQ==", + "license": "MIT" + }, + "node_modules/@types/linkify-it": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/@types/linkify-it/-/linkify-it-5.0.0.tgz", + "integrity": "sha512-sVDA58zAw4eWAffKOaQH5/5j3XeayukzDk+ewSsnv3p4yJEZHCCzMDiZM8e0OUrRvmpGZ85jf4yDHkHsgBNr9Q==", + "dev": true, + "license": "MIT" + }, + "node_modules/@types/markdown-it": { + "version": "14.1.2", + "resolved": "https://registry.npmjs.org/@types/markdown-it/-/markdown-it-14.1.2.tgz", + "integrity": "sha512-promo4eFwuiW+TfGxhi+0x3czqTYJkG8qB17ZUJiVF10Xm7NLVRSLUsfRTU/6h1e24VvRnXCx+hG7li58lkzog==", + "dev": true, + "license": "MIT", + "dependencies": { + "@types/linkify-it": "^5", + "@types/mdurl": "^2" + } + }, + "node_modules/@types/mdast": { + "version": "4.0.4", + "resolved": "https://registry.npmjs.org/@types/mdast/-/mdast-4.0.4.tgz", + "integrity": "sha512-kGaNbPh1k7AFzgpud/gMdvIm5xuECykRR+JnWKQno9TAXVa6WIVCGTPvYGekIDL4uwCZQSYbUxNBSb1aUo79oA==", + "license": "MIT", + "dependencies": { + "@types/unist": "*" + } + }, + "node_modules/@types/mdurl": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/@types/mdurl/-/mdurl-2.0.0.tgz", + "integrity": "sha512-RGdgjQUZba5p6QEFAVx2OGb8rQDL/cPRG7GiedRzMcJ1tYnUANBncjbSB1NRGwbvjcPeikRABz2nshyPk1bhWg==", + "dev": true, + "license": "MIT" + }, + "node_modules/@types/ms": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/@types/ms/-/ms-2.1.0.tgz", + "integrity": "sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA==", + "license": "MIT" + }, + "node_modules/@types/node": { + "version": "22.13.1", + "resolved": "https://registry.npmjs.org/@types/node/-/node-22.13.1.tgz", + "integrity": "sha512-jK8uzQlrvXqEU91UxiK5J7pKHyzgnI1Qnl0QDHIgVGuolJhRb9EEl28Cj9b3rGR8B2lhFCtvIm5os8lFnO/1Ew==", + "devOptional": true, + "license": "MIT", + "dependencies": { + "undici-types": "~6.20.0" + } + }, + "node_modules/@types/prop-types": { + "version": "15.7.14", + "resolved": "https://registry.npmjs.org/@types/prop-types/-/prop-types-15.7.14.tgz", + "integrity": "sha512-gNMvNH49DJ7OJYv+KAKn0Xp45p8PLl6zo2YnvDIbTd4J6MER2BmWN49TG7n9LvkyihINxeKW8+3bfS2yDC9dzQ==", + "license": "MIT" + }, + "node_modules/@types/react": { + "version": "18.3.18", + "resolved": "https://registry.npmjs.org/@types/react/-/react-18.3.18.tgz", + "integrity": "sha512-t4yC+vtgnkYjNSKlFx1jkAhH8LgTo2N/7Qvi83kdEaUtMDiwpbLAktKDaAMlRcJ5eSxZkH74eEGt1ky31d7kfQ==", + "license": "MIT", + "dependencies": { + "@types/prop-types": "*", + "csstype": "^3.0.2" + } + }, + "node_modules/@types/react-dom": { + "version": "18.3.5", + "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.3.5.tgz", + "integrity": "sha512-P4t6saawp+b/dFrUr2cvkVsfvPguwsxtH6dNIYRllMsefqFzkZk5UIjzyDOv5g1dXIPdG4Sp1yCR4Z6RCUsG/Q==", + "dev": true, + "license": "MIT", + "peerDependencies": { + "@types/react": "^18.0.0" + } + }, + "node_modules/@types/unist": { + "version": "3.0.3", + "resolved": "https://registry.npmjs.org/@types/unist/-/unist-3.0.3.tgz", + "integrity": "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==", + "license": "MIT" + }, + "node_modules/@typescript-eslint/eslint-plugin": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/@typescript-eslint/eslint-plugin/-/eslint-plugin-8.23.0.tgz", + "integrity": "sha512-vBz65tJgRrA1Q5gWlRfvoH+w943dq9K1p1yDBY2pc+a1nbBLZp7fB9+Hk8DaALUbzjqlMfgaqlVPT1REJdkt/w==", + "dev": true, + "license": "MIT", + "dependencies": { + "@eslint-community/regexpp": "^4.10.0", + "@typescript-eslint/scope-manager": "8.23.0", + "@typescript-eslint/type-utils": "8.23.0", + "@typescript-eslint/utils": "8.23.0", + "@typescript-eslint/visitor-keys": "8.23.0", + "graphemer": "^1.4.0", + "ignore": "^5.3.1", + "natural-compare": "^1.4.0", + "ts-api-utils": "^2.0.1" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + }, + "peerDependencies": { + "@typescript-eslint/parser": "^8.0.0 || ^8.0.0-alpha.0", + "eslint": "^8.57.0 || ^9.0.0", + "typescript": ">=4.8.4 <5.8.0" + } + }, + "node_modules/@typescript-eslint/parser": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/@typescript-eslint/parser/-/parser-8.23.0.tgz", + "integrity": "sha512-h2lUByouOXFAlMec2mILeELUbME5SZRN/7R9Cw2RD2lRQQY08MWMM+PmVVKKJNK1aIwqTo9t/0CvOxwPbRIE2Q==", + "dev": true, + "license": "MIT", + "dependencies": { + "@typescript-eslint/scope-manager": "8.23.0", + "@typescript-eslint/types": "8.23.0", + "@typescript-eslint/typescript-estree": "8.23.0", + "@typescript-eslint/visitor-keys": "8.23.0", + "debug": "^4.3.4" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + }, + "peerDependencies": { + "eslint": "^8.57.0 || ^9.0.0", + "typescript": ">=4.8.4 <5.8.0" + } + }, + "node_modules/@typescript-eslint/scope-manager": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/@typescript-eslint/scope-manager/-/scope-manager-8.23.0.tgz", + "integrity": "sha512-OGqo7+dXHqI7Hfm+WqkZjKjsiRtFUQHPdGMXzk5mYXhJUedO7e/Y7i8AK3MyLMgZR93TX4bIzYrfyVjLC+0VSw==", + "dev": true, + "license": "MIT", + "dependencies": { + "@typescript-eslint/types": "8.23.0", + "@typescript-eslint/visitor-keys": "8.23.0" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + } + }, + "node_modules/@typescript-eslint/type-utils": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/@typescript-eslint/type-utils/-/type-utils-8.23.0.tgz", + "integrity": "sha512-iIuLdYpQWZKbiH+RkCGc6iu+VwscP5rCtQ1lyQ7TYuKLrcZoeJVpcLiG8DliXVkUxirW/PWlmS+d6yD51L9jvA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@typescript-eslint/typescript-estree": "8.23.0", + "@typescript-eslint/utils": "8.23.0", + "debug": "^4.3.4", + "ts-api-utils": "^2.0.1" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + }, + "peerDependencies": { + "eslint": "^8.57.0 || ^9.0.0", + "typescript": ">=4.8.4 <5.8.0" + } + }, + "node_modules/@typescript-eslint/types": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/@typescript-eslint/types/-/types-8.23.0.tgz", + "integrity": "sha512-1sK4ILJbCmZOTt9k4vkoulT6/y5CHJ1qUYxqpF1K/DBAd8+ZUL4LlSCxOssuH5m4rUaaN0uS0HlVPvd45zjduQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + } + }, + "node_modules/@typescript-eslint/typescript-estree": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/@typescript-eslint/typescript-estree/-/typescript-estree-8.23.0.tgz", + "integrity": "sha512-LcqzfipsB8RTvH8FX24W4UUFk1bl+0yTOf9ZA08XngFwMg4Kj8A+9hwz8Cr/ZS4KwHrmo9PJiLZkOt49vPnuvQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@typescript-eslint/types": "8.23.0", + "@typescript-eslint/visitor-keys": "8.23.0", + "debug": "^4.3.4", + "fast-glob": "^3.3.2", + "is-glob": "^4.0.3", + "minimatch": "^9.0.4", + "semver": "^7.6.0", + "ts-api-utils": "^2.0.1" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + }, + "peerDependencies": { + "typescript": ">=4.8.4 <5.8.0" + } + }, + "node_modules/@typescript-eslint/typescript-estree/node_modules/brace-expansion": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz", + "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==", + "dev": true, + "license": "MIT", + "dependencies": { + "balanced-match": "^1.0.0" + } + }, + "node_modules/@typescript-eslint/typescript-estree/node_modules/minimatch": { + "version": "9.0.5", + "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-9.0.5.tgz", + "integrity": "sha512-G6T0ZX48xgozx7587koeX9Ys2NYy6Gmv//P89sEte9V9whIapMNF4idKxnW2QtCcLiTWlb/wfCabAtAFWhhBow==", + "dev": true, + "license": "ISC", + "dependencies": { + "brace-expansion": "^2.0.1" + }, + "engines": { + "node": ">=16 || 14 >=14.17" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/@typescript-eslint/typescript-estree/node_modules/semver": { + "version": "7.7.1", + "resolved": "https://registry.npmjs.org/semver/-/semver-7.7.1.tgz", + "integrity": "sha512-hlq8tAfn0m/61p4BVRcPzIGr6LKiMwo4VM6dGi6pt4qcRkmNzTcWq6eCEjEh+qXjkMDvPlOFFSGwQjoEa6gyMA==", + "dev": true, + "license": "ISC", + "bin": { + "semver": "bin/semver.js" + }, + "engines": { + "node": ">=10" + } + }, + "node_modules/@typescript-eslint/utils": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/@typescript-eslint/utils/-/utils-8.23.0.tgz", + "integrity": "sha512-uB/+PSo6Exu02b5ZEiVtmY6RVYO7YU5xqgzTIVZwTHvvK3HsL8tZZHFaTLFtRG3CsV4A5mhOv+NZx5BlhXPyIA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@eslint-community/eslint-utils": "^4.4.0", + "@typescript-eslint/scope-manager": "8.23.0", + "@typescript-eslint/types": "8.23.0", + "@typescript-eslint/typescript-estree": "8.23.0" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + }, + "peerDependencies": { + "eslint": "^8.57.0 || ^9.0.0", + "typescript": ">=4.8.4 <5.8.0" + } + }, + "node_modules/@typescript-eslint/visitor-keys": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/@typescript-eslint/visitor-keys/-/visitor-keys-8.23.0.tgz", + "integrity": "sha512-oWWhcWDLwDfu++BGTZcmXWqpwtkwb5o7fxUIGksMQQDSdPW9prsSnfIOZMlsj4vBOSrcnjIUZMiIjODgGosFhQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@typescript-eslint/types": "8.23.0", + "eslint-visitor-keys": "^4.2.0" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + } + }, + "node_modules/@ungap/structured-clone": { + "version": "1.3.0", + "resolved": "https://registry.npmjs.org/@ungap/structured-clone/-/structured-clone-1.3.0.tgz", + "integrity": "sha512-WmoN8qaIAo7WTYWbAZuG8PYEhn5fkz7dZrqTBZ7dtt//lL2Gwms1IcnQ5yHqjDfX8Ft5j4YzDM23f87zBfDe9g==", + "license": "ISC" + }, + "node_modules/@vitejs/plugin-react": { + "version": "4.3.4", + "resolved": "https://registry.npmjs.org/@vitejs/plugin-react/-/plugin-react-4.3.4.tgz", + "integrity": "sha512-SCCPBJtYLdE8PX/7ZQAs1QAZ8Jqwih+0VBLum1EGqmCCQal+MIUqLCzj3ZUy8ufbC0cAM4LRlSTm7IQJwWT4ug==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/core": "^7.26.0", + "@babel/plugin-transform-react-jsx-self": "^7.25.9", + "@babel/plugin-transform-react-jsx-source": "^7.25.9", + "@types/babel__core": "^7.20.5", + "react-refresh": "^0.14.2" + }, + "engines": { + "node": "^14.18.0 || >=16.0.0" + }, + "peerDependencies": { + "vite": "^4.2.0 || ^5.0.0 || ^6.0.0" + } + }, + "node_modules/@vscode/markdown-it-katex": { + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/@vscode/markdown-it-katex/-/markdown-it-katex-1.1.1.tgz", + "integrity": "sha512-3KTlbsRBPJQLE2YmLL7K6nunTlU+W9T5+FjfNdWuIUKgxSS6HWLQHaO3L4MkJi7z7MpIPpY+g4N+cWNBPE/MSA==", + "license": "MIT", + "dependencies": { + "katex": "^0.16.4" + } + }, + "node_modules/acorn": { + "version": "8.14.0", + "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.14.0.tgz", + "integrity": "sha512-cl669nCJTZBsL97OF4kUQm5g5hC2uihk0NxY3WENAC0TYdILVkAyHymAntgxGkl7K+t0cXIrH5siy5S4XkFycA==", + "dev": true, + "license": "MIT", + "bin": { + "acorn": "bin/acorn" + }, + "engines": { + "node": ">=0.4.0" + } + }, + "node_modules/acorn-jsx": { + "version": "5.3.2", + "resolved": "https://registry.npmjs.org/acorn-jsx/-/acorn-jsx-5.3.2.tgz", + "integrity": "sha512-rq9s+JNhf0IChjtDXxllJ7g41oZk5SlXtp0LHwyA5cejwn7vKmKp4pPri6YEePv2PU65sAsegbXtIinmDFDXgQ==", + "dev": true, + "license": "MIT", + "peerDependencies": { + "acorn": "^6.0.0 || ^7.0.0 || ^8.0.0" + } + }, + "node_modules/ajv": { + "version": "6.12.6", + "resolved": "https://registry.npmjs.org/ajv/-/ajv-6.12.6.tgz", + "integrity": "sha512-j3fVLgvTo527anyYyJOGTYJbG+vnnQYvE0m5mmkc1TK+nxAppkCLMIL0aZ4dblVCNoGShhm+kzE4ZUykBoMg4g==", + "dev": true, + "license": "MIT", + "dependencies": { + "fast-deep-equal": "^3.1.1", + "fast-json-stable-stringify": "^2.0.0", + "json-schema-traverse": "^0.4.1", + "uri-js": "^4.2.2" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/epoberezkin" + } + }, + "node_modules/ansi-styles": { + "version": "4.3.0", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.3.0.tgz", + "integrity": "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==", + "dev": true, + "license": "MIT", + "dependencies": { + "color-convert": "^2.0.1" + }, + "engines": { + "node": ">=8" + }, + "funding": { + "url": "https://github.com/chalk/ansi-styles?sponsor=1" + } + }, + "node_modules/argparse": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/argparse/-/argparse-2.0.1.tgz", + "integrity": "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q==", + "dev": true, + "license": "Python-2.0" + }, + "node_modules/autoprefixer": { + "version": "10.4.20", + "resolved": "https://registry.npmjs.org/autoprefixer/-/autoprefixer-10.4.20.tgz", + "integrity": "sha512-XY25y5xSv/wEoqzDyXXME4AFfkZI0P23z6Fs3YgymDnKJkCGOnkL0iTxCa85UTqaSgfcqyf3UA6+c7wUvx/16g==", + "funding": [ + { + "type": "opencollective", + "url": "https://opencollective.com/postcss/" + }, + { + "type": "tidelift", + "url": "https://tidelift.com/funding/github/npm/autoprefixer" + }, + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ], + "license": "MIT", + "dependencies": { + "browserslist": "^4.23.3", + "caniuse-lite": "^1.0.30001646", + "fraction.js": "^4.3.7", + "normalize-range": "^0.1.2", + "picocolors": "^1.0.1", + "postcss-value-parser": "^4.2.0" + }, + "bin": { + "autoprefixer": "bin/autoprefixer" + }, + "engines": { + "node": "^10 || ^12 || >=14" + }, + "peerDependencies": { + "postcss": "^8.1.0" + } + }, + "node_modules/bail": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/bail/-/bail-2.0.2.tgz", + "integrity": "sha512-0xO6mYd7JB2YesxDKplafRpsiOzPt9V02ddPCLbY1xYGPOX24NTyN50qnUxgCPcSoYMhKpAuBTjQoRZCAkUDRw==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/balanced-match": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz", + "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==", + "dev": true, + "license": "MIT" + }, + "node_modules/brace-expansion": { + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz", + "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==", + "dev": true, + "license": "MIT", + "dependencies": { + "balanced-match": "^1.0.0", + "concat-map": "0.0.1" + } + }, + "node_modules/braces": { + "version": "3.0.3", + "resolved": "https://registry.npmjs.org/braces/-/braces-3.0.3.tgz", + "integrity": "sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==", + "license": "MIT", + "dependencies": { + "fill-range": "^7.1.1" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/browserslist": { + "version": "4.24.4", + "resolved": "https://registry.npmjs.org/browserslist/-/browserslist-4.24.4.tgz", + "integrity": "sha512-KDi1Ny1gSePi1vm0q4oxSF8b4DR44GF4BbmS2YdhPLOEqd8pDviZOGH/GsmRwoWJ2+5Lr085X7naowMwKHDG1A==", + "funding": [ + { + "type": "opencollective", + "url": "https://opencollective.com/browserslist" + }, + { + "type": "tidelift", + "url": "https://tidelift.com/funding/github/npm/browserslist" + }, + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ], + "license": "MIT", + "dependencies": { + "caniuse-lite": "^1.0.30001688", + "electron-to-chromium": "^1.5.73", + "node-releases": "^2.0.19", + "update-browserslist-db": "^1.1.1" + }, + "bin": { + "browserslist": "cli.js" + }, + "engines": { + "node": "^6 || ^7 || ^8 || ^9 || ^10 || ^11 || ^12 || >=13.7" + } + }, + "node_modules/buffer-builder": { + "version": "0.2.0", + "resolved": "https://registry.npmjs.org/buffer-builder/-/buffer-builder-0.2.0.tgz", + "integrity": "sha512-7VPMEPuYznPSoR21NE1zvd2Xna6c/CloiZCfcMXR1Jny6PjX0N4Nsa38zcBFo/FMK+BlA+FLKbJCQ0i2yxp+Xg==", + "devOptional": true, + "license": "MIT/X11" + }, + "node_modules/callsites": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz", + "integrity": "sha512-P8BjAsXvZS+VIDUI11hHCQEv74YT67YUi5JJFNWIqL235sBmjX4+qx9Muvls5ivyNENctx46xQLQ3aTuE7ssaQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6" + } + }, + "node_modules/caniuse-lite": { + "version": "1.0.30001697", + "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001697.tgz", + "integrity": "sha512-GwNPlWJin8E+d7Gxq96jxM6w0w+VFeyyXRsjU58emtkYqnbwHqXm5uT2uCmO0RQE9htWknOP4xtBlLmM/gWxvQ==", + "funding": [ + { + "type": "opencollective", + "url": "https://opencollective.com/browserslist" + }, + { + "type": "tidelift", + "url": "https://tidelift.com/funding/github/npm/caniuse-lite" + }, + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ], + "license": "CC-BY-4.0" + }, + "node_modules/ccount": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/ccount/-/ccount-2.0.1.tgz", + "integrity": "sha512-eyrF0jiFpY+3drT6383f1qhkbGsLSifNAjA61IUjZjmLCWjItY6LB9ft9YhoDgwfmclB2zhu51Lc7+95b8NRAg==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/chalk": { + "version": "4.1.2", + "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz", + "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==", + "dev": true, + "license": "MIT", + "dependencies": { + "ansi-styles": "^4.1.0", + "supports-color": "^7.1.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/chalk?sponsor=1" + } + }, + "node_modules/character-entities": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/character-entities/-/character-entities-2.0.2.tgz", + "integrity": "sha512-shx7oQ0Awen/BRIdkjkvz54PnEEI/EjwXDSIZp86/KKdbafHh1Df/RYGBhn4hbe2+uKC9FnT5UCEdyPz3ai9hQ==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/character-entities-html4": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/character-entities-html4/-/character-entities-html4-2.1.0.tgz", + "integrity": "sha512-1v7fgQRj6hnSwFpq1Eu0ynr/CDEw0rXo2B61qXrLNdHZmPKgb7fqS1a2JwF0rISo9q77jDI8VMEHoApn8qDoZA==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/character-entities-legacy": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/character-entities-legacy/-/character-entities-legacy-3.0.0.tgz", + "integrity": "sha512-RpPp0asT/6ufRm//AJVwpViZbGM/MkjQFxJccQRHmISF/22NBtsHqAWmL+/pmkPWoIUJdWyeVleTl1wydHATVQ==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/character-reference-invalid": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/character-reference-invalid/-/character-reference-invalid-2.0.1.tgz", + "integrity": "sha512-iBZ4F4wRbyORVsu0jPV7gXkOsGYjGHPmAyv+HiHG8gi5PtC9KI2j1+v8/tlibRvjoWX027ypmG/n0HtO5t7unw==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/color-convert": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz", + "integrity": "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "color-name": "~1.1.4" + }, + "engines": { + "node": ">=7.0.0" + } + }, + "node_modules/color-name": { + "version": "1.1.4", + "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz", + "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==", + "dev": true, + "license": "MIT" + }, + "node_modules/colorjs.io": { + "version": "0.5.2", + "resolved": "https://registry.npmjs.org/colorjs.io/-/colorjs.io-0.5.2.tgz", + "integrity": "sha512-twmVoizEW7ylZSN32OgKdXRmo1qg+wT5/6C3xu5b9QsWzSFAhHLn2xd8ro0diCsKfCj1RdaTP/nrcW+vAoQPIw==", + "devOptional": true, + "license": "MIT" + }, + "node_modules/comma-separated-tokens": { + "version": "2.0.3", + "resolved": "https://registry.npmjs.org/comma-separated-tokens/-/comma-separated-tokens-2.0.3.tgz", + "integrity": "sha512-Fu4hJdvzeylCfQPp9SGWidpzrMs7tTrlu6Vb8XGaRGck8QSNZJJp538Wrb60Lax4fPwR64ViY468OIUTbRlGZg==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/commander": { + "version": "8.3.0", + "resolved": "https://registry.npmjs.org/commander/-/commander-8.3.0.tgz", + "integrity": "sha512-OkTL9umf+He2DZkUq8f8J9of7yL6RJKI24dVITBmNfZBmri9zYZQrKkuXiKhyfPSu8tUhnVBB1iKXevvnlR4Ww==", + "license": "MIT", + "engines": { + "node": ">= 12" + } + }, + "node_modules/concat-map": { + "version": "0.0.1", + "resolved": "https://registry.npmjs.org/concat-map/-/concat-map-0.0.1.tgz", + "integrity": "sha512-/Srv4dswyQNBfohGpz9o6Yb3Gz3SrUDqBH5rTuhGR7ahtlbYKnVxw2bCFMRljaA7EXHaXZ8wsHdodFvbkhKmqg==", + "dev": true, + "license": "MIT" + }, + "node_modules/convert-source-map": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/convert-source-map/-/convert-source-map-2.0.0.tgz", + "integrity": "sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg==", + "dev": true, + "license": "MIT" + }, + "node_modules/cookie": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/cookie/-/cookie-1.0.2.tgz", + "integrity": "sha512-9Kr/j4O16ISv8zBBhJoi4bXOYNTkFLOqSL3UDB0njXxCXNezjeyVrJyGOWtgfs/q2km1gwBcfH8q1yEGoMYunA==", + "license": "MIT", + "engines": { + "node": ">=18" + } + }, + "node_modules/cross-spawn": { + "version": "7.0.6", + "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz", + "integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==", + "dev": true, + "license": "MIT", + "dependencies": { + "path-key": "^3.1.0", + "shebang-command": "^2.0.0", + "which": "^2.0.1" + }, + "engines": { + "node": ">= 8" + } + }, + "node_modules/csstype": { + "version": "3.1.3", + "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.1.3.tgz", + "integrity": "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw==", + "license": "MIT" + }, + "node_modules/daisyui": { + "version": "5.0.12", + "resolved": "https://registry.npmjs.org/daisyui/-/daisyui-5.0.12.tgz", + "integrity": "sha512-01DU0eYBcHgPtuf5fxcrkGkIN6/Uyaqmkle5Yo3ZyW9YVAu036ALZbjv2KH5euvUbeQ4r9q3gAarGcf7Tywhng==", + "license": "MIT", + "funding": { + "url": "https://github.com/saadeghi/daisyui?sponsor=1" + } + }, + "node_modules/debug": { + "version": "4.4.0", + "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.0.tgz", + "integrity": "sha512-6WTZ/IxCY/T6BALoZHaE4ctp9xm+Z5kY/pzYaCHRFeyVhojxlrm+46y68HA6hr0TcwEssoxNiDEUJQjfPZ/RYA==", + "license": "MIT", + "dependencies": { + "ms": "^2.1.3" + }, + "engines": { + "node": ">=6.0" + }, + "peerDependenciesMeta": { + "supports-color": { + "optional": true + } + } + }, + "node_modules/decode-named-character-reference": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/decode-named-character-reference/-/decode-named-character-reference-1.0.2.tgz", + "integrity": "sha512-O8x12RzrUF8xyVcY0KJowWsmaJxQbmy0/EtnNtHRpsOcT7dFk5W598coHqBVpmWo1oQQfsCqfCmkZN5DJrZVdg==", + "license": "MIT", + "dependencies": { + "character-entities": "^2.0.0" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/deep-is": { + "version": "0.1.4", + "resolved": "https://registry.npmjs.org/deep-is/-/deep-is-0.1.4.tgz", + "integrity": "sha512-oIPzksmTg4/MriiaYGO+okXDT7ztn/w3Eptv/+gSIdMdKsJo0u4CfYNFJPy+4SKMuCqGw2wxnA+URMg3t8a/bQ==", + "dev": true, + "license": "MIT" + }, + "node_modules/dequal": { + "version": "2.0.3", + "resolved": "https://registry.npmjs.org/dequal/-/dequal-2.0.3.tgz", + "integrity": "sha512-0je+qPKHEMohvfRTCEo3CrPG6cAzAYgmzKyxRiYSSDkS6eGJdyVJm7WaYA5ECaAD9wLB2T4EEeymA5aFVcYXCA==", + "license": "MIT", + "engines": { + "node": ">=6" + } + }, + "node_modules/detect-libc": { + "version": "2.0.3", + "resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.0.3.tgz", + "integrity": "sha512-bwy0MGW55bG41VqxxypOsdSdGqLwXPI/focwgTYCFMbdUiBAxLg9CFzG08sz2aqzknwiX7Hkl0bQENjg8iLByw==", + "license": "Apache-2.0", + "engines": { + "node": ">=8" + } + }, + "node_modules/devlop": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/devlop/-/devlop-1.1.0.tgz", + "integrity": "sha512-RWmIqhcFf1lRYBvNmr7qTNuyCt/7/ns2jbpp1+PalgE/rDQcBT0fioSMUpJ93irlUhC5hrg4cYqe6U+0ImW0rA==", + "license": "MIT", + "dependencies": { + "dequal": "^2.0.0" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/dexie": { + "version": "4.0.11", + "resolved": "https://registry.npmjs.org/dexie/-/dexie-4.0.11.tgz", + "integrity": "sha512-SOKO002EqlvBYYKQSew3iymBoN2EQ4BDw/3yprjh7kAfFzjBYkaMNa/pZvcA7HSWlcKSQb9XhPe3wKyQ0x4A8A==", + "license": "Apache-2.0" + }, + "node_modules/electron-to-chromium": { + "version": "1.5.91", + "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.91.tgz", + "integrity": "sha512-sNSHHyq048PFmZY4S90ax61q+gLCs0X0YmcOII9wG9S2XwbVr+h4VW2wWhnbp/Eys3cCwTxVF292W3qPaxIapQ==", + "license": "ISC" + }, + "node_modules/enhanced-resolve": { + "version": "5.18.1", + "resolved": "https://registry.npmjs.org/enhanced-resolve/-/enhanced-resolve-5.18.1.tgz", + "integrity": "sha512-ZSW3ma5GkcQBIpwZTSRAI8N71Uuwgs93IezB7mf7R60tC8ZbJideoDNKjHn2O9KIlx6rkGTTEk1xUCK2E1Y2Yg==", + "license": "MIT", + "dependencies": { + "graceful-fs": "^4.2.4", + "tapable": "^2.2.0" + }, + "engines": { + "node": ">=10.13.0" + } + }, + "node_modules/entities": { + "version": "4.5.0", + "resolved": "https://registry.npmjs.org/entities/-/entities-4.5.0.tgz", + "integrity": "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, + "node_modules/esbuild": { + "version": "0.24.2", + "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.24.2.tgz", + "integrity": "sha512-+9egpBW8I3CD5XPe0n6BfT5fxLzxrlDzqydF3aviG+9ni1lDC/OvMHcxqEFV0+LANZG5R1bFMWfUrjVsdwxJvA==", + "hasInstallScript": true, + "license": "MIT", + "bin": { + "esbuild": "bin/esbuild" + }, + "engines": { + "node": ">=18" + }, + "optionalDependencies": { + "@esbuild/aix-ppc64": "0.24.2", + "@esbuild/android-arm": "0.24.2", + "@esbuild/android-arm64": "0.24.2", + "@esbuild/android-x64": "0.24.2", + "@esbuild/darwin-arm64": "0.24.2", + "@esbuild/darwin-x64": "0.24.2", + "@esbuild/freebsd-arm64": "0.24.2", + "@esbuild/freebsd-x64": "0.24.2", + "@esbuild/linux-arm": "0.24.2", + "@esbuild/linux-arm64": "0.24.2", + "@esbuild/linux-ia32": "0.24.2", + "@esbuild/linux-loong64": "0.24.2", + "@esbuild/linux-mips64el": "0.24.2", + "@esbuild/linux-ppc64": "0.24.2", + "@esbuild/linux-riscv64": "0.24.2", + "@esbuild/linux-s390x": "0.24.2", + "@esbuild/linux-x64": "0.24.2", + "@esbuild/netbsd-arm64": "0.24.2", + "@esbuild/netbsd-x64": "0.24.2", + "@esbuild/openbsd-arm64": "0.24.2", + "@esbuild/openbsd-x64": "0.24.2", + "@esbuild/sunos-x64": "0.24.2", + "@esbuild/win32-arm64": "0.24.2", + "@esbuild/win32-ia32": "0.24.2", + "@esbuild/win32-x64": "0.24.2" + } + }, + "node_modules/escalade": { + "version": "3.2.0", + "resolved": "https://registry.npmjs.org/escalade/-/escalade-3.2.0.tgz", + "integrity": "sha512-WUj2qlxaQtO4g6Pq5c29GTcWGDyd8itL8zTlipgECz3JesAiiOKotd8JU6otB3PACgG6xkJUyVhboMS+bje/jA==", + "license": "MIT", + "engines": { + "node": ">=6" + } + }, + "node_modules/escape-string-regexp": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-4.0.0.tgz", + "integrity": "sha512-TtpcNJ3XAzx3Gq8sWRzJaVajRs0uVxA2YAkdb1jm2YkPz4G6egUFAyA3n5vtEIZefPk5Wa4UXbKuS5fKkJWdgA==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/eslint": { + "version": "9.19.0", + "resolved": "https://registry.npmjs.org/eslint/-/eslint-9.19.0.tgz", + "integrity": "sha512-ug92j0LepKlbbEv6hD911THhoRHmbdXt2gX+VDABAW/Ir7D3nqKdv5Pf5vtlyY6HQMTEP2skXY43ueqTCWssEA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@eslint-community/eslint-utils": "^4.2.0", + "@eslint-community/regexpp": "^4.12.1", + "@eslint/config-array": "^0.19.0", + "@eslint/core": "^0.10.0", + "@eslint/eslintrc": "^3.2.0", + "@eslint/js": "9.19.0", + "@eslint/plugin-kit": "^0.2.5", + "@humanfs/node": "^0.16.6", + "@humanwhocodes/module-importer": "^1.0.1", + "@humanwhocodes/retry": "^0.4.1", + "@types/estree": "^1.0.6", + "@types/json-schema": "^7.0.15", + "ajv": "^6.12.4", + "chalk": "^4.0.0", + "cross-spawn": "^7.0.6", + "debug": "^4.3.2", + "escape-string-regexp": "^4.0.0", + "eslint-scope": "^8.2.0", + "eslint-visitor-keys": "^4.2.0", + "espree": "^10.3.0", + "esquery": "^1.5.0", + "esutils": "^2.0.2", + "fast-deep-equal": "^3.1.3", + "file-entry-cache": "^8.0.0", + "find-up": "^5.0.0", + "glob-parent": "^6.0.2", + "ignore": "^5.2.0", + "imurmurhash": "^0.1.4", + "is-glob": "^4.0.0", + "json-stable-stringify-without-jsonify": "^1.0.1", + "lodash.merge": "^4.6.2", + "minimatch": "^3.1.2", + "natural-compare": "^1.4.0", + "optionator": "^0.9.3" + }, + "bin": { + "eslint": "bin/eslint.js" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "url": "https://eslint.org/donate" + }, + "peerDependencies": { + "jiti": "*" + }, + "peerDependenciesMeta": { + "jiti": { + "optional": true + } + } + }, + "node_modules/eslint-plugin-react-hooks": { + "version": "5.1.0", + "resolved": "https://registry.npmjs.org/eslint-plugin-react-hooks/-/eslint-plugin-react-hooks-5.1.0.tgz", + "integrity": "sha512-mpJRtPgHN2tNAvZ35AMfqeB3Xqeo273QxrHJsbBEPWODRM4r0yB6jfoROqKEYrOn27UtRPpcpHc2UqyBSuUNTw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=10" + }, + "peerDependencies": { + "eslint": "^3.0.0 || ^4.0.0 || ^5.0.0 || ^6.0.0 || ^7.0.0 || ^8.0.0-0 || ^9.0.0" + } + }, + "node_modules/eslint-plugin-react-refresh": { + "version": "0.4.18", + "resolved": "https://registry.npmjs.org/eslint-plugin-react-refresh/-/eslint-plugin-react-refresh-0.4.18.tgz", + "integrity": "sha512-IRGEoFn3OKalm3hjfolEWGqoF/jPqeEYFp+C8B0WMzwGwBMvlRDQd06kghDhF0C61uJ6WfSDhEZE/sAQjduKgw==", + "dev": true, + "license": "MIT", + "peerDependencies": { + "eslint": ">=8.40" + } + }, + "node_modules/eslint-scope": { + "version": "8.2.0", + "resolved": "https://registry.npmjs.org/eslint-scope/-/eslint-scope-8.2.0.tgz", + "integrity": "sha512-PHlWUfG6lvPc3yvP5A4PNyBL1W8fkDUccmI21JUu/+GKZBoH/W5u6usENXUrWFRsyoW5ACUjFGgAFQp5gUlb/A==", + "dev": true, + "license": "BSD-2-Clause", + "dependencies": { + "esrecurse": "^4.3.0", + "estraverse": "^5.2.0" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "url": "https://opencollective.com/eslint" + } + }, + "node_modules/eslint-visitor-keys": { + "version": "4.2.0", + "resolved": "https://registry.npmjs.org/eslint-visitor-keys/-/eslint-visitor-keys-4.2.0.tgz", + "integrity": "sha512-UyLnSehNt62FFhSwjZlHmeokpRK59rcz29j+F1/aDgbkbRTk7wIc9XzdoasMUbRNKDM0qQt/+BJ4BrpFeABemw==", + "dev": true, + "license": "Apache-2.0", + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "url": "https://opencollective.com/eslint" + } + }, + "node_modules/espree": { + "version": "10.3.0", + "resolved": "https://registry.npmjs.org/espree/-/espree-10.3.0.tgz", + "integrity": "sha512-0QYC8b24HWY8zjRnDTL6RiHfDbAWn63qb4LMj1Z4b076A4une81+z03Kg7l7mn/48PUTqoLptSXez8oknU8Clg==", + "dev": true, + "license": "BSD-2-Clause", + "dependencies": { + "acorn": "^8.14.0", + "acorn-jsx": "^5.3.2", + "eslint-visitor-keys": "^4.2.0" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "url": "https://opencollective.com/eslint" + } + }, + "node_modules/esquery": { + "version": "1.6.0", + "resolved": "https://registry.npmjs.org/esquery/-/esquery-1.6.0.tgz", + "integrity": "sha512-ca9pw9fomFcKPvFLXhBKUK90ZvGibiGOvRJNbjljY7s7uq/5YO4BOzcYtJqExdx99rF6aAcnRxHmcUHcz6sQsg==", + "dev": true, + "license": "BSD-3-Clause", + "dependencies": { + "estraverse": "^5.1.0" + }, + "engines": { + "node": ">=0.10" + } + }, + "node_modules/esrecurse": { + "version": "4.3.0", + "resolved": "https://registry.npmjs.org/esrecurse/-/esrecurse-4.3.0.tgz", + "integrity": "sha512-KmfKL3b6G+RXvP8N1vr3Tq1kL/oCFgn2NYXEtqP8/L3pKapUA4G8cFVaoF3SU323CD4XypR/ffioHmkti6/Tag==", + "dev": true, + "license": "BSD-2-Clause", + "dependencies": { + "estraverse": "^5.2.0" + }, + "engines": { + "node": ">=4.0" + } + }, + "node_modules/estraverse": { + "version": "5.3.0", + "resolved": "https://registry.npmjs.org/estraverse/-/estraverse-5.3.0.tgz", + "integrity": "sha512-MMdARuVEQziNTeJD8DgMqmhwR11BRQ/cBP+pLtYdSTnf3MIO8fFeiINEbX36ZdNlfU/7A9f3gUw49B3oQsvwBA==", + "dev": true, + "license": "BSD-2-Clause", + "engines": { + "node": ">=4.0" + } + }, + "node_modules/estree-util-is-identifier-name": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/estree-util-is-identifier-name/-/estree-util-is-identifier-name-3.0.0.tgz", + "integrity": "sha512-hFtqIDZTIUZ9BXLb8y4pYGyk6+wekIivNVTcmvk8NoOh+VeRn5y6cEHzbURrWbfp1fIqdVipilzj+lfaadNZmg==", + "license": "MIT", + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/esutils": { + "version": "2.0.3", + "resolved": "https://registry.npmjs.org/esutils/-/esutils-2.0.3.tgz", + "integrity": "sha512-kVscqXk4OCp68SZ0dkgEKVi6/8ij300KBWTJq32P/dYeWTSwK41WyTxalN1eRmA5Z9UU/LX9D7FWSmV9SAYx6g==", + "dev": true, + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/extend": { + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/extend/-/extend-3.0.2.tgz", + "integrity": "sha512-fjquC59cD7CyW6urNXK0FBufkZcoiGG80wTuPujX590cB5Ttln20E2UB4S/WARVqhXffZl2LNgS+gQdPIIim/g==", + "license": "MIT" + }, + "node_modules/fast-deep-equal": { + "version": "3.1.3", + "resolved": "https://registry.npmjs.org/fast-deep-equal/-/fast-deep-equal-3.1.3.tgz", + "integrity": "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q==", + "dev": true, + "license": "MIT" + }, + "node_modules/fast-glob": { + "version": "3.3.3", + "resolved": "https://registry.npmjs.org/fast-glob/-/fast-glob-3.3.3.tgz", + "integrity": "sha512-7MptL8U0cqcFdzIzwOTHoilX9x5BrNqye7Z/LuC7kCMRio1EMSyqRK3BEAUD7sXRq4iT4AzTVuZdhgQ2TCvYLg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@nodelib/fs.stat": "^2.0.2", + "@nodelib/fs.walk": "^1.2.3", + "glob-parent": "^5.1.2", + "merge2": "^1.3.0", + "micromatch": "^4.0.8" + }, + "engines": { + "node": ">=8.6.0" + } + }, + "node_modules/fast-glob/node_modules/glob-parent": { + "version": "5.1.2", + "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-5.1.2.tgz", + "integrity": "sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==", + "dev": true, + "license": "ISC", + "dependencies": { + "is-glob": "^4.0.1" + }, + "engines": { + "node": ">= 6" + } + }, + "node_modules/fast-json-stable-stringify": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/fast-json-stable-stringify/-/fast-json-stable-stringify-2.1.0.tgz", + "integrity": "sha512-lhd/wF+Lk98HZoTCtlVraHtfh5XYijIjalXck7saUtuanSDyLMxnHhSXEDJqHxD7msR8D0uCmqlkwjCV8xvwHw==", + "dev": true, + "license": "MIT" + }, + "node_modules/fast-levenshtein": { + "version": "2.0.6", + "resolved": "https://registry.npmjs.org/fast-levenshtein/-/fast-levenshtein-2.0.6.tgz", + "integrity": "sha512-DCXu6Ifhqcks7TZKY3Hxp3y6qphY5SJZmrWMDrKcERSOXWQdMhU9Ig/PYrzyw/ul9jOIyh0N4M0tbC5hodg8dw==", + "dev": true, + "license": "MIT" + }, + "node_modules/fastq": { + "version": "1.19.0", + "resolved": "https://registry.npmjs.org/fastq/-/fastq-1.19.0.tgz", + "integrity": "sha512-7SFSRCNjBQIZH/xZR3iy5iQYR8aGBE0h3VG6/cwlbrpdciNYBMotQav8c1XI3HjHH+NikUpP53nPdlZSdWmFzA==", + "dev": true, + "license": "ISC", + "dependencies": { + "reusify": "^1.0.4" + } + }, + "node_modules/file-entry-cache": { + "version": "8.0.0", + "resolved": "https://registry.npmjs.org/file-entry-cache/-/file-entry-cache-8.0.0.tgz", + "integrity": "sha512-XXTUwCvisa5oacNGRP9SfNtYBNAMi+RPwBFmblZEF7N7swHYQS6/Zfk7SRwx4D5j3CH211YNRco1DEMNVfZCnQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "flat-cache": "^4.0.0" + }, + "engines": { + "node": ">=16.0.0" + } + }, + "node_modules/fill-range": { + "version": "7.1.1", + "resolved": "https://registry.npmjs.org/fill-range/-/fill-range-7.1.1.tgz", + "integrity": "sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==", + "license": "MIT", + "dependencies": { + "to-regex-range": "^5.0.1" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/find-up": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/find-up/-/find-up-5.0.0.tgz", + "integrity": "sha512-78/PXT1wlLLDgTzDs7sjq9hzz0vXD+zn+7wypEe4fXQxCmdmqfGsEPQxmiCSQI3ajFV91bVSsvNtrJRiW6nGng==", + "dev": true, + "license": "MIT", + "dependencies": { + "locate-path": "^6.0.0", + "path-exists": "^4.0.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/flat-cache": { + "version": "4.0.1", + "resolved": "https://registry.npmjs.org/flat-cache/-/flat-cache-4.0.1.tgz", + "integrity": "sha512-f7ccFPK3SXFHpx15UIGyRJ/FJQctuKZ0zVuN3frBo4HnK3cay9VEW0R6yPYFHC0AgqhukPzKjq22t5DmAyqGyw==", + "dev": true, + "license": "MIT", + "dependencies": { + "flatted": "^3.2.9", + "keyv": "^4.5.4" + }, + "engines": { + "node": ">=16" + } + }, + "node_modules/flatted": { + "version": "3.3.2", + "resolved": "https://registry.npmjs.org/flatted/-/flatted-3.3.2.tgz", + "integrity": "sha512-AiwGJM8YcNOaobumgtng+6NHuOqC3A7MixFeDafM3X9cIUM+xUXoS5Vfgf+OihAYe20fxqNM9yPBXJzRtZ/4eA==", + "dev": true, + "license": "ISC" + }, + "node_modules/fraction.js": { + "version": "4.3.7", + "resolved": "https://registry.npmjs.org/fraction.js/-/fraction.js-4.3.7.tgz", + "integrity": "sha512-ZsDfxO51wGAXREY55a7la9LScWpwv9RxIrYABrlvOFBlH/ShPnrtsXeuUIfXKKOVicNxQ+o8JTbJvjS4M89yew==", + "license": "MIT", + "engines": { + "node": "*" + }, + "funding": { + "type": "patreon", + "url": "https://github.com/sponsors/rawify" + } + }, + "node_modules/fsevents": { + "version": "2.3.3", + "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.3.tgz", + "integrity": "sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==", + "hasInstallScript": true, + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": "^8.16.0 || ^10.6.0 || >=11.0.0" + } + }, + "node_modules/gensync": { + "version": "1.0.0-beta.2", + "resolved": "https://registry.npmjs.org/gensync/-/gensync-1.0.0-beta.2.tgz", + "integrity": "sha512-3hN7NaskYvMDLQY55gnW3NQ+mesEAepTqlg+VEbj7zzqEMBVNhzcGYYeqFo/TlYz6eQiFcp1HcsCZO+nGgS8zg==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6.9.0" + } + }, + "node_modules/glob-parent": { + "version": "6.0.2", + "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-6.0.2.tgz", + "integrity": "sha512-XxwI8EOhVQgWp6iDL+3b0r86f4d6AX6zSU55HfB4ydCEuXLXc5FcYeOu+nnGftS4TEju/11rt4KJPTMgbfmv4A==", + "dev": true, + "license": "ISC", + "dependencies": { + "is-glob": "^4.0.3" + }, + "engines": { + "node": ">=10.13.0" + } + }, + "node_modules/globals": { + "version": "15.14.0", + "resolved": "https://registry.npmjs.org/globals/-/globals-15.14.0.tgz", + "integrity": "sha512-OkToC372DtlQeje9/zHIo5CT8lRP/FUgEOKBEhU4e0abL7J7CD24fD9ohiLN5hagG/kWCYj4K5oaxxtj2Z0Dig==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=18" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/graceful-fs": { + "version": "4.2.11", + "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz", + "integrity": "sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==", + "license": "ISC" + }, + "node_modules/graphemer": { + "version": "1.4.0", + "resolved": "https://registry.npmjs.org/graphemer/-/graphemer-1.4.0.tgz", + "integrity": "sha512-EtKwoO6kxCL9WO5xipiHTZlSzBm7WLT627TqC/uVRd0HKmq8NXyebnNYxDoBi7wt8eTWrUrKXCOVaFq9x1kgag==", + "dev": true, + "license": "MIT" + }, + "node_modules/has-flag": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-4.0.0.tgz", + "integrity": "sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==", + "devOptional": true, + "license": "MIT", + "engines": { + "node": ">=8" + } + }, + "node_modules/hast-util-from-dom": { + "version": "5.0.1", + "resolved": "https://registry.npmjs.org/hast-util-from-dom/-/hast-util-from-dom-5.0.1.tgz", + "integrity": "sha512-N+LqofjR2zuzTjCPzyDUdSshy4Ma6li7p/c3pA78uTwzFgENbgbUrm2ugwsOdcjI1muO+o6Dgzp9p8WHtn/39Q==", + "license": "ISC", + "dependencies": { + "@types/hast": "^3.0.0", + "hastscript": "^9.0.0", + "web-namespaces": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hast-util-from-html": { + "version": "2.0.3", + "resolved": "https://registry.npmjs.org/hast-util-from-html/-/hast-util-from-html-2.0.3.tgz", + "integrity": "sha512-CUSRHXyKjzHov8yKsQjGOElXy/3EKpyX56ELnkHH34vDVw1N1XSQ1ZcAvTyAPtGqLTuKP/uxM+aLkSPqF/EtMw==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "devlop": "^1.1.0", + "hast-util-from-parse5": "^8.0.0", + "parse5": "^7.0.0", + "vfile": "^6.0.0", + "vfile-message": "^4.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hast-util-from-html-isomorphic": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/hast-util-from-html-isomorphic/-/hast-util-from-html-isomorphic-2.0.0.tgz", + "integrity": "sha512-zJfpXq44yff2hmE0XmwEOzdWin5xwH+QIhMLOScpX91e/NSGPsAzNCvLQDIEPyO2TXi+lBmU6hjLIhV8MwP2kw==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "hast-util-from-dom": "^5.0.0", + "hast-util-from-html": "^2.0.0", + "unist-util-remove-position": "^5.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hast-util-from-parse5": { + "version": "8.0.2", + "resolved": "https://registry.npmjs.org/hast-util-from-parse5/-/hast-util-from-parse5-8.0.2.tgz", + "integrity": "sha512-SfMzfdAi/zAoZ1KkFEyyeXBn7u/ShQrfd675ZEE9M3qj+PMFX05xubzRyF76CCSJu8au9jgVxDV1+okFvgZU4A==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "@types/unist": "^3.0.0", + "devlop": "^1.0.0", + "hastscript": "^9.0.0", + "property-information": "^6.0.0", + "vfile": "^6.0.0", + "vfile-location": "^5.0.0", + "web-namespaces": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hast-util-is-element": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/hast-util-is-element/-/hast-util-is-element-3.0.0.tgz", + "integrity": "sha512-Val9mnv2IWpLbNPqc/pUem+a7Ipj2aHacCwgNfTiK0vJKl0LF+4Ba4+v1oPHFpf3bLYmreq0/l3Gud9S5OH42g==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hast-util-parse-selector": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/hast-util-parse-selector/-/hast-util-parse-selector-4.0.0.tgz", + "integrity": "sha512-wkQCkSYoOGCRKERFWcxMVMOcYE2K1AaNLU8DXS9arxnLOUEWbOXKXiJUNzEpqZ3JOKpnha3jkFrumEjVliDe7A==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hast-util-to-jsx-runtime": { + "version": "2.3.2", + "resolved": "https://registry.npmjs.org/hast-util-to-jsx-runtime/-/hast-util-to-jsx-runtime-2.3.2.tgz", + "integrity": "sha512-1ngXYb+V9UT5h+PxNRa1O1FYguZK/XL+gkeqvp7EdHlB9oHUG0eYRo/vY5inBdcqo3RkPMC58/H94HvkbfGdyg==", + "license": "MIT", + "dependencies": { + "@types/estree": "^1.0.0", + "@types/hast": "^3.0.0", + "@types/unist": "^3.0.0", + "comma-separated-tokens": "^2.0.0", + "devlop": "^1.0.0", + "estree-util-is-identifier-name": "^3.0.0", + "hast-util-whitespace": "^3.0.0", + "mdast-util-mdx-expression": "^2.0.0", + "mdast-util-mdx-jsx": "^3.0.0", + "mdast-util-mdxjs-esm": "^2.0.0", + "property-information": "^6.0.0", + "space-separated-tokens": "^2.0.0", + "style-to-object": "^1.0.0", + "unist-util-position": "^5.0.0", + "vfile-message": "^4.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hast-util-to-text": { + "version": "4.0.2", + "resolved": "https://registry.npmjs.org/hast-util-to-text/-/hast-util-to-text-4.0.2.tgz", + "integrity": "sha512-KK6y/BN8lbaq654j7JgBydev7wuNMcID54lkRav1P0CaE1e47P72AWWPiGKXTJU271ooYzcvTAn/Zt0REnvc7A==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "@types/unist": "^3.0.0", + "hast-util-is-element": "^3.0.0", + "unist-util-find-after": "^5.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hast-util-whitespace": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/hast-util-whitespace/-/hast-util-whitespace-3.0.0.tgz", + "integrity": "sha512-88JUN06ipLwsnv+dVn+OIYOvAuvBMy/Qoi6O7mQHxdPXpjy+Cd6xRkWwux7DKO+4sYILtLBRIKgsdpS2gQc7qw==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/hastscript": { + "version": "9.0.0", + "resolved": "https://registry.npmjs.org/hastscript/-/hastscript-9.0.0.tgz", + "integrity": "sha512-jzaLBGavEDKHrc5EfFImKN7nZKKBdSLIdGvCwDZ9TfzbF2ffXiov8CKE445L2Z1Ek2t/m4SKQ2j6Ipv7NyUolw==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "comma-separated-tokens": "^2.0.0", + "hast-util-parse-selector": "^4.0.0", + "property-information": "^6.0.0", + "space-separated-tokens": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/highlight.js": { + "version": "11.11.1", + "resolved": "https://registry.npmjs.org/highlight.js/-/highlight.js-11.11.1.tgz", + "integrity": "sha512-Xwwo44whKBVCYoliBQwaPvtd/2tYFkRQtXDWj1nackaV2JPXx3L0+Jvd8/qCJ2p+ML0/XVkJ2q+Mr+UVdpJK5w==", + "license": "BSD-3-Clause", + "engines": { + "node": ">=12.0.0" + } + }, + "node_modules/html-url-attributes": { + "version": "3.0.1", + "resolved": "https://registry.npmjs.org/html-url-attributes/-/html-url-attributes-3.0.1.tgz", + "integrity": "sha512-ol6UPyBWqsrO6EJySPz2O7ZSr856WDrEzM5zMqp+FJJLGMW35cLYmmZnl0vztAZxRUoNZJFTCohfjuIJ8I4QBQ==", + "license": "MIT", + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/ignore": { + "version": "5.3.2", + "resolved": "https://registry.npmjs.org/ignore/-/ignore-5.3.2.tgz", + "integrity": "sha512-hsBTNUqQTDwkWtcdYI2i06Y/nUBEsNEDJKjWdigLvegy8kDuJAS8uRlpkkcQpyEXL0Z/pjDy5HBmMjRCJ2gq+g==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">= 4" + } + }, + "node_modules/immutable": { + "version": "5.0.3", + "resolved": "https://registry.npmjs.org/immutable/-/immutable-5.0.3.tgz", + "integrity": "sha512-P8IdPQHq3lA1xVeBRi5VPqUm5HDgKnx0Ru51wZz5mjxHr5n3RWhjIpOFU7ybkUxfB+5IToy+OLaHYDBIWsv+uw==", + "devOptional": true, + "license": "MIT" + }, + "node_modules/import-fresh": { + "version": "3.3.1", + "resolved": "https://registry.npmjs.org/import-fresh/-/import-fresh-3.3.1.tgz", + "integrity": "sha512-TR3KfrTZTYLPB6jUjfx6MF9WcWrHL9su5TObK4ZkYgBdWKPOFoSoQIdEuTuR82pmtxH2spWG9h6etwfr1pLBqQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "parent-module": "^1.0.0", + "resolve-from": "^4.0.0" + }, + "engines": { + "node": ">=6" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/imurmurhash": { + "version": "0.1.4", + "resolved": "https://registry.npmjs.org/imurmurhash/-/imurmurhash-0.1.4.tgz", + "integrity": "sha512-JmXMZ6wuvDmLiHEml9ykzqO6lwFbof0GG4IkcGaENdCRDDmMVnny7s5HsIgHCbaq0w2MyPhDqkhTUgS2LU2PHA==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=0.8.19" + } + }, + "node_modules/inline-style-parser": { + "version": "0.2.4", + "resolved": "https://registry.npmjs.org/inline-style-parser/-/inline-style-parser-0.2.4.tgz", + "integrity": "sha512-0aO8FkhNZlj/ZIbNi7Lxxr12obT7cL1moPfE4tg1LkX7LlLfC6DeX4l2ZEud1ukP9jNQyNnfzQVqwbwmAATY4Q==", + "license": "MIT" + }, + "node_modules/is-alphabetical": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/is-alphabetical/-/is-alphabetical-2.0.1.tgz", + "integrity": "sha512-FWyyY60MeTNyeSRpkM2Iry0G9hpr7/9kD40mD/cGQEuilcZYS4okz8SN2Q6rLCJ8gbCt6fN+rC+6tMGS99LaxQ==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/is-alphanumerical": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/is-alphanumerical/-/is-alphanumerical-2.0.1.tgz", + "integrity": "sha512-hmbYhX/9MUMF5uh7tOXyK/n0ZvWpad5caBA17GsC6vyuCqaWliRG5K1qS9inmUhEMaOBIW7/whAnSwveW/LtZw==", + "license": "MIT", + "dependencies": { + "is-alphabetical": "^2.0.0", + "is-decimal": "^2.0.0" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/is-decimal": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/is-decimal/-/is-decimal-2.0.1.tgz", + "integrity": "sha512-AAB9hiomQs5DXWcRB1rqsxGUstbRroFOPPVAomNk/3XHR5JyEZChOyTWe2oayKnsSsr/kcGqF+z6yuH6HHpN0A==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/is-extglob": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/is-extglob/-/is-extglob-2.1.1.tgz", + "integrity": "sha512-SbKbANkN603Vi4jEZv49LeVJMn4yGwsbzZworEoyEiutsN3nJYdbO36zfhGJ6QEDpOZIFkDtnq5JRxmvl3jsoQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/is-glob": { + "version": "4.0.3", + "resolved": "https://registry.npmjs.org/is-glob/-/is-glob-4.0.3.tgz", + "integrity": "sha512-xelSayHH36ZgE7ZWhli7pW34hNbNl8Ojv5KVmkJD4hBdD3th8Tfk9vYasLM+mXWOZhFkgZfxhLSnrwRr4elSSg==", + "dev": true, + "license": "MIT", + "dependencies": { + "is-extglob": "^2.1.1" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/is-hexadecimal": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/is-hexadecimal/-/is-hexadecimal-2.0.1.tgz", + "integrity": "sha512-DgZQp241c8oO6cA1SbTEWiXeoxV42vlcJxgH+B3hi1AiqqKruZR3ZGF8In3fj4+/y/7rHvlOZLZtgJ/4ttYGZg==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/is-number": { + "version": "7.0.0", + "resolved": "https://registry.npmjs.org/is-number/-/is-number-7.0.0.tgz", + "integrity": "sha512-41Cifkg6e8TylSpdtTpeLVMqvSBEVzTttHvERD741+pnZ8ANv0004MRL43QKPDlK9cGvNp6NZWZUBlbGXYxxng==", + "license": "MIT", + "engines": { + "node": ">=0.12.0" + } + }, + "node_modules/is-plain-obj": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/is-plain-obj/-/is-plain-obj-4.1.0.tgz", + "integrity": "sha512-+Pgi+vMuUNkJyExiMBt5IlFoMyKnr5zhJ4Uspz58WOhBF5QoIZkFyNHIbBAtHwzVAgk5RtndVNsDRN61/mmDqg==", + "license": "MIT", + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/isexe": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz", + "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==", + "dev": true, + "license": "ISC" + }, + "node_modules/jiti": { + "version": "2.4.2", + "resolved": "https://registry.npmjs.org/jiti/-/jiti-2.4.2.tgz", + "integrity": "sha512-rg9zJN+G4n2nfJl5MW3BMygZX56zKPNVEYYqq7adpmMh4Jn2QNEwhvQlFy6jPVdcod7txZtKHWnyZiA3a0zP7A==", + "license": "MIT", + "bin": { + "jiti": "lib/jiti-cli.mjs" + } + }, + "node_modules/js-tokens": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz", + "integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==", + "license": "MIT" + }, + "node_modules/js-yaml": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.0.tgz", + "integrity": "sha512-wpxZs9NoxZaJESJGIZTyDEaYpl0FKSA+FB9aJiyemKhMwkxQg63h4T1KJgUGHpTqPDNRcmmYLugrRjJlBtWvRA==", + "dev": true, + "license": "MIT", + "dependencies": { + "argparse": "^2.0.1" + }, + "bin": { + "js-yaml": "bin/js-yaml.js" + } + }, + "node_modules/jsesc": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/jsesc/-/jsesc-3.1.0.tgz", + "integrity": "sha512-/sM3dO2FOzXjKQhJuo0Q173wf2KOo8t4I8vHy6lF9poUp7bKT0/NHE8fPX23PwfhnykfqnC2xRxOnVw5XuGIaA==", + "dev": true, + "license": "MIT", + "bin": { + "jsesc": "bin/jsesc" + }, + "engines": { + "node": ">=6" + } + }, + "node_modules/json-buffer": { + "version": "3.0.1", + "resolved": "https://registry.npmjs.org/json-buffer/-/json-buffer-3.0.1.tgz", + "integrity": "sha512-4bV5BfR2mqfQTJm+V5tPPdf+ZpuhiIvTuAB5g8kcrXOZpTT/QwwVRWBywX1ozr6lEuPdbHxwaJlm9G6mI2sfSQ==", + "dev": true, + "license": "MIT" + }, + "node_modules/json-schema-traverse": { + "version": "0.4.1", + "resolved": "https://registry.npmjs.org/json-schema-traverse/-/json-schema-traverse-0.4.1.tgz", + "integrity": "sha512-xbbCH5dCYU5T8LcEhhuh7HJ88HXuW3qsI3Y0zOZFKfZEHcpWiHU/Jxzk629Brsab/mMiHQti9wMP+845RPe3Vg==", + "dev": true, + "license": "MIT" + }, + "node_modules/json-stable-stringify-without-jsonify": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/json-stable-stringify-without-jsonify/-/json-stable-stringify-without-jsonify-1.0.1.tgz", + "integrity": "sha512-Bdboy+l7tA3OGW6FjyFHWkP5LuByj1Tk33Ljyq0axyzdk9//JSi2u3fP1QSmd1KNwq6VOKYGlAu87CisVir6Pw==", + "dev": true, + "license": "MIT" + }, + "node_modules/json5": { + "version": "2.2.3", + "resolved": "https://registry.npmjs.org/json5/-/json5-2.2.3.tgz", + "integrity": "sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg==", + "dev": true, + "license": "MIT", + "bin": { + "json5": "lib/cli.js" + }, + "engines": { + "node": ">=6" + } + }, + "node_modules/katex": { + "version": "0.16.21", + "resolved": "https://registry.npmjs.org/katex/-/katex-0.16.21.tgz", + "integrity": "sha512-XvqR7FgOHtWupfMiigNzmh+MgUVmDGU2kXZm899ZkPfcuoPuFxyHmXsgATDpFZDAXCI8tvinaVcDo8PIIJSo4A==", + "funding": [ + "https://opencollective.com/katex", + "https://github.com/sponsors/katex" + ], + "license": "MIT", + "dependencies": { + "commander": "^8.3.0" + }, + "bin": { + "katex": "cli.js" + } + }, + "node_modules/keyv": { + "version": "4.5.4", + "resolved": "https://registry.npmjs.org/keyv/-/keyv-4.5.4.tgz", + "integrity": "sha512-oxVHkHR/EJf2CNXnWxRLW6mg7JyCCUcG0DtEGmL2ctUo1PNTin1PUil+r/+4r5MpVgC/fn1kjsx7mjSujKqIpw==", + "dev": true, + "license": "MIT", + "dependencies": { + "json-buffer": "3.0.1" + } + }, + "node_modules/levn": { + "version": "0.4.1", + "resolved": "https://registry.npmjs.org/levn/-/levn-0.4.1.tgz", + "integrity": "sha512-+bT2uH4E5LGE7h/n3evcS/sQlJXCpIp6ym8OWJ5eV6+67Dsql/LaaT7qJBAt2rzfoa/5QBGBhxDix1dMt2kQKQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "prelude-ls": "^1.2.1", + "type-check": "~0.4.0" + }, + "engines": { + "node": ">= 0.8.0" + } + }, + "node_modules/lightningcss": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss/-/lightningcss-1.29.2.tgz", + "integrity": "sha512-6b6gd/RUXKaw5keVdSEtqFVdzWnU5jMxTUjA2bVcMNPLwSQ08Sv/UodBVtETLCn7k4S1Ibxwh7k68IwLZPgKaA==", + "license": "MPL-2.0", + "dependencies": { + "detect-libc": "^2.0.3" + }, + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + }, + "optionalDependencies": { + "lightningcss-darwin-arm64": "1.29.2", + "lightningcss-darwin-x64": "1.29.2", + "lightningcss-freebsd-x64": "1.29.2", + "lightningcss-linux-arm-gnueabihf": "1.29.2", + "lightningcss-linux-arm64-gnu": "1.29.2", + "lightningcss-linux-arm64-musl": "1.29.2", + "lightningcss-linux-x64-gnu": "1.29.2", + "lightningcss-linux-x64-musl": "1.29.2", + "lightningcss-win32-arm64-msvc": "1.29.2", + "lightningcss-win32-x64-msvc": "1.29.2" + } + }, + "node_modules/lightningcss-darwin-arm64": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-darwin-arm64/-/lightningcss-darwin-arm64-1.29.2.tgz", + "integrity": "sha512-cK/eMabSViKn/PG8U/a7aCorpeKLMlK0bQeNHmdb7qUnBkNPnL+oV5DjJUo0kqWsJUapZsM4jCfYItbqBDvlcA==", + "cpu": [ + "arm64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-darwin-x64": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-darwin-x64/-/lightningcss-darwin-x64-1.29.2.tgz", + "integrity": "sha512-j5qYxamyQw4kDXX5hnnCKMf3mLlHvG44f24Qyi2965/Ycz829MYqjrVg2H8BidybHBp9kom4D7DR5VqCKDXS0w==", + "cpu": [ + "x64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-freebsd-x64": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-freebsd-x64/-/lightningcss-freebsd-x64-1.29.2.tgz", + "integrity": "sha512-wDk7M2tM78Ii8ek9YjnY8MjV5f5JN2qNVO+/0BAGZRvXKtQrBC4/cn4ssQIpKIPP44YXw6gFdpUF+Ps+RGsCwg==", + "cpu": [ + "x64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "freebsd" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-arm-gnueabihf": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-linux-arm-gnueabihf/-/lightningcss-linux-arm-gnueabihf-1.29.2.tgz", + "integrity": "sha512-IRUrOrAF2Z+KExdExe3Rz7NSTuuJ2HvCGlMKoquK5pjvo2JY4Rybr+NrKnq0U0hZnx5AnGsuFHjGnNT14w26sg==", + "cpu": [ + "arm" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-arm64-gnu": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-linux-arm64-gnu/-/lightningcss-linux-arm64-gnu-1.29.2.tgz", + "integrity": "sha512-KKCpOlmhdjvUTX/mBuaKemp0oeDIBBLFiU5Fnqxh1/DZ4JPZi4evEH7TKoSBFOSOV3J7iEmmBaw/8dpiUvRKlQ==", + "cpu": [ + "arm64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-arm64-musl": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-linux-arm64-musl/-/lightningcss-linux-arm64-musl-1.29.2.tgz", + "integrity": "sha512-Q64eM1bPlOOUgxFmoPUefqzY1yV3ctFPE6d/Vt7WzLW4rKTv7MyYNky+FWxRpLkNASTnKQUaiMJ87zNODIrrKQ==", + "cpu": [ + "arm64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-x64-gnu": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-linux-x64-gnu/-/lightningcss-linux-x64-gnu-1.29.2.tgz", + "integrity": "sha512-0v6idDCPG6epLXtBH/RPkHvYx74CVziHo6TMYga8O2EiQApnUPZsbR9nFNrg2cgBzk1AYqEd95TlrsL7nYABQg==", + "cpu": [ + "x64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-linux-x64-musl": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-linux-x64-musl/-/lightningcss-linux-x64-musl-1.29.2.tgz", + "integrity": "sha512-rMpz2yawkgGT8RULc5S4WiZopVMOFWjiItBT7aSfDX4NQav6M44rhn5hjtkKzB+wMTRlLLqxkeYEtQ3dd9696w==", + "cpu": [ + "x64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-win32-arm64-msvc": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-win32-arm64-msvc/-/lightningcss-win32-arm64-msvc-1.29.2.tgz", + "integrity": "sha512-nL7zRW6evGQqYVu/bKGK+zShyz8OVzsCotFgc7judbt6wnB2KbiKKJwBE4SGoDBQ1O94RjW4asrCjQL4i8Fhbw==", + "cpu": [ + "arm64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/lightningcss-win32-x64-msvc": { + "version": "1.29.2", + "resolved": "https://registry.npmjs.org/lightningcss-win32-x64-msvc/-/lightningcss-win32-x64-msvc-1.29.2.tgz", + "integrity": "sha512-EdIUW3B2vLuHmv7urfzMI/h2fmlnOQBk1xlsDxkN1tCWKjNFjfLhGxYk8C8mzpSfr+A6jFFIi8fU6LbQGsRWjA==", + "cpu": [ + "x64" + ], + "license": "MPL-2.0", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">= 12.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/parcel" + } + }, + "node_modules/locate-path": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/locate-path/-/locate-path-6.0.0.tgz", + "integrity": "sha512-iPZK6eYjbxRu3uB4/WZ3EsEIMJFMqAoopl3R+zuq0UjcAm/MO6KCweDgPfP3elTztoKP3KtnVHxTn2NHBSDVUw==", + "dev": true, + "license": "MIT", + "dependencies": { + "p-locate": "^5.0.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/lodash.merge": { + "version": "4.6.2", + "resolved": "https://registry.npmjs.org/lodash.merge/-/lodash.merge-4.6.2.tgz", + "integrity": "sha512-0KpjqXRVvrYyCsX1swR/XTK0va6VQkQM6MNo7PqW77ByjAhoARA8EfrP1N4+KlKj8YS0ZUCtRT/YUuhyYDujIQ==", + "dev": true, + "license": "MIT" + }, + "node_modules/longest-streak": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/longest-streak/-/longest-streak-3.1.0.tgz", + "integrity": "sha512-9Ri+o0JYgehTaVBBDoMqIl8GXtbWg711O3srftcHhZ0dqnETqLaoIK0x17fUw9rFSlK/0NlsKe0Ahhyl5pXE2g==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/loose-envify": { + "version": "1.4.0", + "resolved": "https://registry.npmjs.org/loose-envify/-/loose-envify-1.4.0.tgz", + "integrity": "sha512-lyuxPGr/Wfhrlem2CL/UcnUc1zcqKAImBDzukY7Y5F/yQiNdko6+fRLevlw1HgMySw7f611UIY408EtxRSoK3Q==", + "license": "MIT", + "dependencies": { + "js-tokens": "^3.0.0 || ^4.0.0" + }, + "bin": { + "loose-envify": "cli.js" + } + }, + "node_modules/lowlight": { + "version": "3.3.0", + "resolved": "https://registry.npmjs.org/lowlight/-/lowlight-3.3.0.tgz", + "integrity": "sha512-0JNhgFoPvP6U6lE/UdVsSq99tn6DhjjpAj5MxG49ewd2mOBVtwWYIT8ClyABhq198aXXODMU6Ox8DrGy/CpTZQ==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "devlop": "^1.0.0", + "highlight.js": "~11.11.0" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/lru-cache": { + "version": "5.1.1", + "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-5.1.1.tgz", + "integrity": "sha512-KpNARQA3Iwv+jTA0utUVVbrh+Jlrr1Fv0e56GGzAFOXN7dk/FviaDW8LHmK52DlcH4WP2n6gI8vN1aesBFgo9w==", + "dev": true, + "license": "ISC", + "dependencies": { + "yallist": "^3.0.2" + } + }, + "node_modules/markdown-table": { + "version": "3.0.4", + "resolved": "https://registry.npmjs.org/markdown-table/-/markdown-table-3.0.4.tgz", + "integrity": "sha512-wiYz4+JrLyb/DqW2hkFJxP7Vd7JuTDm77fvbM8VfEQdmSMqcImWeeRbHwZjBjIFki/VaMK2BhFi7oUUZeM5bqw==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/mdast-util-find-and-replace": { + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/mdast-util-find-and-replace/-/mdast-util-find-and-replace-3.0.2.tgz", + "integrity": "sha512-Tmd1Vg/m3Xz43afeNxDIhWRtFZgM2VLyaf4vSTYwudTyeuTneoL3qtWMA5jeLyz/O1vDJmmV4QuScFCA2tBPwg==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "escape-string-regexp": "^5.0.0", + "unist-util-is": "^6.0.0", + "unist-util-visit-parents": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-find-and-replace/node_modules/escape-string-regexp": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-5.0.0.tgz", + "integrity": "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw==", + "license": "MIT", + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/mdast-util-from-markdown": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/mdast-util-from-markdown/-/mdast-util-from-markdown-2.0.2.tgz", + "integrity": "sha512-uZhTV/8NBuw0WHkPTrCqDOl0zVe1BIng5ZtHoDk49ME1qqcjYmmLmOf0gELgcRMxN4w2iuIeVso5/6QymSrgmA==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "@types/unist": "^3.0.0", + "decode-named-character-reference": "^1.0.0", + "devlop": "^1.0.0", + "mdast-util-to-string": "^4.0.0", + "micromark": "^4.0.0", + "micromark-util-decode-numeric-character-reference": "^2.0.0", + "micromark-util-decode-string": "^2.0.0", + "micromark-util-normalize-identifier": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0", + "unist-util-stringify-position": "^4.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-gfm": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/mdast-util-gfm/-/mdast-util-gfm-3.0.0.tgz", + "integrity": "sha512-dgQEX5Amaq+DuUqf26jJqSK9qgixgd6rYDHAv4aTBuA92cTknZlKpPfa86Z/s8Dj8xsAQpFfBmPUHWJBWqS4Bw==", + "license": "MIT", + "dependencies": { + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-gfm-autolink-literal": "^2.0.0", + "mdast-util-gfm-footnote": "^2.0.0", + "mdast-util-gfm-strikethrough": "^2.0.0", + "mdast-util-gfm-table": "^2.0.0", + "mdast-util-gfm-task-list-item": "^2.0.0", + "mdast-util-to-markdown": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-gfm-autolink-literal": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/mdast-util-gfm-autolink-literal/-/mdast-util-gfm-autolink-literal-2.0.1.tgz", + "integrity": "sha512-5HVP2MKaP6L+G6YaxPNjuL0BPrq9orG3TsrZ9YXbA3vDw/ACI4MEsnoDpn6ZNm7GnZgtAcONJyPhOP8tNJQavQ==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "ccount": "^2.0.0", + "devlop": "^1.0.0", + "mdast-util-find-and-replace": "^3.0.0", + "micromark-util-character": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-gfm-footnote": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/mdast-util-gfm-footnote/-/mdast-util-gfm-footnote-2.0.0.tgz", + "integrity": "sha512-5jOT2boTSVkMnQ7LTrd6n/18kqwjmuYqo7JUPe+tRCY6O7dAuTFMtTPauYYrMPpox9hlN0uOx/FL8XvEfG9/mQ==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "devlop": "^1.1.0", + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-to-markdown": "^2.0.0", + "micromark-util-normalize-identifier": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-gfm-strikethrough": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/mdast-util-gfm-strikethrough/-/mdast-util-gfm-strikethrough-2.0.0.tgz", + "integrity": "sha512-mKKb915TF+OC5ptj5bJ7WFRPdYtuHv0yTRxK2tJvi+BDqbkiG7h7u/9SI89nRAYcmap2xHQL9D+QG/6wSrTtXg==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-to-markdown": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-gfm-table": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/mdast-util-gfm-table/-/mdast-util-gfm-table-2.0.0.tgz", + "integrity": "sha512-78UEvebzz/rJIxLvE7ZtDd/vIQ0RHv+3Mh5DR96p7cS7HsBhYIICDBCu8csTNWNO6tBWfqXPWekRuj2FNOGOZg==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "devlop": "^1.0.0", + "markdown-table": "^3.0.0", + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-to-markdown": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-gfm-task-list-item": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/mdast-util-gfm-task-list-item/-/mdast-util-gfm-task-list-item-2.0.0.tgz", + "integrity": "sha512-IrtvNvjxC1o06taBAVJznEnkiHxLFTzgonUdy8hzFVeDun0uTjxxrRGVaNFqkU1wJR3RBPEfsxmU6jDWPofrTQ==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "devlop": "^1.0.0", + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-to-markdown": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-math": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/mdast-util-math/-/mdast-util-math-3.0.0.tgz", + "integrity": "sha512-Tl9GBNeG/AhJnQM221bJR2HPvLOSnLE/T9cJI9tlc6zwQk2nPk/4f0cHkOdEixQPC/j8UtKDdITswvLAy1OZ1w==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "@types/mdast": "^4.0.0", + "devlop": "^1.0.0", + "longest-streak": "^3.0.0", + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-to-markdown": "^2.1.0", + "unist-util-remove-position": "^5.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-mdx-expression": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/mdast-util-mdx-expression/-/mdast-util-mdx-expression-2.0.1.tgz", + "integrity": "sha512-J6f+9hUp+ldTZqKRSg7Vw5V6MqjATc+3E4gf3CFNcuZNWD8XdyI6zQ8GqH7f8169MM6P7hMBRDVGnn7oHB9kXQ==", + "license": "MIT", + "dependencies": { + "@types/estree-jsx": "^1.0.0", + "@types/hast": "^3.0.0", + "@types/mdast": "^4.0.0", + "devlop": "^1.0.0", + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-to-markdown": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-mdx-jsx": { + "version": "3.2.0", + "resolved": "https://registry.npmjs.org/mdast-util-mdx-jsx/-/mdast-util-mdx-jsx-3.2.0.tgz", + "integrity": "sha512-lj/z8v0r6ZtsN/cGNNtemmmfoLAFZnjMbNyLzBafjzikOM+glrjNHPlf6lQDOTccj9n5b0PPihEBbhneMyGs1Q==", + "license": "MIT", + "dependencies": { + "@types/estree-jsx": "^1.0.0", + "@types/hast": "^3.0.0", + "@types/mdast": "^4.0.0", + "@types/unist": "^3.0.0", + "ccount": "^2.0.0", + "devlop": "^1.1.0", + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-to-markdown": "^2.0.0", + "parse-entities": "^4.0.0", + "stringify-entities": "^4.0.0", + "unist-util-stringify-position": "^4.0.0", + "vfile-message": "^4.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-mdxjs-esm": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/mdast-util-mdxjs-esm/-/mdast-util-mdxjs-esm-2.0.1.tgz", + "integrity": "sha512-EcmOpxsZ96CvlP03NghtH1EsLtr0n9Tm4lPUJUBccV9RwUOneqSycg19n5HGzCf+10LozMRSObtVr3ee1WoHtg==", + "license": "MIT", + "dependencies": { + "@types/estree-jsx": "^1.0.0", + "@types/hast": "^3.0.0", + "@types/mdast": "^4.0.0", + "devlop": "^1.0.0", + "mdast-util-from-markdown": "^2.0.0", + "mdast-util-to-markdown": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-newline-to-break": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/mdast-util-newline-to-break/-/mdast-util-newline-to-break-2.0.0.tgz", + "integrity": "sha512-MbgeFca0hLYIEx/2zGsszCSEJJ1JSCdiY5xQxRcLDDGa8EPvlLPupJ4DSajbMPAnC0je8jfb9TiUATnxxrHUog==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "mdast-util-find-and-replace": "^3.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-phrasing": { + "version": "4.1.0", + "resolved": "https://registry.npmjs.org/mdast-util-phrasing/-/mdast-util-phrasing-4.1.0.tgz", + "integrity": "sha512-TqICwyvJJpBwvGAMZjj4J2n0X8QWp21b9l0o7eXyVJ25YNWYbJDVIyD1bZXE6WtV6RmKJVYmQAKWa0zWOABz2w==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "unist-util-is": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-to-hast": { + "version": "13.2.0", + "resolved": "https://registry.npmjs.org/mdast-util-to-hast/-/mdast-util-to-hast-13.2.0.tgz", + "integrity": "sha512-QGYKEuUsYT9ykKBCMOEDLsU5JRObWQusAolFMeko/tYPufNkRffBAQjIE+99jbA87xv6FgmjLtwjh9wBWajwAA==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "@types/mdast": "^4.0.0", + "@ungap/structured-clone": "^1.0.0", + "devlop": "^1.0.0", + "micromark-util-sanitize-uri": "^2.0.0", + "trim-lines": "^3.0.0", + "unist-util-position": "^5.0.0", + "unist-util-visit": "^5.0.0", + "vfile": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-to-markdown": { + "version": "2.1.2", + "resolved": "https://registry.npmjs.org/mdast-util-to-markdown/-/mdast-util-to-markdown-2.1.2.tgz", + "integrity": "sha512-xj68wMTvGXVOKonmog6LwyJKrYXZPvlwabaryTjLh9LuvovB/KAH+kvi8Gjj+7rJjsFi23nkUxRQv1KqSroMqA==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "@types/unist": "^3.0.0", + "longest-streak": "^3.0.0", + "mdast-util-phrasing": "^4.0.0", + "mdast-util-to-string": "^4.0.0", + "micromark-util-classify-character": "^2.0.0", + "micromark-util-decode-string": "^2.0.0", + "unist-util-visit": "^5.0.0", + "zwitch": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/mdast-util-to-string": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/mdast-util-to-string/-/mdast-util-to-string-4.0.0.tgz", + "integrity": "sha512-0H44vDimn51F0YwvxSJSm0eCDOJTRlmN0R1yBh4HLj9wiV1Dn0QoXGbvFAWj2hSItVTlCmBF1hqKlIyUBVFLPg==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/merge2": { + "version": "1.4.1", + "resolved": "https://registry.npmjs.org/merge2/-/merge2-1.4.1.tgz", + "integrity": "sha512-8q7VEgMJW4J8tcfVPy8g09NcQwZdbwFEqhe/WZkoIzjn/3TGDwtOCYtXGxA3O8tPzpczCCDgv+P2P5y00ZJOOg==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">= 8" + } + }, + "node_modules/micromark": { + "version": "4.0.1", + "resolved": "https://registry.npmjs.org/micromark/-/micromark-4.0.1.tgz", + "integrity": "sha512-eBPdkcoCNvYcxQOAKAlceo5SNdzZWfF+FcSupREAzdAh9rRmE239CEQAiTwIgblwnoM8zzj35sZ5ZwvSEOF6Kw==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "@types/debug": "^4.0.0", + "debug": "^4.0.0", + "decode-named-character-reference": "^1.0.0", + "devlop": "^1.0.0", + "micromark-core-commonmark": "^2.0.0", + "micromark-factory-space": "^2.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-chunked": "^2.0.0", + "micromark-util-combine-extensions": "^2.0.0", + "micromark-util-decode-numeric-character-reference": "^2.0.0", + "micromark-util-encode": "^2.0.0", + "micromark-util-normalize-identifier": "^2.0.0", + "micromark-util-resolve-all": "^2.0.0", + "micromark-util-sanitize-uri": "^2.0.0", + "micromark-util-subtokenize": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-core-commonmark": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/micromark-core-commonmark/-/micromark-core-commonmark-2.0.2.tgz", + "integrity": "sha512-FKjQKbxd1cibWMM1P9N+H8TwlgGgSkWZMmfuVucLCHaYqeSvJ0hFeHsIa65pA2nYbes0f8LDHPMrd9X7Ujxg9w==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "decode-named-character-reference": "^1.0.0", + "devlop": "^1.0.0", + "micromark-factory-destination": "^2.0.0", + "micromark-factory-label": "^2.0.0", + "micromark-factory-space": "^2.0.0", + "micromark-factory-title": "^2.0.0", + "micromark-factory-whitespace": "^2.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-chunked": "^2.0.0", + "micromark-util-classify-character": "^2.0.0", + "micromark-util-html-tag-name": "^2.0.0", + "micromark-util-normalize-identifier": "^2.0.0", + "micromark-util-resolve-all": "^2.0.0", + "micromark-util-subtokenize": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-extension-gfm": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/micromark-extension-gfm/-/micromark-extension-gfm-3.0.0.tgz", + "integrity": "sha512-vsKArQsicm7t0z2GugkCKtZehqUm31oeGBV/KVSorWSy8ZlNAv7ytjFhvaryUiCUJYqs+NoE6AFhpQvBTM6Q4w==", + "license": "MIT", + "dependencies": { + "micromark-extension-gfm-autolink-literal": "^2.0.0", + "micromark-extension-gfm-footnote": "^2.0.0", + "micromark-extension-gfm-strikethrough": "^2.0.0", + "micromark-extension-gfm-table": "^2.0.0", + "micromark-extension-gfm-tagfilter": "^2.0.0", + "micromark-extension-gfm-task-list-item": "^2.0.0", + "micromark-util-combine-extensions": "^2.0.0", + "micromark-util-types": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/micromark-extension-gfm-autolink-literal": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/micromark-extension-gfm-autolink-literal/-/micromark-extension-gfm-autolink-literal-2.1.0.tgz", + "integrity": "sha512-oOg7knzhicgQ3t4QCjCWgTmfNhvQbDDnJeVu9v81r7NltNCVmhPy1fJRX27pISafdjL+SVc4d3l48Gb6pbRypw==", + "license": "MIT", + "dependencies": { + "micromark-util-character": "^2.0.0", + "micromark-util-sanitize-uri": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/micromark-extension-gfm-footnote": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/micromark-extension-gfm-footnote/-/micromark-extension-gfm-footnote-2.1.0.tgz", + "integrity": "sha512-/yPhxI1ntnDNsiHtzLKYnE3vf9JZ6cAisqVDauhp4CEHxlb4uoOTxOCJ+9s51bIB8U1N1FJ1RXOKTIlD5B/gqw==", + "license": "MIT", + "dependencies": { + "devlop": "^1.0.0", + "micromark-core-commonmark": "^2.0.0", + "micromark-factory-space": "^2.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-normalize-identifier": "^2.0.0", + "micromark-util-sanitize-uri": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/micromark-extension-gfm-strikethrough": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/micromark-extension-gfm-strikethrough/-/micromark-extension-gfm-strikethrough-2.1.0.tgz", + "integrity": "sha512-ADVjpOOkjz1hhkZLlBiYA9cR2Anf8F4HqZUO6e5eDcPQd0Txw5fxLzzxnEkSkfnD0wziSGiv7sYhk/ktvbf1uw==", + "license": "MIT", + "dependencies": { + "devlop": "^1.0.0", + "micromark-util-chunked": "^2.0.0", + "micromark-util-classify-character": "^2.0.0", + "micromark-util-resolve-all": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/micromark-extension-gfm-table": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/micromark-extension-gfm-table/-/micromark-extension-gfm-table-2.1.1.tgz", + "integrity": "sha512-t2OU/dXXioARrC6yWfJ4hqB7rct14e8f7m0cbI5hUmDyyIlwv5vEtooptH8INkbLzOatzKuVbQmAYcbWoyz6Dg==", + "license": "MIT", + "dependencies": { + "devlop": "^1.0.0", + "micromark-factory-space": "^2.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/micromark-extension-gfm-tagfilter": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/micromark-extension-gfm-tagfilter/-/micromark-extension-gfm-tagfilter-2.0.0.tgz", + "integrity": "sha512-xHlTOmuCSotIA8TW1mDIM6X2O1SiX5P9IuDtqGonFhEK0qgRI4yeC6vMxEV2dgyr2TiD+2PQ10o+cOhdVAcwfg==", + "license": "MIT", + "dependencies": { + "micromark-util-types": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/micromark-extension-gfm-task-list-item": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/micromark-extension-gfm-task-list-item/-/micromark-extension-gfm-task-list-item-2.1.0.tgz", + "integrity": "sha512-qIBZhqxqI6fjLDYFTBIa4eivDMnP+OZqsNwmQ3xNLE4Cxwc+zfQEfbs6tzAo2Hjq+bh6q5F+Z8/cksrLFYWQQw==", + "license": "MIT", + "dependencies": { + "devlop": "^1.0.0", + "micromark-factory-space": "^2.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/micromark-extension-math": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/micromark-extension-math/-/micromark-extension-math-3.1.0.tgz", + "integrity": "sha512-lvEqd+fHjATVs+2v/8kg9i5Q0AP2k85H0WUOwpIVvUML8BapsMvh1XAogmQjOCsLpoKRCVQqEkQBB3NhVBcsOg==", + "license": "MIT", + "dependencies": { + "@types/katex": "^0.16.0", + "devlop": "^1.0.0", + "katex": "^0.16.0", + "micromark-factory-space": "^2.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/micromark-factory-destination": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-factory-destination/-/micromark-factory-destination-2.0.1.tgz", + "integrity": "sha512-Xe6rDdJlkmbFRExpTOmRj9N3MaWmbAgdpSrBQvCFqhezUn4AHqJHbaEnfbVYYiexVSs//tqOdY/DxhjdCiJnIA==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-character": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-factory-label": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-factory-label/-/micromark-factory-label-2.0.1.tgz", + "integrity": "sha512-VFMekyQExqIW7xIChcXn4ok29YE3rnuyveW3wZQWWqF4Nv9Wk5rgJ99KzPvHjkmPXF93FXIbBp6YdW3t71/7Vg==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "devlop": "^1.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-factory-space": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-factory-space/-/micromark-factory-space-2.0.1.tgz", + "integrity": "sha512-zRkxjtBxxLd2Sc0d+fbnEunsTj46SWXgXciZmHq0kDYGnck/ZSGj9/wULTV95uoeYiK5hRXP2mJ98Uo4cq/LQg==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-character": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-factory-title": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-factory-title/-/micromark-factory-title-2.0.1.tgz", + "integrity": "sha512-5bZ+3CjhAd9eChYTHsjy6TGxpOFSKgKKJPJxr293jTbfry2KDoWkhBb6TcPVB4NmzaPhMs1Frm9AZH7OD4Cjzw==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-factory-space": "^2.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-factory-whitespace": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-factory-whitespace/-/micromark-factory-whitespace-2.0.1.tgz", + "integrity": "sha512-Ob0nuZ3PKt/n0hORHyvoD9uZhr+Za8sFoP+OnMcnWK5lngSzALgQYKMr9RJVOWLqQYuyn6ulqGWSXdwf6F80lQ==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-factory-space": "^2.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-util-character": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/micromark-util-character/-/micromark-util-character-2.1.1.tgz", + "integrity": "sha512-wv8tdUTJ3thSFFFJKtpYKOYiGP2+v96Hvk4Tu8KpCAsTMs6yi+nVmGh1syvSCsaxz45J6Jbw+9DD6g97+NV67Q==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-util-chunked": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-chunked/-/micromark-util-chunked-2.0.1.tgz", + "integrity": "sha512-QUNFEOPELfmvv+4xiNg2sRYeS/P84pTW0TCgP5zc9FpXetHY0ab7SxKyAQCNCc1eK0459uoLI1y5oO5Vc1dbhA==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-symbol": "^2.0.0" + } + }, + "node_modules/micromark-util-classify-character": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-classify-character/-/micromark-util-classify-character-2.0.1.tgz", + "integrity": "sha512-K0kHzM6afW/MbeWYWLjoHQv1sgg2Q9EccHEDzSkxiP/EaagNzCm7T/WMKZ3rjMbvIpvBiZgwR3dKMygtA4mG1Q==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-character": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-util-combine-extensions": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-combine-extensions/-/micromark-util-combine-extensions-2.0.1.tgz", + "integrity": "sha512-OnAnH8Ujmy59JcyZw8JSbK9cGpdVY44NKgSM7E9Eh7DiLS2E9RNQf0dONaGDzEG9yjEl5hcqeIsj4hfRkLH/Bg==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-chunked": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-util-decode-numeric-character-reference": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/micromark-util-decode-numeric-character-reference/-/micromark-util-decode-numeric-character-reference-2.0.2.tgz", + "integrity": "sha512-ccUbYk6CwVdkmCQMyr64dXz42EfHGkPQlBj5p7YVGzq8I7CtjXZJrubAYezf7Rp+bjPseiROqe7G6foFd+lEuw==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-symbol": "^2.0.0" + } + }, + "node_modules/micromark-util-decode-string": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-decode-string/-/micromark-util-decode-string-2.0.1.tgz", + "integrity": "sha512-nDV/77Fj6eH1ynwscYTOsbK7rR//Uj0bZXBwJZRfaLEJ1iGBR6kIfNmlNqaqJf649EP0F3NWNdeJi03elllNUQ==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "decode-named-character-reference": "^1.0.0", + "micromark-util-character": "^2.0.0", + "micromark-util-decode-numeric-character-reference": "^2.0.0", + "micromark-util-symbol": "^2.0.0" + } + }, + "node_modules/micromark-util-encode": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-encode/-/micromark-util-encode-2.0.1.tgz", + "integrity": "sha512-c3cVx2y4KqUnwopcO9b/SCdo2O67LwJJ/UyqGfbigahfegL9myoEFoDYZgkT7f36T0bLrM9hZTAaAyH+PCAXjw==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT" + }, + "node_modules/micromark-util-html-tag-name": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-html-tag-name/-/micromark-util-html-tag-name-2.0.1.tgz", + "integrity": "sha512-2cNEiYDhCWKI+Gs9T0Tiysk136SnR13hhO8yW6BGNyhOC4qYFnwF1nKfD3HFAIXA5c45RrIG1ub11GiXeYd1xA==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT" + }, + "node_modules/micromark-util-normalize-identifier": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-normalize-identifier/-/micromark-util-normalize-identifier-2.0.1.tgz", + "integrity": "sha512-sxPqmo70LyARJs0w2UclACPUUEqltCkJ6PhKdMIDuJ3gSf/Q+/GIe3WKl0Ijb/GyH9lOpUkRAO2wp0GVkLvS9Q==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-symbol": "^2.0.0" + } + }, + "node_modules/micromark-util-resolve-all": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-resolve-all/-/micromark-util-resolve-all-2.0.1.tgz", + "integrity": "sha512-VdQyxFWFT2/FGJgwQnJYbe1jjQoNTS4RjglmSjTUlpUMa95Htx9NHeYW4rGDJzbjvCsl9eLjMQwGeElsqmzcHg==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-util-sanitize-uri": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-sanitize-uri/-/micromark-util-sanitize-uri-2.0.1.tgz", + "integrity": "sha512-9N9IomZ/YuGGZZmQec1MbgxtlgougxTodVwDzzEouPKo3qFWvymFHWcnDi2vzV1ff6kas9ucW+o3yzJK9YB1AQ==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "micromark-util-character": "^2.0.0", + "micromark-util-encode": "^2.0.0", + "micromark-util-symbol": "^2.0.0" + } + }, + "node_modules/micromark-util-subtokenize": { + "version": "2.0.4", + "resolved": "https://registry.npmjs.org/micromark-util-subtokenize/-/micromark-util-subtokenize-2.0.4.tgz", + "integrity": "sha512-N6hXjrin2GTJDe3MVjf5FuXpm12PGm80BrUAeub9XFXca8JZbP+oIwY4LJSVwFUCL1IPm/WwSVUN7goFHmSGGQ==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT", + "dependencies": { + "devlop": "^1.0.0", + "micromark-util-chunked": "^2.0.0", + "micromark-util-symbol": "^2.0.0", + "micromark-util-types": "^2.0.0" + } + }, + "node_modules/micromark-util-symbol": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-symbol/-/micromark-util-symbol-2.0.1.tgz", + "integrity": "sha512-vs5t8Apaud9N28kgCrRUdEed4UJ+wWNvicHLPxCa9ENlYuAY31M0ETy5y1vA33YoNPDFTghEbnh6efaE8h4x0Q==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT" + }, + "node_modules/micromark-util-types": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/micromark-util-types/-/micromark-util-types-2.0.1.tgz", + "integrity": "sha512-534m2WhVTddrcKVepwmVEVnUAmtrx9bfIjNoQHRqfnvdaHQiFytEhJoTgpWJvDEXCO5gLTQh3wYC1PgOJA4NSQ==", + "funding": [ + { + "type": "GitHub Sponsors", + "url": "https://github.com/sponsors/unifiedjs" + }, + { + "type": "OpenCollective", + "url": "https://opencollective.com/unified" + } + ], + "license": "MIT" + }, + "node_modules/micromatch": { + "version": "4.0.8", + "resolved": "https://registry.npmjs.org/micromatch/-/micromatch-4.0.8.tgz", + "integrity": "sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==", + "license": "MIT", + "dependencies": { + "braces": "^3.0.3", + "picomatch": "^2.3.1" + }, + "engines": { + "node": ">=8.6" + } + }, + "node_modules/minimatch": { + "version": "3.1.2", + "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz", + "integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==", + "dev": true, + "license": "ISC", + "dependencies": { + "brace-expansion": "^1.1.7" + }, + "engines": { + "node": "*" + } + }, + "node_modules/ms": { + "version": "2.1.3", + "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz", + "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==", + "license": "MIT" + }, + "node_modules/nanoid": { + "version": "3.3.8", + "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.8.tgz", + "integrity": "sha512-WNLf5Sd8oZxOm+TzppcYk8gVOgP+l58xNy58D0nbUnOxOWRWvlcCV4kUF7ltmI6PsrLl/BgKEyS4mqsGChFN0w==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ], + "license": "MIT", + "bin": { + "nanoid": "bin/nanoid.cjs" + }, + "engines": { + "node": "^10 || ^12 || ^13.7 || ^14 || >=15.0.1" + } + }, + "node_modules/natural-compare": { + "version": "1.4.0", + "resolved": "https://registry.npmjs.org/natural-compare/-/natural-compare-1.4.0.tgz", + "integrity": "sha512-OWND8ei3VtNC9h7V60qff3SVobHr996CTwgxubgyQYEpg290h9J0buyECNNJexkFm5sOajh5G116RYA1c8ZMSw==", + "dev": true, + "license": "MIT" + }, + "node_modules/node-releases": { + "version": "2.0.19", + "resolved": "https://registry.npmjs.org/node-releases/-/node-releases-2.0.19.tgz", + "integrity": "sha512-xxOWJsBKtzAq7DY0J+DTzuz58K8e7sJbdgwkbMWQe8UYB6ekmsQ45q0M/tJDsGaZmbC+l7n57UV8Hl5tHxO9uw==", + "license": "MIT" + }, + "node_modules/normalize-range": { + "version": "0.1.2", + "resolved": "https://registry.npmjs.org/normalize-range/-/normalize-range-0.1.2.tgz", + "integrity": "sha512-bdok/XvKII3nUpklnV6P2hxtMNrCboOjAcyBuQnWEhO665FwrSNRxU+AqpsyvO6LgGYPspN+lu5CLtw4jPRKNA==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/optionator": { + "version": "0.9.4", + "resolved": "https://registry.npmjs.org/optionator/-/optionator-0.9.4.tgz", + "integrity": "sha512-6IpQ7mKUxRcZNLIObR0hz7lxsapSSIYNZJwXPGeF0mTVqGKFIXj1DQcMoT22S3ROcLyY/rz0PWaWZ9ayWmad9g==", + "dev": true, + "license": "MIT", + "dependencies": { + "deep-is": "^0.1.3", + "fast-levenshtein": "^2.0.6", + "levn": "^0.4.1", + "prelude-ls": "^1.2.1", + "type-check": "^0.4.0", + "word-wrap": "^1.2.5" + }, + "engines": { + "node": ">= 0.8.0" + } + }, + "node_modules/p-limit": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/p-limit/-/p-limit-3.1.0.tgz", + "integrity": "sha512-TYOanM3wGwNGsZN2cVTYPArw454xnXj5qmWF1bEoAc4+cU/ol7GVh7odevjp1FNHduHc3KZMcFduxU5Xc6uJRQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "yocto-queue": "^0.1.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/p-locate": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/p-locate/-/p-locate-5.0.0.tgz", + "integrity": "sha512-LaNjtRWUBY++zB5nE/NwcaoMylSPk+S+ZHNB1TzdbMJMny6dynpAGt7X/tl/QYq3TIeE6nxHppbo2LGymrG5Pw==", + "dev": true, + "license": "MIT", + "dependencies": { + "p-limit": "^3.0.2" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/parent-module": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/parent-module/-/parent-module-1.0.1.tgz", + "integrity": "sha512-GQ2EWRpQV8/o+Aw8YqtfZZPfNRWZYkbidE9k5rpl/hC3vtHHBfGm2Ifi6qWV+coDGkrUKZAxE3Lot5kcsRlh+g==", + "dev": true, + "license": "MIT", + "dependencies": { + "callsites": "^3.0.0" + }, + "engines": { + "node": ">=6" + } + }, + "node_modules/parse-entities": { + "version": "4.0.2", + "resolved": "https://registry.npmjs.org/parse-entities/-/parse-entities-4.0.2.tgz", + "integrity": "sha512-GG2AQYWoLgL877gQIKeRPGO1xF9+eG1ujIb5soS5gPvLQ1y2o8FL90w2QWNdf9I361Mpp7726c+lj3U0qK1uGw==", + "license": "MIT", + "dependencies": { + "@types/unist": "^2.0.0", + "character-entities-legacy": "^3.0.0", + "character-reference-invalid": "^2.0.0", + "decode-named-character-reference": "^1.0.0", + "is-alphanumerical": "^2.0.0", + "is-decimal": "^2.0.0", + "is-hexadecimal": "^2.0.0" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/parse-entities/node_modules/@types/unist": { + "version": "2.0.11", + "resolved": "https://registry.npmjs.org/@types/unist/-/unist-2.0.11.tgz", + "integrity": "sha512-CmBKiL6NNo/OqgmMn95Fk9Whlp2mtvIv+KNpQKN2F4SjvrEesubTRWGYSg+BnWZOnlCaSTU1sMpsBOzgbYhnsA==", + "license": "MIT" + }, + "node_modules/parse5": { + "version": "7.2.1", + "resolved": "https://registry.npmjs.org/parse5/-/parse5-7.2.1.tgz", + "integrity": "sha512-BuBYQYlv1ckiPdQi/ohiivi9Sagc9JG+Ozs0r7b/0iK3sKmrb0b9FdWdBbOdx6hBCM/F9Ir82ofnBhtZOjCRPQ==", + "license": "MIT", + "dependencies": { + "entities": "^4.5.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/path-exists": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/path-exists/-/path-exists-4.0.0.tgz", + "integrity": "sha512-ak9Qy5Q7jYb2Wwcey5Fpvg2KoAc/ZIhLSLOSBmRmygPsGwkVVt0fZa0qrtMz+m6tJTAHfZQ8FnmB4MG4LWy7/w==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=8" + } + }, + "node_modules/path-key": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz", + "integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=8" + } + }, + "node_modules/picocolors": { + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz", + "integrity": "sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==", + "license": "ISC" + }, + "node_modules/picomatch": { + "version": "2.3.1", + "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.1.tgz", + "integrity": "sha512-JU3teHTNjmE2VCGFzuY8EXzCDVwEqB2a8fsIvwaStHhAWJEeVd1o1QD80CU6+ZdEXXSLbSsuLwJjkCBWqRQUVA==", + "license": "MIT", + "engines": { + "node": ">=8.6" + }, + "funding": { + "url": "https://github.com/sponsors/jonschlinkert" + } + }, + "node_modules/postcss": { + "version": "8.5.1", + "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.1.tgz", + "integrity": "sha512-6oz2beyjc5VMn/KV1pPw8fliQkhBXrVn1Z3TVyqZxU8kZpzEKhBdmCFqI6ZbmGtamQvQGuU1sgPTk8ZrXDD7jQ==", + "funding": [ + { + "type": "opencollective", + "url": "https://opencollective.com/postcss/" + }, + { + "type": "tidelift", + "url": "https://tidelift.com/funding/github/npm/postcss" + }, + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ], + "license": "MIT", + "dependencies": { + "nanoid": "^3.3.8", + "picocolors": "^1.1.1", + "source-map-js": "^1.2.1" + }, + "engines": { + "node": "^10 || ^12 || >=14" + } + }, + "node_modules/postcss-value-parser": { + "version": "4.2.0", + "resolved": "https://registry.npmjs.org/postcss-value-parser/-/postcss-value-parser-4.2.0.tgz", + "integrity": "sha512-1NNCs6uurfkVbeXG4S8JFT9t19m45ICnif8zWLd5oPSZ50QnwMfK+H3jv408d4jw/7Bttv5axS5IiHoLaVNHeQ==", + "license": "MIT" + }, + "node_modules/prelude-ls": { + "version": "1.2.1", + "resolved": "https://registry.npmjs.org/prelude-ls/-/prelude-ls-1.2.1.tgz", + "integrity": "sha512-vkcDPrRZo1QZLbn5RLGPpg/WmIQ65qoWWhcGKf/b5eplkkarX0m9z8ppCat4mlOqUsWpyNuYgO3VRyrYHSzX5g==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">= 0.8.0" + } + }, + "node_modules/prettier": { + "version": "3.4.2", + "resolved": "https://registry.npmjs.org/prettier/-/prettier-3.4.2.tgz", + "integrity": "sha512-e9MewbtFo+Fevyuxn/4rrcDAaq0IYxPGLvObpQjiZBMAzB9IGmzlnG9RZy3FFas+eBMu2vA0CszMeduow5dIuQ==", + "dev": true, + "license": "MIT", + "bin": { + "prettier": "bin/prettier.cjs" + }, + "engines": { + "node": ">=14" + }, + "funding": { + "url": "https://github.com/prettier/prettier?sponsor=1" + } + }, + "node_modules/property-information": { + "version": "6.5.0", + "resolved": "https://registry.npmjs.org/property-information/-/property-information-6.5.0.tgz", + "integrity": "sha512-PgTgs/BlvHxOu8QuEN7wi5A0OmXaBcHpmCSTehcs6Uuu9IkDIEo13Hy7n898RHfrQ49vKCoGeWZSaAK01nwVig==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/punycode": { + "version": "2.3.1", + "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz", + "integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=6" + } + }, + "node_modules/queue-microtask": { + "version": "1.2.3", + "resolved": "https://registry.npmjs.org/queue-microtask/-/queue-microtask-1.2.3.tgz", + "integrity": "sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/feross" + }, + { + "type": "patreon", + "url": "https://www.patreon.com/feross" + }, + { + "type": "consulting", + "url": "https://feross.org/support" + } + ], + "license": "MIT" + }, + "node_modules/react": { + "version": "18.3.1", + "resolved": "https://registry.npmjs.org/react/-/react-18.3.1.tgz", + "integrity": "sha512-wS+hAgJShR0KhEvPJArfuPVN1+Hz1t0Y6n5jLrGQbkb4urgPE/0Rve+1kMB1v/oWgHgm4WIcV+i7F2pTVj+2iQ==", + "license": "MIT", + "dependencies": { + "loose-envify": "^1.1.0" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/react-dom": { + "version": "18.3.1", + "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-18.3.1.tgz", + "integrity": "sha512-5m4nQKp+rZRb09LNH59GM4BxTh9251/ylbKIbpe7TpGxfJ+9kv6BLkLBXIjjspbgbnIBNqlI23tRnTWT0snUIw==", + "license": "MIT", + "dependencies": { + "loose-envify": "^1.1.0", + "scheduler": "^0.23.2" + }, + "peerDependencies": { + "react": "^18.3.1" + } + }, + "node_modules/react-markdown": { + "version": "9.0.3", + "resolved": "https://registry.npmjs.org/react-markdown/-/react-markdown-9.0.3.tgz", + "integrity": "sha512-Yk7Z94dbgYTOrdk41Z74GoKA7rThnsbbqBTRYuxoe08qvfQ9tJVhmAKw6BJS/ZORG7kTy/s1QvYzSuaoBA1qfw==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "devlop": "^1.0.0", + "hast-util-to-jsx-runtime": "^2.0.0", + "html-url-attributes": "^3.0.0", + "mdast-util-to-hast": "^13.0.0", + "remark-parse": "^11.0.0", + "remark-rehype": "^11.0.0", + "unified": "^11.0.0", + "unist-util-visit": "^5.0.0", + "vfile": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + }, + "peerDependencies": { + "@types/react": ">=18", + "react": ">=18" + } + }, + "node_modules/react-refresh": { + "version": "0.14.2", + "resolved": "https://registry.npmjs.org/react-refresh/-/react-refresh-0.14.2.tgz", + "integrity": "sha512-jCvmsr+1IUSMUyzOkRcvnVbX3ZYC6g9TDrDbFuFmRDq7PD4yaGbLKNQL6k2jnArV8hjYxh7hVhAZB6s9HDGpZA==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/react-router": { + "version": "7.1.5", + "resolved": "https://registry.npmjs.org/react-router/-/react-router-7.1.5.tgz", + "integrity": "sha512-8BUF+hZEU4/z/JD201yK6S+UYhsf58bzYIDq2NS1iGpwxSXDu7F+DeGSkIXMFBuHZB21FSiCzEcUb18cQNdRkA==", + "license": "MIT", + "dependencies": { + "@types/cookie": "^0.6.0", + "cookie": "^1.0.1", + "set-cookie-parser": "^2.6.0", + "turbo-stream": "2.4.0" + }, + "engines": { + "node": ">=20.0.0" + }, + "peerDependencies": { + "react": ">=18", + "react-dom": ">=18" + }, + "peerDependenciesMeta": { + "react-dom": { + "optional": true + } + } + }, + "node_modules/rehype-highlight": { + "version": "7.0.2", + "resolved": "https://registry.npmjs.org/rehype-highlight/-/rehype-highlight-7.0.2.tgz", + "integrity": "sha512-k158pK7wdC2qL3M5NcZROZ2tR/l7zOzjxXd5VGdcfIyoijjQqpHd3JKtYSBDpDZ38UI2WJWuFAtkMDxmx5kstA==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "hast-util-to-text": "^4.0.0", + "lowlight": "^3.0.0", + "unist-util-visit": "^5.0.0", + "vfile": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/rehype-katex": { + "version": "7.0.1", + "resolved": "https://registry.npmjs.org/rehype-katex/-/rehype-katex-7.0.1.tgz", + "integrity": "sha512-OiM2wrZ/wuhKkigASodFoo8wimG3H12LWQaH8qSPVJn9apWKFSH3YOCtbKpBorTVw/eI7cuT21XBbvwEswbIOA==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "@types/katex": "^0.16.0", + "hast-util-from-html-isomorphic": "^2.0.0", + "hast-util-to-text": "^4.0.0", + "katex": "^0.16.0", + "unist-util-visit-parents": "^6.0.0", + "vfile": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/remark-breaks": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/remark-breaks/-/remark-breaks-4.0.0.tgz", + "integrity": "sha512-IjEjJOkH4FuJvHZVIW0QCDWxcG96kCq7An/KVH2NfJe6rKZU2AsHeB3OEjPNRxi4QC34Xdx7I2KGYn6IpT7gxQ==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "mdast-util-newline-to-break": "^2.0.0", + "unified": "^11.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/remark-gfm": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/remark-gfm/-/remark-gfm-4.0.0.tgz", + "integrity": "sha512-U92vJgBPkbw4Zfu/IiW2oTZLSL3Zpv+uI7My2eq8JxKgqraFdU8YUGicEJCEgSbeaG+QDFqIcwwfMTOEelPxuA==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "mdast-util-gfm": "^3.0.0", + "micromark-extension-gfm": "^3.0.0", + "remark-parse": "^11.0.0", + "remark-stringify": "^11.0.0", + "unified": "^11.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/remark-math": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/remark-math/-/remark-math-6.0.0.tgz", + "integrity": "sha512-MMqgnP74Igy+S3WwnhQ7kqGlEerTETXMvJhrUzDikVZ2/uogJCb+WHUg97hK9/jcfc0dkD73s3LN8zU49cTEtA==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "mdast-util-math": "^3.0.0", + "micromark-extension-math": "^3.0.0", + "unified": "^11.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/remark-parse": { + "version": "11.0.0", + "resolved": "https://registry.npmjs.org/remark-parse/-/remark-parse-11.0.0.tgz", + "integrity": "sha512-FCxlKLNGknS5ba/1lmpYijMUzX2esxW5xQqjWxw2eHFfS2MSdaHVINFmhjo+qN1WhZhNimq0dZATN9pH0IDrpA==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "mdast-util-from-markdown": "^2.0.0", + "micromark-util-types": "^2.0.0", + "unified": "^11.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/remark-rehype": { + "version": "11.1.1", + "resolved": "https://registry.npmjs.org/remark-rehype/-/remark-rehype-11.1.1.tgz", + "integrity": "sha512-g/osARvjkBXb6Wo0XvAeXQohVta8i84ACbenPpoSsxTOQH/Ae0/RGP4WZgnMH5pMLpsj4FG7OHmcIcXxpza8eQ==", + "license": "MIT", + "dependencies": { + "@types/hast": "^3.0.0", + "@types/mdast": "^4.0.0", + "mdast-util-to-hast": "^13.0.0", + "unified": "^11.0.0", + "vfile": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/remark-stringify": { + "version": "11.0.0", + "resolved": "https://registry.npmjs.org/remark-stringify/-/remark-stringify-11.0.0.tgz", + "integrity": "sha512-1OSmLd3awB/t8qdoEOMazZkNsfVTeY4fTsgzcQFdXNq8ToTN4ZGwrMnlda4K6smTFKD+GRV6O48i6Z4iKgPPpw==", + "license": "MIT", + "dependencies": { + "@types/mdast": "^4.0.0", + "mdast-util-to-markdown": "^2.0.0", + "unified": "^11.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/resolve-from": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/resolve-from/-/resolve-from-4.0.0.tgz", + "integrity": "sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=4" + } + }, + "node_modules/reusify": { + "version": "1.0.4", + "resolved": "https://registry.npmjs.org/reusify/-/reusify-1.0.4.tgz", + "integrity": "sha512-U9nH88a3fc/ekCF1l0/UP1IosiuIjyTh7hBvXVMHYgVcfGvt897Xguj2UOLDeI5BG2m7/uwyaLVT6fbtCwTyzw==", + "dev": true, + "license": "MIT", + "engines": { + "iojs": ">=1.0.0", + "node": ">=0.10.0" + } + }, + "node_modules/rollup": { + "version": "4.34.2", + "resolved": "https://registry.npmjs.org/rollup/-/rollup-4.34.2.tgz", + "integrity": "sha512-sBDUoxZEaqLu9QeNalL8v3jw6WjPku4wfZGyTU7l7m1oC+rpRihXc/n/H+4148ZkGz5Xli8CHMns//fFGKvpIQ==", + "license": "MIT", + "dependencies": { + "@types/estree": "1.0.6" + }, + "bin": { + "rollup": "dist/bin/rollup" + }, + "engines": { + "node": ">=18.0.0", + "npm": ">=8.0.0" + }, + "optionalDependencies": { + "@rollup/rollup-android-arm-eabi": "4.34.2", + "@rollup/rollup-android-arm64": "4.34.2", + "@rollup/rollup-darwin-arm64": "4.34.2", + "@rollup/rollup-darwin-x64": "4.34.2", + "@rollup/rollup-freebsd-arm64": "4.34.2", + "@rollup/rollup-freebsd-x64": "4.34.2", + "@rollup/rollup-linux-arm-gnueabihf": "4.34.2", + "@rollup/rollup-linux-arm-musleabihf": "4.34.2", + "@rollup/rollup-linux-arm64-gnu": "4.34.2", + "@rollup/rollup-linux-arm64-musl": "4.34.2", + "@rollup/rollup-linux-loongarch64-gnu": "4.34.2", + "@rollup/rollup-linux-powerpc64le-gnu": "4.34.2", + "@rollup/rollup-linux-riscv64-gnu": "4.34.2", + "@rollup/rollup-linux-s390x-gnu": "4.34.2", + "@rollup/rollup-linux-x64-gnu": "4.34.2", + "@rollup/rollup-linux-x64-musl": "4.34.2", + "@rollup/rollup-win32-arm64-msvc": "4.34.2", + "@rollup/rollup-win32-ia32-msvc": "4.34.2", + "@rollup/rollup-win32-x64-msvc": "4.34.2", + "fsevents": "~2.3.2" + } + }, + "node_modules/run-parallel": { + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/run-parallel/-/run-parallel-1.2.0.tgz", + "integrity": "sha512-5l4VyZR86LZ/lDxZTR6jqL8AFE2S0IFLMP26AbjsLVADxHdhB/c0GUsH+y39UfCi3dzz8OlQuPmnaJOMoDHQBA==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/feross" + }, + { + "type": "patreon", + "url": "https://www.patreon.com/feross" + }, + { + "type": "consulting", + "url": "https://feross.org/support" + } + ], + "license": "MIT", + "dependencies": { + "queue-microtask": "^1.2.2" + } + }, + "node_modules/rxjs": { + "version": "7.8.1", + "resolved": "https://registry.npmjs.org/rxjs/-/rxjs-7.8.1.tgz", + "integrity": "sha512-AA3TVj+0A2iuIoQkWEK/tqFjBq2j+6PO6Y0zJcvzLAFhEFIO3HL0vls9hWLncZbAAbK0mar7oZ4V079I/qPMxg==", + "devOptional": true, + "license": "Apache-2.0", + "dependencies": { + "tslib": "^2.1.0" + } + }, + "node_modules/sass-embedded": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded/-/sass-embedded-1.83.4.tgz", + "integrity": "sha512-Hf2burRA/y5PGxsg6jB9UpoK/xZ6g/pgrkOcdl6j+rRg1Zj8XhGKZ1MTysZGtTPUUmiiErqzkP5+Kzp95yv9GQ==", + "devOptional": true, + "license": "MIT", + "dependencies": { + "@bufbuild/protobuf": "^2.0.0", + "buffer-builder": "^0.2.0", + "colorjs.io": "^0.5.0", + "immutable": "^5.0.2", + "rxjs": "^7.4.0", + "supports-color": "^8.1.1", + "sync-child-process": "^1.0.2", + "varint": "^6.0.0" + }, + "bin": { + "sass": "dist/bin/sass.js" + }, + "engines": { + "node": ">=16.0.0" + }, + "optionalDependencies": { + "sass-embedded-android-arm": "1.83.4", + "sass-embedded-android-arm64": "1.83.4", + "sass-embedded-android-ia32": "1.83.4", + "sass-embedded-android-riscv64": "1.83.4", + "sass-embedded-android-x64": "1.83.4", + "sass-embedded-darwin-arm64": "1.83.4", + "sass-embedded-darwin-x64": "1.83.4", + "sass-embedded-linux-arm": "1.83.4", + "sass-embedded-linux-arm64": "1.83.4", + "sass-embedded-linux-ia32": "1.83.4", + "sass-embedded-linux-musl-arm": "1.83.4", + "sass-embedded-linux-musl-arm64": "1.83.4", + "sass-embedded-linux-musl-ia32": "1.83.4", + "sass-embedded-linux-musl-riscv64": "1.83.4", + "sass-embedded-linux-musl-x64": "1.83.4", + "sass-embedded-linux-riscv64": "1.83.4", + "sass-embedded-linux-x64": "1.83.4", + "sass-embedded-win32-arm64": "1.83.4", + "sass-embedded-win32-ia32": "1.83.4", + "sass-embedded-win32-x64": "1.83.4" + } + }, + "node_modules/sass-embedded-android-arm": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-android-arm/-/sass-embedded-android-arm-1.83.4.tgz", + "integrity": "sha512-9Z4pJAOgEkXa3VDY/o+U6l5XvV0mZTJcSl0l/mSPHihjAHSpLYnOW6+KOWeM8dxqrsqTYcd6COzhanI/a++5Gw==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-android-arm64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-android-arm64/-/sass-embedded-android-arm64-1.83.4.tgz", + "integrity": "sha512-tgX4FzmbVqnQmD67ZxQDvI+qFNABrboOQgwsG05E5bA/US42zGajW9AxpECJYiMXVOHmg+d81ICbjb0fsVHskw==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-android-ia32": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-android-ia32/-/sass-embedded-android-ia32-1.83.4.tgz", + "integrity": "sha512-RsFOziFqPcfZXdFRULC4Ayzy9aK6R6FwQ411broCjlOBX+b0gurjRadkue3cfUEUR5mmy0KeCbp7zVKPLTK+5Q==", + "cpu": [ + "ia32" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-android-riscv64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-android-riscv64/-/sass-embedded-android-riscv64-1.83.4.tgz", + "integrity": "sha512-EHwh0nmQarBBrMRU928eTZkFGx19k/XW2YwbPR4gBVdWLkbTgCA5aGe8hTE6/1zStyx++3nDGvTZ78+b/VvvLg==", + "cpu": [ + "riscv64" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-android-x64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-android-x64/-/sass-embedded-android-x64-1.83.4.tgz", + "integrity": "sha512-0PgQNuPWYy1jEOEPDVsV89KfqOsMLIp9CSbjBY7jRcwRhyVAcigqrUG6bDeNtojHUYKA1kU+Eh/85WxOHUOgBw==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-darwin-arm64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-darwin-arm64/-/sass-embedded-darwin-arm64-1.83.4.tgz", + "integrity": "sha512-rp2ywymWc3nymnSnAFG5R/8hvxWCsuhK3wOnD10IDlmNB7o4rzKby1c+2ZfpQGowlYGWsWWTgz8FW2qzmZsQRw==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-darwin-x64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-darwin-x64/-/sass-embedded-darwin-x64-1.83.4.tgz", + "integrity": "sha512-kLkN2lXz9PCgGfDS8Ev5YVcl/V2173L6379en/CaFuJJi7WiyPgBymW7hOmfCt4uO4R1y7CP2Uc08DRtZsBlAA==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-arm": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-arm/-/sass-embedded-linux-arm-1.83.4.tgz", + "integrity": "sha512-nL90ryxX2lNmFucr9jYUyHHx21AoAgdCL1O5Ltx2rKg2xTdytAGHYo2MT5S0LIeKLa/yKP/hjuSvrbICYNDvtA==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-arm64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-arm64/-/sass-embedded-linux-arm64-1.83.4.tgz", + "integrity": "sha512-E0zjsZX2HgESwyqw31EHtI39DKa7RgK7nvIhIRco1d0QEw227WnoR9pjH3M/ZQy4gQj3GKilOFHM5Krs/omeIA==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-ia32": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-ia32/-/sass-embedded-linux-ia32-1.83.4.tgz", + "integrity": "sha512-ew5HpchSzgAYbQoriRh8QhlWn5Kw2nQ2jHoV9YLwGKe3fwwOWA0KDedssvDv7FWnY/FCqXyymhLd6Bxae4Xquw==", + "cpu": [ + "ia32" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-musl-arm": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-musl-arm/-/sass-embedded-linux-musl-arm-1.83.4.tgz", + "integrity": "sha512-0RrJRwMrmm+gG0VOB5b5Cjs7Sd+lhqpQJa6EJNEaZHljJokEfpE5GejZsGMRMIQLxEvVphZnnxl6sonCGFE/QQ==", + "cpu": [ + "arm" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-musl-arm64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-musl-arm64/-/sass-embedded-linux-musl-arm64-1.83.4.tgz", + "integrity": "sha512-IzMgalf6MZOxgp4AVCgsaWAFDP/IVWOrgVXxkyhw29fyAEoSWBJH4k87wyPhEtxSuzVHLxKNbc8k3UzdWmlBFg==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-musl-ia32": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-musl-ia32/-/sass-embedded-linux-musl-ia32-1.83.4.tgz", + "integrity": "sha512-LLb4lYbcxPzX4UaJymYXC+WwokxUlfTJEFUv5VF0OTuSsHAGNRs/rslPtzVBTvMeG9TtlOQDhku1F7G6iaDotA==", + "cpu": [ + "ia32" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-musl-riscv64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-musl-riscv64/-/sass-embedded-linux-musl-riscv64-1.83.4.tgz", + "integrity": "sha512-zoKlPzD5Z13HKin1UGR74QkEy+kZEk2AkGX5RelRG494mi+IWwRuWCppXIovor9+BQb9eDWPYPoMVahwN5F7VA==", + "cpu": [ + "riscv64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-musl-x64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-musl-x64/-/sass-embedded-linux-musl-x64-1.83.4.tgz", + "integrity": "sha512-hB8+/PYhfEf2zTIcidO5Bpof9trK6WJjZ4T8g2MrxQh8REVtdPcgIkoxczRynqybf9+fbqbUwzXtiUao2GV+vQ==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-riscv64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-riscv64/-/sass-embedded-linux-riscv64-1.83.4.tgz", + "integrity": "sha512-83fL4n+oeDJ0Y4KjASmZ9jHS1Vl9ESVQYHMhJE0i4xDi/P3BNarm2rsKljq/QtrwGpbqwn8ujzOu7DsNCMDSHA==", + "cpu": [ + "riscv64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-linux-x64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-linux-x64/-/sass-embedded-linux-x64-1.83.4.tgz", + "integrity": "sha512-NlnGdvCmTD5PK+LKXlK3sAuxOgbRIEoZfnHvxd157imCm/s2SYF/R28D0DAAjEViyI8DovIWghgbcqwuertXsA==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-win32-arm64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-win32-arm64/-/sass-embedded-win32-arm64-1.83.4.tgz", + "integrity": "sha512-J2BFKrEaeSrVazU2qTjyQdAk+MvbzJeTuCET0uAJEXSKtvQ3AzxvzndS7LqkDPbF32eXAHLw8GVpwcBwKbB3Uw==", + "cpu": [ + "arm64" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-win32-ia32": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-win32-ia32/-/sass-embedded-win32-ia32-1.83.4.tgz", + "integrity": "sha512-uPAe9T/5sANFhJS5dcfAOhOJy8/l2TRYG4r+UO3Wp4yhqbN7bggPvY9c7zMYS0OC8tU/bCvfYUDFHYMCl91FgA==", + "cpu": [ + "ia32" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded-win32-x64": { + "version": "1.83.4", + "resolved": "https://registry.npmjs.org/sass-embedded-win32-x64/-/sass-embedded-win32-x64-1.83.4.tgz", + "integrity": "sha512-C9fkDY0jKITdJFij4UbfPFswxoXN9O/Dr79v17fJnstVwtUojzVJWKHUXvF0Zg2LIR7TCc4ju3adejKFxj7ueA==", + "cpu": [ + "x64" + ], + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=14.0.0" + } + }, + "node_modules/sass-embedded/node_modules/supports-color": { + "version": "8.1.1", + "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-8.1.1.tgz", + "integrity": "sha512-MpUEN2OodtUzxvKQl72cUF7RQ5EiHsGvSsVG0ia9c5RbWGL2CI4C7EpPS8UTBIplnlzZiNuV56w+FuNxy3ty2Q==", + "devOptional": true, + "license": "MIT", + "dependencies": { + "has-flag": "^4.0.0" + }, + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/supports-color?sponsor=1" + } + }, + "node_modules/scheduler": { + "version": "0.23.2", + "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.23.2.tgz", + "integrity": "sha512-UOShsPwz7NrMUqhR6t0hWjFduvOzbtv7toDH1/hIrfRNIDBnnBWd0CwJTGvTpngVlmwGCdP9/Zl/tVrDqcuYzQ==", + "license": "MIT", + "dependencies": { + "loose-envify": "^1.1.0" + } + }, + "node_modules/semver": { + "version": "6.3.1", + "resolved": "https://registry.npmjs.org/semver/-/semver-6.3.1.tgz", + "integrity": "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA==", + "dev": true, + "license": "ISC", + "bin": { + "semver": "bin/semver.js" + } + }, + "node_modules/set-cookie-parser": { + "version": "2.7.1", + "resolved": "https://registry.npmjs.org/set-cookie-parser/-/set-cookie-parser-2.7.1.tgz", + "integrity": "sha512-IOc8uWeOZgnb3ptbCURJWNjWUPcO3ZnTTdzsurqERrP6nPyv+paC55vJM0LpOlT2ne+Ix+9+CRG1MNLlyZ4GjQ==", + "license": "MIT" + }, + "node_modules/shebang-command": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz", + "integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==", + "dev": true, + "license": "MIT", + "dependencies": { + "shebang-regex": "^3.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/shebang-regex": { + "version": "3.0.0", + "resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz", + "integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=8" + } + }, + "node_modules/source-map-js": { + "version": "1.2.1", + "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz", + "integrity": "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==", + "license": "BSD-3-Clause", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/space-separated-tokens": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/space-separated-tokens/-/space-separated-tokens-2.0.2.tgz", + "integrity": "sha512-PEGlAwrG8yXGXRjW32fGbg66JAlOAwbObuqVoJpv/mRgoWDQfgH1wDPvtzWyUSNAXBGSk8h755YDbbcEy3SH2Q==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/stringify-entities": { + "version": "4.0.4", + "resolved": "https://registry.npmjs.org/stringify-entities/-/stringify-entities-4.0.4.tgz", + "integrity": "sha512-IwfBptatlO+QCJUo19AqvrPNqlVMpW9YEL2LIVY+Rpv2qsjCGxaDLNRgeGsQWJhfItebuJhsGSLjaBbNSQ+ieg==", + "license": "MIT", + "dependencies": { + "character-entities-html4": "^2.0.0", + "character-entities-legacy": "^3.0.0" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/strip-json-comments": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/strip-json-comments/-/strip-json-comments-3.1.1.tgz", + "integrity": "sha512-6fPc+R4ihwqP6N/aIv2f1gMH8lOVtWQHoqC4yK6oSDVVocumAsfCqjkXnqiYMhmMwS/mEHLp7Vehlt3ql6lEig==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=8" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/style-to-object": { + "version": "1.0.8", + "resolved": "https://registry.npmjs.org/style-to-object/-/style-to-object-1.0.8.tgz", + "integrity": "sha512-xT47I/Eo0rwJmaXC4oilDGDWLohVhR6o/xAQcPQN8q6QBuZVL8qMYL85kLmST5cPjAorwvqIA4qXTRQoYHaL6g==", + "license": "MIT", + "dependencies": { + "inline-style-parser": "0.2.4" + } + }, + "node_modules/supports-color": { + "version": "7.2.0", + "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-7.2.0.tgz", + "integrity": "sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==", + "dev": true, + "license": "MIT", + "dependencies": { + "has-flag": "^4.0.0" + }, + "engines": { + "node": ">=8" + } + }, + "node_modules/sync-child-process": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/sync-child-process/-/sync-child-process-1.0.2.tgz", + "integrity": "sha512-8lD+t2KrrScJ/7KXCSyfhT3/hRq78rC0wBFqNJXv3mZyn6hW2ypM05JmlSvtqRbeq6jqA94oHbxAr2vYsJ8vDA==", + "devOptional": true, + "license": "MIT", + "dependencies": { + "sync-message-port": "^1.0.0" + }, + "engines": { + "node": ">=16.0.0" + } + }, + "node_modules/sync-message-port": { + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/sync-message-port/-/sync-message-port-1.1.3.tgz", + "integrity": "sha512-GTt8rSKje5FilG+wEdfCkOcLL7LWqpMlr2c3LRuKt/YXxcJ52aGSbGBAdI4L3aaqfrBt6y711El53ItyH1NWzg==", + "devOptional": true, + "license": "MIT", + "engines": { + "node": ">=16.0.0" + } + }, + "node_modules/tailwindcss": { + "version": "4.1.1", + "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.1.tgz", + "integrity": "sha512-QNbdmeS979Efzim2g/bEvfuh+fTcIdp1y7gA+sb6OYSW74rt7Cr7M78AKdf6HqWT3d5AiTb7SwTT3sLQxr4/qw==", + "license": "MIT" + }, + "node_modules/tapable": { + "version": "2.2.1", + "resolved": "https://registry.npmjs.org/tapable/-/tapable-2.2.1.tgz", + "integrity": "sha512-GNzQvQTOIP6RyTfE2Qxb8ZVlNmw0n88vp1szwWRimP02mnTsx3Wtn5qRdqY9w2XduFNUgvOwhNnQsjwCp+kqaQ==", + "license": "MIT", + "engines": { + "node": ">=6" + } + }, + "node_modules/textlinestream": { + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/textlinestream/-/textlinestream-1.1.1.tgz", + "integrity": "sha512-iBHbi7BQxrFmwZUQJsT0SjNzlLLsXhvW/kg7EyOMVMBIrlnj/qYofwo1LVLZi+3GbUEo96Iu2eqToI2+lZoAEQ==", + "license": "MIT" + }, + "node_modules/to-regex-range": { + "version": "5.0.1", + "resolved": "https://registry.npmjs.org/to-regex-range/-/to-regex-range-5.0.1.tgz", + "integrity": "sha512-65P7iz6X5yEr1cwcgvQxbbIw7Uk3gOy5dIdtZ4rDveLqhrdJP+Li/Hx6tyK0NEb+2GCyneCMJiGqrADCSNk8sQ==", + "license": "MIT", + "dependencies": { + "is-number": "^7.0.0" + }, + "engines": { + "node": ">=8.0" + } + }, + "node_modules/trim-lines": { + "version": "3.0.1", + "resolved": "https://registry.npmjs.org/trim-lines/-/trim-lines-3.0.1.tgz", + "integrity": "sha512-kRj8B+YHZCc9kQYdWfJB2/oUl9rA99qbowYYBtr4ui4mZyAQ2JpvVBd/6U2YloATfqBhBTSMhTpgBHtU0Mf3Rg==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/trough": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/trough/-/trough-2.2.0.tgz", + "integrity": "sha512-tmMpK00BjZiUyVyvrBK7knerNgmgvcV/KLVyuma/SC+TQN167GrMRciANTz09+k3zW8L8t60jWO1GpfkZdjTaw==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/ts-api-utils": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/ts-api-utils/-/ts-api-utils-2.0.1.tgz", + "integrity": "sha512-dnlgjFSVetynI8nzgJ+qF62efpglpWRk8isUEWZGWlJYySCTD6aKvbUDu+zbPeDakk3bg5H4XpitHukgfL1m9w==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=18.12" + }, + "peerDependencies": { + "typescript": ">=4.8.4" + } + }, + "node_modules/tslib": { + "version": "2.8.1", + "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.8.1.tgz", + "integrity": "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==", + "devOptional": true, + "license": "0BSD" + }, + "node_modules/turbo-stream": { + "version": "2.4.0", + "resolved": "https://registry.npmjs.org/turbo-stream/-/turbo-stream-2.4.0.tgz", + "integrity": "sha512-FHncC10WpBd2eOmGwpmQsWLDoK4cqsA/UT/GqNoaKOQnT8uzhtCbg3EoUDMvqpOSAI0S26mr0rkjzbOO6S3v1g==", + "license": "ISC" + }, + "node_modules/type-check": { + "version": "0.4.0", + "resolved": "https://registry.npmjs.org/type-check/-/type-check-0.4.0.tgz", + "integrity": "sha512-XleUoc9uwGXqjWwXaUTZAmzMcFZ5858QA2vvx1Ur5xIcixXIP+8LnFDgRplU30us6teqdlskFfu+ae4K79Ooew==", + "dev": true, + "license": "MIT", + "dependencies": { + "prelude-ls": "^1.2.1" + }, + "engines": { + "node": ">= 0.8.0" + } + }, + "node_modules/typescript": { + "version": "5.6.3", + "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.6.3.tgz", + "integrity": "sha512-hjcS1mhfuyi4WW8IWtjP7brDrG2cuDZukyrYrSauoXGNgx0S7zceP07adYkJycEr56BOUTNPzbInooiN3fn1qw==", + "dev": true, + "license": "Apache-2.0", + "bin": { + "tsc": "bin/tsc", + "tsserver": "bin/tsserver" + }, + "engines": { + "node": ">=14.17" + } + }, + "node_modules/typescript-eslint": { + "version": "8.23.0", + "resolved": "https://registry.npmjs.org/typescript-eslint/-/typescript-eslint-8.23.0.tgz", + "integrity": "sha512-/LBRo3HrXr5LxmrdYSOCvoAMm7p2jNizNfbIpCgvG4HMsnoprRUOce/+8VJ9BDYWW68rqIENE/haVLWPeFZBVQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@typescript-eslint/eslint-plugin": "8.23.0", + "@typescript-eslint/parser": "8.23.0", + "@typescript-eslint/utils": "8.23.0" + }, + "engines": { + "node": "^18.18.0 || ^20.9.0 || >=21.1.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/typescript-eslint" + }, + "peerDependencies": { + "eslint": "^8.57.0 || ^9.0.0", + "typescript": ">=4.8.4 <5.8.0" + } + }, + "node_modules/undici-types": { + "version": "6.20.0", + "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.20.0.tgz", + "integrity": "sha512-Ny6QZ2Nju20vw1SRHe3d9jVu6gJ+4e3+MMpqu7pqE5HT6WsTSlce++GQmK5UXS8mzV8DSYHrQH+Xrf2jVcuKNg==", + "devOptional": true, + "license": "MIT" + }, + "node_modules/unified": { + "version": "11.0.5", + "resolved": "https://registry.npmjs.org/unified/-/unified-11.0.5.tgz", + "integrity": "sha512-xKvGhPWw3k84Qjh8bI3ZeJjqnyadK+GEFtazSfZv/rKeTkTjOJho6mFqh2SM96iIcZokxiOpg78GazTSg8+KHA==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0", + "bail": "^2.0.0", + "devlop": "^1.0.0", + "extend": "^3.0.0", + "is-plain-obj": "^4.0.0", + "trough": "^2.0.0", + "vfile": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/unist-util-find-after": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/unist-util-find-after/-/unist-util-find-after-5.0.0.tgz", + "integrity": "sha512-amQa0Ep2m6hE2g72AugUItjbuM8X8cGQnFoHk0pGfrFeT9GZhzN5SW8nRsiGKK7Aif4CrACPENkA6P/Lw6fHGQ==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0", + "unist-util-is": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/unist-util-is": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/unist-util-is/-/unist-util-is-6.0.0.tgz", + "integrity": "sha512-2qCTHimwdxLfz+YzdGfkqNlH0tLi9xjTnHddPmJwtIG9MGsdbutfTc4P+haPD7l7Cjxf/WZj+we5qfVPvvxfYw==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/unist-util-position": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/unist-util-position/-/unist-util-position-5.0.0.tgz", + "integrity": "sha512-fucsC7HjXvkB5R3kTCO7kUjRdrS0BJt3M/FPxmHMBOm8JQi2BsHAHFsy27E0EolP8rp0NzXsJ+jNPyDWvOJZPA==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/unist-util-remove-position": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/unist-util-remove-position/-/unist-util-remove-position-5.0.0.tgz", + "integrity": "sha512-Hp5Kh3wLxv0PHj9m2yZhhLt58KzPtEYKQQ4yxfYFEO7EvHwzyDYnduhHnY1mDxoqr7VUwVuHXk9RXKIiYS1N8Q==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0", + "unist-util-visit": "^5.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/unist-util-stringify-position": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/unist-util-stringify-position/-/unist-util-stringify-position-4.0.0.tgz", + "integrity": "sha512-0ASV06AAoKCDkS2+xw5RXJywruurpbC4JZSm7nr7MOt1ojAzvyyaO+UxZf18j8FCF6kmzCZKcAgN/yu2gm2XgQ==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/unist-util-visit": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/unist-util-visit/-/unist-util-visit-5.0.0.tgz", + "integrity": "sha512-MR04uvD+07cwl/yhVuVWAtw+3GOR/knlL55Nd/wAdblk27GCVt3lqpTivy/tkJcZoNPzTwS1Y+KMojlLDhoTzg==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0", + "unist-util-is": "^6.0.0", + "unist-util-visit-parents": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/unist-util-visit-parents": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/unist-util-visit-parents/-/unist-util-visit-parents-6.0.1.tgz", + "integrity": "sha512-L/PqWzfTP9lzzEa6CKs0k2nARxTdZduw3zyh8d2NVBnsyvHjSX4TWse388YrrQKbvI8w20fGjGlhgT96WwKykw==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0", + "unist-util-is": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/update-browserslist-db": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/update-browserslist-db/-/update-browserslist-db-1.1.2.tgz", + "integrity": "sha512-PPypAm5qvlD7XMZC3BujecnaOxwhrtoFR+Dqkk5Aa/6DssiH0ibKoketaj9w8LP7Bont1rYeoV5plxD7RTEPRg==", + "funding": [ + { + "type": "opencollective", + "url": "https://opencollective.com/browserslist" + }, + { + "type": "tidelift", + "url": "https://tidelift.com/funding/github/npm/browserslist" + }, + { + "type": "github", + "url": "https://github.com/sponsors/ai" + } + ], + "license": "MIT", + "dependencies": { + "escalade": "^3.2.0", + "picocolors": "^1.1.1" + }, + "bin": { + "update-browserslist-db": "cli.js" + }, + "peerDependencies": { + "browserslist": ">= 4.21.0" + } + }, + "node_modules/uri-js": { + "version": "4.4.1", + "resolved": "https://registry.npmjs.org/uri-js/-/uri-js-4.4.1.tgz", + "integrity": "sha512-7rKUyy33Q1yc98pQ1DAmLtwX109F7TIfWlW1Ydo8Wl1ii1SeHieeh0HHfPeL2fMXK6z0s8ecKs9frCuLJvndBg==", + "dev": true, + "license": "BSD-2-Clause", + "dependencies": { + "punycode": "^2.1.0" + } + }, + "node_modules/varint": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/varint/-/varint-6.0.0.tgz", + "integrity": "sha512-cXEIW6cfr15lFv563k4GuVuW/fiwjknytD37jIOLSdSWuOI6WnO/oKwmP2FQTU2l01LP8/M5TSAJpzUaGe3uWg==", + "devOptional": true, + "license": "MIT" + }, + "node_modules/vfile": { + "version": "6.0.3", + "resolved": "https://registry.npmjs.org/vfile/-/vfile-6.0.3.tgz", + "integrity": "sha512-KzIbH/9tXat2u30jf+smMwFCsno4wHVdNmzFyL+T/L3UGqqk6JKfVqOFOZEpZSHADH1k40ab6NUIXZq422ov3Q==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0", + "vfile-message": "^4.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/vfile-location": { + "version": "5.0.3", + "resolved": "https://registry.npmjs.org/vfile-location/-/vfile-location-5.0.3.tgz", + "integrity": "sha512-5yXvWDEgqeiYiBe1lbxYF7UMAIm/IcopxMHrMQDq3nvKcjPKIhZklUKL+AE7J7uApI4kwe2snsK+eI6UTj9EHg==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0", + "vfile": "^6.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/vfile-message": { + "version": "4.0.2", + "resolved": "https://registry.npmjs.org/vfile-message/-/vfile-message-4.0.2.tgz", + "integrity": "sha512-jRDZ1IMLttGj41KcZvlrYAaI3CfqpLpfpf+Mfig13viT6NKvRzWZ+lXz0Y5D60w6uJIBAOGq9mSHf0gktF0duw==", + "license": "MIT", + "dependencies": { + "@types/unist": "^3.0.0", + "unist-util-stringify-position": "^4.0.0" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/unified" + } + }, + "node_modules/vite": { + "version": "6.0.11", + "resolved": "https://registry.npmjs.org/vite/-/vite-6.0.11.tgz", + "integrity": "sha512-4VL9mQPKoHy4+FE0NnRE/kbY51TOfaknxAjt3fJbGJxhIpBZiqVzlZDEesWWsuREXHwNdAoOFZ9MkPEVXczHwg==", + "license": "MIT", + "dependencies": { + "esbuild": "^0.24.2", + "postcss": "^8.4.49", + "rollup": "^4.23.0" + }, + "bin": { + "vite": "bin/vite.js" + }, + "engines": { + "node": "^18.0.0 || ^20.0.0 || >=22.0.0" + }, + "funding": { + "url": "https://github.com/vitejs/vite?sponsor=1" + }, + "optionalDependencies": { + "fsevents": "~2.3.3" + }, + "peerDependencies": { + "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0", + "jiti": ">=1.21.0", + "less": "*", + "lightningcss": "^1.21.0", + "sass": "*", + "sass-embedded": "*", + "stylus": "*", + "sugarss": "*", + "terser": "^5.16.0", + "tsx": "^4.8.1", + "yaml": "^2.4.2" + }, + "peerDependenciesMeta": { + "@types/node": { + "optional": true + }, + "jiti": { + "optional": true + }, + "less": { + "optional": true + }, + "lightningcss": { + "optional": true + }, + "sass": { + "optional": true + }, + "sass-embedded": { + "optional": true + }, + "stylus": { + "optional": true + }, + "sugarss": { + "optional": true + }, + "terser": { + "optional": true + }, + "tsx": { + "optional": true + }, + "yaml": { + "optional": true + } + } + }, + "node_modules/vite-plugin-singlefile": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/vite-plugin-singlefile/-/vite-plugin-singlefile-2.1.0.tgz", + "integrity": "sha512-7tJo+UgZABlKpY/nubth/wxJ4+pUGREPnEwNOknxwl2MM0zTvF14KTU4Ln1lc140gjLLV5mjDrvuoquU7OZqCg==", + "license": "MIT", + "dependencies": { + "micromatch": "^4.0.8" + }, + "engines": { + "node": ">18.0.0" + }, + "peerDependencies": { + "rollup": "^4.28.1", + "vite": "^5.4.11 || ^6.0.0" + } + }, + "node_modules/web-namespaces": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/web-namespaces/-/web-namespaces-2.0.1.tgz", + "integrity": "sha512-bKr1DkiNa2krS7qxNtdrtHAmzuYGFQLiQ13TsorsdT6ULTkPLKuu5+GsFpDlg6JFjUTwX2DyhMPG2be8uPrqsQ==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + }, + "node_modules/which": { + "version": "2.0.2", + "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz", + "integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==", + "dev": true, + "license": "ISC", + "dependencies": { + "isexe": "^2.0.0" + }, + "bin": { + "node-which": "bin/node-which" + }, + "engines": { + "node": ">= 8" + } + }, + "node_modules/word-wrap": { + "version": "1.2.5", + "resolved": "https://registry.npmjs.org/word-wrap/-/word-wrap-1.2.5.tgz", + "integrity": "sha512-BN22B5eaMMI9UMtjrGd5g5eCYPpCPDUy0FJXbYsaT5zYxjFOckS53SQDE3pWkVoWpHXVb3BrYcEN4Twa55B5cA==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/yallist": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/yallist/-/yallist-3.1.1.tgz", + "integrity": "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==", + "dev": true, + "license": "ISC" + }, + "node_modules/yaml": { + "version": "2.7.0", + "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.7.0.tgz", + "integrity": "sha512-+hSoy/QHluxmC9kCIJyL/uyFmLmc+e5CFR5Wa+bpIhIj85LVb9ZH2nVnqrHoSvKogwODv0ClqZkmiSSaIH5LTA==", + "license": "ISC", + "optional": true, + "peer": true, + "bin": { + "yaml": "bin.mjs" + }, + "engines": { + "node": ">= 14" + } + }, + "node_modules/yocto-queue": { + "version": "0.1.0", + "resolved": "https://registry.npmjs.org/yocto-queue/-/yocto-queue-0.1.0.tgz", + "integrity": "sha512-rVksvsnNCdJ/ohGc6xgPwyN8eheCxsiLM8mxuE/t/mOVqJewPuO1miLpTHQiRgTKCLexL4MeAFVagts7HmNZ2Q==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/zwitch": { + "version": "2.0.4", + "resolved": "https://registry.npmjs.org/zwitch/-/zwitch-2.0.4.tgz", + "integrity": "sha512-bXE4cR/kVZhKZX/RjPEflHaKVhUVl85noU3v6b8apfQEc1x4A+zBxjZ4lN8LqGd6WZ3dl98pY4o717VFmoPp+A==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/wooorm" + } + } + } +} diff --git a/tools/server/webui/package.json b/tools/server/webui/package.json new file mode 100644 index 00000000..6ac06b1a --- /dev/null +++ b/tools/server/webui/package.json @@ -0,0 +1,62 @@ +{ + "name": "webui", + "private": true, + "version": "0.0.0", + "type": "module", + "scripts": { + "dev": "vite", + "build": "tsc -b && vite build", + "format": "eslint . && prettier --write .", + "lint": "eslint .", + "preview": "vite preview" + }, + "dependencies": { + "@heroicons/react": "^2.2.0", + "@sec-ant/readable-stream": "^0.6.0", + "@tailwindcss/postcss": "^4.1.1", + "@tailwindcss/vite": "^4.1.1", + "@vscode/markdown-it-katex": "^1.1.1", + "autoprefixer": "^10.4.20", + "daisyui": "^5.0.12", + "dexie": "^4.0.11", + "highlight.js": "^11.10.0", + "katex": "^0.16.15", + "postcss": "^8.4.49", + "react": "^18.3.1", + "react-dom": "^18.3.1", + "react-markdown": "^9.0.3", + "react-router": "^7.1.5", + "rehype-highlight": "^7.0.2", + "rehype-katex": "^7.0.1", + "remark-breaks": "^4.0.0", + "remark-gfm": "^4.0.0", + "remark-math": "^6.0.0", + "tailwindcss": "^4.1.1", + "textlinestream": "^1.1.1", + "vite-plugin-singlefile": "^2.0.3" + }, + "devDependencies": { + "@eslint/js": "^9.17.0", + "@types/markdown-it": "^14.1.2", + "@types/node": "^22.13.1", + "@types/react": "^18.3.18", + "@types/react-dom": "^18.3.5", + "@vitejs/plugin-react": "^4.3.4", + "eslint": "^9.17.0", + "eslint-plugin-react-hooks": "^5.0.0", + "eslint-plugin-react-refresh": "^0.4.16", + "globals": "^15.14.0", + "prettier": "^3.4.2", + "sass-embedded": "^1.83.4", + "typescript": "~5.6.2", + "typescript-eslint": "^8.18.2", + "vite": "^6.0.5" + }, + "prettier": { + "trailingComma": "es5", + "tabWidth": 2, + "semi": true, + "singleQuote": true, + "bracketSameLine": false + } +} diff --git a/tools/server/webui/postcss.config.js b/tools/server/webui/postcss.config.js new file mode 100644 index 00000000..fb05b569 --- /dev/null +++ b/tools/server/webui/postcss.config.js @@ -0,0 +1,5 @@ +export default { + plugins: { + "@tailwindcss/postcss": {}, + }, +} diff --git a/tools/server/webui/public/demo-conversation.json b/tools/server/webui/public/demo-conversation.json new file mode 100644 index 00000000..338b4aea --- /dev/null +++ b/tools/server/webui/public/demo-conversation.json @@ -0,0 +1,33 @@ +{ + "demo": true, + "id": "conv-1734086746930", + "lastModified": 1734087548943, + "messages": [ + { + "id": 1734086764521, + "role": "user", + "content": "this is a demo conversation, used in dev mode" + }, + { + "id": 1734087548327, + "role": "assistant", + "content": "This is the formula:\n\n$\\frac{e^{x_i}}{\\sum_{j=1}^{n}e^{x_j}}$\n\nGiven an input vector \$\\mathbf{x} = [x_1, x_2, \\ldots, x_n]\$\n\n\\[\ny_i = \\frac{e^{x_i}}{\\sum_{j=1}^n e^{x_j}}\n\\]\n\n$2x + y = z$\n\nCode block latex:\n```latex\n\\frac{e^{x_i}}{\\sum_{j=1}^{n}e^{x_j}}\n```\n\nTest dollar sign: $1234 $4567\n\nInvalid latex syntax: $E = mc^$ and $$E = mc^$$", + "timings": { + "prompt_n": 1, + "prompt_ms": 28.923, + "predicted_n": 25, + "predicted_ms": 573.016 + } + }, + { + "id": 1734087548328, + "role": "user", + "content": "this is a demo conversation, used in dev mode" + }, + { + "id": 1734087548329, + "role": "assistant", + "content": "Code block:\n```js\nconsole.log('hello world')\n```\n```sh\nls -la /dev\n```" + } + ] +} diff --git a/tools/server/webui/src/App.tsx b/tools/server/webui/src/App.tsx new file mode 100644 index 00000000..cc4659e1 --- /dev/null +++ b/tools/server/webui/src/App.tsx @@ -0,0 +1,47 @@ +import { HashRouter, Outlet, Route, Routes } from 'react-router'; +import Header from './components/Header'; +import Sidebar from './components/Sidebar'; +import { AppContextProvider, useAppContext } from './utils/app.context'; +import ChatScreen from './components/ChatScreen'; +import SettingDialog from './components/SettingDialog'; + +function App() { + return ( + +
+ + + }> + } /> + } /> + + + +
+ + ); +} + +function AppLayout() { + const { showSettings, setShowSettings } = useAppContext(); + return ( + <> + +
+
+ +
+ { + setShowSettings(false)} + /> + } + + ); +} + +export default App; diff --git a/tools/server/webui/src/Config.ts b/tools/server/webui/src/Config.ts new file mode 100644 index 00000000..dd1cc0e1 --- /dev/null +++ b/tools/server/webui/src/Config.ts @@ -0,0 +1,92 @@ +import daisyuiThemes from 'daisyui/theme/object'; +import { isNumeric } from './utils/misc'; + +export const isDev = import.meta.env.MODE === 'development'; + +// constants +export const BASE_URL = new URL('.', document.baseURI).href + .toString() + .replace(/\/$/, ''); + +export const CONFIG_DEFAULT = { + // Note: in order not to introduce breaking changes, please keep the same data type (number, string, etc) if you want to change the default value. Do not use null or undefined for default value. + // Do not use nested objects, keep it single level. Prefix the key if you need to group them. + apiKey: '', + systemMessage: 'You are a helpful assistant.', + showTokensPerSecond: false, + showThoughtInProgress: false, + excludeThoughtOnReq: true, + // make sure these default values are in sync with `common.h` + samplers: 'edkypmxt', + temperature: 0.8, + dynatemp_range: 0.0, + dynatemp_exponent: 1.0, + top_k: 40, + top_p: 0.95, + min_p: 0.05, + xtc_probability: 0.0, + xtc_threshold: 0.1, + typical_p: 1.0, + repeat_last_n: 64, + repeat_penalty: 1.0, + presence_penalty: 0.0, + frequency_penalty: 0.0, + dry_multiplier: 0.0, + dry_base: 1.75, + dry_allowed_length: 2, + dry_penalty_last_n: -1, + max_tokens: -1, + custom: '', // custom json-stringified object + // experimental features + pyIntepreterEnabled: false, +}; +export const CONFIG_INFO: Record = { + apiKey: 'Set the API Key if you are using --api-key option for the server.', + systemMessage: 'The starting message that defines how model should behave.', + samplers: + 'The order at which samplers are applied, in simplified way. Default is "dkypmxt": dry->top_k->typ_p->top_p->min_p->xtc->temperature', + temperature: + 'Controls the randomness of the generated text by affecting the probability distribution of the output tokens. Higher = more random, lower = more focused.', + dynatemp_range: + 'Addon for the temperature sampler. The added value to the range of dynamic temperature, which adjusts probabilities by entropy of tokens.', + dynatemp_exponent: + 'Addon for the temperature sampler. Smoothes out the probability redistribution based on the most probable token.', + top_k: 'Keeps only k top tokens.', + top_p: + 'Limits tokens to those that together have a cumulative probability of at least p', + min_p: + 'Limits tokens based on the minimum probability for a token to be considered, relative to the probability of the most likely token.', + xtc_probability: + 'XTC sampler cuts out top tokens; this parameter controls the chance of cutting tokens at all. 0 disables XTC.', + xtc_threshold: + 'XTC sampler cuts out top tokens; this parameter controls the token probability that is required to cut that token.', + typical_p: + 'Sorts and limits tokens based on the difference between log-probability and entropy.', + repeat_last_n: 'Last n tokens to consider for penalizing repetition', + repeat_penalty: + 'Controls the repetition of token sequences in the generated text', + presence_penalty: + 'Limits tokens based on whether they appear in the output or not.', + frequency_penalty: + 'Limits tokens based on how often they appear in the output.', + dry_multiplier: + 'DRY sampling reduces repetition in generated text even across long contexts. This parameter sets the DRY sampling multiplier.', + dry_base: + 'DRY sampling reduces repetition in generated text even across long contexts. This parameter sets the DRY sampling base value.', + dry_allowed_length: + 'DRY sampling reduces repetition in generated text even across long contexts. This parameter sets the allowed length for DRY sampling.', + dry_penalty_last_n: + 'DRY sampling reduces repetition in generated text even across long contexts. This parameter sets DRY penalty for the last n tokens.', + max_tokens: 'The maximum number of token per output.', + custom: '', // custom json-stringified object +}; +// config keys having numeric value (i.e. temperature, top_k, top_p, etc) +export const CONFIG_NUMERIC_KEYS = Object.entries(CONFIG_DEFAULT) + .filter((e) => isNumeric(e[1])) + .map((e) => e[0]); +// list of themes supported by daisyui +export const THEMES = ['light', 'dark'] + // make sure light & dark are always at the beginning + .concat( + Object.keys(daisyuiThemes).filter((t) => t !== 'light' && t !== 'dark') + ); diff --git a/tools/server/webui/src/components/CanvasPyInterpreter.tsx b/tools/server/webui/src/components/CanvasPyInterpreter.tsx new file mode 100644 index 00000000..c2707fe2 --- /dev/null +++ b/tools/server/webui/src/components/CanvasPyInterpreter.tsx @@ -0,0 +1,195 @@ +import { useEffect, useState } from 'react'; +import { useAppContext } from '../utils/app.context'; +import { OpenInNewTab, XCloseButton } from '../utils/common'; +import { CanvasType } from '../utils/types'; +import { PlayIcon, StopIcon } from '@heroicons/react/24/outline'; +import StorageUtils from '../utils/storage'; + +const canInterrupt = typeof SharedArrayBuffer === 'function'; + +// adapted from https://pyodide.org/en/stable/usage/webworker.html +const WORKER_CODE = ` +importScripts("https://cdn.jsdelivr.net/pyodide/v0.27.2/full/pyodide.js"); + +let stdOutAndErr = []; + +let pyodideReadyPromise = loadPyodide({ + stdout: (data) => stdOutAndErr.push(data), + stderr: (data) => stdOutAndErr.push(data), +}); + +let alreadySetBuff = false; + +self.onmessage = async (event) => { + stdOutAndErr = []; + + // make sure loading is done + const pyodide = await pyodideReadyPromise; + const { id, python, context, interruptBuffer } = event.data; + + if (interruptBuffer && !alreadySetBuff) { + pyodide.setInterruptBuffer(interruptBuffer); + alreadySetBuff = true; + } + + // Now load any packages we need, run the code, and send the result back. + await pyodide.loadPackagesFromImports(python); + + // make a Python dictionary with the data from content + const dict = pyodide.globals.get("dict"); + const globals = dict(Object.entries(context)); + try { + self.postMessage({ id, running: true }); + // Execute the python code in this context + const result = pyodide.runPython(python, { globals }); + self.postMessage({ result, id, stdOutAndErr }); + } catch (error) { + self.postMessage({ error: error.message, id }); + } + interruptBuffer[0] = 0; +}; +`; + +let worker: Worker; +const interruptBuffer = canInterrupt + ? new Uint8Array(new SharedArrayBuffer(1)) + : null; + +const startWorker = () => { + if (!worker) { + worker = new Worker( + URL.createObjectURL(new Blob([WORKER_CODE], { type: 'text/javascript' })) + ); + } +}; + +if (StorageUtils.getConfig().pyIntepreterEnabled) { + startWorker(); +} + +const runCodeInWorker = ( + pyCode: string, + callbackRunning: () => void +): { + donePromise: Promise; + interrupt: () => void; +} => { + startWorker(); + const id = Math.random() * 1e8; + const context = {}; + if (interruptBuffer) { + interruptBuffer[0] = 0; + } + + const donePromise = new Promise((resolve) => { + worker.onmessage = (event) => { + const { error, stdOutAndErr, running } = event.data; + if (id !== event.data.id) return; + if (running) { + callbackRunning(); + return; + } else if (error) { + resolve(error.toString()); + } else { + resolve(stdOutAndErr.join('\n')); + } + }; + worker.postMessage({ id, python: pyCode, context, interruptBuffer }); + }); + + const interrupt = () => { + console.log('Interrupting...'); + console.trace(); + if (interruptBuffer) { + interruptBuffer[0] = 2; + } + }; + + return { donePromise, interrupt }; +}; + +export default function CanvasPyInterpreter() { + const { canvasData, setCanvasData } = useAppContext(); + + const [code, setCode] = useState(canvasData?.content ?? ''); // copy to avoid direct mutation + const [running, setRunning] = useState(false); + const [output, setOutput] = useState(''); + const [interruptFn, setInterruptFn] = useState<() => void>(); + const [showStopBtn, setShowStopBtn] = useState(false); + + const runCode = async (pycode: string) => { + interruptFn?.(); + setRunning(true); + setOutput('Loading Pyodide...'); + const { donePromise, interrupt } = runCodeInWorker(pycode, () => { + setOutput('Running...'); + setShowStopBtn(canInterrupt); + }); + setInterruptFn(() => interrupt); + const out = await donePromise; + setOutput(out); + setRunning(false); + setShowStopBtn(false); + }; + + // run code on mount + useEffect(() => { + setCode(canvasData?.content ?? ''); + runCode(canvasData?.content ?? ''); + // eslint-disable-next-line react-hooks/exhaustive-deps + }, [canvasData?.content]); + + if (canvasData?.type !== CanvasType.PY_INTERPRETER) { + return null; + } + + return ( +
+
+
+ Python Interpreter + setCanvasData(null)} + /> +
+
+ setCode(e.target.value)} + > +
+
+ + {showStopBtn && ( + + )} + + + Report a bug + + +
+ +
+
+
+
+ ); +} diff --git a/tools/server/webui/src/components/ChatMessage.tsx b/tools/server/webui/src/components/ChatMessage.tsx new file mode 100644 index 00000000..40ea7471 --- /dev/null +++ b/tools/server/webui/src/components/ChatMessage.tsx @@ -0,0 +1,296 @@ +import { useMemo, useState } from 'react'; +import { useAppContext } from '../utils/app.context'; +import { Message, PendingMessage } from '../utils/types'; +import { classNames } from '../utils/misc'; +import MarkdownDisplay, { CopyButton } from './MarkdownDisplay'; +import { ChevronLeftIcon, ChevronRightIcon } from '@heroicons/react/24/outline'; + +interface SplitMessage { + content: PendingMessage['content']; + thought?: string; + isThinking?: boolean; +} + +export default function ChatMessage({ + msg, + siblingLeafNodeIds, + siblingCurrIdx, + id, + onRegenerateMessage, + onEditMessage, + onChangeSibling, + isPending, +}: { + msg: Message | PendingMessage; + siblingLeafNodeIds: Message['id'][]; + siblingCurrIdx: number; + id?: string; + onRegenerateMessage(msg: Message): void; + onEditMessage(msg: Message, content: string): void; + onChangeSibling(sibling: Message['id']): void; + isPending?: boolean; +}) { + const { viewingChat, config } = useAppContext(); + const [editingContent, setEditingContent] = useState(null); + const timings = useMemo( + () => + msg.timings + ? { + ...msg.timings, + prompt_per_second: + (msg.timings.prompt_n / msg.timings.prompt_ms) * 1000, + predicted_per_second: + (msg.timings.predicted_n / msg.timings.predicted_ms) * 1000, + } + : null, + [msg.timings] + ); + const nextSibling = siblingLeafNodeIds[siblingCurrIdx + 1]; + const prevSibling = siblingLeafNodeIds[siblingCurrIdx - 1]; + + // for reasoning model, we split the message into content and thought + // TODO: implement this as remark/rehype plugin in the future + const { content, thought, isThinking }: SplitMessage = useMemo(() => { + if (msg.content === null || msg.role !== 'assistant') { + return { content: msg.content }; + } + let actualContent = ''; + let thought = ''; + let isThinking = false; + let thinkSplit = msg.content.split('', 2); + actualContent += thinkSplit[0]; + while (thinkSplit[1] !== undefined) { + // tag found + thinkSplit = thinkSplit[1].split('', 2); + thought += thinkSplit[0]; + isThinking = true; + if (thinkSplit[1] !== undefined) { + // closing tag found + isThinking = false; + thinkSplit = thinkSplit[1].split('', 2); + actualContent += thinkSplit[0]; + } + } + return { content: actualContent, thought, isThinking }; + }, [msg]); + + if (!viewingChat) return null; + + return ( +
+
+
+ {/* textarea for editing message */} + {editingContent !== null && ( + <> + setEditingContent(e.target.value)} + > +
+ + + + )} + {/* not editing content, render message */} + {editingContent === null && ( + <> + {content === null ? ( + <> + {/* show loading dots for pending message */} + + + ) : ( + <> + {/* render message as markdown */} +
+ {thought && ( +
+
+ {isPending && isThinking ? ( + + + Thinking + + ) : ( + Thought Process + )} +
+
+ +
+
+ )} + + {msg.extra && msg.extra.length > 0 && ( +
+
+ Extra content +
+
+ {msg.extra.map( + (extra, i) => + extra.type === 'textFile' ? ( +
+ {extra.name} +
{extra.content}
+
+ ) : extra.type === 'context' ? ( +
+
{extra.content}
+
+ ) : null // TODO: support other extra types + )} +
+
+ )} + + +
+ + )} + {/* render timings if enabled */} + {timings && config.showTokensPerSecond && ( +
+
+ Speed: {timings.predicted_per_second.toFixed(1)} t/s +
+
+ Prompt +
- Tokens: {timings.prompt_n} +
- Time: {timings.prompt_ms} ms +
- Speed: {timings.prompt_per_second.toFixed(1)} t/s +
+ Generation +
- Tokens: {timings.predicted_n} +
- Time: {timings.predicted_ms} ms +
- Speed: {timings.predicted_per_second.toFixed(1)} t/s +
+
+
+ )} + + )} +
+
+ + {/* actions for each message */} + {msg.content !== null && ( +
+ {siblingLeafNodeIds && siblingLeafNodeIds.length > 1 && ( +
+ + + {siblingCurrIdx + 1} / {siblingLeafNodeIds.length} + + +
+ )} + {/* user message */} + {msg.role === 'user' && ( + + )} + {/* assistant message */} + {msg.role === 'assistant' && ( + <> + {!isPending && ( + + )} + + )} + +
+ )} +
+ ); +} diff --git a/tools/server/webui/src/components/ChatScreen.tsx b/tools/server/webui/src/components/ChatScreen.tsx new file mode 100644 index 00000000..29ab5ea6 --- /dev/null +++ b/tools/server/webui/src/components/ChatScreen.tsx @@ -0,0 +1,296 @@ +import { useEffect, useMemo, useState } from 'react'; +import { CallbackGeneratedChunk, useAppContext } from '../utils/app.context'; +import ChatMessage from './ChatMessage'; +import { CanvasType, Message, PendingMessage } from '../utils/types'; +import { classNames, cleanCurrentUrl, throttle } from '../utils/misc'; +import CanvasPyInterpreter from './CanvasPyInterpreter'; +import StorageUtils from '../utils/storage'; +import { useVSCodeContext } from '../utils/llama-vscode'; +import { useChatTextarea, ChatTextareaApi } from './useChatTextarea.ts'; + +/** + * A message display is a message node with additional information for rendering. + * For example, siblings of the message node are stored as their last node (aka leaf node). + */ +export interface MessageDisplay { + msg: Message | PendingMessage; + siblingLeafNodeIds: Message['id'][]; + siblingCurrIdx: number; + isPending?: boolean; +} + +/** + * If the current URL contains "?m=...", prefill the message input with the value. + * If the current URL contains "?q=...", prefill and SEND the message. + */ +const prefilledMsg = { + content() { + const url = new URL(window.location.href); + return url.searchParams.get('m') ?? url.searchParams.get('q') ?? ''; + }, + shouldSend() { + const url = new URL(window.location.href); + return url.searchParams.has('q'); + }, + clear() { + cleanCurrentUrl(['m', 'q']); + }, +}; + +function getListMessageDisplay( + msgs: Readonly, + leafNodeId: Message['id'] +): MessageDisplay[] { + const currNodes = StorageUtils.filterByLeafNodeId(msgs, leafNodeId, true); + const res: MessageDisplay[] = []; + const nodeMap = new Map(); + for (const msg of msgs) { + nodeMap.set(msg.id, msg); + } + // find leaf node from a message node + const findLeafNode = (msgId: Message['id']): Message['id'] => { + let currNode: Message | undefined = nodeMap.get(msgId); + while (currNode) { + if (currNode.children.length === 0) break; + currNode = nodeMap.get(currNode.children.at(-1) ?? -1); + } + return currNode?.id ?? -1; + }; + // traverse the current nodes + for (const msg of currNodes) { + const parentNode = nodeMap.get(msg.parent ?? -1); + if (!parentNode) continue; + const siblings = parentNode.children; + if (msg.type !== 'root') { + res.push({ + msg, + siblingLeafNodeIds: siblings.map(findLeafNode), + siblingCurrIdx: siblings.indexOf(msg.id), + }); + } + } + return res; +} + +const scrollToBottom = throttle( + (requiresNearBottom: boolean, delay: number = 80) => { + const mainScrollElem = document.getElementById('main-scroll'); + if (!mainScrollElem) return; + const spaceToBottom = + mainScrollElem.scrollHeight - + mainScrollElem.scrollTop - + mainScrollElem.clientHeight; + if (!requiresNearBottom || spaceToBottom < 50) { + setTimeout( + () => mainScrollElem.scrollTo({ top: mainScrollElem.scrollHeight }), + delay + ); + } + }, + 80 +); + +export default function ChatScreen() { + const { + viewingChat, + sendMessage, + isGenerating, + stopGenerating, + pendingMessages, + canvasData, + replaceMessageAndGenerate, + } = useAppContext(); + + const textarea: ChatTextareaApi = useChatTextarea(prefilledMsg.content()); + + const { extraContext, clearExtraContext } = useVSCodeContext(textarea); + // TODO: improve this when we have "upload file" feature + const currExtra: Message['extra'] = extraContext ? [extraContext] : undefined; + + // keep track of leaf node for rendering + const [currNodeId, setCurrNodeId] = useState(-1); + const messages: MessageDisplay[] = useMemo(() => { + if (!viewingChat) return []; + else return getListMessageDisplay(viewingChat.messages, currNodeId); + }, [currNodeId, viewingChat]); + + const currConvId = viewingChat?.conv.id ?? null; + const pendingMsg: PendingMessage | undefined = + pendingMessages[currConvId ?? '']; + + useEffect(() => { + // reset to latest node when conversation changes + setCurrNodeId(-1); + // scroll to bottom when conversation changes + scrollToBottom(false, 1); + }, [currConvId]); + + const onChunk: CallbackGeneratedChunk = (currLeafNodeId?: Message['id']) => { + if (currLeafNodeId) { + setCurrNodeId(currLeafNodeId); + } + scrollToBottom(true); + }; + + const sendNewMessage = async () => { + const lastInpMsg = textarea.value(); + if (lastInpMsg.trim().length === 0 || isGenerating(currConvId ?? '')) + return; + textarea.setValue(''); + scrollToBottom(false); + setCurrNodeId(-1); + // get the last message node + const lastMsgNodeId = messages.at(-1)?.msg.id ?? null; + if ( + !(await sendMessage( + currConvId, + lastMsgNodeId, + lastInpMsg, + currExtra, + onChunk + )) + ) { + // restore the input message if failed + textarea.setValue(lastInpMsg); + } + // OK + clearExtraContext(); + }; + + const handleEditMessage = async (msg: Message, content: string) => { + if (!viewingChat) return; + setCurrNodeId(msg.id); + scrollToBottom(false); + await replaceMessageAndGenerate( + viewingChat.conv.id, + msg.parent, + content, + msg.extra, + onChunk + ); + setCurrNodeId(-1); + scrollToBottom(false); + }; + + const handleRegenerateMessage = async (msg: Message) => { + if (!viewingChat) return; + setCurrNodeId(msg.parent); + scrollToBottom(false); + await replaceMessageAndGenerate( + viewingChat.conv.id, + msg.parent, + null, + msg.extra, + onChunk + ); + setCurrNodeId(-1); + scrollToBottom(false); + }; + + const hasCanvas = !!canvasData; + + useEffect(() => { + if (prefilledMsg.shouldSend()) { + // send the prefilled message if needed + sendNewMessage(); + } else { + // otherwise, focus on the input + textarea.focus(); + } + prefilledMsg.clear(); + // no need to keep track of sendNewMessage + // eslint-disable-next-line react-hooks/exhaustive-deps + }, [textarea.ref]); + + // due to some timing issues of StorageUtils.appendMsg(), we need to make sure the pendingMsg is not duplicated upon rendering (i.e. appears once in the saved conversation and once in the pendingMsg) + const pendingMsgDisplay: MessageDisplay[] = + pendingMsg && messages.at(-1)?.msg.id !== pendingMsg.id + ? [ + { + msg: pendingMsg, + siblingLeafNodeIds: [], + siblingCurrIdx: 0, + isPending: true, + }, + ] + : []; + + return ( +
+
+ {/* chat messages */} +
+
+ {/* placeholder to shift the message to the bottom */} + {viewingChat ? '' : 'Send a message to start'} +
+ {[...messages, ...pendingMsgDisplay].map((msg) => ( + + ))} +
+ + {/* chat input */} +
+ { + if (e.nativeEvent.isComposing || e.keyCode === 229) return; + if (e.key === 'Enter' && !e.shiftKey) { + e.preventDefault(); + sendNewMessage(); + } + }} + id="msg-input" + dir="auto" + // Set a base height of 2 rows for mobile views + // On lg+ screens, the hook will calculate and set the initial height anyway + rows={2} + > + + {isGenerating(currConvId ?? '') ? ( + + ) : ( + + )} +
+
+
+ {canvasData?.type === CanvasType.PY_INTERPRETER && ( + + )} +
+
+ ); +} diff --git a/tools/server/webui/src/components/Header.tsx b/tools/server/webui/src/components/Header.tsx new file mode 100644 index 00000000..4c6b291e --- /dev/null +++ b/tools/server/webui/src/components/Header.tsx @@ -0,0 +1,178 @@ +import { useEffect, useState } from 'react'; +import StorageUtils from '../utils/storage'; +import { useAppContext } from '../utils/app.context'; +import { classNames } from '../utils/misc'; +import daisyuiThemes from 'daisyui/theme/object'; +import { THEMES } from '../Config'; +import { useNavigate } from 'react-router'; + +export default function Header() { + const navigate = useNavigate(); + const [selectedTheme, setSelectedTheme] = useState(StorageUtils.getTheme()); + const { setShowSettings } = useAppContext(); + + const setTheme = (theme: string) => { + StorageUtils.setTheme(theme); + setSelectedTheme(theme); + }; + + useEffect(() => { + document.body.setAttribute('data-theme', selectedTheme); + document.body.setAttribute( + 'data-color-scheme', + daisyuiThemes[selectedTheme]?.['color-scheme'] ?? 'auto' + ); + }, [selectedTheme]); + + const { isGenerating, viewingChat } = useAppContext(); + const isCurrConvGenerating = isGenerating(viewingChat?.conv.id ?? ''); + + const removeConversation = () => { + if (isCurrConvGenerating || !viewingChat) return; + const convId = viewingChat?.conv.id; + if (window.confirm('Are you sure to delete this conversation?')) { + StorageUtils.remove(convId); + navigate('/'); + } + }; + + const downloadConversation = () => { + if (isCurrConvGenerating || !viewingChat) return; + const convId = viewingChat?.conv.id; + const conversationJson = JSON.stringify(viewingChat, null, 2); + const blob = new Blob([conversationJson], { type: 'application/json' }); + const url = URL.createObjectURL(blob); + const a = document.createElement('a'); + a.href = url; + a.download = `conversation_${convId}.json`; + document.body.appendChild(a); + a.click(); + document.body.removeChild(a); + URL.revokeObjectURL(url); + }; + + return ( +
+ {/* open sidebar button */} + + + + +
llama.cpp
+ + {/* action buttons (top right) */} +
+ {viewingChat && ( +
+ {/* "..." button */} + + {/* dropdown menu */} +
+
+ Download +
+
+ Delete +
+
+
+ )} + +
+ +
+ + {/* theme controller is copied from https://daisyui.com/components/theme-controller/ */} +
+
+
+ +
+
+
+ +
+ {THEMES.map((theme) => ( +
+ e.target.checked && setTheme(theme)} + /> +
+ ))} +
+
+
+
+
+ ); +} diff --git a/tools/server/webui/src/components/MarkdownDisplay.tsx b/tools/server/webui/src/components/MarkdownDisplay.tsx new file mode 100644 index 00000000..5b7a7259 --- /dev/null +++ b/tools/server/webui/src/components/MarkdownDisplay.tsx @@ -0,0 +1,310 @@ +import React, { useMemo, useState } from 'react'; +import Markdown, { ExtraProps } from 'react-markdown'; +import remarkGfm from 'remark-gfm'; +import rehypeHightlight from 'rehype-highlight'; +import rehypeKatex from 'rehype-katex'; +import remarkMath from 'remark-math'; +import remarkBreaks from 'remark-breaks'; +import 'katex/dist/katex.min.css'; +import { classNames, copyStr } from '../utils/misc'; +import { ElementContent, Root } from 'hast'; +import { visit } from 'unist-util-visit'; +import { useAppContext } from '../utils/app.context'; +import { CanvasType } from '../utils/types'; + +export default function MarkdownDisplay({ + content, + isGenerating, +}: { + content: string; + isGenerating?: boolean; +}) { + const preprocessedContent = useMemo( + () => preprocessLaTeX(content), + [content] + ); + return ( + ( + + ), + // note: do not use "pre", "p" or other basic html elements here, it will cause the node to re-render when the message is being generated (this should be a bug with react-markdown, not sure how to fix it) + }} + > + {preprocessedContent} + + ); +} + +const CodeBlockButtons: React.ElementType< + React.ClassAttributes & + React.HTMLAttributes & + ExtraProps & { origContent: string; isGenerating?: boolean } +> = ({ node, origContent, isGenerating }) => { + const { config } = useAppContext(); + const startOffset = node?.position?.start.offset ?? 0; + const endOffset = node?.position?.end.offset ?? 0; + + const copiedContent = useMemo( + () => + origContent + .substring(startOffset, endOffset) + .replace(/^```[^\n]+\n/g, '') + .replace(/```$/g, ''), + [origContent, startOffset, endOffset] + ); + + const codeLanguage = useMemo( + () => + origContent + .substring(startOffset, startOffset + 10) + .match(/^```([^\n]+)\n/)?.[1] ?? '', + [origContent, startOffset] + ); + + const canRunCode = + !isGenerating && + config.pyIntepreterEnabled && + codeLanguage.startsWith('py'); + + return ( +
+ + {canRunCode && ( + + )} +
+ ); +}; + +export const CopyButton = ({ + content, + className, +}: { + content: string; + className?: string; +}) => { + const [copied, setCopied] = useState(false); + return ( + + ); +}; + +export const RunPyCodeButton = ({ + content, + className, +}: { + content: string; + className?: string; +}) => { + const { setCanvasData } = useAppContext(); + return ( + <> + + + ); +}; + +/** + * This injects the "button" element before each "pre" element. + * The actual button will be replaced with a react component in the MarkdownDisplay. + * We don't replace "pre" node directly because it will cause the node to re-render, which causes this bug: https://github.com/ggerganov/llama.cpp/issues/9608 + */ +function rehypeCustomCopyButton() { + return function (tree: Root) { + visit(tree, 'element', function (node) { + if (node.tagName === 'pre' && !node.properties.visited) { + const preNode = { ...node }; + // replace current node + preNode.properties.visited = 'true'; + node.tagName = 'div'; + node.properties = {}; + // add node for button + const btnNode: ElementContent = { + type: 'element', + tagName: 'button', + properties: {}, + children: [], + position: node.position, + }; + node.children = [btnNode, preNode]; + } + }); + }; +} + +/** + * The part below is copied and adapted from: + * https://github.com/danny-avila/LibreChat/blob/main/client/src/utils/latex.ts + * (MIT License) + */ + +// Regex to check if the processed content contains any potential LaTeX patterns +const containsLatexRegex = + /\\$.*?\\$|\\\[.*?\\\]|\$.*?\$|\\begin\{equation\}.*?\\end\{equation\}/; + +// Regex for inline and block LaTeX expressions +const inlineLatex = new RegExp(/\\$(.+?)\\$/, 'g'); +const blockLatex = new RegExp(/\\\[(.*?[^\\])\\\]/, 'gs'); + +// Function to restore code blocks +const restoreCodeBlocks = (content: string, codeBlocks: string[]) => { + return content.replace( + /<>/g, + (_, index) => codeBlocks[index] + ); +}; + +// Regex to identify code blocks and inline code +const codeBlockRegex = /(```[\s\S]*?```|`.*?`)/g; + +export const processLaTeX = (_content: string) => { + let content = _content; + // Temporarily replace code blocks and inline code with placeholders + const codeBlocks: string[] = []; + let index = 0; + content = content.replace(codeBlockRegex, (match) => { + codeBlocks[index] = match; + return `<>`; + }); + + // Escape dollar signs followed by a digit or space and digit + let processedContent = content.replace(/(\$)(?=\s?\d)/g, '\\$'); + + // If no LaTeX patterns are found, restore code blocks and return the processed content + if (!containsLatexRegex.test(processedContent)) { + return restoreCodeBlocks(processedContent, codeBlocks); + } + + // Convert LaTeX expressions to a markdown compatible format + processedContent = processedContent + .replace(inlineLatex, (_: string, equation: string) => `$${equation}$`) // Convert inline LaTeX + .replace(blockLatex, (_: string, equation: string) => `$$${equation}$$`); // Convert block LaTeX + + // Restore code blocks + return restoreCodeBlocks(processedContent, codeBlocks); +}; + +/** + * Preprocesses LaTeX content by replacing delimiters and escaping certain characters. + * + * @param content The input string containing LaTeX expressions. + * @returns The processed string with replaced delimiters and escaped characters. + */ +export function preprocessLaTeX(content: string): string { + // Step 1: Protect code blocks + const codeBlocks: string[] = []; + content = content.replace(/(```[\s\S]*?```|`[^`\n]+`)/g, (_, code) => { + codeBlocks.push(code); + return `<>`; + }); + + // Step 2: Protect existing LaTeX expressions + const latexExpressions: string[] = []; + + // Protect block math ($$...$$), \[...\], and $...$ as before. + content = content.replace( + /(\$\$[\s\S]*?\$\$|\\\[[\s\S]*?\\\]|\\$.*?\\$)/g, + (match) => { + latexExpressions.push(match); + return `<>`; + } + ); + + // Protect inline math ($...$) only if it does NOT match a currency pattern. + // We assume a currency pattern is one where the inner content is purely numeric (with optional decimals). + content = content.replace(/\$([^$]+)\$/g, (match, inner) => { + if (/^\s*\d+(?:\.\d+)?\s*$/.test(inner)) { + // This looks like a currency value (e.g. "$123" or "$12.34"), + // so don't protect it. + return match; + } else { + // Otherwise, treat it as a LaTeX expression. + latexExpressions.push(match); + return `<>`; + } + }); + + // Step 3: Escape dollar signs that are likely currency indicators. + // (Now that inline math is protected, this will only escape dollars not already protected) + content = content.replace(/\$(?=\d)/g, '\\$'); + + // Step 4: Restore LaTeX expressions + content = content.replace( + /<>/g, + (_, index) => latexExpressions[parseInt(index)] + ); + + // Step 5: Restore code blocks + content = content.replace( + /<>/g, + (_, index) => codeBlocks[parseInt(index)] + ); + + // Step 6: Apply additional escaping functions + content = escapeBrackets(content); + content = escapeMhchem(content); + + return content; +} + +export function escapeBrackets(text: string): string { + const pattern = + /(```[\S\s]*?```|`.*?`)|\\\[([\S\s]*?[^\\])\\]|\\$(.*?)\\$/g; + return text.replace( + pattern, + ( + match: string, + codeBlock: string | undefined, + squareBracket: string | undefined, + roundBracket: string | undefined + ): string => { + if (codeBlock != null) { + return codeBlock; + } else if (squareBracket != null) { + return `$$${squareBracket}$$`; + } else if (roundBracket != null) { + return `$${roundBracket}$`; + } + return match; + } + ); +} + +export function escapeMhchem(text: string) { + return text.replaceAll('$\\ce{', '$\\\\ce{').replaceAll('$\\pu{', '$\\\\pu{'); +} diff --git a/tools/server/webui/src/components/SettingDialog.tsx b/tools/server/webui/src/components/SettingDialog.tsx new file mode 100644 index 00000000..b0044d25 --- /dev/null +++ b/tools/server/webui/src/components/SettingDialog.tsx @@ -0,0 +1,536 @@ +import { useState } from 'react'; +import { useAppContext } from '../utils/app.context'; +import { CONFIG_DEFAULT, CONFIG_INFO } from '../Config'; +import { isDev } from '../Config'; +import StorageUtils from '../utils/storage'; +import { classNames, isBoolean, isNumeric, isString } from '../utils/misc'; +import { + BeakerIcon, + ChatBubbleOvalLeftEllipsisIcon, + Cog6ToothIcon, + FunnelIcon, + HandRaisedIcon, + SquaresPlusIcon, +} from '@heroicons/react/24/outline'; +import { OpenInNewTab } from '../utils/common'; + +type SettKey = keyof typeof CONFIG_DEFAULT; + +const BASIC_KEYS: SettKey[] = [ + 'temperature', + 'top_k', + 'top_p', + 'min_p', + 'max_tokens', +]; +const SAMPLER_KEYS: SettKey[] = [ + 'dynatemp_range', + 'dynatemp_exponent', + 'typical_p', + 'xtc_probability', + 'xtc_threshold', +]; +const PENALTY_KEYS: SettKey[] = [ + 'repeat_last_n', + 'repeat_penalty', + 'presence_penalty', + 'frequency_penalty', + 'dry_multiplier', + 'dry_base', + 'dry_allowed_length', + 'dry_penalty_last_n', +]; + +enum SettingInputType { + SHORT_INPUT, + LONG_INPUT, + CHECKBOX, + CUSTOM, +} + +interface SettingFieldInput { + type: Exclude; + label: string | React.ReactElement; + help?: string | React.ReactElement; + key: SettKey; +} + +interface SettingFieldCustom { + type: SettingInputType.CUSTOM; + key: SettKey; + component: + | string + | React.FC<{ + value: string | boolean | number; + onChange: (value: string) => void; + }>; +} + +interface SettingSection { + title: React.ReactElement; + fields: (SettingFieldInput | SettingFieldCustom)[]; +} + +const ICON_CLASSNAME = 'w-4 h-4 mr-1 inline'; + +const SETTING_SECTIONS: SettingSection[] = [ + { + title: ( + <> + + General + + ), + fields: [ + { + type: SettingInputType.SHORT_INPUT, + label: 'API Key', + key: 'apiKey', + }, + { + type: SettingInputType.LONG_INPUT, + label: 'System Message (will be disabled if left empty)', + key: 'systemMessage', + }, + ...BASIC_KEYS.map( + (key) => + ({ + type: SettingInputType.SHORT_INPUT, + label: key, + key, + }) as SettingFieldInput + ), + ], + }, + { + title: ( + <> + + Samplers + + ), + fields: [ + { + type: SettingInputType.SHORT_INPUT, + label: 'Samplers queue', + key: 'samplers', + }, + ...SAMPLER_KEYS.map( + (key) => + ({ + type: SettingInputType.SHORT_INPUT, + label: key, + key, + }) as SettingFieldInput + ), + ], + }, + { + title: ( + <> + + Penalties + + ), + fields: PENALTY_KEYS.map((key) => ({ + type: SettingInputType.SHORT_INPUT, + label: key, + key, + })), + }, + { + title: ( + <> + + Reasoning + + ), + fields: [ + { + type: SettingInputType.CHECKBOX, + label: 'Expand thought process by default when generating messages', + key: 'showThoughtInProgress', + }, + { + type: SettingInputType.CHECKBOX, + label: + 'Exclude thought process when sending requests to API (Recommended for DeepSeek-R1)', + key: 'excludeThoughtOnReq', + }, + ], + }, + { + title: ( + <> + + Advanced + + ), + fields: [ + { + type: SettingInputType.CUSTOM, + key: 'custom', // dummy key, won't be used + component: () => { + const debugImportDemoConv = async () => { + const res = await fetch('/demo-conversation.json'); + const demoConv = await res.json(); + StorageUtils.remove(demoConv.id); + for (const msg of demoConv.messages) { + StorageUtils.appendMsg(demoConv.id, msg); + } + }; + return ( + + ); + }, + }, + { + type: SettingInputType.CHECKBOX, + label: 'Show tokens per second', + key: 'showTokensPerSecond', + }, + { + type: SettingInputType.LONG_INPUT, + label: ( + <> + Custom JSON config (For more info, refer to{' '} + + server documentation + + ) + + ), + key: 'custom', + }, + ], + }, + { + title: ( + <> + + Experimental + + ), + fields: [ + { + type: SettingInputType.CUSTOM, + key: 'custom', // dummy key, won't be used + component: () => ( + <> +
+ Experimental features are not guaranteed to work correctly. +
+
+ If you encounter any problems, create a{' '} + + Bug (misc.) + {' '} + report on Github. Please also specify webui/experimental on + the report title and include screenshots. +
+
+ Some features may require packages downloaded from CDN, so they + need internet connection. +
+ + ), + }, + { + type: SettingInputType.CHECKBOX, + label: ( + <> + Enable Python interpreter +
+ + This feature uses{' '} + pyodide, + downloaded from CDN. To use this feature, ask the LLM to generate + Python code inside a Markdown code block. You will see a "Run" + button on the code block, near the "Copy" button. + + + ), + key: 'pyIntepreterEnabled', + }, + ], + }, +]; + +export default function SettingDialog({ + show, + onClose, +}: { + show: boolean; + onClose: () => void; +}) { + const { config, saveConfig } = useAppContext(); + const [sectionIdx, setSectionIdx] = useState(0); + + // clone the config object to prevent direct mutation + const [localConfig, setLocalConfig] = useState( + JSON.parse(JSON.stringify(config)) + ); + + const resetConfig = () => { + if (window.confirm('Are you sure you want to reset all settings?')) { + setLocalConfig(CONFIG_DEFAULT); + } + }; + + const handleSave = () => { + // copy the local config to prevent direct mutation + const newConfig: typeof CONFIG_DEFAULT = JSON.parse( + JSON.stringify(localConfig) + ); + // validate the config + for (const key in newConfig) { + const value = newConfig[key as SettKey]; + const mustBeBoolean = isBoolean(CONFIG_DEFAULT[key as SettKey]); + const mustBeString = isString(CONFIG_DEFAULT[key as SettKey]); + const mustBeNumeric = isNumeric(CONFIG_DEFAULT[key as SettKey]); + if (mustBeString) { + if (!isString(value)) { + alert(`Value for ${key} must be string`); + return; + } + } else if (mustBeNumeric) { + const trimmedValue = value.toString().trim(); + const numVal = Number(trimmedValue); + if (isNaN(numVal) || !isNumeric(numVal) || trimmedValue.length === 0) { + alert(`Value for ${key} must be numeric`); + return; + } + // force conversion to number + // @ts-expect-error this is safe + newConfig[key] = numVal; + } else if (mustBeBoolean) { + if (!isBoolean(value)) { + alert(`Value for ${key} must be boolean`); + return; + } + } else { + console.error(`Unknown default type for key ${key}`); + } + } + if (isDev) console.log('Saving config', newConfig); + saveConfig(newConfig); + onClose(); + }; + + const onChange = (key: SettKey) => (value: string | boolean) => { + // note: we do not perform validation here, because we may get incomplete value as user is still typing it + setLocalConfig({ ...localConfig, [key]: value }); + }; + + return ( + +
+
Settings
+
+ {/* Left panel, showing sections - Desktop version */} +
+ {SETTING_SECTIONS.map((section, idx) => ( +
setSectionIdx(idx)} + dir="auto" + > + {section.title} +
+ ))} +
+ + {/* Left panel, showing sections - Mobile version */} +
+
+
+ {SETTING_SECTIONS[sectionIdx].title} +
+
+ {SETTING_SECTIONS.map((section, idx) => ( +
setSectionIdx(idx)} + dir="auto" + > + {section.title} +
+ ))} +
+
+
+ + {/* Right panel, showing setting fields */} +
+ {SETTING_SECTIONS[sectionIdx].fields.map((field, idx) => { + const key = `${sectionIdx}-${idx}`; + if (field.type === SettingInputType.SHORT_INPUT) { + return ( + + ); + } else if (field.type === SettingInputType.LONG_INPUT) { + return ( + + ); + } else if (field.type === SettingInputType.CHECKBOX) { + return ( + + ); + } else if (field.type === SettingInputType.CUSTOM) { + return ( +
+ {typeof field.component === 'string' + ? field.component + : field.component({ + value: localConfig[field.key], + onChange: onChange(field.key), + })} +
+ ); + } + })} + +
+ Settings are saved in browser's localStorage +
+
+
+ +
+ + + +
+
+ + ); +} + +function SettingsModalLongInput({ + configKey, + value, + onChange, + label, +}: { + configKey: SettKey; + value: string; + onChange: (value: string) => void; + label?: string; +}) { + return ( + +
{label || configKey}
+ onChange(e.target.value)} + /> + </label> + ); +} + +function SettingsModalShortInput({ + configKey, + value, + onChange, + label, +}: { + configKey: SettKey; + // eslint-disable-next-line @typescript-eslint/no-explicit-any + value: any; + onChange: (value: string) => void; + label?: string; +}) { + const helpMsg = CONFIG_INFO[configKey]; + + return ( + <> + {/* on mobile, we simply show the help message here */} + {helpMsg && ( + <div className="block md:hidden mb-1"> + <b>{label || configKey}</b> + <br /> + <p className="text-xs">{helpMsg}</p> + </div> + )} + <label className="input input-bordered join-item grow flex items-center gap-2 mb-2"> + <div className="dropdown dropdown-hover"> + <div tabIndex={0} role="button" className="font-bold hidden md:block"> + {label || configKey} + </div> + {helpMsg && ( + <div className="dropdown-content menu bg-base-100 rounded-box z-10 w-64 p-2 shadow mt-4"> + {helpMsg} + </div> + )} + </div> + <input + type="text" + className="grow" + placeholder={`Default: ${CONFIG_DEFAULT[configKey] || 'none'}`} + value={value} + onChange={(e) => onChange(e.target.value)} + /> + </label> + </> + ); +} + +function SettingsModalCheckbox({ + configKey, + value, + onChange, + label, +}: { + configKey: SettKey; + value: boolean; + onChange: (value: boolean) => void; + label: string; +}) { + return ( + <div className="flex flex-row items-center mb-2"> + <input + type="checkbox" + className="toggle" + checked={value} + onChange={(e) => onChange(e.target.checked)} + /> + <span className="ml-4">{label || configKey}</span> + </div> + ); +} diff --git a/tools/server/webui/src/components/Sidebar.tsx b/tools/server/webui/src/components/Sidebar.tsx new file mode 100644 index 00000000..34727c62 --- /dev/null +++ b/tools/server/webui/src/components/Sidebar.tsx @@ -0,0 +1,96 @@ +import { useEffect, useState } from 'react'; +import { classNames } from '../utils/misc'; +import { Conversation } from '../utils/types'; +import StorageUtils from '../utils/storage'; +import { useNavigate, useParams } from 'react-router'; + +export default function Sidebar() { + const params = useParams(); + const navigate = useNavigate(); + + const [conversations, setConversations] = useState<Conversation[]>([]); + const [currConv, setCurrConv] = useState<Conversation | null>(null); + + useEffect(() => { + StorageUtils.getOneConversation(params.convId ?? '').then(setCurrConv); + }, [params.convId]); + + useEffect(() => { + const handleConversationChange = async () => { + setConversations(await StorageUtils.getAllConversations()); + }; + StorageUtils.onConversationChanged(handleConversationChange); + handleConversationChange(); + return () => { + StorageUtils.offConversationChanged(handleConversationChange); + }; + }, []); + + return ( + <> + <input + id="toggle-drawer" + type="checkbox" + className="drawer-toggle" + defaultChecked + /> + + <div className="drawer-side h-screen lg:h-screen z-50 lg:max-w-64"> + <label + htmlFor="toggle-drawer" + aria-label="close sidebar" + className="drawer-overlay" + ></label> + <div className="flex flex-col bg-base-200 min-h-full max-w-64 py-4 px-4"> + <div className="flex flex-row items-center justify-between mb-4 mt-4"> + <h2 className="font-bold ml-4">Conversations</h2> + + {/* close sidebar button */} + <label htmlFor="toggle-drawer" className="btn btn-ghost lg:hidden"> + <svg + xmlns="http://www.w3.org/2000/svg" + width="16" + height="16" + fill="currentColor" + className="bi bi-arrow-bar-left" + viewBox="0 0 16 16" + > + <path + fillRule="evenodd" + d="M12.5 15a.5.5 0 0 1-.5-.5v-13a.5.5 0 0 1 1 0v13a.5.5 0 0 1-.5.5M10 8a.5.5 0 0 1-.5.5H3.707l2.147 2.146a.5.5 0 0 1-.708.708l-3-3a.5.5 0 0 1 0-.708l3-3a.5.5 0 1 1 .708.708L3.707 7.5H9.5a.5.5 0 0 1 .5.5" + /> + </svg> + </label> + </div> + + {/* list of conversations */} + <div + className={classNames({ + 'btn btn-ghost justify-start': true, + 'btn-active': !currConv, + })} + onClick={() => navigate('/')} + > + + New conversation + </div> + {conversations.map((conv) => ( + <div + key={conv.id} + className={classNames({ + 'btn btn-ghost justify-start font-normal': true, + 'btn-active': conv.id === currConv?.id, + })} + onClick={() => navigate(`/chat/${conv.id}`)} + dir="auto" + > + <span className="truncate">{conv.name}</span> + </div> + ))} + <div className="text-center text-xs opacity-40 mt-auto mx-4"> + Conversations are saved to browser's IndexedDB + </div> + </div> + </div> + </> + ); +} diff --git a/tools/server/webui/src/components/useChatTextarea.ts b/tools/server/webui/src/components/useChatTextarea.ts new file mode 100644 index 00000000..42b12819 --- /dev/null +++ b/tools/server/webui/src/components/useChatTextarea.ts @@ -0,0 +1,96 @@ +import { useEffect, useRef, useState, useCallback } from 'react'; + +// Media Query for detecting "large" screens (matching Tailwind's lg: breakpoint) +const LARGE_SCREEN_MQ = '(min-width: 1024px)'; + +// Calculates and sets the textarea height based on its scrollHeight +const adjustTextareaHeight = (textarea: HTMLTextAreaElement | null) => { + if (!textarea) return; + + // Only perform auto-sizing on large screens + if (!window.matchMedia(LARGE_SCREEN_MQ).matches) { + // On small screens, reset inline height and max-height styles. + // This allows CSS (e.g., `rows` attribute or classes) to control the height, + // and enables manual resizing if `resize-vertical` is set. + textarea.style.height = ''; // Use 'auto' or '' to reset + textarea.style.maxHeight = ''; + return; // Do not adjust height programmatically on small screens + } + + const computedStyle = window.getComputedStyle(textarea); + // Get the max-height specified by CSS (e.g., from `lg:max-h-48`) + const currentMaxHeight = computedStyle.maxHeight; + + // Temporarily remove max-height to allow scrollHeight to be calculated correctly + textarea.style.maxHeight = 'none'; + // Reset height to 'auto' to measure the actual scrollHeight needed + textarea.style.height = 'auto'; + // Set the height to the calculated scrollHeight + textarea.style.height = `${textarea.scrollHeight}px`; + // Re-apply the original max-height from CSS to enforce the limit + textarea.style.maxHeight = currentMaxHeight; +}; + +// Interface describing the API returned by the hook +export interface ChatTextareaApi { + value: () => string; + setValue: (value: string) => void; + focus: () => void; + ref: React.RefObject<HTMLTextAreaElement>; + onInput: (event: React.FormEvent<HTMLTextAreaElement>) => void; // Input handler +} + +// This is a workaround to prevent the textarea from re-rendering when the inner content changes +// See https://github.com/ggml-org/llama.cpp/pull/12299 +// combined now with auto-sizing logic. +export function useChatTextarea(initValue: string): ChatTextareaApi { + const [savedInitValue, setSavedInitValue] = useState<string>(initValue); + const textareaRef = useRef<HTMLTextAreaElement>(null); + + // Effect to set initial value and height on mount or when initValue changes + useEffect(() => { + const textarea = textareaRef.current; + if (textarea) { + if (typeof savedInitValue === 'string' && savedInitValue.length > 0) { + textarea.value = savedInitValue; + // Call adjustTextareaHeight - it will check screen size internally + setTimeout(() => adjustTextareaHeight(textarea), 0); + setSavedInitValue(''); // Reset after applying + } else { + // Adjust height even if there's no initial value (for initial render) + setTimeout(() => adjustTextareaHeight(textarea), 0); + } + } + }, [textareaRef, savedInitValue]); // Depend on ref and savedInitValue + + const handleInput = useCallback( + (event: React.FormEvent<HTMLTextAreaElement>) => { + // Call adjustTextareaHeight on every input - it will decide whether to act + adjustTextareaHeight(event.currentTarget); + }, + [] + ); + + return { + // Method to get the current value directly from the textarea + value: () => { + return textareaRef.current?.value ?? ''; + }, + // Method to programmatically set the value and trigger height adjustment + setValue: (value: string) => { + const textarea = textareaRef.current; + if (textarea) { + textarea.value = value; + // Call adjustTextareaHeight - it will check screen size internally + setTimeout(() => adjustTextareaHeight(textarea), 0); + } + }, + focus: () => { + if (textareaRef.current) { + textareaRef.current.focus(); + } + }, + ref: textareaRef, + onInput: handleInput, + }; +} diff --git a/tools/server/webui/src/index.scss b/tools/server/webui/src/index.scss new file mode 100644 index 00000000..a18f0945 --- /dev/null +++ b/tools/server/webui/src/index.scss @@ -0,0 +1,78 @@ +@use 'sass:meta'; +@use 'tailwindcss'; + +@plugin 'daisyui' { + themes: all; +} + +html { + scrollbar-gutter: auto; +} + +.markdown { + h1, + h2, + h3, + h4, + h5, + h6, + ul, + ol, + li { + all: revert; + } + pre { + @apply whitespace-pre-wrap rounded-lg p-2; + border: 1px solid currentColor; + } + p { + @apply mb-2; + } + /* TODO: fix markdown table */ +} + +.show-on-hover { + @apply md:opacity-0 md:group-hover:opacity-100; +} +.btn-mini { + @apply cursor-pointer hover:shadow-md; +} +.chat-screen { + max-width: 900px; +} + +.chat-bubble-base-300 { + --tw-bg-opacity: 1; + --tw-text-opacity: 1; + @apply bg-base-300 text-base-content; +} + +/* Highlight.js */ +[data-color-scheme='light'] { + @include meta.load-css('highlight.js/styles/stackoverflow-light'); + .dark-color { + @apply bg-base-content text-base-100; + } +} +[data-color-scheme='dark'] { + @include meta.load-css('highlight.js/styles/stackoverflow-dark'); +} +[data-color-scheme='auto'] { + @media (prefers-color-scheme: light) { + @include meta.load-css('highlight.js/styles/stackoverflow-light'); + .dark-color { + @apply bg-base-content text-base-100; + } + } + @media (prefers-color-scheme: dark) { + @include meta.load-css('highlight.js/styles/stackoverflow-dark'); + } +} +.hljs { + background: transparent !important; + padding: 0.5em !important; +} + +.katex-display { + margin: 0 0 !important; +} diff --git a/tools/server/webui/src/main.tsx b/tools/server/webui/src/main.tsx new file mode 100644 index 00000000..631e96a7 --- /dev/null +++ b/tools/server/webui/src/main.tsx @@ -0,0 +1,10 @@ +import { StrictMode } from 'react'; +import { createRoot } from 'react-dom/client'; +import './index.scss'; +import App from './App.tsx'; + +createRoot(document.getElementById('root')!).render( + <StrictMode> + <App /> + </StrictMode> +); diff --git a/tools/server/webui/src/utils/app.context.tsx b/tools/server/webui/src/utils/app.context.tsx new file mode 100644 index 00000000..54bb65b6 --- /dev/null +++ b/tools/server/webui/src/utils/app.context.tsx @@ -0,0 +1,387 @@ +import React, { createContext, useContext, useEffect, useState } from 'react'; +import { + APIMessage, + CanvasData, + Conversation, + Message, + PendingMessage, + ViewingChat, +} from './types'; +import StorageUtils from './storage'; +import { + filterThoughtFromMsgs, + normalizeMsgsForAPI, + getSSEStreamAsync, +} from './misc'; +import { BASE_URL, CONFIG_DEFAULT, isDev } from '../Config'; +import { matchPath, useLocation, useNavigate } from 'react-router'; + +interface AppContextValue { + // conversations and messages + viewingChat: ViewingChat | null; + pendingMessages: Record<Conversation['id'], PendingMessage>; + isGenerating: (convId: string) => boolean; + sendMessage: ( + convId: string | null, + leafNodeId: Message['id'] | null, + content: string, + extra: Message['extra'], + onChunk: CallbackGeneratedChunk + ) => Promise<boolean>; + stopGenerating: (convId: string) => void; + replaceMessageAndGenerate: ( + convId: string, + parentNodeId: Message['id'], // the parent node of the message to be replaced + content: string | null, + extra: Message['extra'], + onChunk: CallbackGeneratedChunk + ) => Promise<void>; + + // canvas + canvasData: CanvasData | null; + setCanvasData: (data: CanvasData | null) => void; + + // config + config: typeof CONFIG_DEFAULT; + saveConfig: (config: typeof CONFIG_DEFAULT) => void; + showSettings: boolean; + setShowSettings: (show: boolean) => void; +} + +// this callback is used for scrolling to the bottom of the chat and switching to the last node +export type CallbackGeneratedChunk = (currLeafNodeId?: Message['id']) => void; + +// eslint-disable-next-line @typescript-eslint/no-explicit-any +const AppContext = createContext<AppContextValue>({} as any); + +const getViewingChat = async (convId: string): Promise<ViewingChat | null> => { + const conv = await StorageUtils.getOneConversation(convId); + if (!conv) return null; + return { + conv: conv, + // all messages from all branches, not filtered by last node + messages: await StorageUtils.getMessages(convId), + }; +}; + +export const AppContextProvider = ({ + children, +}: { + children: React.ReactElement; +}) => { + const { pathname } = useLocation(); + const navigate = useNavigate(); + const params = matchPath('/chat/:convId', pathname); + const convId = params?.params?.convId; + + const [viewingChat, setViewingChat] = useState<ViewingChat | null>(null); + const [pendingMessages, setPendingMessages] = useState< + Record<Conversation['id'], PendingMessage> + >({}); + const [aborts, setAborts] = useState< + Record<Conversation['id'], AbortController> + >({}); + const [config, setConfig] = useState(StorageUtils.getConfig()); + const [canvasData, setCanvasData] = useState<CanvasData | null>(null); + const [showSettings, setShowSettings] = useState(false); + + // handle change when the convId from URL is changed + useEffect(() => { + // also reset the canvas data + setCanvasData(null); + const handleConversationChange = async (changedConvId: string) => { + if (changedConvId !== convId) return; + setViewingChat(await getViewingChat(changedConvId)); + }; + StorageUtils.onConversationChanged(handleConversationChange); + getViewingChat(convId ?? '').then(setViewingChat); + return () => { + StorageUtils.offConversationChanged(handleConversationChange); + }; + }, [convId]); + + const setPending = (convId: string, pendingMsg: PendingMessage | null) => { + // if pendingMsg is null, remove the key from the object + if (!pendingMsg) { + setPendingMessages((prev) => { + const newState = { ...prev }; + delete newState[convId]; + return newState; + }); + } else { + setPendingMessages((prev) => ({ ...prev, [convId]: pendingMsg })); + } + }; + + const setAbort = (convId: string, controller: AbortController | null) => { + if (!controller) { + setAborts((prev) => { + const newState = { ...prev }; + delete newState[convId]; + return newState; + }); + } else { + setAborts((prev) => ({ ...prev, [convId]: controller })); + } + }; + + //////////////////////////////////////////////////////////////////////// + // public functions + + const isGenerating = (convId: string) => !!pendingMessages[convId]; + + const generateMessage = async ( + convId: string, + leafNodeId: Message['id'], + onChunk: CallbackGeneratedChunk + ) => { + if (isGenerating(convId)) return; + + const config = StorageUtils.getConfig(); + const currConversation = await StorageUtils.getOneConversation(convId); + if (!currConversation) { + throw new Error('Current conversation is not found'); + } + + const currMessages = StorageUtils.filterByLeafNodeId( + await StorageUtils.getMessages(convId), + leafNodeId, + false + ); + const abortController = new AbortController(); + setAbort(convId, abortController); + + if (!currMessages) { + throw new Error('Current messages are not found'); + } + + const pendingId = Date.now() + 1; + let pendingMsg: PendingMessage = { + id: pendingId, + convId, + type: 'text', + timestamp: pendingId, + role: 'assistant', + content: null, + parent: leafNodeId, + children: [], + }; + setPending(convId, pendingMsg); + + try { + // prepare messages for API + let messages: APIMessage[] = [ + ...(config.systemMessage.length === 0 + ? [] + : [{ role: 'system', content: config.systemMessage } as APIMessage]), + ...normalizeMsgsForAPI(currMessages), + ]; + if (config.excludeThoughtOnReq) { + messages = filterThoughtFromMsgs(messages); + } + if (isDev) console.log({ messages }); + + // prepare params + const params = { + messages, + stream: true, + cache_prompt: true, + samplers: config.samplers, + temperature: config.temperature, + dynatemp_range: config.dynatemp_range, + dynatemp_exponent: config.dynatemp_exponent, + top_k: config.top_k, + top_p: config.top_p, + min_p: config.min_p, + typical_p: config.typical_p, + xtc_probability: config.xtc_probability, + xtc_threshold: config.xtc_threshold, + repeat_last_n: config.repeat_last_n, + repeat_penalty: config.repeat_penalty, + presence_penalty: config.presence_penalty, + frequency_penalty: config.frequency_penalty, + dry_multiplier: config.dry_multiplier, + dry_base: config.dry_base, + dry_allowed_length: config.dry_allowed_length, + dry_penalty_last_n: config.dry_penalty_last_n, + max_tokens: config.max_tokens, + timings_per_token: !!config.showTokensPerSecond, + ...(config.custom.length ? JSON.parse(config.custom) : {}), + }; + + // send request + const fetchResponse = await fetch(`${BASE_URL}/v1/chat/completions`, { + method: 'POST', + headers: { + 'Content-Type': 'application/json', + ...(config.apiKey + ? { Authorization: `Bearer ${config.apiKey}` } + : {}), + }, + body: JSON.stringify(params), + signal: abortController.signal, + }); + if (fetchResponse.status !== 200) { + const body = await fetchResponse.json(); + throw new Error(body?.error?.message || 'Unknown error'); + } + const chunks = getSSEStreamAsync(fetchResponse); + for await (const chunk of chunks) { + // const stop = chunk.stop; + if (chunk.error) { + throw new Error(chunk.error?.message || 'Unknown error'); + } + const addedContent = chunk.choices[0].delta.content; + const lastContent = pendingMsg.content || ''; + if (addedContent) { + pendingMsg = { + ...pendingMsg, + content: lastContent + addedContent, + }; + } + const timings = chunk.timings; + if (timings && config.showTokensPerSecond) { + // only extract what's really needed, to save some space + pendingMsg.timings = { + prompt_n: timings.prompt_n, + prompt_ms: timings.prompt_ms, + predicted_n: timings.predicted_n, + predicted_ms: timings.predicted_ms, + }; + } + setPending(convId, pendingMsg); + onChunk(); // don't need to switch node for pending message + } + } catch (err) { + setPending(convId, null); + if ((err as Error).name === 'AbortError') { + // user stopped the generation via stopGeneration() function + // we can safely ignore this error + } else { + console.error(err); + // eslint-disable-next-line @typescript-eslint/no-explicit-any + alert((err as any)?.message ?? 'Unknown error'); + throw err; // rethrow + } + } + + if (pendingMsg.content !== null) { + await StorageUtils.appendMsg(pendingMsg as Message, leafNodeId); + } + setPending(convId, null); + onChunk(pendingId); // trigger scroll to bottom and switch to the last node + }; + + const sendMessage = async ( + convId: string | null, + leafNodeId: Message['id'] | null, + content: string, + extra: Message['extra'], + onChunk: CallbackGeneratedChunk + ): Promise<boolean> => { + if (isGenerating(convId ?? '') || content.trim().length === 0) return false; + + if (convId === null || convId.length === 0 || leafNodeId === null) { + const conv = await StorageUtils.createConversation( + content.substring(0, 256) + ); + convId = conv.id; + leafNodeId = conv.currNode; + // if user is creating a new conversation, redirect to the new conversation + navigate(`/chat/${convId}`); + } + + const now = Date.now(); + const currMsgId = now; + StorageUtils.appendMsg( + { + id: currMsgId, + timestamp: now, + type: 'text', + convId, + role: 'user', + content, + extra, + parent: leafNodeId, + children: [], + }, + leafNodeId + ); + onChunk(currMsgId); + + try { + await generateMessage(convId, currMsgId, onChunk); + return true; + } catch (_) { + // TODO: rollback + } + return false; + }; + + const stopGenerating = (convId: string) => { + setPending(convId, null); + aborts[convId]?.abort(); + }; + + // if content is undefined, we remove last assistant message + const replaceMessageAndGenerate = async ( + convId: string, + parentNodeId: Message['id'], // the parent node of the message to be replaced + content: string | null, + extra: Message['extra'], + onChunk: CallbackGeneratedChunk + ) => { + if (isGenerating(convId)) return; + + if (content !== null) { + const now = Date.now(); + const currMsgId = now; + StorageUtils.appendMsg( + { + id: currMsgId, + timestamp: now, + type: 'text', + convId, + role: 'user', + content, + extra, + parent: parentNodeId, + children: [], + }, + parentNodeId + ); + parentNodeId = currMsgId; + } + onChunk(parentNodeId); + + await generateMessage(convId, parentNodeId, onChunk); + }; + + const saveConfig = (config: typeof CONFIG_DEFAULT) => { + StorageUtils.setConfig(config); + setConfig(config); + }; + + return ( + <AppContext.Provider + value={{ + isGenerating, + viewingChat, + pendingMessages, + sendMessage, + stopGenerating, + replaceMessageAndGenerate, + canvasData, + setCanvasData, + config, + saveConfig, + showSettings, + setShowSettings, + }} + > + {children} + </AppContext.Provider> + ); +}; + +export const useAppContext = () => useContext(AppContext); diff --git a/tools/server/webui/src/utils/common.tsx b/tools/server/webui/src/utils/common.tsx new file mode 100644 index 00000000..09b08b5c --- /dev/null +++ b/tools/server/webui/src/utils/common.tsx @@ -0,0 +1,38 @@ +export const XCloseButton: React.ElementType< + React.ClassAttributes<HTMLButtonElement> & + React.HTMLAttributes<HTMLButtonElement> +> = ({ className, ...props }) => ( + <button className={`btn btn-square btn-sm ${className ?? ''}`} {...props}> + <svg + xmlns="http://www.w3.org/2000/svg" + className="h-6 w-6" + fill="none" + viewBox="0 0 24 24" + stroke="currentColor" + > + <path + strokeLinecap="round" + strokeLinejoin="round" + strokeWidth="2" + d="M6 18L18 6M6 6l12 12" + /> + </svg> + </button> +); + +export const OpenInNewTab = ({ + href, + children, +}: { + href: string; + children: string; +}) => ( + <a + className="underline" + href={href} + target="_blank" + rel="noopener noreferrer" + > + {children} + </a> +); diff --git a/tools/server/webui/src/utils/llama-vscode.ts b/tools/server/webui/src/utils/llama-vscode.ts new file mode 100644 index 00000000..c45b0d39 --- /dev/null +++ b/tools/server/webui/src/utils/llama-vscode.ts @@ -0,0 +1,60 @@ +import { useEffect, useState } from 'react'; +import { MessageExtraContext } from './types'; +import { ChatTextareaApi } from '../components/useChatTextarea.ts'; + +// Extra context when using llama.cpp WebUI from llama-vscode, inside an iframe +// Ref: https://github.com/ggml-org/llama.cpp/pull/11940 + +interface SetTextEvData { + text: string; + context: string; +} + +/** + * To test it: + * window.postMessage({ command: 'setText', text: 'Spot the syntax error', context: 'def test()\n return 123' }, '*'); + */ + +export const useVSCodeContext = (textarea: ChatTextareaApi) => { + const [extraContext, setExtraContext] = useState<MessageExtraContext | null>( + null + ); + + // Accept setText message from a parent window and set inputMsg and extraContext + useEffect(() => { + const handleMessage = (event: MessageEvent) => { + if (event.data?.command === 'setText') { + const data: SetTextEvData = event.data; + textarea.setValue(data?.text); + if (data?.context && data.context.length > 0) { + setExtraContext({ + type: 'context', + content: data.context, + }); + } + textarea.focus(); + } + }; + + window.addEventListener('message', handleMessage); + return () => window.removeEventListener('message', handleMessage); + }, [textarea]); + + // Add a keydown listener that sends the "escapePressed" message to the parent window + useEffect(() => { + const handleKeyDown = (event: KeyboardEvent) => { + if (event.key === 'Escape') { + window.parent.postMessage({ command: 'escapePressed' }, '*'); + } + }; + + window.addEventListener('keydown', handleKeyDown); + return () => window.removeEventListener('keydown', handleKeyDown); + }, []); + + return { + extraContext, + // call once the user message is sent, to clear the extra context + clearExtraContext: () => setExtraContext(null), + }; +}; diff --git a/tools/server/webui/src/utils/misc.ts b/tools/server/webui/src/utils/misc.ts new file mode 100644 index 00000000..87f55b2a --- /dev/null +++ b/tools/server/webui/src/utils/misc.ts @@ -0,0 +1,128 @@ +// @ts-expect-error this package does not have typing +import TextLineStream from 'textlinestream'; +import { APIMessage, Message } from './types'; + +// ponyfill for missing ReadableStream asyncIterator on Safari +import { asyncIterator } from '@sec-ant/readable-stream/ponyfill/asyncIterator'; + +// eslint-disable-next-line @typescript-eslint/no-explicit-any +export const isString = (x: any) => !!x.toLowerCase; +// eslint-disable-next-line @typescript-eslint/no-explicit-any +export const isBoolean = (x: any) => x === true || x === false; +// eslint-disable-next-line @typescript-eslint/no-explicit-any +export const isNumeric = (n: any) => !isString(n) && !isNaN(n) && !isBoolean(n); +export const escapeAttr = (str: string) => + str.replace(/>/g, '>').replace(/"/g, '"'); + +// wrapper for SSE +export async function* getSSEStreamAsync(fetchResponse: Response) { + if (!fetchResponse.body) throw new Error('Response body is empty'); + const lines: ReadableStream<string> = fetchResponse.body + .pipeThrough(new TextDecoderStream()) + .pipeThrough(new TextLineStream()); + // @ts-expect-error asyncIterator complains about type, but it should work + for await (const line of asyncIterator(lines)) { + //if (isDev) console.log({ line }); + if (line.startsWith('data:') && !line.endsWith('[DONE]')) { + const data = JSON.parse(line.slice(5)); + yield data; + } else if (line.startsWith('error:')) { + const data = JSON.parse(line.slice(6)); + throw new Error(data.message || 'Unknown error'); + } + } +} + +// copy text to clipboard +export const copyStr = (textToCopy: string) => { + // Navigator clipboard api needs a secure context (https) + if (navigator.clipboard && window.isSecureContext) { + navigator.clipboard.writeText(textToCopy); + } else { + // Use the 'out of viewport hidden text area' trick + const textArea = document.createElement('textarea'); + textArea.value = textToCopy; + // Move textarea out of the viewport so it's not visible + textArea.style.position = 'absolute'; + textArea.style.left = '-999999px'; + document.body.prepend(textArea); + textArea.select(); + document.execCommand('copy'); + } +}; + +/** + * filter out redundant fields upon sending to API + * also format extra into text + */ +export function normalizeMsgsForAPI(messages: Readonly<Message[]>) { + return messages.map((msg) => { + let newContent = ''; + + for (const extra of msg.extra ?? []) { + if (extra.type === 'context') { + newContent += `${extra.content}\n\n`; + } + } + + newContent += msg.content; + + return { + role: msg.role, + content: newContent, + }; + }) as APIMessage[]; +} + +/** + * recommended for DeepsSeek-R1, filter out content between <think> and </think> tags + */ +export function filterThoughtFromMsgs(messages: APIMessage[]) { + return messages.map((msg) => { + return { + role: msg.role, + content: + msg.role === 'assistant' + ? msg.content.split('</think>').at(-1)!.trim() + : msg.content, + } as APIMessage; + }); +} + +export function classNames(classes: Record<string, boolean>): string { + return Object.entries(classes) + .filter(([_, value]) => value) + .map(([key, _]) => key) + .join(' '); +} + +export const delay = (ms: number) => + new Promise((resolve) => setTimeout(resolve, ms)); + +export const throttle = <T extends unknown[]>( + callback: (...args: T) => void, + delay: number +) => { + let isWaiting = false; + + return (...args: T) => { + if (isWaiting) { + return; + } + + callback(...args); + isWaiting = true; + + setTimeout(() => { + isWaiting = false; + }, delay); + }; +}; + +export const cleanCurrentUrl = (removeQueryParams: string[]) => { + const url = new URL(window.location.href); + removeQueryParams.forEach((param) => { + url.searchParams.delete(param); + }); + window.history.replaceState({}, '', url.toString()); +}; diff --git a/tools/server/webui/src/utils/storage.ts b/tools/server/webui/src/utils/storage.ts new file mode 100644 index 00000000..1dfc9d97 --- /dev/null +++ b/tools/server/webui/src/utils/storage.ts @@ -0,0 +1,284 @@ +// coversations is stored in localStorage +// format: { [convId]: { id: string, lastModified: number, messages: [...] } } + +import { CONFIG_DEFAULT } from '../Config'; +import { Conversation, Message, TimingReport } from './types'; +import Dexie, { Table } from 'dexie'; + +const event = new EventTarget(); + +type CallbackConversationChanged = (convId: string) => void; +let onConversationChangedHandlers: [ + CallbackConversationChanged, + EventListener, +][] = []; +const dispatchConversationChange = (convId: string) => { + event.dispatchEvent( + new CustomEvent('conversationChange', { detail: { convId } }) + ); +}; + +const db = new Dexie('LlamacppWebui') as Dexie & { + conversations: Table<Conversation>; + messages: Table<Message>; +}; + +// https://dexie.org/docs/Version/Version.stores() +db.version(1).stores({ + // Unlike SQL, you donât need to specify all properties but only the one you wish to index. + conversations: '&id, lastModified', + messages: '&id, convId, [convId+id], timestamp', +}); + +// convId is a string prefixed with 'conv-' +const StorageUtils = { + /** + * manage conversations + */ + async getAllConversations(): Promise<Conversation[]> { + await migrationLStoIDB().catch(console.error); // noop if already migrated + return (await db.conversations.toArray()).sort( + (a, b) => b.lastModified - a.lastModified + ); + }, + /** + * can return null if convId does not exist + */ + async getOneConversation(convId: string): Promise<Conversation | null> { + return (await db.conversations.where('id').equals(convId).first()) ?? null; + }, + /** + * get all message nodes in a conversation + */ + async getMessages(convId: string): Promise<Message[]> { + return await db.messages.where({ convId }).toArray(); + }, + /** + * use in conjunction with getMessages to filter messages by leafNodeId + * includeRoot: whether to include the root node in the result + * if node with leafNodeId does not exist, return the path with the latest timestamp + */ + filterByLeafNodeId( + msgs: Readonly<Message[]>, + leafNodeId: Message['id'], + includeRoot: boolean + ): Readonly<Message[]> { + const res: Message[] = []; + const nodeMap = new Map<Message['id'], Message>(); + for (const msg of msgs) { + nodeMap.set(msg.id, msg); + } + let startNode: Message | undefined = nodeMap.get(leafNodeId); + if (!startNode) { + // if not found, we return the path with the latest timestamp + let latestTime = -1; + for (const msg of msgs) { + if (msg.timestamp > latestTime) { + startNode = msg; + latestTime = msg.timestamp; + } + } + } + // traverse the path from leafNodeId to root + // startNode can never be undefined here + let currNode: Message | undefined = startNode; + while (currNode) { + if (currNode.type !== 'root' || (currNode.type === 'root' && includeRoot)) + res.push(currNode); + currNode = nodeMap.get(currNode.parent ?? -1); + } + res.sort((a, b) => a.timestamp - b.timestamp); + return res; + }, + /** + * create a new conversation with a default root node + */ + async createConversation(name: string): Promise<Conversation> { + const now = Date.now(); + const msgId = now; + const conv: Conversation = { + id: `conv-${now}`, + lastModified: now, + currNode: msgId, + name, + }; + await db.conversations.add(conv); + // create a root node + await db.messages.add({ + id: msgId, + convId: conv.id, + type: 'root', + timestamp: now, + role: 'system', + content: '', + parent: -1, + children: [], + }); + return conv; + }, + /** + * if convId does not exist, throw an error + */ + async appendMsg( + msg: Exclude<Message, 'parent' | 'children'>, + parentNodeId: Message['id'] + ): Promise<void> { + if (msg.content === null) return; + const { convId } = msg; + await db.transaction('rw', db.conversations, db.messages, async () => { + const conv = await StorageUtils.getOneConversation(convId); + const parentMsg = await db.messages + .where({ convId, id: parentNodeId }) + .first(); + // update the currNode of conversation + if (!conv) { + throw new Error(`Conversation ${convId} does not exist`); + } + if (!parentMsg) { + throw new Error( + `Parent message ID ${parentNodeId} does not exist in conversation ${convId}` + ); + } + await db.conversations.update(convId, { + lastModified: Date.now(), + currNode: msg.id, + }); + // update parent + await db.messages.update(parentNodeId, { + children: [...parentMsg.children, msg.id], + }); + // create message + await db.messages.add({ + ...msg, + parent: parentNodeId, + children: [], + }); + }); + dispatchConversationChange(convId); + }, + /** + * remove conversation by id + */ + async remove(convId: string): Promise<void> { + await db.transaction('rw', db.conversations, db.messages, async () => { + await db.conversations.delete(convId); + await db.messages.where({ convId }).delete(); + }); + dispatchConversationChange(convId); + }, + + // event listeners + onConversationChanged(callback: CallbackConversationChanged) { + const fn = (e: Event) => callback((e as CustomEvent).detail.convId); + onConversationChangedHandlers.push([callback, fn]); + event.addEventListener('conversationChange', fn); + }, + offConversationChanged(callback: CallbackConversationChanged) { + const fn = onConversationChangedHandlers.find(([cb, _]) => cb === callback); + if (fn) { + event.removeEventListener('conversationChange', fn[1]); + } + onConversationChangedHandlers = []; + }, + + // manage config + getConfig(): typeof CONFIG_DEFAULT { + const savedVal = JSON.parse(localStorage.getItem('config') || '{}'); + // to prevent breaking changes in the future, we always provide default value for missing keys + return { + ...CONFIG_DEFAULT, + ...savedVal, + }; + }, + setConfig(config: typeof CONFIG_DEFAULT) { + localStorage.setItem('config', JSON.stringify(config)); + }, + getTheme(): string { + return localStorage.getItem('theme') || 'auto'; + }, + setTheme(theme: string) { + if (theme === 'auto') { + localStorage.removeItem('theme'); + } else { + localStorage.setItem('theme', theme); + } + }, +}; + +export default StorageUtils; + +// Migration from localStorage to IndexedDB + +// these are old types, LS prefix stands for LocalStorage +interface LSConversation { + id: string; // format: `conv-{timestamp}` + lastModified: number; // timestamp from Date.now() + messages: LSMessage[]; +} +interface LSMessage { + id: number; + role: 'user' | 'assistant' | 'system'; + content: string; + timings?: TimingReport; +} +async function migrationLStoIDB() { + if (localStorage.getItem('migratedToIDB')) return; + const res: LSConversation[] = []; + for (const key in localStorage) { + if (key.startsWith('conv-')) { + res.push(JSON.parse(localStorage.getItem(key) ?? '{}')); + } + } + if (res.length === 0) return; + await db.transaction('rw', db.conversations, db.messages, async () => { + let migratedCount = 0; + for (const conv of res) { + const { id: convId, lastModified, messages } = conv; + const firstMsg = messages[0]; + const lastMsg = messages.at(-1); + if (messages.length < 2 || !firstMsg || !lastMsg) { + console.log( + `Skipping conversation ${convId} with ${messages.length} messages` + ); + continue; + } + const name = firstMsg.content ?? '(no messages)'; + await db.conversations.add({ + id: convId, + lastModified, + currNode: lastMsg.id, + name, + }); + const rootId = messages[0].id - 2; + await db.messages.add({ + id: rootId, + convId: convId, + type: 'root', + timestamp: rootId, + role: 'system', + content: '', + parent: -1, + children: [firstMsg.id], + }); + for (let i = 0; i < messages.length; i++) { + const msg = messages[i]; + await db.messages.add({ + ...msg, + type: 'text', + convId: convId, + timestamp: msg.id, + parent: i === 0 ? rootId : messages[i - 1].id, + children: i === messages.length - 1 ? [] : [messages[i + 1].id], + }); + } + migratedCount++; + console.log( + `Migrated conversation ${convId} with ${messages.length} messages` + ); + } + console.log( + `Migrated ${migratedCount} conversations from localStorage to IndexedDB` + ); + localStorage.setItem('migratedToIDB', '1'); + }); +} diff --git a/tools/server/webui/src/utils/types.ts b/tools/server/webui/src/utils/types.ts new file mode 100644 index 00000000..0eb77400 --- /dev/null +++ b/tools/server/webui/src/utils/types.ts @@ -0,0 +1,91 @@ +export interface TimingReport { + prompt_n: number; + prompt_ms: number; + predicted_n: number; + predicted_ms: number; +} + +/** + * What is conversation "branching"? It is a feature that allows the user to edit an old message in the history, while still keeping the conversation flow. + * Inspired by ChatGPT / Claude / Hugging Chat where you edit a message, a new branch of the conversation is created, and the old message is still visible. + * + * We use the same node-based structure like other chat UIs, where each message has a parent and children. A "root" message is the first message in a conversation, which will not be displayed in the UI. + * + * root + * âââ message 1 + * â âââ message 2 + * â âââ message 3 + * âââ message 4 + * âââ message 5 + * + * In the above example, assuming that user wants to edit message 2, a new branch will be created: + * + * âââ message 2 + * â âââ message 3 + * âââ message 6 + * + * Message 2 and 6 are siblings, and message 6 is the new branch. + * + * We only need to know the last node (aka leaf) to get the current branch. In the above example, message 5 is the leaf of branch containing message 4 and 5. + * + * For the implementation: + * - StorageUtils.getMessages() returns list of all nodes + * - StorageUtils.filterByLeafNodeId() filters the list of nodes from a given leaf node + */ + +// Note: the term "message" and "node" are used interchangeably in this context +export interface Message { + id: number; + convId: string; + type: 'text' | 'root'; + timestamp: number; // timestamp from Date.now() + role: 'user' | 'assistant' | 'system'; + content: string; + timings?: TimingReport; + extra?: MessageExtra[]; + // node based system for branching + parent: Message['id']; + children: Message['id'][]; +} + +type MessageExtra = MessageExtraTextFile | MessageExtraContext; // TODO: will add more in the future + +export interface MessageExtraTextFile { + type: 'textFile'; + name: string; + content: string; +} + +export interface MessageExtraContext { + type: 'context'; + content: string; +} + +export type APIMessage = Pick<Message, 'role' | 'content'>; + +export interface Conversation { + id: string; // format: `conv-{timestamp}` + lastModified: number; // timestamp from Date.now() + currNode: Message['id']; // the current message node being viewed + name: string; +} + +export interface ViewingChat { + conv: Readonly<Conversation>; + messages: Readonly<Message[]>; +} + +export type PendingMessage = Omit<Message, 'content'> & { + content: string | null; +}; + +export enum CanvasType { + PY_INTERPRETER, +} + +export interface CanvasPyInterpreter { + type: CanvasType.PY_INTERPRETER; + content: string; +} + +export type CanvasData = CanvasPyInterpreter; diff --git a/tools/server/webui/src/vite-env.d.ts b/tools/server/webui/src/vite-env.d.ts new file mode 100644 index 00000000..11f02fe2 --- /dev/null +++ b/tools/server/webui/src/vite-env.d.ts @@ -0,0 +1 @@ +/// <reference types="vite/client" /> diff --git a/tools/server/webui/tailwind.config.js b/tools/server/webui/tailwind.config.js new file mode 100644 index 00000000..c43066a1 --- /dev/null +++ b/tools/server/webui/tailwind.config.js @@ -0,0 +1,16 @@ +/** @type {import('tailwindcss').Config} */ +export default { + content: [ + "./index.html", + "./src/**/*.{js,ts,jsx,tsx}", + ], + theme: { + extend: {}, + }, + plugins: [ + require('daisyui'), + ], + daisyui: { + themes: ['light', 'dark', 'cupcake', 'bumblebee', 'emerald', 'corporate', 'synthwave', 'retro', 'cyberpunk', 'valentine', 'halloween', 'garden', 'forest', 'aqua', 'lofi', 'pastel', 'fantasy', 'wireframe', 'black', 'luxury', 'dracula', 'cmyk', 'autumn', 'business', 'acid', 'lemonade', 'night', 'coffee', 'winter', 'dim', 'nord', 'sunset'], + } +} diff --git a/tools/server/webui/tsconfig.app.json b/tools/server/webui/tsconfig.app.json new file mode 100644 index 00000000..cb24c26f --- /dev/null +++ b/tools/server/webui/tsconfig.app.json @@ -0,0 +1,26 @@ +{ + "compilerOptions": { + "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.app.tsbuildinfo", + "target": "ES2021", + "useDefineForClassFields": true, + "lib": ["ES2021", "DOM", "DOM.Iterable"], + "module": "ESNext", + "skipLibCheck": true, + + /* Bundler mode */ + "moduleResolution": "bundler", + "allowImportingTsExtensions": true, + "isolatedModules": true, + "moduleDetection": "force", + "noEmit": true, + "jsx": "react-jsx", + + /* Linting */ + "strict": true, + "noUnusedLocals": true, + "noUnusedParameters": true, + "noFallthroughCasesInSwitch": true, + "noUncheckedSideEffectImports": true + }, + "include": ["src"] +} diff --git a/tools/server/webui/tsconfig.json b/tools/server/webui/tsconfig.json new file mode 100644 index 00000000..1ffef600 --- /dev/null +++ b/tools/server/webui/tsconfig.json @@ -0,0 +1,7 @@ +{ + "files": [], + "references": [ + { "path": "./tsconfig.app.json" }, + { "path": "./tsconfig.node.json" } + ] +} diff --git a/tools/server/webui/tsconfig.node.json b/tools/server/webui/tsconfig.node.json new file mode 100644 index 00000000..db0becc8 --- /dev/null +++ b/tools/server/webui/tsconfig.node.json @@ -0,0 +1,24 @@ +{ + "compilerOptions": { + "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.node.tsbuildinfo", + "target": "ES2022", + "lib": ["ES2023"], + "module": "ESNext", + "skipLibCheck": true, + + /* Bundler mode */ + "moduleResolution": "bundler", + "allowImportingTsExtensions": true, + "isolatedModules": true, + "moduleDetection": "force", + "noEmit": true, + + /* Linting */ + "strict": true, + "noUnusedLocals": true, + "noUnusedParameters": true, + "noFallthroughCasesInSwitch": true, + "noUncheckedSideEffectImports": true + }, + "include": ["vite.config.ts"] +} diff --git a/tools/server/webui/vite.config.ts b/tools/server/webui/vite.config.ts new file mode 100644 index 00000000..b8a0f03d --- /dev/null +++ b/tools/server/webui/vite.config.ts @@ -0,0 +1,80 @@ +import { defineConfig, PluginOption } from 'vite'; +import react from '@vitejs/plugin-react'; +import { viteSingleFile } from 'vite-plugin-singlefile'; +import path from 'node:path'; +import fs from 'node:fs'; +import zlib from 'node:zlib'; + +/* eslint-disable */ + +const MAX_BUNDLE_SIZE = 1.5 * 1024 * 1024; // only increase when absolutely necessary + +const GUIDE_FOR_FRONTEND = ` + +`.trim(); + +const FRONTEND_PLUGINS = [react()]; + +const BUILD_PLUGINS = [ + ...FRONTEND_PLUGINS, + viteSingleFile(), + (function llamaCppPlugin() { + let config: any; + return { + name: 'llamacpp:build', + apply: 'build', + async configResolved(_config: any) { + config = _config; + }, + writeBundle() { + const outputIndexHtml = path.join(config.build.outDir, 'index.html'); + const content = + GUIDE_FOR_FRONTEND + '\n' + fs.readFileSync(outputIndexHtml, 'utf-8'); + const compressed = zlib.gzipSync(Buffer.from(content, 'utf-8'), { + level: 9, + }); + + // because gzip header contains machine-specific info, we must remove these data from the header + // timestamp + compressed[0x4] = 0; + compressed[0x5] = 0; + compressed[0x6] = 0; + compressed[0x7] = 0; + // OS + compressed[0x9] = 0; + + if (compressed.byteLength > MAX_BUNDLE_SIZE) { + throw new Error( + `Bundle size is too large (${Math.ceil(compressed.byteLength / 1024)} KB).\n` + + `Please reduce the size of the frontend or increase MAX_BUNDLE_SIZE in vite.config.js.\n` + ); + } + + const targetOutputFile = path.join( + config.build.outDir, + '../../public/index.html.gz' + ); + fs.writeFileSync(targetOutputFile, compressed); + }, + } satisfies PluginOption; + })(), +]; + +export default defineConfig({ + // @ts-ignore + plugins: process.env.ANALYZE ? FRONTEND_PLUGINS : BUILD_PLUGINS, + server: { + proxy: { + '/v1': 'http://localhost:8080', + }, + headers: { + 'Cross-Origin-Embedder-Policy': 'require-corp', + 'Cross-Origin-Opener-Policy': 'same-origin', + }, + }, +}); diff --git a/tools/tokenize/CMakeLists.txt b/tools/tokenize/CMakeLists.txt new file mode 100644 index 00000000..1690b53e --- /dev/null +++ b/tools/tokenize/CMakeLists.txt @@ -0,0 +1,5 @@ +set(TARGET llama-tokenize) +add_executable(${TARGET} tokenize.cpp) +install(TARGETS ${TARGET} RUNTIME) +target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT}) +target_compile_features(${TARGET} PRIVATE cxx_std_17) diff --git a/tools/tokenize/tokenize.cpp b/tools/tokenize/tokenize.cpp new file mode 100644 index 00000000..7375759e --- /dev/null +++ b/tools/tokenize/tokenize.cpp @@ -0,0 +1,416 @@ +#include "common.h" +//#include "log.h" // TODO: start using log.h +#include "llama.h" + +#include <cstdio> +#include <cstring> +#include <fstream> +#include <string> +#include <vector> +#include <iostream> // TODO: remove me + +#if defined(_WIN32) +#define WIN32_LEAN_AND_MEAN +#include <windows.h> +#include <shellapi.h> // For CommandLineToArgvW +#endif + +static void print_usage_information(const char * argv0) { + printf("usage: %s [options]\n\n", argv0); + printf("The tokenize program tokenizes a prompt using a given model,\n"); + printf("and prints the resulting tokens to standard output.\n\n"); + printf("It needs a model file, a prompt, and optionally other flags\n"); + printf("to control the behavior of the tokenizer.\n\n"); + printf(" The possible options are:\n"); + printf("\n"); + printf(" -h, --help print this help and exit\n"); + printf(" -m MODEL_PATH, --model MODEL_PATH path to model.\n"); + printf(" --ids if given, only print numerical token IDs, and not token strings.\n"); + printf(" The output format looks like [1, 2, 3], i.e. parseable by Python.\n"); + printf(" -f PROMPT_FNAME, --file PROMPT_FNAME read prompt from a file.\n"); + printf(" -p PROMPT, --prompt PROMPT read prompt from the argument.\n"); + printf(" --stdin read prompt from standard input.\n"); + printf(" --no-bos do not ever add a BOS token to the prompt, even if normally the model uses a BOS token.\n"); + printf(" --no-escape do not escape input (such as \\n, \\t, etc.).\n"); + printf(" --no-parse-special do not parse control tokens.\n"); + printf(" --log-disable disable logs. Makes stderr quiet when loading the model.\n"); + printf(" --show-count print the total number of tokens.\n"); +} + +static void llama_log_callback_null(ggml_log_level level, const char * text, void * user_data) { + (void) level; + (void) text; + (void) user_data; +} + +static std::string read_prompt_from_file(const char * filepath, bool & success) { + success = false; + + std::ifstream in(filepath, std::ios::binary); + if (!in) { + fprintf(stderr, "%s: could not open file '%s' for reading: %s\n", __func__, filepath, strerror(errno)); + return std::string(); + } + // do not assume the file is seekable (e.g. /dev/stdin) + std::stringstream buffer; + buffer << in.rdbuf(); + if (in.fail()) { + fprintf(stderr, "%s: could not read the entire file '%s': %s\n", __func__, filepath, strerror(errno)); + return std::string(); + } + + success = true; + return buffer.str(); +} + +// +// Function: ingest_args(...) -> vector<string> +// +// Takes argc and argv arguments, and converts them to a vector of UTF-8 encoded +// strings, as an STL vector<string>. +// +// In particular, it handles character encoding shenanigans on Windows. +// +// Note: raw_argc and raw_argv are not actually read at all on Windows. +// On Windows we call GetCommandLineW to get the arguments in wchar_t +// format, ignoring the regular argc/argv arguments to main(). +// +// TODO: potential opportunity to roll common stuff into common/console.cpp +// in relation to Windows wchar_t shenanigans. +static std::vector<std::string> ingest_args(int raw_argc, char ** raw_argv) { + std::vector<std::string> argv; + + // Handle Windows, if given non-ASCII arguments. + // We convert wchar_t arguments into UTF-8 char* on this platform. + // Lets you invoke 'tokenize' on Windows cmd.exe with non-ASCII characters + // without throwing tantrums. +#if defined(_WIN32) + int argc; + const LPWSTR cmdline_wargv = GetCommandLineW(); + LPWSTR * wargv = CommandLineToArgvW(cmdline_wargv, &argc); + + // silence unused arg warnings + (void) raw_argc; + (void) raw_argv; + + for (int i = 0; i < argc; ++i) { + int length_needed = WideCharToMultiByte(CP_UTF8, 0, wargv[i], wcslen(wargv[i]), 0, 0, NULL, NULL); + char * output_buf = (char *) calloc(length_needed+1, sizeof(char)); + GGML_ASSERT(output_buf); + + WideCharToMultiByte(CP_UTF8, 0, wargv[i], wcslen(wargv[i]), output_buf, length_needed, NULL, NULL); + output_buf[length_needed] = '\0'; + + argv.push_back(output_buf); + free(output_buf); + } + + LocalFree((HLOCAL) wargv); +#else + int argc = raw_argc; + for (int i = 0; i < argc; ++i) { + argv.push_back(raw_argv[i]); + } +#endif + + GGML_ASSERT((unsigned int) argc == argv.size()); + + return argv; +} + +// +// Function: write_utf8_cstr_to_stdout(const char *) -> <writes to stdout> +// +// writes a string to standard output; taking into account that on Windows +// to display correctly you have to use special handling. Works even if the +// user has not set a unicode code page on a Windows cmd.exe. +// +// In case of invalid UTF-8, invalid_utf8 is set to true on Windows, and something +// a human-readable is written instead. +// +// On non-Windows systems, simply printfs() the string. +static void write_utf8_cstr_to_stdout(const char * str, bool & invalid_utf8) { + invalid_utf8 = false; + +#if defined(_WIN32) + // Are we in a console? + HANDLE hConsole = GetStdHandle(STD_OUTPUT_HANDLE); + DWORD dwMode = 0; + + // According to Microsoft docs: + // "WriteConsole fails if it is used with a standard handle that is redirected to a file." + // Also according to the docs, you can use GetConsoleMode to check for that. + if (hConsole == INVALID_HANDLE_VALUE || !GetConsoleMode(hConsole, &dwMode)) { + printf("%s", str); + return; + } + + // MultiByteToWideChar reports an error if str is empty, don't report + // them as invalid_utf8. + if (*str == 0) { + return; + } + int length_needed = MultiByteToWideChar(CP_UTF8, MB_ERR_INVALID_CHARS, str, strlen(str), NULL, 0); + if (length_needed == 0) { + DWORD err = GetLastError(); + if (err == ERROR_NO_UNICODE_TRANSLATION) { + invalid_utf8 = true; + int len = strlen(str); + printf("<"); + for (int i = 0; i < len; ++i) { + if (i > 0) { + printf(" "); + } + printf("%02x", (uint8_t) str[i]); + } + printf(">"); + return; + } + GGML_ABORT("MultiByteToWideChar() failed in an unexpected way."); + } + + LPWSTR wstr = (LPWSTR) calloc(length_needed+1, sizeof(*wstr)); + GGML_ASSERT(wstr); + + MultiByteToWideChar(CP_UTF8, 0, str, strlen(str), wstr, length_needed); + WriteConsoleW(hConsole, wstr, length_needed, NULL, NULL); + + free(wstr); +#else + // TODO: reporting invalid_utf8 would be useful on non-Windows too. + // printf will silently just write bad unicode. + printf("%s", str); +#endif +} + +int main(int raw_argc, char ** raw_argv) { + const std::vector<std::string> argv = ingest_args(raw_argc, raw_argv); + const int argc = argv.size(); + + if (argc <= 1) { + print_usage_information(argv[0].c_str()); + return 1; + } + + ////// + // Read out all the command line arguments. + ////// + + // variables where to put any arguments we see. + bool printing_ids = false; + bool no_bos = false; + bool no_escape = false; + bool no_parse_special = false; + bool disable_logging = false; + bool show_token_count = false; + const char * model_path = NULL; + const char * prompt_path = NULL; + const char * prompt_arg = NULL; + + // track which arguments were explicitly given + // used for sanity checking down the line + bool model_path_set = false; + bool prompt_path_set = false; + bool prompt_set = false; + bool stdin_set = false; + + int iarg = 1; + for (; iarg < argc; ++iarg) { + std::string arg{argv[iarg]}; + if (arg == "-h" || arg == "--help") { + print_usage_information(argv[0].c_str()); + return 0; + } + else if (arg == "--ids") { + printing_ids = true; + } + else if (arg == "-m" || arg == "--model") { + if (model_path_set) { + fprintf(stderr, "Error: -m or --model specified multiple times.\n"); + return 1; + } + model_path = argv[++iarg].c_str(); + model_path_set = true; + } + else if (arg == "--no-bos") { + no_bos = true; + } + else if (arg == "--no-escape") { + no_escape = true; + } + else if (arg == "--no-parse-special") { + no_parse_special = true; + } + else if (arg == "-p" || arg == "--prompt") { + if (prompt_set) { + fprintf(stderr, "Error: -p or --prompt specified multiple times.\n"); + return 1; + } + prompt_arg = argv[++iarg].c_str(); + prompt_set = true; + } + else if (arg == "-f" || arg == "--file") { + if (prompt_path_set) { + fprintf(stderr, "Error: -f or --file specified multiple times.\n"); + return 1; + } + prompt_path = argv[++iarg].c_str(); + prompt_path_set = true; + } + else if (arg == "--stdin") { + stdin_set = true; + } + else if (arg == "--log-disable") { + disable_logging = true; + } + else if (arg == "--show-count") { + show_token_count = true; + } + else { + fprintf(stderr, "Error: unknown option '%s'\n", argv[iarg].c_str()); + return 1; + } + } + + ////// + // Sanity check the command line arguments. + ////// + + // Check that we have the required stuff set. + if (model_path_set && model_path == NULL) { + fprintf(stderr, "Error: --model requires an argument.\n"); + return 1; + } + if (!model_path_set) { + fprintf(stderr, "Error: must specify --model.\n"); + return 1; + } + if (prompt_path_set && prompt_path == NULL) { + fprintf(stderr, "Error: --file requires an argument.\n"); + return 1; + } + if (prompt_set && prompt_arg == NULL) { + fprintf(stderr, "Error: --prompt requires an argument.\n"); + return 1; + } + const int prompts_set = !!(prompt_path_set) + !!(prompt_set) + !!(stdin_set); + if (prompts_set > 1) { + fprintf(stderr, "Error: --stdin, --file and --prompt are mutually exclusive.\n"); + return 1; + } + // Must have some prompt. + if (prompts_set == 0) { + fprintf(stderr, "Error: must specify one of: --stdin, --file or --prompt.\n"); + return 1; + } + + GGML_ASSERT(model_path); + GGML_ASSERT(prompt_path || prompt_arg || stdin_set); + + ////// + // Figure out where will the prompt come from. + ////// + + std::string prompt; + if (prompt_path_set) { + bool success = false; + prompt = read_prompt_from_file(prompt_path, success); + if (!success) { + return 1; + } + } else if (prompt_set) { + prompt = prompt_arg; + } else { + GGML_ASSERT(stdin_set); + // we read stdin *after* loading model (early exit if model cannot + // be loaded, which can be a nicer user experience) + } + + ////// + // Start actually doing the tokenizing stuff. + ////// + + if (disable_logging) { + llama_log_set(llama_log_callback_null, NULL); + } + + llama_backend_init(); + + llama_model_params model_params = llama_model_default_params(); + model_params.vocab_only = true; + llama_model * model = llama_model_load_from_file(model_path, model_params); + if (!model) { + fprintf(stderr, "Error: could not load model from file '%s'.\n", model_path); + return 1; + } + + const llama_vocab * vocab = llama_model_get_vocab(model); + + llama_context_params ctx_params = llama_context_default_params(); + llama_context * ctx = llama_init_from_model(model, ctx_params); + if (!ctx) { + fprintf(stderr, "Error: could not create context.\n"); + return 1; + } + + // read entire prompt from stdin? + if (stdin_set) { + GGML_ASSERT(!prompt_path_set && !prompt_set); + + std::stringstream stdin_buffer; + stdin_buffer << std::cin.rdbuf(); + if (std::cin.fail()) { + fprintf(stderr, "Error: could not read the entire standard input.\n"); + return 1; + } + + prompt = stdin_buffer.str(); + } + + const bool model_wants_add_bos = llama_vocab_get_add_bos(vocab); + const bool add_bos = model_wants_add_bos && !no_bos; + const bool parse_special = !no_parse_special; + const bool escape = !no_escape; + + if (escape) { + string_process_escapes(prompt); + } + + std::vector<llama_token> tokens; + tokens = common_tokenize(vocab, prompt, add_bos, parse_special); + + if (printing_ids) { + printf("["); + } + + for (int i = 0; i < (int) tokens.size(); i++) { + if (printing_ids) { + if (i > 0) { + printf(", "); + } + printf("%d", tokens[i]); + } else { + bool invalid_utf8 = false; + printf("%6d -> '", tokens[i]); + write_utf8_cstr_to_stdout(common_token_to_piece(ctx, tokens[i]).c_str(), invalid_utf8); + if (invalid_utf8) { + printf("' (utf-8 decode failure)\n"); + } else { + printf("'\n"); + } + } + } + + if (printing_ids) { + printf("]\n"); + } + + if (show_token_count) { + printf("Total number of tokens: %zu\n", tokens.size()); + } + // silence valgrind + llama_free(ctx); + llama_model_free(model); + + return 0; +} diff --git a/tools/tts/CMakeLists.txt b/tools/tts/CMakeLists.txt new file mode 100644 index 00000000..c72bd814 --- /dev/null +++ b/tools/tts/CMakeLists.txt @@ -0,0 +1,5 @@ +set(TARGET llama-tts) +add_executable(${TARGET} tts.cpp) +install(TARGETS ${TARGET} RUNTIME) +target_link_libraries(${TARGET} PRIVATE llama common ${CMAKE_THREAD_LIBS_INIT}) +target_compile_features(${TARGET} PRIVATE cxx_std_17) diff --git a/tools/tts/README.md b/tools/tts/README.md new file mode 100644 index 00000000..557014ae --- /dev/null +++ b/tools/tts/README.md @@ -0,0 +1,117 @@ +# llama.cpp/example/tts +This example demonstrates the Text To Speech feature. It uses a +[model](https://www.outeai.com/blog/outetts-0.2-500m) from +[outeai](https://www.outeai.com/). + +## Quickstart +If you have built llama.cpp with `-DLLAMA_CURL=ON` you can simply run the +following command and the required models will be downloaded automatically: +```console +$ build/bin/llama-tts --tts-oute-default -p "Hello world" && aplay output.wav +``` +For details about the models and how to convert them to the required format +see the following sections. + +### Model conversion +Checkout or download the model that contains the LLM model: +```console +$ pushd models +$ git clone --branch main --single-branch --depth 1 https://huggingface.co/OuteAI/OuteTTS-0.2-500M +$ cd OuteTTS-0.2-500M && git lfs install && git lfs pull +$ popd +``` +Convert the model to .gguf format: +```console +(venv) python convert_hf_to_gguf.py models/OuteTTS-0.2-500M \ + --outfile models/outetts-0.2-0.5B-f16.gguf --outtype f16 +``` +The generated model will be `models/outetts-0.2-0.5B-f16.gguf`. + +We can optionally quantize this to Q8_0 using the following command: +```console +$ build/bin/llama-quantize models/outetts-0.2-0.5B-f16.gguf \ + models/outetts-0.2-0.5B-q8_0.gguf q8_0 +``` +The quantized model will be `models/outetts-0.2-0.5B-q8_0.gguf`. + +Next we do something simlar for the audio decoder. First download or checkout +the model for the voice decoder: +```console +$ pushd models +$ git clone --branch main --single-branch --depth 1 https://huggingface.co/novateur/WavTokenizer-large-speech-75token +$ cd WavTokenizer-large-speech-75token && git lfs install && git lfs pull +$ popd +``` +This model file is PyTorch checkpoint (.ckpt) and we first need to convert it to +huggingface format: +```console +(venv) python tools/tts/convert_pt_to_hf.py \ + models/WavTokenizer-large-speech-75token/wavtokenizer_large_speech_320_24k.ckpt +... +Model has been successfully converted and saved to models/WavTokenizer-large-speech-75token/model.safetensors +Metadata has been saved to models/WavTokenizer-large-speech-75token/index.json +Config has been saved to models/WavTokenizer-large-speech-75tokenconfig.json +``` +Then we can convert the huggingface format to gguf: +```console +(venv) python convert_hf_to_gguf.py models/WavTokenizer-large-speech-75token \ + --outfile models/wavtokenizer-large-75-f16.gguf --outtype f16 +... +INFO:hf-to-gguf:Model successfully exported to models/wavtokenizer-large-75-f16.gguf +``` + +### Running the example + +With both of the models generated, the LLM model and the voice decoder model, +we can run the example: +```console +$ build/bin/llama-tts -m ./models/outetts-0.2-0.5B-q8_0.gguf \ + -mv ./models/wavtokenizer-large-75-f16.gguf \ + -p "Hello world" +... +main: audio written to file 'output.wav' +``` +The output.wav file will contain the audio of the prompt. This can be heard +by playing the file with a media player. On Linux the following command will +play the audio: +```console +$ aplay output.wav +``` + +### Running the example with llama-server +Running this example with `llama-server` is also possible and requires two +server instances to be started. One will serve the LLM model and the other +will serve the voice decoder model. + +The LLM model server can be started with the following command: +```console +$ ./build/bin/llama-server -m ./models/outetts-0.2-0.5B-q8_0.gguf --port 8020 +``` + +And the voice decoder model server can be started using: +```console +./build/bin/llama-server -m ./models/wavtokenizer-large-75-f16.gguf --port 8021 --embeddings --pooling none +``` + +Then we can run [tts-outetts.py](tts-outetts.py) to generate the audio. + +First create a virtual environment for python and install the required +dependencies (this in only required to be done once): +```console +$ python3 -m venv venv +$ source venv/bin/activate +(venv) pip install requests numpy +``` + +And then run the python script using: +```conole +(venv) python ./tools/tts/tts-outetts.py http://localhost:8020 http://localhost:8021 "Hello world" +spectrogram generated: n_codes: 90, n_embd: 1282 +converting to audio ... +audio generated: 28800 samples +audio written to file "output.wav" +``` +And to play the audio we can again use aplay or any other media player: +```console +$ aplay output.wav +``` diff --git a/tools/tts/convert_pt_to_hf.py b/tools/tts/convert_pt_to_hf.py new file mode 100644 index 00000000..8909a65f --- /dev/null +++ b/tools/tts/convert_pt_to_hf.py @@ -0,0 +1,180 @@ +# convert the https://huggingface.co/novateur/WavTokenizer-large-speech-75token to HF format +# the goal is to be able to reuse the convert_hf_to_gguf.py after that to create a GGUF file with the WavTokenizer decoder +# +# TODO: this script is LLM-generated and probably very inefficient and should be rewritten + +import torch +import json +import os +import sys +import re + +from safetensors.torch import save_file + +# default +model_path = './model.pt'; + +# read from CLI +if len(sys.argv) > 1: + model_path = sys.argv[1] + +# get the directory of the input model +path_dst = os.path.dirname(model_path) + +print(f"Loading model from {model_path}") + +model = torch.load(model_path, map_location='cpu') + +#print(model) + +# print all keys +for key in model.keys(): + print(key) + if key == 'hyper_parameters': + #print(model[key]) + # dump as json pretty + print(json.dumps(model[key], indent=4)) + #if key != 'state_dict' and key != 'optimizer_states': + # print(model[key]) + +# Check if the loaded model is a state_dict or a model instance +if isinstance(model, torch.nn.Module): + state_dict = model.state_dict() +else: + state_dict = model + +# Print the structure of the state_dict to understand its format +print("State dictionary keys:") +for key in state_dict.keys(): + print(key) + +# Ensure the state_dict is flat and contains only torch.Tensor objects +def flatten_state_dict(state_dict, parent_key='', sep='.'): + items = [] + items_new = [] + + for k, v in state_dict.items(): + new_key = f"{parent_key}{sep}{k}" if parent_key else k + if isinstance(v, torch.Tensor): + items.append((new_key, v)) + elif isinstance(v, dict): + items.extend(flatten_state_dict(v, new_key, sep=sep).items()) + return dict(items) + + size_total_mb = 0 + + for key, value in list(items): + # keep only what we need for inference + if not key.startswith('state_dict.feature_extractor.encodec.quantizer.') and \ + not key.startswith('state_dict.backbone.') and \ + not key.startswith('state_dict.head.out'): + print('Skipping key: ', key) + continue + + new_key = key + + new_key = new_key.replace('state_dict.', '') + new_key = new_key.replace('pos_net', 'posnet') + + # check if matches "backbone.posnet.%d.bias" or "backbone.posnet.%d.weight" + if new_key.startswith("backbone.posnet."): + match = re.match(r"backbone\.posnet\.(\d+)\.(bias|weight)", new_key) + if match: + new_key = f"backbone.posnet.{match.group(1)}.norm.{match.group(2)}" + + # "feature_extractor.encodec.quantizer.vq.layers.0._codebook.embed" -> "backbone.embedding.weight" + if new_key == "feature_extractor.encodec.quantizer.vq.layers.0._codebook.embed": + new_key = "backbone.embedding.weight" + + # these are the only rows used + # ref: https://github.com/edwko/OuteTTS/blob/a613e79c489d8256dd657ea9168d78de75895d82/outetts/wav_tokenizer/audio_codec.py#L100 + if new_key.endswith("norm.scale.weight"): + new_key = new_key.replace("norm.scale.weight", "norm.weight") + value = value[0] + + if new_key.endswith("norm.shift.weight"): + new_key = new_key.replace("norm.shift.weight", "norm.bias") + value = value[0] + + if new_key.endswith("gamma"): + new_key = new_key.replace("gamma", "gamma.weight") + + # convert from 1D [768] to 2D [768, 1] so that ggml_add can broadcast the bias + if (new_key.endswith("norm.weight") or new_key.endswith("norm1.weight") or new_key.endswith("norm2.weight") or new_key.endswith(".bias")) and (new_key.startswith("backbone.posnet") or new_key.startswith("backbone.embed.bias")): + value = value.unsqueeze(1) + + if new_key.endswith("dwconv.bias"): + value = value.unsqueeze(1) + + size_mb = value.element_size() * value.nelement() / (1024 * 1024) + print(f"{size_mb:8.2f} MB - {new_key}: {value.shape}") + + size_total_mb += size_mb + + #print(key, '->', new_key, ': ', value) + #print(key, '->', new_key) + + items_new.append((new_key, value)) + + print(f"Total size: {size_total_mb:8.2f} MB") + + return dict(items_new) + +flattened_state_dict = flatten_state_dict(state_dict) + + +# Convert the model to the safetensors format +output_path = path_dst + '/model.safetensors' +save_file(flattened_state_dict, output_path) + +print(f"Model has been successfully converted and saved to {output_path}") + +# Calculate the total size of the .safetensors file +total_size = os.path.getsize(output_path) + +# Create the weight map +weight_map = { + "model.safetensors": ["*"] # Assuming all weights are in one file +} + +# Create metadata for the index.json file +metadata = { + "total_size": total_size, + "weight_map": weight_map +} + +# Save the metadata to index.json +index_path = path_dst + '/index.json' +with open(index_path, 'w') as f: + json.dump(metadata, f, indent=4) + +print(f"Metadata has been saved to {index_path}") + +config = { + "architectures": [ + "WavTokenizerDec" + ], + "hidden_size": 1282, + "n_embd_features": 512, + "n_ff": 2304, + "vocab_size": 4096, + "n_head": 1, + "layer_norm_epsilon": 1e-6, + "group_norm_epsilon": 1e-6, + "group_norm_groups": 32, + "max_position_embeddings": 8192, # ? + "n_layer": 12, + "posnet": { + "n_embd": 768, + "n_layer": 6 + }, + "convnext": { + "n_embd": 768, + "n_layer": 12 + }, +} + +with open(path_dst + '/config.json', 'w') as f: + json.dump(config, f, indent=4) + +print(f"Config has been saved to {path_dst + 'config.json'}") diff --git a/tools/tts/tts-outetts.py b/tools/tts/tts-outetts.py new file mode 100644 index 00000000..3791f9fc --- /dev/null +++ b/tools/tts/tts-outetts.py @@ -0,0 +1,299 @@ +import sys +#import json +#import struct +import requests +import re +import struct +import numpy as np +from concurrent.futures import ThreadPoolExecutor + + +def fill_hann_window(size, periodic=True): + if periodic: + return np.hanning(size + 1)[:-1] + return np.hanning(size) + + +def irfft(n_fft, complex_input): + return np.fft.irfft(complex_input, n=n_fft) + + +def fold(buffer, n_out, n_win, n_hop, n_pad): + result = np.zeros(n_out) + n_frames = len(buffer) // n_win + + for i in range(n_frames): + start = i * n_hop + end = start + n_win + result[start:end] += buffer[i * n_win:(i + 1) * n_win] + + return result[n_pad:-n_pad] if n_pad > 0 else result + + +def process_frame(args): + l, n_fft, ST, hann = args + frame = irfft(n_fft, ST[l]) + frame = frame * hann + hann2 = hann * hann + return frame, hann2 + + +def embd_to_audio(embd, n_codes, n_embd, n_thread=4): + embd = np.asarray(embd, dtype=np.float32).reshape(n_codes, n_embd) + + n_fft = 1280 + n_hop = 320 + n_win = 1280 + n_pad = (n_win - n_hop) // 2 + n_out = (n_codes - 1) * n_hop + n_win + + hann = fill_hann_window(n_fft, True) + + E = np.zeros((n_embd, n_codes), dtype=np.float32) + for l in range(n_codes): + for k in range(n_embd): + E[k, l] = embd[l, k] + + half_embd = n_embd // 2 + S = np.zeros((n_codes, half_embd + 1), dtype=np.complex64) + + for k in range(half_embd): + for l in range(n_codes): + mag = E[k, l] + phi = E[k + half_embd, l] + + mag = np.clip(np.exp(mag), 0, 1e2) + S[l, k] = mag * np.exp(1j * phi) + + res = np.zeros(n_codes * n_fft) + hann2_buffer = np.zeros(n_codes * n_fft) + + with ThreadPoolExecutor(max_workers=n_thread) as executor: + args = [(l, n_fft, S, hann) for l in range(n_codes)] + results = list(executor.map(process_frame, args)) + + for l, (frame, hann2) in enumerate(results): + res[l*n_fft:(l+1)*n_fft] = frame + hann2_buffer[l*n_fft:(l+1)*n_fft] = hann2 + + audio = fold(res, n_out, n_win, n_hop, n_pad) + env = fold(hann2_buffer, n_out, n_win, n_hop, n_pad) + + mask = env > 1e-10 + audio[mask] /= env[mask] + + return audio + + +def save_wav(filename, audio_data, sample_rate): + num_channels = 1 + bits_per_sample = 16 + bytes_per_sample = bits_per_sample // 8 + data_size = len(audio_data) * bytes_per_sample + byte_rate = sample_rate * num_channels * bytes_per_sample + block_align = num_channels * bytes_per_sample + chunk_size = 36 + data_size # 36 = size of header minus first 8 bytes + + header = struct.pack( + '<4sI4s4sIHHIIHH4sI', + b'RIFF', + chunk_size, + b'WAVE', + b'fmt ', + 16, # fmt chunk size + 1, # audio format (PCM) + num_channels, + sample_rate, + byte_rate, + block_align, + bits_per_sample, + b'data', + data_size + ) + + audio_data = np.clip(audio_data * 32767, -32768, 32767) + pcm_data = audio_data.astype(np.int16) + + with open(filename, 'wb') as f: + f.write(header) + f.write(pcm_data.tobytes()) + + +def process_text(text: str): + text = re.sub(r'\d+(\.\d+)?', lambda x: x.group(), text.lower()) # TODO this needs to be fixed + text = re.sub(r'[-_/,\.\\]', ' ', text) + text = re.sub(r'[^a-z\s]', '', text) + text = re.sub(r'\s+', ' ', text).strip() + return text.split() + +# usage: +# python tts-outetts.py http://server-llm:port http://server-dec:port "text" + +if len(sys.argv) <= 3: + print("usage: python tts-outetts.py http://server-llm:port http://server-dec:port \"text\"") + exit(1) + +host_llm = sys.argv[1] +host_dec = sys.argv[2] +text = sys.argv[3] + +prefix = """<|im_start|> +<|text_start|>the<|text_sep|>overall<|text_sep|>package<|text_sep|>from<|text_sep|>just<|text_sep|>two<|text_sep|>people<|text_sep|>is<|text_sep|>pretty<|text_sep|>remarkable<|text_sep|>sure<|text_sep|>i<|text_sep|>have<|text_sep|>some<|text_sep|>critiques<|text_sep|>about<|text_sep|>some<|text_sep|>of<|text_sep|>the<|text_sep|>gameplay<|text_sep|>aspects<|text_sep|>but<|text_sep|>its<|text_sep|>still<|text_sep|>really<|text_sep|>enjoyable<|text_sep|>and<|text_sep|>it<|text_sep|>looks<|text_sep|>lovely<|text_sep|>""" + +words = process_text(text) +words = "<|text_sep|>".join([i.strip() for i in words]) +words += "<|text_end|>\n" + +# voice data +# TODO: load from json +#suffix = """<|audio_start|> +#the<|t_0.08|><|code_start|><|257|><|740|><|636|><|913|><|788|><|1703|><|code_end|> +#overall<|t_0.36|><|code_start|><|127|><|201|><|191|><|774|><|700|><|532|><|1056|><|557|><|798|><|298|><|1741|><|747|><|1662|><|1617|><|1702|><|1527|><|368|><|1588|><|1049|><|1008|><|1625|><|747|><|1576|><|728|><|1019|><|1696|><|1765|><|code_end|> +#package<|t_0.56|><|code_start|><|935|><|584|><|1319|><|627|><|1016|><|1491|><|1344|><|1117|><|1526|><|1040|><|239|><|1435|><|951|><|498|><|723|><|1180|><|535|><|789|><|1649|><|1637|><|78|><|465|><|1668|><|901|><|595|><|1675|><|117|><|1009|><|1667|><|320|><|840|><|79|><|507|><|1762|><|1508|><|1228|><|1768|><|802|><|1450|><|1457|><|232|><|639|><|code_end|> +#from<|t_0.19|><|code_start|><|604|><|782|><|1682|><|872|><|1532|><|1600|><|1036|><|1761|><|647|><|1554|><|1371|><|653|><|1595|><|950|><|code_end|> +#just<|t_0.25|><|code_start|><|1782|><|1670|><|317|><|786|><|1748|><|631|><|599|><|1155|><|1364|><|1524|><|36|><|1591|><|889|><|1535|><|541|><|440|><|1532|><|50|><|870|><|code_end|> +#two<|t_0.24|><|code_start|><|1681|><|1510|><|673|><|799|><|805|><|1342|><|330|><|519|><|62|><|640|><|1138|><|565|><|1552|><|1497|><|1552|><|572|><|1715|><|1732|><|code_end|> +#people<|t_0.39|><|code_start|><|593|><|274|><|136|><|740|><|691|><|633|><|1484|><|1061|><|1138|><|1485|><|344|><|428|><|397|><|1562|><|645|><|917|><|1035|><|1449|><|1669|><|487|><|442|><|1484|><|1329|><|1832|><|1704|><|600|><|761|><|653|><|269|><|code_end|> +#is<|t_0.16|><|code_start|><|566|><|583|><|1755|><|646|><|1337|><|709|><|802|><|1008|><|485|><|1583|><|652|><|10|><|code_end|> +#pretty<|t_0.32|><|code_start|><|1818|><|1747|><|692|><|733|><|1010|><|534|><|406|><|1697|><|1053|><|1521|><|1355|><|1274|><|816|><|1398|><|211|><|1218|><|817|><|1472|><|1703|><|686|><|13|><|822|><|445|><|1068|><|code_end|> +#remarkable<|t_0.68|><|code_start|><|230|><|1048|><|1705|><|355|><|706|><|1149|><|1535|><|1787|><|1356|><|1396|><|835|><|1583|><|486|><|1249|><|286|><|937|><|1076|><|1150|><|614|><|42|><|1058|><|705|><|681|><|798|><|934|><|490|><|514|><|1399|><|572|><|1446|><|1703|><|1346|><|1040|><|1426|><|1304|><|664|><|171|><|1530|><|625|><|64|><|1708|><|1830|><|1030|><|443|><|1509|><|1063|><|1605|><|1785|><|721|><|1440|><|923|><|code_end|> +#sure<|t_0.36|><|code_start|><|792|><|1780|><|923|><|1640|><|265|><|261|><|1525|><|567|><|1491|><|1250|><|1730|><|362|><|919|><|1766|><|543|><|1|><|333|><|113|><|970|><|252|><|1606|><|133|><|302|><|1810|><|1046|><|1190|><|1675|><|code_end|> +#i<|t_0.08|><|code_start|><|123|><|439|><|1074|><|705|><|1799|><|637|><|code_end|> +#have<|t_0.16|><|code_start|><|1509|><|599|><|518|><|1170|><|552|><|1029|><|1267|><|864|><|419|><|143|><|1061|><|0|><|code_end|> +#some<|t_0.16|><|code_start|><|619|><|400|><|1270|><|62|><|1370|><|1832|><|917|><|1661|><|167|><|269|><|1366|><|1508|><|code_end|> +#critiques<|t_0.60|><|code_start|><|559|><|584|><|1163|><|1129|><|1313|><|1728|><|721|><|1146|><|1093|><|577|><|928|><|27|><|630|><|1080|><|1346|><|1337|><|320|><|1382|><|1175|><|1682|><|1556|><|990|><|1683|><|860|><|1721|><|110|><|786|><|376|><|1085|><|756|><|1523|><|234|><|1334|><|1506|><|1578|><|659|><|612|><|1108|><|1466|><|1647|><|308|><|1470|><|746|><|556|><|1061|><|code_end|> +#about<|t_0.29|><|code_start|><|26|><|1649|><|545|><|1367|><|1263|><|1728|><|450|><|859|><|1434|><|497|><|1220|><|1285|><|179|><|755|><|1154|><|779|><|179|><|1229|><|1213|><|922|><|1774|><|1408|><|code_end|> +#some<|t_0.23|><|code_start|><|986|><|28|><|1649|><|778|><|858|><|1519|><|1|><|18|><|26|><|1042|><|1174|><|1309|><|1499|><|1712|><|1692|><|1516|><|1574|><|code_end|> +#of<|t_0.07|><|code_start|><|197|><|716|><|1039|><|1662|><|64|><|code_end|> +#the<|t_0.08|><|code_start|><|1811|><|1568|><|569|><|886|><|1025|><|1374|><|code_end|> +#gameplay<|t_0.48|><|code_start|><|1269|><|1092|><|933|><|1362|><|1762|><|1700|><|1675|><|215|><|781|><|1086|><|461|><|838|><|1022|><|759|><|649|><|1416|><|1004|><|551|><|909|><|787|><|343|><|830|><|1391|><|1040|><|1622|><|1779|><|1360|><|1231|><|1187|><|1317|><|76|><|997|><|989|><|978|><|737|><|189|><|code_end|> +#aspects<|t_0.56|><|code_start|><|1423|><|797|><|1316|><|1222|><|147|><|719|><|1347|><|386|><|1390|><|1558|><|154|><|440|><|634|><|592|><|1097|><|1718|><|712|><|763|><|1118|><|1721|><|1311|><|868|><|580|><|362|><|1435|><|868|><|247|><|221|><|886|><|1145|><|1274|><|1284|><|457|><|1043|><|1459|><|1818|><|62|><|599|><|1035|><|62|><|1649|><|778|><|code_end|> +#but<|t_0.20|><|code_start|><|780|><|1825|><|1681|><|1007|><|861|><|710|><|702|><|939|><|1669|><|1491|><|613|><|1739|><|823|><|1469|><|648|><|code_end|> +#its<|t_0.09|><|code_start|><|92|><|688|><|1623|><|962|><|1670|><|527|><|599|><|code_end|> +#still<|t_0.27|><|code_start|><|636|><|10|><|1217|><|344|><|713|><|957|><|823|><|154|><|1649|><|1286|><|508|><|214|><|1760|><|1250|><|456|><|1352|><|1368|><|921|><|615|><|5|><|code_end|> +#really<|t_0.36|><|code_start|><|55|><|420|><|1008|><|1659|><|27|><|644|><|1266|><|617|><|761|><|1712|><|109|><|1465|><|1587|><|503|><|1541|><|619|><|197|><|1019|><|817|><|269|><|377|><|362|><|1381|><|507|><|1488|><|4|><|1695|><|code_end|> +#enjoyable<|t_0.49|><|code_start|><|678|><|501|><|864|><|319|><|288|><|1472|><|1341|><|686|><|562|><|1463|><|619|><|1563|><|471|><|911|><|730|><|1811|><|1006|><|520|><|861|><|1274|><|125|><|1431|><|638|><|621|><|153|><|876|><|1770|><|437|><|987|><|1653|><|1109|><|898|><|1285|><|80|><|593|><|1709|><|843|><|code_end|> +#and<|t_0.15|><|code_start|><|1285|><|987|><|303|><|1037|><|730|><|1164|><|502|><|120|><|1737|><|1655|><|1318|><|code_end|> +#it<|t_0.09|><|code_start|><|848|><|1366|><|395|><|1601|><|1513|><|593|><|1302|><|code_end|> +#looks<|t_0.27|><|code_start|><|1281|><|1266|><|1755|><|572|><|248|><|1751|><|1257|><|695|><|1380|><|457|><|659|><|585|><|1315|><|1105|><|1776|><|736|><|24|><|736|><|654|><|1027|><|code_end|> +#lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|1481|><|1721|><|1123|><|438|><|1246|><|1251|><|795|><|659|><|1381|><|1658|><|217|><|1772|><|562|><|952|><|107|><|1129|><|1112|><|467|><|550|><|1079|><|840|><|1615|><|1469|><|1380|><|168|><|917|><|836|><|1827|><|437|><|583|><|67|><|595|><|1087|><|1646|><|1493|><|1677|><|code_end|>""" + +# TODO: tokenization is slow for some reason - here is pre-tokenized input +suffix = [ 151667, 198, 1782, 155780, 151669, 151929, 152412, 152308, 152585, 152460, 153375, 151670, 198, 74455, + 155808, 151669, 151799, 151873, 151863, 152446, 152372, 152204, 152728, 152229, 152470, 151970, 153413, + 152419, 153334, 153289, 153374, 153199, 152040, 153260, 152721, 152680, 153297, 152419, 153248, 152400, + 152691, 153368, 153437, 151670, 198, 1722, 155828, 151669, 152607, 152256, 152991, 152299, 152688, 153163, + 153016, 152789, 153198, 152712, 151911, 153107, 152623, 152170, 152395, 152852, 152207, 152461, 153321, + 153309, 151750, 152137, 153340, 152573, 152267, 153347, 151789, 152681, 153339, 151992, 152512, 151751, + 152179, 153434, 153180, 152900, 153440, 152474, 153122, 153129, 151904, 152311, 151670, 198, 1499, 155791, + 151669, 152276, 152454, 153354, 152544, 153204, 153272, 152708, 153433, 152319, 153226, 153043, 152325, + 153267, 152622, 151670, 198, 4250, 155797, 151669, 153454, 153342, 151989, 152458, 153420, 152303, 152271, + 152827, 153036, 153196, 151708, 153263, 152561, 153207, 152213, 152112, 153204, 151722, 152542, 151670, 198, + 19789, 155796, 151669, 153353, 153182, 152345, 152471, 152477, 153014, 152002, 152191, 151734, 152312, 152810, + 152237, 153224, 153169, 153224, 152244, 153387, 153404, 151670, 198, 16069, 155811, 151669, 152265, 151946, + 151808, 152412, 152363, 152305, 153156, 152733, 152810, 153157, 152016, 152100, 152069, 153234, 152317, + 152589, 152707, 153121, 153341, 152159, 152114, 153156, 153001, 153504, 153376, 152272, 152433, 152325, + 151941, 151670, 198, 285, 155788, 151669, 152238, 152255, 153427, 152318, 153009, 152381, 152474, 152680, + 152157, 153255, 152324, 151682, 151670, 198, 32955, 155804, 151669, 153490, 153419, 152364, 152405, 152682, + 152206, 152078, 153369, 152725, 153193, 153027, 152946, 152488, 153070, 151883, 152890, 152489, 153144, + 153375, 152358, 151685, 152494, 152117, 152740, 151670, 198, 37448, 480, 155840, 151669, 151902, 152720, + 153377, 152027, 152378, 152821, 153207, 153459, 153028, 153068, 152507, 153255, 152158, 152921, 151958, + 152609, 152748, 152822, 152286, 151714, 152730, 152377, 152353, 152470, 152606, 152162, 152186, 153071, + 152244, 153118, 153375, 153018, 152712, 153098, 152976, 152336, 151843, 153202, 152297, 151736, 153380, + 153502, 152702, 152115, 153181, 152735, 153277, 153457, 152393, 153112, 152595, 151670, 198, 19098, 155808, + 151669, 152464, 153452, 152595, 153312, 151937, 151933, 153197, 152239, 153163, 152922, 153402, 152034, + 152591, 153438, 152215, 151673, 152005, 151785, 152642, 151924, 153278, 151805, 151974, 153482, 152718, + 152862, 153347, 151670, 198, 72, 155780, 151669, 151795, 152111, 152746, 152377, 153471, 152309, 151670, 198, + 19016, 155788, 151669, 153181, 152271, 152190, 152842, 152224, 152701, 152939, 152536, 152091, 151815, 152733, + 151672, 151670, 198, 14689, 155788, 151669, 152291, 152072, 152942, 151734, 153042, 153504, 152589, 153333, + 151839, 151941, 153038, 153180, 151670, 198, 36996, 8303, 155832, 151669, 152231, 152256, 152835, 152801, + 152985, 153400, 152393, 152818, 152765, 152249, 152600, 151699, 152302, 152752, 153018, 153009, 151992, + 153054, 152847, 153354, 153228, 152662, 153355, 152532, 153393, 151782, 152458, 152048, 152757, 152428, + 153195, 151906, 153006, 153178, 153250, 152331, 152284, 152780, 153138, 153319, 151980, 153142, 152418, + 152228, 152733, 151670, 198, 9096, 155801, 151669, 151698, 153321, 152217, 153039, 152935, 153400, 152122, + 152531, 153106, 152169, 152892, 152957, 151851, 152427, 152826, 152451, 151851, 152901, 152885, 152594, + 153446, 153080, 151670, 198, 14689, 155795, 151669, 152658, 151700, 153321, 152450, 152530, 153191, 151673, + 151690, 151698, 152714, 152846, 152981, 153171, 153384, 153364, 153188, 153246, 151670, 198, 1055, 155779, + 151669, 151869, 152388, 152711, 153334, 151736, 151670, 198, 1782, 155780, 151669, 153483, 153240, 152241, + 152558, 152697, 153046, 151670, 198, 5804, 1363, 155820, 151669, 152941, 152764, 152605, 153034, 153434, + 153372, 153347, 151887, 152453, 152758, 152133, 152510, 152694, 152431, 152321, 153088, 152676, 152223, + 152581, 152459, 152015, 152502, 153063, 152712, 153294, 153451, 153032, 152903, 152859, 152989, 151748, + 152669, 152661, 152650, 152409, 151861, 151670, 198, 300, 7973, 155828, 151669, 153095, 152469, 152988, + 152894, 151819, 152391, 153019, 152058, 153062, 153230, 151826, 152112, 152306, 152264, 152769, 153390, + 152384, 152435, 152790, 153393, 152983, 152540, 152252, 152034, 153107, 152540, 151919, 151893, 152558, + 152817, 152946, 152956, 152129, 152715, 153131, 153490, 151734, 152271, 152707, 151734, 153321, 152450, + 151670, 198, 8088, 155792, 151669, 152452, 153497, 153353, 152679, 152533, 152382, 152374, 152611, 153341, + 153163, 152285, 153411, 152495, 153141, 152320, 151670, 198, 1199, 155781, 151669, 151764, 152360, 153295, + 152634, 153342, 152199, 152271, 151670, 198, 43366, 155799, 151669, 152308, 151682, 152889, 152016, 152385, + 152629, 152495, 151826, 153321, 152958, 152180, 151886, 153432, 152922, 152128, 153024, 153040, 152593, + 152287, 151677, 151670, 198, 53660, 155808, 151669, 151727, 152092, 152680, 153331, 151699, 152316, 152938, + 152289, 152433, 153384, 151781, 153137, 153259, 152175, 153213, 152291, 151869, 152691, 152489, 151941, + 152049, 152034, 153053, 152179, 153160, 151676, 153367, 151670, 198, 268, 4123, 480, 155821, 151669, 152350, + 152173, 152536, 151991, 151960, 153144, 153013, 152358, 152234, 153135, 152291, 153235, 152143, 152583, + 152402, 153483, 152678, 152192, 152533, 152946, 151797, 153103, 152310, 152293, 151825, 152548, 153442, + 152109, 152659, 153325, 152781, 152570, 152957, 151752, 152265, 153381, 152515, 151670, 198, 437, 155787, + 151669, 152957, 152659, 151975, 152709, 152402, 152836, 152174, 151792, 153409, 153327, 152990, 151670, 198, + 275, 155781, 151669, 152520, 153038, 152067, 153273, 153185, 152265, 152974, 151670, 198, 94273, 155799, + 151669, 152953, 152938, 153427, 152244, 151920, 153423, 152929, 152367, 153052, 152129, 152331, 152257, + 152987, 152777, 153448, 152408, 151696, 152408, 152326, 152699, 151670, 198, 385, 16239, 155828, 151669, + 152306, 152268, 153438, 153228, 152978, 152957, 153153, 153393, 152795, 152110, 152918, 152923, 152467, + 152331, 153053, 153330, 151889, 153444, 152234, 152624, 151779, 152801, 152784, 152139, 152222, 152751, + 152512, 153287, 153141, 153052, 151840, 152589, 152508, 153499, 152109, 152255, 151739, 152267, 152759, + 153318, 153165, 153349, 151670, ] + +response = requests.post( + host_llm + "/completion", + json={ + "prompt": [prefix + words, *suffix], + "n_predict": 1024, + "cache_prompt": True, + "return_tokens": True, + "samplers": ["top_k"], + "top_k": 16, + "seed": 1003, + } +) + +response_json = response.json() + +#print(json.dumps(response_json, indent=4)) +#print(json.dumps(response_json["prompt"], indent=4).replace("\\n", "\n")) +#print(json.dumps(response_json["timings"], indent=4)) +#print(json.dumps(response_json["tokens"], indent=4)) + +codes = response_json["tokens"] + +codes = [t - 151672 for t in codes if t >= 151672 and t <= 155772] + +response = requests.post( + host_dec + "/embeddings", + json={ + "input": [*codes], + } +) + +response_json = response.json() + +#print(json.dumps(response_json, indent=4)) + +# spectrogram +embd = response_json[0]["embedding"] + +n_codes = len(embd) +n_embd = len(embd[0]) + +print('spectrogram generated: n_codes: %d, n_embd: %d' % (n_codes, n_embd)) + +# post-process the spectrogram to convert to audio +print('converting to audio ...') +audio = embd_to_audio(embd, n_codes, n_embd) +print('audio generated: %d samples' % len(audio)) + +filename = "output.wav" +sample_rate = 24000 # sampling rate + +# zero out first 0.25 seconds +audio[:24000 // 4] = 0.0 + +save_wav(filename, audio, sample_rate) +print('audio written to file "%s"' % filename) diff --git a/tools/tts/tts.cpp b/tools/tts/tts.cpp new file mode 100644 index 00000000..0f047986 --- /dev/null +++ b/tools/tts/tts.cpp @@ -0,0 +1,1090 @@ +#define _USE_MATH_DEFINES // For M_PI on MSVC + +#include "arg.h" +#include "common.h" +#include "sampling.h" +#include "log.h" +#include "llama.h" +#include "json.hpp" + +#include <algorithm> +#include <cmath> +#include <cstdio> +#include <fstream> +#include <map> +#include <regex> +#include <string> +#include <thread> +#include <vector> + +using json = nlohmann::ordered_json; + +enum outetts_version { + OUTETTS_V0_2, + OUTETTS_V0_3, +}; + +// +// Terminal utils +// + +#define SQR(X) ((X) * (X)) +#define UNCUBE(x) x < 48 ? 0 : x < 115 ? 1 : (x - 35) / 40 + +/** + * Quantizes 24-bit RGB to xterm256 code range [16,256). + */ +static int rgb2xterm256(int r, int g, int b) { + unsigned char cube[] = {0, 0137, 0207, 0257, 0327, 0377}; + int av, ir, ig, ib, il, qr, qg, qb, ql; + av = r * .299 + g * .587 + b * .114 + .5; + ql = (il = av > 238 ? 23 : (av - 3) / 10) * 10 + 8; + qr = cube[(ir = UNCUBE(r))]; + qg = cube[(ig = UNCUBE(g))]; + qb = cube[(ib = UNCUBE(b))]; + if (SQR(qr - r) + SQR(qg - g) + SQR(qb - b) <= + SQR(ql - r) + SQR(ql - g) + SQR(ql - b)) + return ir * 36 + ig * 6 + ib + 020; + return il + 0350; +} + +static std::string set_xterm256_foreground(int r, int g, int b) { + int x = rgb2xterm256(r, g, b); + std::ostringstream oss; + oss << "\033[38;5;" << x << "m"; + return oss.str(); +} + +const std::vector<std::string> k_colors = { + set_xterm256_foreground(220, 5, 12), + set_xterm256_foreground(232, 96, 28), + set_xterm256_foreground(241, 147, 45), + set_xterm256_foreground(246, 193, 65), + set_xterm256_foreground(247, 240, 86), + set_xterm256_foreground(144, 201, 135), + set_xterm256_foreground( 78, 178, 101), +}; + +static void print_usage(int, char ** argv) { + LOG("\nexample usage:\n"); + LOG("\n %s -m model.gguf -p \"Hello!\"\n", argv[0]); + LOG("\n"); +} + +struct wav_header { + char riff[4] = {'R', 'I', 'F', 'F'}; + uint32_t chunk_size; + char wave[4] = {'W', 'A', 'V', 'E'}; + char fmt[4] = {'f', 'm', 't', ' '}; + uint32_t fmt_chunk_size = 16; + uint16_t audio_format = 1; // PCM + uint16_t num_channels = 1; // Mono + uint32_t sample_rate; + uint32_t byte_rate; + uint16_t block_align; + uint16_t bits_per_sample = 16; + char data[4] = {'d', 'a', 't', 'a'}; + uint32_t data_size; +}; + +static bool save_wav16(const std::string & fname, const std::vector<float> & data, int sample_rate) { + std::ofstream file(fname, std::ios::binary); + if (!file) { + LOG_ERR("%s: Failed to open file '%s' for writing.\n", __func__, fname.c_str()); + return false; + } + + wav_header header; + header.sample_rate = sample_rate; + header.byte_rate = header.sample_rate * header.num_channels * (header.bits_per_sample / 8); + header.block_align = header.num_channels * (header.bits_per_sample / 8); + header.data_size = data.size() * (header.bits_per_sample / 8); + header.chunk_size = 36 + header.data_size; + + file.write(reinterpret_cast<const char*>(&header), sizeof(header)); + + for (const auto & sample : data) { + int16_t pcm_sample = static_cast<int16_t>(std::clamp(sample * 32767.0, -32768.0, 32767.0)); + file.write(reinterpret_cast<const char*>(&pcm_sample), sizeof(pcm_sample)); + } + + return file.good(); +} + +static void fill_hann_window(int length, bool periodic, float * output) { + int offset = -1; + if (periodic) { + offset = 0; + } + for (int i = 0; i < length; i++) { + output[i] = 0.5 * (1.0 - cosf((2.0 * M_PI * i) / (length + offset))); + } +} + +// very poor-man fft +static void twiddle(float * real, float * imag, int k, int N) { + float angle = 2 * M_PI * k / N; + *real = cos(angle); + *imag = sin(angle); +} + +static void irfft(int n, const float * inp_cplx, float * out_real) { + int N = n / 2 + 1; + + std::vector<float> real_input(N); + std::vector<float> imag_input(N); + for (int i = 0; i < N; ++i) { + real_input[i] = inp_cplx[2 * i]; + imag_input[i] = inp_cplx[2 * i + 1]; + } + + std::vector<float> real_output(n); + std::vector<float> imag_output(n); + + for (int k = 0; k < n; ++k) { + real_output[k] = 0.0f; + imag_output[k] = 0.0f; + for (int m = 0; m < N; ++m) { + float twiddle_real; + float twiddle_imag; + + twiddle(&twiddle_real, &twiddle_imag, k * m, n); + + real_output[k] += real_input[m] * twiddle_real - imag_input[m] * twiddle_imag; + imag_output[k] += real_input[m] * twiddle_imag + imag_input[m] * twiddle_real; + } + } + + for (int i = 0; i < n; ++i) { + out_real[i] = real_output[i] / N; + } +} + +// +// y = torch.nn.functional.fold( +// data, output_size=(1, output_size), kernel_size=(1, self.win_length), stride=(1, self.hop_length), +// )[:, 0, 0, pad:-pad] +// +// data.shape = torch.Size([1, 1280, 261]) +// output_size = 84480 +// win_length = 1280 +// hop_length = 320 +// pad = 480 +// +static void fold(const std::vector<float> & data, int64_t n_out, int64_t n_win, int64_t n_hop, int64_t n_pad, std::vector<float> & output) { + int64_t output_height = n_out; + int64_t kernel_w = n_win; + int64_t stride_w = n_hop; + int64_t width = n_out; + + output.resize(width, 0.0f); + + int64_t col_idx = 0; + for (int64_t w_col = 0; w_col < width; ++w_col) { + int64_t start = w_col * stride_w - n_pad; + int64_t end = start + kernel_w; + + for (int64_t w_im = start; w_im < end; ++w_im) { + if (w_im >= 0 && w_im < output_height && col_idx < (int64_t) data.size()) { + output[w_im] += data[col_idx]; + } + col_idx++; + } + } + + output.resize(n_out - 2 * n_pad); +} + +// TODO: not optimized at all +static std::vector<float> embd_to_audio( + const float * embd, + const int n_codes, + const int n_embd, + const int n_thread) { + const int n_fft = 1280; + const int n_hop = 320; + const int n_win = 1280; + const int n_pad = (n_win - n_hop)/2; + const int n_out = (n_codes - 1)*n_hop + n_win; + + std::vector<float> hann(n_fft); + + fill_hann_window(hann.size(), true, hann.data()); + + int n_spec = n_embd*n_codes; + + std::vector<float> E (n_spec); + std::vector<float> S (n_spec); + std::vector<float> ST(n_spec); + + for (int l = 0; l < n_codes; ++l) { + for (int k = 0; k < n_embd; ++k) { + E[k*n_codes + l] = embd[l*n_embd + k]; + } + } + + for (int k = 0; k < n_embd/2; ++k) { + for (int l = 0; l < n_codes; ++l) { + float mag = E[(k )*n_codes + l]; + float phi = E[(k + n_embd/2)*n_codes + l]; + + mag = exp(mag); + + if (mag > 1e2) { + mag = 1e2; + } + S[2*(k*n_codes + l) + 0] = mag*cosf(phi); + S[2*(k*n_codes + l) + 1] = mag*sinf(phi); + } + } + + for (int l = 0; l < n_codes; ++l) { + for (int k = 0; k < n_embd/2; ++k) { + ST[l*n_embd + 2*k + 0] = S[2*(k*n_codes + l) + 0]; + ST[l*n_embd + 2*k + 1] = S[2*(k*n_codes + l) + 1]; + } + } + + std::vector<float> res (n_codes*n_fft); + std::vector<float> hann2(n_codes*n_fft); + + std::vector<std::thread> workers(n_thread); + for (int i = 0; i < n_thread; ++i) { + workers[i] = std::thread([&, i]() { + for (int l = i; l < n_codes; l += n_thread) { + irfft(n_fft, ST.data() + l*n_embd, res.data() + l*n_fft); + for (int j = 0; j < n_fft; ++j) { + res [l*n_fft + j] *= hann[j]; + hann2[l*n_fft + j] = hann[j] * hann[j]; + } + } + }); + } + for (int i = 0; i < n_thread; ++i) { + workers[i].join(); + } + + std::vector<float> audio; + std::vector<float> env; + + fold(res, n_out, n_win, n_hop, n_pad, audio); + fold(hann2, n_out, n_win, n_hop, n_pad, env); // TODO: can be done once + + for (size_t i = 0; i < audio.size(); ++i) { + audio[i] /= env[i]; + } + + return audio; +} + +static const std::map<int, std::string> ones = { + {0, "zero"}, {1, "one"}, {2, "two"}, {3, "three"}, {4, "four"}, + {5, "five"}, {6, "six"}, {7, "seven"}, {8, "eight"}, {9, "nine"}, + {10, "ten"}, {11, "eleven"}, {12, "twelve"}, {13, "thirteen"}, {14, "fourteen"}, + {15, "fifteen"}, {16, "sixteen"}, {17, "seventeen"}, {18, "eighteen"}, {19, "nineteen"} +}; + +static const std::map<int, std::string> tens = { + {2, "twenty"}, {3, "thirty"}, {4, "forty"}, {5, "fifty"}, + {6, "sixty"}, {7, "seventy"}, {8, "eighty"}, {9, "ninety"} +}; + +// Convert a number less than 1000 to words +static std::string convert_less_than_thousand(int num) { + std::string result; + + if (num >= 100) { + result += ones.at(num / 100) + " hundred "; + num %= 100; + } + + if (num >= 20) { + result += tens.at(num / 10); + if (num % 10 > 0) { + result += "-" + ones.at(num % 10); + } + } else if (num > 0) { + result += ones.at(num); + } + + return result; +} + +static std::string number_to_words(const std::string & number_str) { + try { + size_t decimal_pos = number_str.find('.'); + std::string integer_part = number_str.substr(0, decimal_pos); + + int int_number = std::stoi(integer_part); + std::string result; + + if (int_number == 0) { + result = "zero"; + } else { + if (int_number >= 1000000000) { + int billions = int_number / 1000000000; + result += convert_less_than_thousand(billions) + " billion "; + int_number %= 1000000000; + } + + if (int_number >= 1000000) { + int millions = int_number / 1000000; + result += convert_less_than_thousand(millions) + " million "; + int_number %= 1000000; + } + + if (int_number >= 1000) { + int thousands = int_number / 1000; + result += convert_less_than_thousand(thousands) + " thousand "; + int_number %= 1000; + } + + if (int_number > 0) { + result += convert_less_than_thousand(int_number); + } + } + + // Handle decimal part + if (decimal_pos != std::string::npos) { + result += " point"; + std::string decimal_part = number_str.substr(decimal_pos + 1); + for (char digit : decimal_part) { + result += " " + ones.at(digit - '0'); + } + } + + return result; + } catch (const std::exception& e) { + // Skip if fails + return " "; + } +} + +static std::string replace_numbers_with_words(const std::string & input_text) { + std::regex number_pattern(R"(\d+(\.\d+)?)"); + std::string result; + auto it = std::sregex_iterator(input_text.begin(), input_text.end(), number_pattern); + auto end = std::sregex_iterator(); + + size_t last_pos = 0; + for (std::sregex_iterator i = it; i != end; ++i) { + const std::smatch& match = *i; + result.append(input_text, last_pos, match.position() - last_pos); + result.append(number_to_words(match.str())); + last_pos = match.position() + match.length(); + } + result.append(input_text, last_pos); + + return result; +} + +// Based on: https://github.com/edwko/OuteTTS/blob/a613e79c489d8256dd657ea9168d78de75895d82/outetts/version/v1/prompt_processor.py#L39 +static std::string process_text(const std::string & text, const outetts_version tts_version = OUTETTS_V0_2) { + + // For now I skipped text romanization as I am unsure how to handle + // uroman and MeCab implementations in C++ + // maybe something like https://github.com/anyascii/anyascii/ could work. + // currently only English would be supported in this function + + std::string processed_text = replace_numbers_with_words(text); + + std::transform(processed_text.begin(), processed_text.end(), + processed_text.begin(), ::tolower); + + std::regex special_chars(R"([-_/,\.\\])"); + processed_text = std::regex_replace(processed_text, special_chars, " "); + + std::regex non_alpha(R"([^a-z\s])"); + processed_text = std::regex_replace(processed_text, non_alpha, ""); + + std::regex multiple_spaces(R"(\s+)"); + processed_text = std::regex_replace(processed_text, multiple_spaces, " "); + + processed_text = std::regex_replace(processed_text, std::regex(R"(^\s+|\s+$)"), ""); + + /* + Replace spaces with the separator token same as in line 365 + + for (auto & c : prompt_user) { + if (c == ' ') { + prompt_clean += "<|text_sep|>"; + */ + std::string separator = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|text_sep|>"; + processed_text = std::regex_replace(processed_text, std::regex(R"(\s)"), separator); + + return processed_text; +} + +static void prompt_add(llama_tokens & prompt, llama_token token) { + prompt.push_back(token); +} + +static void prompt_add(llama_tokens & prompt, const llama_tokens & tokens) { + prompt.insert(prompt.end(), tokens.begin(), tokens.end()); +} + +static void prompt_add(llama_tokens & prompt, const llama_vocab * vocab, const std::string & txt, bool add_special, bool parse_special) { + auto tmp = common_tokenize(vocab, txt, add_special, parse_special); + prompt_add(prompt, tmp); +} + +static void prompt_init(llama_tokens & prompt, const llama_vocab * vocab) { + prompt.clear(); + + prompt_add(prompt, vocab, "<|im_start|>\n", true, true); +} + +static std::vector<llama_token> prepare_guide_tokens(const llama_vocab * vocab, const std::string & str, const outetts_version tts_version = OUTETTS_V0_2) { + const std::string& delimiter = (tts_version == OUTETTS_V0_3 ? "<|space|>" : "<|text_sep|>"); + + std::vector<llama_token> result; + size_t start = 0; + size_t end = str.find(delimiter); + + //first token is always a newline, as it was not previously added + result.push_back(common_tokenize(vocab, "\n", false, true)[0]); + + while (end != std::string::npos) { + std::string current_word = str.substr(start, end - start); + auto tmp = common_tokenize(vocab, current_word, false, true); + result.push_back(tmp[0]); + start = end + delimiter.length(); + end = str.find(delimiter, start); + } + + // Add the last part + std::string current_word = str.substr(start); + auto tmp = common_tokenize(vocab, current_word, false, true); + if (tmp.size() > 0) { + result.push_back(tmp[0]); + } + return result; +} + +static json speaker_from_file(const std::string & speaker_file) { + std::ifstream file(speaker_file); + if (!file) { + LOG_ERR("%s: Failed to open file '%s' for reading\n", __func__, speaker_file.c_str()); + return json(); + } + + json speaker = json::parse(file); + return speaker; +} + +static outetts_version get_tts_version(llama_model *model, json speaker = json::object()) { + if (speaker.contains("version")) { + std::string version = speaker["version"].get<std::string>(); + if (version == "0.2") { + return OUTETTS_V0_2; + } else if (version == "0.3") { + return OUTETTS_V0_3; + } else { + LOG_ERR("%s: Unsupported speaker version '%s'\n", __func__, version.c_str()); + } + } + + // Also could get version from model itself + const char *chat_template = llama_model_chat_template(model, nullptr); + if (chat_template && std::string(chat_template) == "outetts-0.3") { + return OUTETTS_V0_3; + } + + // Use 0.2 as the default version + return OUTETTS_V0_2; +} + +static std::string audio_text_from_speaker(json speaker, const outetts_version tts_version = OUTETTS_V0_2) { + std::string audio_text = "<|text_start|>"; + + if (tts_version == OUTETTS_V0_2 || tts_version == OUTETTS_V0_3) { + std::string separator = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|text_sep|>"; + for (const auto &word : speaker["words"]) { + audio_text += word["word"].get<std::string>() + separator; + } + } + + return audio_text; +} + +static std::string audio_data_from_speaker(json speaker, const outetts_version tts_version = OUTETTS_V0_2) { + std::string audio_data = "<|audio_start|>\n"; + + if (tts_version == OUTETTS_V0_2 || tts_version == OUTETTS_V0_3) { + std::string code_start = (tts_version == OUTETTS_V0_3) ? "" : "<|code_start|>"; + std::string code_end = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|code_end|>"; + for (const auto &word : speaker["words"]) { + std::string word_text = word["word"].get<std::string>(); + double duration = word["duration"].get<double>(); + std::vector<int> codes = word["codes"].get<std::vector<int>>(); + + // Create the audio output entry + std::ostringstream word_entry; + word_entry << word_text << "<|t_" << std::fixed << std::setprecision(2) + << duration << "|>" + code_start; + for (const auto &Code : codes) { + word_entry << "<|" << Code << "|>"; + } + word_entry << code_end << "\n"; + audio_data += word_entry.str(); + } + } + + return audio_data; +} + +int main(int argc, char ** argv) { + common_params params; + + params.out_file = "output.wav"; + params.prompt = ""; + + params.n_predict = 4096; + params.n_batch = 8192; + params.n_ctx = 8192; + + params.sampling.top_k = 4; + params.sampling.samplers = { COMMON_SAMPLER_TYPE_TOP_K, }; + + if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_TTS, print_usage)) { + return 1; + } + + const int n_parallel = params.n_parallel; + const int n_predict = params.n_predict; + + common_init(); + + // init LLM + + llama_backend_init(); + llama_numa_init(params.numa); + + llama_model * model_ttc = NULL; // text-to-codes + llama_model * model_cts = NULL; // codes-to-speech + + llama_context * ctx_ttc = NULL; + llama_context * ctx_cts = NULL; + + common_init_result llama_init_ttc = common_init_from_params(params); + + model_ttc = llama_init_ttc.model.get(); + ctx_ttc = llama_init_ttc.context.get(); + + if (model_ttc == nullptr || ctx_ttc == nullptr) { + return ENOENT; + } + + const llama_vocab * vocab = llama_model_get_vocab(model_ttc); + + params.model = params.vocoder.model; + params.embedding = true; + + common_init_result llama_init_cts = common_init_from_params(params); + + model_cts = llama_init_cts.model.get(); + ctx_cts = llama_init_cts.context.get(); + + if (model_cts == nullptr || ctx_cts == nullptr) { + return ENOENT; + } + + std::vector<common_sampler *> smpl(n_parallel); + for (int i = 0; i < n_parallel; ++i) { + params.sampling.no_perf = (i != 0); + params.sampling.seed = params.sampling.seed + 1; + + smpl[i] = common_sampler_init(model_ttc, params.sampling); + } + + LOG_INF("sampler seed: %u\n", common_sampler_get_seed(smpl[0])); + LOG_INF("sampler params: \n%s\n", params.sampling.print().c_str()); + LOG_INF("sampler chain: %s\n", common_sampler_print(smpl[0]).c_str()); + + LOG_INF("%s: loading done\n", __func__); + + const auto t_main_start = ggml_time_us(); + + std::vector<llama_token> codes; + std::vector<llama_token> guide_tokens; + + // the default speaker profile is from: https://github.com/edwko/OuteTTS/blob/main/outetts/version/v1/default_speakers/en_male_1.json + std::string audio_text = "<|text_start|>the<|text_sep|>overall<|text_sep|>package<|text_sep|>from<|text_sep|>just<|text_sep|>two<|text_sep|>people<|text_sep|>is<|text_sep|>pretty<|text_sep|>remarkable<|text_sep|>sure<|text_sep|>i<|text_sep|>have<|text_sep|>some<|text_sep|>critiques<|text_sep|>about<|text_sep|>some<|text_sep|>of<|text_sep|>the<|text_sep|>gameplay<|text_sep|>aspects<|text_sep|>but<|text_sep|>its<|text_sep|>still<|text_sep|>really<|text_sep|>enjoyable<|text_sep|>and<|text_sep|>it<|text_sep|>looks<|text_sep|>lovely<|text_sep|>"; + std::string audio_data = R"(<|audio_start|> +the<|t_0.08|><|code_start|><|257|><|740|><|636|><|913|><|788|><|1703|><|code_end|> +overall<|t_0.36|><|code_start|><|127|><|201|><|191|><|774|><|700|><|532|><|1056|><|557|><|798|><|298|><|1741|><|747|><|1662|><|1617|><|1702|><|1527|><|368|><|1588|><|1049|><|1008|><|1625|><|747|><|1576|><|728|><|1019|><|1696|><|1765|><|code_end|> +package<|t_0.56|><|code_start|><|935|><|584|><|1319|><|627|><|1016|><|1491|><|1344|><|1117|><|1526|><|1040|><|239|><|1435|><|951|><|498|><|723|><|1180|><|535|><|789|><|1649|><|1637|><|78|><|465|><|1668|><|901|><|595|><|1675|><|117|><|1009|><|1667|><|320|><|840|><|79|><|507|><|1762|><|1508|><|1228|><|1768|><|802|><|1450|><|1457|><|232|><|639|><|code_end|> +from<|t_0.19|><|code_start|><|604|><|782|><|1682|><|872|><|1532|><|1600|><|1036|><|1761|><|647|><|1554|><|1371|><|653|><|1595|><|950|><|code_end|> +just<|t_0.25|><|code_start|><|1782|><|1670|><|317|><|786|><|1748|><|631|><|599|><|1155|><|1364|><|1524|><|36|><|1591|><|889|><|1535|><|541|><|440|><|1532|><|50|><|870|><|code_end|> +two<|t_0.24|><|code_start|><|1681|><|1510|><|673|><|799|><|805|><|1342|><|330|><|519|><|62|><|640|><|1138|><|565|><|1552|><|1497|><|1552|><|572|><|1715|><|1732|><|code_end|> +people<|t_0.39|><|code_start|><|593|><|274|><|136|><|740|><|691|><|633|><|1484|><|1061|><|1138|><|1485|><|344|><|428|><|397|><|1562|><|645|><|917|><|1035|><|1449|><|1669|><|487|><|442|><|1484|><|1329|><|1832|><|1704|><|600|><|761|><|653|><|269|><|code_end|> +is<|t_0.16|><|code_start|><|566|><|583|><|1755|><|646|><|1337|><|709|><|802|><|1008|><|485|><|1583|><|652|><|10|><|code_end|> +pretty<|t_0.32|><|code_start|><|1818|><|1747|><|692|><|733|><|1010|><|534|><|406|><|1697|><|1053|><|1521|><|1355|><|1274|><|816|><|1398|><|211|><|1218|><|817|><|1472|><|1703|><|686|><|13|><|822|><|445|><|1068|><|code_end|> +remarkable<|t_0.68|><|code_start|><|230|><|1048|><|1705|><|355|><|706|><|1149|><|1535|><|1787|><|1356|><|1396|><|835|><|1583|><|486|><|1249|><|286|><|937|><|1076|><|1150|><|614|><|42|><|1058|><|705|><|681|><|798|><|934|><|490|><|514|><|1399|><|572|><|1446|><|1703|><|1346|><|1040|><|1426|><|1304|><|664|><|171|><|1530|><|625|><|64|><|1708|><|1830|><|1030|><|443|><|1509|><|1063|><|1605|><|1785|><|721|><|1440|><|923|><|code_end|> +sure<|t_0.36|><|code_start|><|792|><|1780|><|923|><|1640|><|265|><|261|><|1525|><|567|><|1491|><|1250|><|1730|><|362|><|919|><|1766|><|543|><|1|><|333|><|113|><|970|><|252|><|1606|><|133|><|302|><|1810|><|1046|><|1190|><|1675|><|code_end|> +i<|t_0.08|><|code_start|><|123|><|439|><|1074|><|705|><|1799|><|637|><|code_end|> +have<|t_0.16|><|code_start|><|1509|><|599|><|518|><|1170|><|552|><|1029|><|1267|><|864|><|419|><|143|><|1061|><|0|><|code_end|> +some<|t_0.16|><|code_start|><|619|><|400|><|1270|><|62|><|1370|><|1832|><|917|><|1661|><|167|><|269|><|1366|><|1508|><|code_end|> +critiques<|t_0.60|><|code_start|><|559|><|584|><|1163|><|1129|><|1313|><|1728|><|721|><|1146|><|1093|><|577|><|928|><|27|><|630|><|1080|><|1346|><|1337|><|320|><|1382|><|1175|><|1682|><|1556|><|990|><|1683|><|860|><|1721|><|110|><|786|><|376|><|1085|><|756|><|1523|><|234|><|1334|><|1506|><|1578|><|659|><|612|><|1108|><|1466|><|1647|><|308|><|1470|><|746|><|556|><|1061|><|code_end|> +about<|t_0.29|><|code_start|><|26|><|1649|><|545|><|1367|><|1263|><|1728|><|450|><|859|><|1434|><|497|><|1220|><|1285|><|179|><|755|><|1154|><|779|><|179|><|1229|><|1213|><|922|><|1774|><|1408|><|code_end|> +some<|t_0.23|><|code_start|><|986|><|28|><|1649|><|778|><|858|><|1519|><|1|><|18|><|26|><|1042|><|1174|><|1309|><|1499|><|1712|><|1692|><|1516|><|1574|><|code_end|> +of<|t_0.07|><|code_start|><|197|><|716|><|1039|><|1662|><|64|><|code_end|> +the<|t_0.08|><|code_start|><|1811|><|1568|><|569|><|886|><|1025|><|1374|><|code_end|> +gameplay<|t_0.48|><|code_start|><|1269|><|1092|><|933|><|1362|><|1762|><|1700|><|1675|><|215|><|781|><|1086|><|461|><|838|><|1022|><|759|><|649|><|1416|><|1004|><|551|><|909|><|787|><|343|><|830|><|1391|><|1040|><|1622|><|1779|><|1360|><|1231|><|1187|><|1317|><|76|><|997|><|989|><|978|><|737|><|189|><|code_end|> +aspects<|t_0.56|><|code_start|><|1423|><|797|><|1316|><|1222|><|147|><|719|><|1347|><|386|><|1390|><|1558|><|154|><|440|><|634|><|592|><|1097|><|1718|><|712|><|763|><|1118|><|1721|><|1311|><|868|><|580|><|362|><|1435|><|868|><|247|><|221|><|886|><|1145|><|1274|><|1284|><|457|><|1043|><|1459|><|1818|><|62|><|599|><|1035|><|62|><|1649|><|778|><|code_end|> +but<|t_0.20|><|code_start|><|780|><|1825|><|1681|><|1007|><|861|><|710|><|702|><|939|><|1669|><|1491|><|613|><|1739|><|823|><|1469|><|648|><|code_end|> +its<|t_0.09|><|code_start|><|92|><|688|><|1623|><|962|><|1670|><|527|><|599|><|code_end|> +still<|t_0.27|><|code_start|><|636|><|10|><|1217|><|344|><|713|><|957|><|823|><|154|><|1649|><|1286|><|508|><|214|><|1760|><|1250|><|456|><|1352|><|1368|><|921|><|615|><|5|><|code_end|> +really<|t_0.36|><|code_start|><|55|><|420|><|1008|><|1659|><|27|><|644|><|1266|><|617|><|761|><|1712|><|109|><|1465|><|1587|><|503|><|1541|><|619|><|197|><|1019|><|817|><|269|><|377|><|362|><|1381|><|507|><|1488|><|4|><|1695|><|code_end|> +enjoyable<|t_0.49|><|code_start|><|678|><|501|><|864|><|319|><|288|><|1472|><|1341|><|686|><|562|><|1463|><|619|><|1563|><|471|><|911|><|730|><|1811|><|1006|><|520|><|861|><|1274|><|125|><|1431|><|638|><|621|><|153|><|876|><|1770|><|437|><|987|><|1653|><|1109|><|898|><|1285|><|80|><|593|><|1709|><|843|><|code_end|> +and<|t_0.15|><|code_start|><|1285|><|987|><|303|><|1037|><|730|><|1164|><|502|><|120|><|1737|><|1655|><|1318|><|code_end|> +it<|t_0.09|><|code_start|><|848|><|1366|><|395|><|1601|><|1513|><|593|><|1302|><|code_end|> +looks<|t_0.27|><|code_start|><|1281|><|1266|><|1755|><|572|><|248|><|1751|><|1257|><|695|><|1380|><|457|><|659|><|585|><|1315|><|1105|><|1776|><|736|><|24|><|736|><|654|><|1027|><|code_end|> +lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|1481|><|1721|><|1123|><|438|><|1246|><|1251|><|795|><|659|><|1381|><|1658|><|217|><|1772|><|562|><|952|><|107|><|1129|><|1112|><|467|><|550|><|1079|><|840|><|1615|><|1469|><|1380|><|168|><|917|><|836|><|1827|><|437|><|583|><|67|><|595|><|1087|><|1646|><|1493|><|1677|><|code_end|>)"; + + // audio data for 0.3 version + outetts_version tts_version = get_tts_version(model_ttc); + if (tts_version == OUTETTS_V0_3) { + audio_text = std::regex_replace(audio_text, std::regex(R"(<\|text_sep\|>)"), "<|space|>"); + audio_data = std::regex_replace(audio_data, std::regex(R"(<\|code_start\|>)"), ""); + audio_data = std::regex_replace(audio_data, std::regex(R"(<\|code_end\|>)"), "<|space|>"); + } + + // load speaker if given + if (!params.vocoder.speaker_file.empty()) { + LOG_INF("%s: loading speaker ..\n", __func__); + json speaker = speaker_from_file(params.vocoder.speaker_file); + if (speaker.empty()) { + LOG_ERR("%s: Failed to load speaker file '%s'\n", __func__, params.vocoder.speaker_file.c_str()); + return 1; + } + audio_text = audio_text_from_speaker(speaker, tts_version); + audio_data = audio_data_from_speaker(speaker, tts_version); + } + + // process prompt and generate voice codes + { + LOG_INF("%s: constructing prompt ..\n", __func__); + + std::vector<llama_token> prompt_inp; + + prompt_init(prompt_inp, vocab); + + prompt_add(prompt_inp, vocab, audio_text, false, true); + + // convert the input text into the necessary format expected by OuteTTS + { + std::string prompt_clean = process_text(params.prompt, tts_version); + if (params.vocoder.use_guide_tokens) { + guide_tokens = prepare_guide_tokens(vocab, prompt_clean, tts_version); + } + + LOG_INF("%s: prompt: '%s'\n", __func__, prompt_clean.c_str()); + + prompt_add(prompt_inp, vocab, prompt_clean, false, true); + } + + prompt_add(prompt_inp, vocab, "<|text_end|>\n", false, true); + + if (!params.vocoder.speaker_file.empty()) { + prompt_add(prompt_inp, vocab, audio_data, false, true); + } else { + // disabled to save time on tokenizing each time +#if 1 + const std::string voice_data = audio_data; + + auto tmp = common_tokenize(vocab, voice_data, false, true); + + std::ostringstream tokens_oss; + for (size_t i = 0; i < tmp.size(); ++i) { + tokens_oss << tmp[i] << ", "; + } + LOG_INF("\n\n%s: llama tokens: %s\n\n", __func__, tokens_oss.str().c_str()); + + prompt_add(prompt_inp, tmp); +#else + prompt_add(prompt_inp, llama_tokens { + 151667, 198, 1782, 155780, 151669, 151929, 152412, 152308, 152585, + 152460, 153375, 151670, 198, 74455, 155808, 151669, 151799, + 151873, 151863, 152446, 152372, 152204, 152728, 152229, 152470, + 151970, 153413, 152419, 153334, 153289, 153374, 153199, 152040, + 153260, 152721, 152680, 153297, 152419, 153248, 152400, 152691, + 153368, 153437, 151670, 198, 1722, 155828, 151669, 152607, + 152256, 152991, 152299, 152688, 153163, 153016, 152789, 153198, + 152712, 151911, 153107, 152623, 152170, 152395, 152852, 152207, + 152461, 153321, 153309, 151750, 152137, 153340, 152573, 152267, + 153347, 151789, 152681, 153339, 151992, 152512, 151751, 152179, + 153434, 153180, 152900, 153440, 152474, 153122, 153129, 151904, + 152311, 151670, 198, 1499, 155791, 151669, 152276, 152454, + 153354, 152544, 153204, 153272, 152708, 153433, 152319, 153226, + 153043, 152325, 153267, 152622, 151670, 198, 4250, 155797, + 151669, 153454, 153342, 151989, 152458, 153420, 152303, 152271, + 152827, 153036, 153196, 151708, 153263, 152561, 153207, 152213, + 152112, 153204, 151722, 152542, 151670, 198, 19789, 155796, + 151669, 153353, 153182, 152345, 152471, 152477, 153014, 152002, + 152191, 151734, 152312, 152810, 152237, 153224, 153169, 153224, + 152244, 153387, 153404, 151670, 198, 16069, 155811, 151669, + 152265, 151946, 151808, 152412, 152363, 152305, 153156, 152733, + 152810, 153157, 152016, 152100, 152069, 153234, 152317, 152589, + 152707, 153121, 153341, 152159, 152114, 153156, 153001, 153504, + 153376, 152272, 152433, 152325, 151941, 151670, 198, 285, + 155788, 151669, 152238, 152255, 153427, 152318, 153009, 152381, + 152474, 152680, 152157, 153255, 152324, 151682, 151670, 198, + 32955, 155804, 151669, 153490, 153419, 152364, 152405, 152682, + 152206, 152078, 153369, 152725, 153193, 153027, 152946, 152488, + 153070, 151883, 152890, 152489, 153144, 153375, 152358, 151685, + 152494, 152117, 152740, 151670, 198, 37448, 480, 155840, 151669, + 151902, 152720, 153377, 152027, 152378, 152821, 153207, 153459, + 153028, 153068, 152507, 153255, 152158, 152921, 151958, 152609, + 152748, 152822, 152286, 151714, 152730, 152377, 152353, 152470, + 152606, 152162, 152186, 153071, 152244, 153118, 153375, 153018, + 152712, 153098, 152976, 152336, 151843, 153202, 152297, 151736, + 153380, 153502, 152702, 152115, 153181, 152735, 153277, 153457, + 152393, 153112, 152595, 151670, 198, 19098, 155808, 151669, + 152464, 153452, 152595, 153312, 151937, 151933, 153197, 152239, + 153163, 152922, 153402, 152034, 152591, 153438, 152215, 151673, + 152005, 151785, 152642, 151924, 153278, 151805, 151974, 153482, + 152718, 152862, 153347, 151670, 198, 72, 155780, 151669, 151795, + 152111, 152746, 152377, 153471, 152309, 151670, 198, 19016, + 155788, 151669, 153181, 152271, 152190, 152842, 152224, 152701, + 152939, 152536, 152091, 151815, 152733, 151672, 151670, 198, + 14689, 155788, 151669, 152291, 152072, 152942, 151734, 153042, + 153504, 152589, 153333, 151839, 151941, 153038, 153180, 151670, + 198, 36996, 8303, 155832, 151669, 152231, 152256, 152835, + 152801, 152985, 153400, 152393, 152818, 152765, 152249, 152600, + 151699, 152302, 152752, 153018, 153009, 151992, 153054, 152847, + 153354, 153228, 152662, 153355, 152532, 153393, 151782, 152458, + 152048, 152757, 152428, 153195, 151906, 153006, 153178, 153250, + 152331, 152284, 152780, 153138, 153319, 151980, 153142, 152418, + 152228, 152733, 151670, 198, 9096, 155801, 151669, 151698, + 153321, 152217, 153039, 152935, 153400, 152122, 152531, 153106, + 152169, 152892, 152957, 151851, 152427, 152826, 152451, 151851, + 152901, 152885, 152594, 153446, 153080, 151670, 198, 14689, + 155795, 151669, 152658, 151700, 153321, 152450, 152530, 153191, + 151673, 151690, 151698, 152714, 152846, 152981, 153171, 153384, + 153364, 153188, 153246, 151670, 198, 1055, 155779, 151669, + 151869, 152388, 152711, 153334, 151736, 151670, 198, 1782, + 155780, 151669, 153483, 153240, 152241, 152558, 152697, 153046, + 151670, 198, 5804, 1363, 155820, 151669, 152941, 152764, 152605, + 153034, 153434, 153372, 153347, 151887, 152453, 152758, 152133, + 152510, 152694, 152431, 152321, 153088, 152676, 152223, 152581, + 152459, 152015, 152502, 153063, 152712, 153294, 153451, 153032, + 152903, 152859, 152989, 151748, 152669, 152661, 152650, 152409, + 151861, 151670, 198, 300, 7973, 155828, 151669, 153095, 152469, + 152988, 152894, 151819, 152391, 153019, 152058, 153062, 153230, + 151826, 152112, 152306, 152264, 152769, 153390, 152384, 152435, + 152790, 153393, 152983, 152540, 152252, 152034, 153107, 152540, + 151919, 151893, 152558, 152817, 152946, 152956, 152129, 152715, + 153131, 153490, 151734, 152271, 152707, 151734, 153321, 152450, + 151670, 198, 8088, 155792, 151669, 152452, 153497, 153353, + 152679, 152533, 152382, 152374, 152611, 153341, 153163, 152285, + 153411, 152495, 153141, 152320, 151670, 198, 1199, 155781, + 151669, 151764, 152360, 153295, 152634, 153342, 152199, 152271, + 151670, 198, 43366, 155799, 151669, 152308, 151682, 152889, + 152016, 152385, 152629, 152495, 151826, 153321, 152958, 152180, + 151886, 153432, 152922, 152128, 153024, 153040, 152593, 152287, + 151677, 151670, 198, 53660, 155808, 151669, 151727, 152092, + 152680, 153331, 151699, 152316, 152938, 152289, 152433, 153384, + 151781, 153137, 153259, 152175, 153213, 152291, 151869, 152691, + 152489, 151941, 152049, 152034, 153053, 152179, 153160, 151676, + 153367, 151670, 198, 268, 4123, 480, 155821, 151669, 152350, + 152173, 152536, 151991, 151960, 153144, 153013, 152358, 152234, + 153135, 152291, 153235, 152143, 152583, 152402, 153483, 152678, + 152192, 152533, 152946, 151797, 153103, 152310, 152293, 151825, + 152548, 153442, 152109, 152659, 153325, 152781, 152570, 152957, + 151752, 152265, 153381, 152515, 151670, 198, 437, 155787, + 151669, 152957, 152659, 151975, 152709, 152402, 152836, 152174, + 151792, 153409, 153327, 152990, 151670, 198, 275, 155781, + 151669, 152520, 153038, 152067, 153273, 153185, 152265, 152974, + 151670, 198, 94273, 155799, 151669, 152953, 152938, 153427, + 152244, 151920, 153423, 152929, 152367, 153052, 152129, 152331, + 152257, 152987, 152777, 153448, 152408, 151696, 152408, 152326, + 152699, 151670, 198, 385, 16239, 155828, 151669, 152306, 152268, + 153438, 153228, 152978, 152957, 153153, 153393, 152795, 152110, + 152918, 152923, 152467, 152331, 153053, 153330, 151889, 153444, + 152234, 152624, 151779, 152801, 152784, 152139, 152222, 152751, + 152512, 153287, 153141, 153052, 151840, 152589, 152508, 153499, + 152109, 152255, 151739, 152267, 152759, 153318, 153165, 153349, + 151670,}); +#endif + } + + // print the prompt token-by-token + + LOG("\n"); + + for (auto id : prompt_inp) { + LOG("%s", common_token_to_piece(ctx_ttc, id).c_str()); + } + + LOG_INF("%s: prompt size: %d\n", __func__, (int) prompt_inp.size()); + + LOG("\n"); + + // create a llama_batch + // we use this object to submit token data for decoding + llama_batch batch = llama_batch_init(std::max(prompt_inp.size(), (size_t) n_parallel), 0, n_parallel); + + std::vector<llama_seq_id> seq_ids(n_parallel, 0); + for (int32_t i = 0; i < n_parallel; ++i) { + seq_ids[i] = i; + } + + // evaluate the initial prompt + for (size_t i = 0; i < prompt_inp.size(); ++i) { + common_batch_add(batch, prompt_inp[i], i, seq_ids, false); + } + GGML_ASSERT(batch.n_tokens == (int) prompt_inp.size()); + + // llama_decode will output logits only for the last token of the prompt + batch.logits[batch.n_tokens - 1] = true; + + if (llama_decode(ctx_ttc, batch) != 0) { + LOG_ERR("%s: llama_decode() failed\n", __func__); + return 1; + } + + if (n_parallel > 1) { + LOG_INF("\n\n%s: generating %d sequences ...\n", __func__, n_parallel); + } + + llama_synchronize(ctx_ttc); + + LOG_INF("%s: time for prompt: %.3f ms\n\n", __func__, (ggml_time_us() - t_main_start) / 1000.0f); + + const auto t_dec_start = ggml_time_us(); + + // main loop + + // remember the batch index of the last token for each parallel sequence + // we need this to determine which logits to sample from + std::vector<int32_t> i_batch(n_parallel, batch.n_tokens - 1); + + int n_past = batch.n_tokens; + int n_decode = 0; + + bool next_token_uses_guide_token = true; + + while (n_decode <= n_predict) { + // prepare the next batch + common_batch_clear(batch); + + // sample the next token for each parallel sequence / stream + for (int32_t i = 0; i < n_parallel; ++i) { + if (i_batch[i] < 0) { + // the stream has already finished + continue; + } + + llama_token new_token_id = common_sampler_sample(smpl[i], ctx_ttc, i_batch[i]); + + //guide tokens help prevent hallucinations by forcing the TTS to use the correct word + if (!guide_tokens.empty() && next_token_uses_guide_token && !llama_vocab_is_control(vocab, new_token_id) && !llama_vocab_is_eog(vocab, new_token_id)) { + llama_token guide_token = guide_tokens[0]; + guide_tokens.erase(guide_tokens.begin()); + new_token_id = guide_token; //ensure correct word fragment is used + } + + //this is the token id that always precedes a new word + next_token_uses_guide_token = (new_token_id == 198); + + common_sampler_accept(smpl[i], new_token_id, true); + + codes.push_back(new_token_id); + + const auto * cands = common_sampler_get_candidates(smpl[i]); + + // is it an end of generation? -> mark the stream as finished + if (llama_vocab_is_eog(vocab, new_token_id) || n_decode == n_predict) { + std::string reason; + if (llama_vocab_is_eog(vocab, new_token_id)) { + reason = "eos"; + } else { + reason = "n_predict"; + } + + i_batch[i] = -1; + + LOG("\n"); + if (n_parallel > 1) { + LOG_CNT("\n"); + LOG_INF("%s: stream %d finished at n_past = %d, reason = '%s'\n", __func__, i, n_past, reason.c_str()); + } + + continue; + } + + { + const float p = cands->data[cands->selected].p; + + const int col = std::max(0, std::min((int) k_colors.size() - 1, (int) ((3*p)*float(k_colors.size())))); + + LOG_CNT("%s%d%s", k_colors[col].c_str(), i, "\033[0m"); + //LOG_CNT("%d", i); + } + + i_batch[i] = batch.n_tokens; + + // push this new token for next evaluation + common_batch_add(batch, new_token_id, n_past, { i }, true); + } + + // all streams are finished + if (batch.n_tokens == 0) { + break; + } + + n_decode += 1; + n_past += 1; + + // evaluate the current batch with the transformer model + if (llama_decode(ctx_ttc, batch)) { + LOG_ERR("%s : failed to eval, return code %d\n", __func__, 1); + return 1; + } + } + + llama_batch_free(batch); + + LOG("\n"); + LOG_INF("%s: time for decoder: %.3f ms\n", __func__, (ggml_time_us() - t_dec_start) / 1000.0f); + } + + common_perf_print(ctx_ttc, smpl[0]); + + //std::vector<llama_token> codes = {198, 88225, 155856, 151669, 152205, + // 153064, 152537, 153421, 153209, 152524, 151689, 152993, 152438, 152695, + // 153091, 152945, 152829, 152534, 152934, 153020, 151997, 152263, 153010, + // 153146, 152399, 153208, 152496, 151793, 152848, 152263, 152571, 153286, + // 152227, 153300, 152934, 152263, 153208, 152263, 152965, 152430, 152296, + // 153146, 152920, 152376, 152556, 153363, 151775, 152044, 152972, 152690, + // 153379, 152368, 152233, 153422, 152490, 151996, 152022, 151694, 152061, + // 153238, 152539, 153356, 152640, 153021, 153123, 151962, 153094, 151670, + // 198, 20339, 13189, 155824, 151669, 152070, 152007, 152910, 151683, + // 152000, 152373, 152760, 152046, 151735, 152334, 152394, 153073, 152908, + // 151856, 151953, 153247, 153293, 151903, 153480, 153168, 152478, 153359, + // 153429, 151905, 151678, 152567, 152411, 152165, 152556, 153075, 153424, + // 151993, 152999, 153078, 152151, 152088, 153389, 152484, 151874, 151670, + // 198, 285, 155784, 151669, 152226, 152126, 152638, 153215, 151729, + // 152959, 153479, 153059, 151838, 151670, 198, 1782, 155783, 151669, + // 153288, 153055, 153314, 152497, 152962, 152741, 152076, 153253, 151670, + // 198, 471, 16488, 155825, 151669, 152060, 152916, 151893, 153469, 152501, + // 152080, 152743, 151932, 153161, 152096, 152761, 152698, 153401, 153242, + // 153336, 152441, 152838, 153467, 152706, 153496, 153310, 152422, 153360, + // 153115, 152763, 151998, 152373, 153450, 152554, 151968, 153323, 152055, + // 152468, 153111, 153358, 152813, 152010, 151770, 152823, 152960, 151670, + // 198, 22627, 155823, 151669, 152814, 152366, 153484, 152931, 153441, + // 152164, 152877, 152915, 153463, 151692, 152911, 152747, 152776, 151831, + // 153449, 151882, 152975, 152031, 152513, 153150, 152448, 152667, 153133, + // 153189, 152619, 153466, 152054, 152106, 153119, 152277, 152439, 153109, + // 152997, 152141, 153154, 153256, 153311, 151922, 151670, 198, 1055, + // 155781, 151669, 152633, 151850, 153060, 153270, 152560, 153348, 152729, + // 151670, 198, 25312, 155803, 151669, 152521, 153403, 152561, 153337, + // 153383, 152199, 153493, 153326, 151830, 152254, 152248, 152349, 152153, + // 153007, 151823, 153037, 152575, 152457, 152406, 152592, 153116, 153365, + // 153456, 151670, 198, 88225, 155817, 151669, 153271, 151925, 152218, + // 152418, 152253, 153140, 151903, 153151, 152626, 152338, 152647, 153464, + // 152785, 152768, 151711, 152037, 152033, 151804, 152216, 151701, 151855, + // 152348, 152995, 152955, 152905, 152342, 152340, 153391, 153453, 152418, + // 153415, 151990, 153083, 152884, 151670, 198, 151668, 198, 151645}; + + { + const std::string inp_txt = common_detokenize(ctx_ttc, codes, true); + + LOG("\n"); + LOG_INF("codes: '%s'\n", inp_txt.c_str()); + LOG_INF("%s: codes size: %d\n", __func__, (int) codes.size()); + } + + // remove all non-audio tokens (i.e. < 151672 || > 155772) + codes.erase(std::remove_if(codes.begin(), codes.end(), [](llama_token t) { return t < 151672 || t > 155772; }), codes.end()); + + { + const std::string inp_txt = common_detokenize(ctx_ttc, codes, true); + LOG_INF("codes audio: '%s'\n", inp_txt.c_str()); + LOG_INF("%s: codes audio size: %d\n", __func__, (int) codes.size()); + } + + for (auto & token : codes) { + token -= 151672; + } + + const auto t_voc_start = ggml_time_us(); + + const int n_codes = codes.size(); + + llama_batch batch = llama_batch_init(n_codes, 0, 1); + + for (size_t i = 0; i < codes.size(); ++i) { + common_batch_add(batch, codes[i], i, { 0 }, true); // TODO: all logits? + } + GGML_ASSERT(batch.n_tokens == n_codes); + + if (llama_decode(ctx_cts, batch) != 0) { + LOG_ERR("%s: llama_decode() failed\n", __func__); + return 1; + } + + llama_synchronize(ctx_cts); + + LOG_INF("%s: time for vocoder: %.3f ms\n", __func__, (ggml_time_us() - t_voc_start) / 1000.0f); + + const auto t_spec_start = ggml_time_us(); + +#if 1 + // spectral operations + const int n_embd = llama_model_n_embd(model_cts); + const float * embd = llama_get_embeddings(ctx_cts); + + auto audio = embd_to_audio(embd, n_codes, n_embd, params.cpuparams.n_threads); + +#else + // read the spectrogram from a file for debugging purposes + std::vector<float> audio; + { + std::ifstream fin("out.bin", std::ios::binary); + if (!fin) { + LOG_ERR("%s: failed to open file '%s'\n", __func__, "out.bin"); + return 1; + } + + std::vector<float> embd; + + int n_codes; + int n_embd; + + fin.read(reinterpret_cast<char *>(&n_codes), sizeof(int)); + fin.read(reinterpret_cast<char *>(&n_embd), sizeof(int)); + + embd.resize(n_codes * n_embd); + fin.read(reinterpret_cast<char *>(embd.data()), n_codes * n_embd * sizeof(float)); + fin.close(); + + LOG_INF("%s: n_codes: %d, n_embd: %d\n", __func__, n_codes, n_embd); + + audio = embd_to_audio(embd.data(), n_codes, n_embd, params.cpuparams.n_threads); + } +#endif + + const int n_sr = 24000; // sampling rate + + // zero out first 0.25 seconds + for (int i = 0; i < 24000/4; ++i) { + audio[i] = 0.0f; + } + + LOG_INF("%s: time for spectral ops: %.3f ms\n", __func__, (ggml_time_us() - t_spec_start) / 1000.0f); + LOG_INF("%s: total time: %.3f ms\n", __func__, (ggml_time_us() - t_main_start) / 1000.0f); + + int retval = 0; + + if (save_wav16(params.out_file, audio, n_sr)) { + LOG_INF("%s: audio written to file '%s'\n", __func__, params.out_file.c_str()); + } else { + retval = ENOENT; + } + + llama_backend_free(); + + return retval; +}