common : add default embeddings presets (#11677)

* common : add default embeddings presets

This commit adds default embeddings presets for the following models:
- bge-small-en-v1.5
- e5-small-v2
- gte-small

These can be used with llama-embedding and llama-server.

For example, with llama-embedding:
```console
./build/bin/llama-embedding --embd-gte-small-default -p "Hello, how are you?"
```

And with llama-server:
```console
./build/bin/llama-server --embd-gte-small-default
```
And the embeddings endpoint can then be called with a POST request:
```console
curl --request POST \
    --url http://localhost:8080/embeddings \
    --header "Content-Type: application/json" \
    --data '{"input": "Hello, how are you?"}'
```

I'm not sure if these are the most common embedding models but hopefully
this can be a good starting point for discussion and further
improvements.

Refs: https://github.com/ggerganov/llama.cpp/issues/10932

diff --git a/common/arg.cpp b/common/arg.cpp
index 76b8988819cda0f169d4e5fba9597be5783404c8..152f671ab738e2c2b56a95951dc8b7a5d1d9eacb 100644 (file)
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -2324,5 +2324,47 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_examples({LLAMA_EXAMPLE_TTS}));
 
+    add_opt(common_arg(
+        {"--embd-bge-small-en-default"},
+        string_format("use default bge-small-en-v1.5 model (note: can download weights from the internet)"),
+        [](common_params & params) {
+            params.hf_repo = "ggml-org/bge-small-en-v1.5-Q8_0-GGUF";
+            params.hf_file = "bge-small-en-v1.5-q8_0.gguf";
+            params.pooling_type = LLAMA_POOLING_TYPE_NONE;
+            params.embd_normalize = 2;
+            params.n_ctx = 512;
+            params.verbose_prompt = true;
+            params.embedding = true;
+        }
+    ).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER}));
+
+    add_opt(common_arg(
+        {"--embd-e5-small-en-default"},
+        string_format("use default e5-small-v2 model (note: can download weights from the internet)"),
+        [](common_params & params) {
+            params.hf_repo = "ggml-org/e5-small-v2-Q8_0-GGUF";
+            params.hf_file = "e5-small-v2-q8_0.gguf";
+            params.pooling_type = LLAMA_POOLING_TYPE_NONE;
+            params.embd_normalize = 2;
+            params.n_ctx = 512;
+            params.verbose_prompt = true;
+            params.embedding = true;
+        }
+    ).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER}));
+
+    add_opt(common_arg(
+        {"--embd-gte-small-default"},
+        string_format("use default gte-small model (note: can download weights from the internet)"),
+        [](common_params & params) {
+            params.hf_repo = "ggml-org/gte-small-Q8_0-GGUF";
+            params.hf_file = "gte-small-q8_0.gguf";
+            params.pooling_type = LLAMA_POOLING_TYPE_NONE;
+            params.embd_normalize = 2;
+            params.n_ctx = 512;
+            params.verbose_prompt = true;
+            params.embedding = true;
+        }
+    ).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER}));
+
     return ctx_arg;
 }