ray.serve.llm.LLMServer.transcriptions#

async LLMServer.transcriptions(request: TranscriptionRequest, raw_request_info: RawRequestInfo | None = None) → AsyncGenerator[List[str | ErrorResponse] | TranscriptionResponse, None][source]#

Runs an transcriptions request to the engine and returns the response.

Returns an AsyncGenerator over the TranscriptionResponse object. This is so that the caller can have a consistent interface across all the methods of chat, completions, embeddings and transcriptions.

Parameters:

  • request – A TranscriptionRequest object.

  • raw_request_info – Optional RawRequestInfo containing data from the original HTTP request.

Returns:

An AsyncGenerator over the TranscriptionResponse object.