[New Feature] Add new route for dllama api for embeding models

[testing0mon21]

std::vector<Route> routes = {
    {
        "/v1/chat/completions",
        HttpMethod::METHOD_POST,
        std::bind(&handleCompletionsRequest, std::placeholders::_1, &api)
    },
    {
        "/v1/models",
        HttpMethod::METHOD_GET,
        std::bind(&handleModelsRequest, std::placeholders::_1)
    }
};

in ddlama api at master branch we have only 2 routes /v1/chat/completions and /v1/models but some model looks like llama3:8b has embedding functionality. Can add you add new route for /api/embeddings ?

[testing0mon21]

@b4rtaz what do you think about new route?

[testing0mon21]

i mean this for ddlama api

Generate Embeddings

POST /api/embeddings

Generate embeddings from a model

[testing0mon21]

i hope that i explain) @b4rtaz

[testing0mon21]

what do you think about this revision or should I explain in more detail? @b4rtaz

[b4rtaz]

Hello @testing0mon21 I'm not too familiar with embedding, but if I see correctly, llama.cpp supports it. This is not a priority for me, but contributions are welcome.