ray.serve.llm.LLMRouter.embeddings#

async LLMRouter.embeddings(body: EmbeddingCompletionRequest | EmbeddingChatRequest, request: fastapi.Request) starlette.responses.Response#

Create embeddings for the provided input.

Parameters:
  • body – The embedding request.

  • request – The raw FastAPI request object.

Returns:

A response object with embeddings.