Function get_embeddings

openai_api_demo/api_server.py:179–212

(request: EmbeddingRequest)

@app.post("/v1/embeddings", response_model=EmbeddingResponse)
async def get_embeddings(request: EmbeddingRequest):
    if isinstance(request.input, str):
        embeddings = [embedding_model.encode(request.input)]
    else:
        embeddings = [embedding_model.encode(text) for text in request.input]
    embeddings = [embedding.tolist() for embedding in embeddings]

    def num_tokens_from_string(string: str) -> int:
        """
        Returns the number of tokens in a text string.
        use cl100k_base tokenizer
        """
        encoding = tiktoken.get_encoding('cl100k_base')
        num_tokens = len(encoding.encode(string))
        return num_tokens

    response = {
        "data": [
            {
                "object": "embedding",
                "embedding": embedding,
                "index": index
            }
            for index, embedding in enumerate(embeddings)
        ],
        "model": request.model,
        "object": "list",
        "usage": CompletionUsage(
            prompt_tokens=sum(len(text.split()) for text in request.input),
            completion_tokens=0,
            total_tokens=sum(num_tokens_from_string(text) for text in request.input),
        )
    }
    return response


@app.get("/v1/models", response_model=ModelList)