Method _stream

models.py:471–497

(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[CallbackManagerForLLMRun] = None,
        **kwargs: Any,
    )

        return output["response_delta"]

    def _stream(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[CallbackManagerForLLMRun] = None,
        **kwargs: Any,
    ) -> Iterator[ChatGenerationChunk]:
        configure_litellm()
        msgs = self._convert_messages(messages)

        # Apply rate limiting if configured
        apply_rate_limiter_sync(self.a0_model_conf, str(msgs))

        result = ChatGenerationResult()
        call_kwargs = _merge_litellm_call_kwargs(self.kwargs, kwargs)
        transport = LiteLLMTransport(
            model=self.model_name,
            messages=msgs,
            kwargs=call_kwargs,
            stop=stop,
        )
        for parsed in transport.stream():
            output = result.add_chunk(parsed)
            if output["response_delta"]:
                yield ChatGenerationChunk(
                    message=AIMessageChunk(content=output["response_delta"])
                )

    async def _astream(
        self,