_generate() — langchain Function Reference

Source Code

libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py lines 723–762

    def _generate(
        self,
        messages: list[BaseMessage],
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        stream: bool | None = None,  # noqa: FBT001
        **kwargs: Any,
    ) -> ChatResult:
        should_stream = stream if stream is not None else self.streaming

        if _is_huggingface_textgen_inference(self.llm):
            message_dicts, params = self._create_message_dicts(messages, stop)
            answer = self.llm.client.chat(messages=message_dicts, **kwargs)
            return self._create_chat_result(answer)
        if _is_huggingface_endpoint(self.llm):
            if should_stream:
                stream_iter = self._stream(
                    messages, stop=stop, run_manager=run_manager, **kwargs
                )
                return generate_from_stream(stream_iter)
            message_dicts, params = self._create_message_dicts(messages, stop)
            params = {
                "stop": stop,
                **params,
                **({"stream": stream} if stream is not None else {}),
                **kwargs,
            }
            answer = self.llm.client.chat_completion(messages=message_dicts, **params)
            return self._create_chat_result(answer)
        llm_input = self._to_chat_prompt(messages)

        if should_stream:
            stream_iter = self.llm._stream(
                llm_input, stop=stop, run_manager=run_manager, **kwargs
            )
            return generate_from_stream(stream_iter)
        llm_result = self.llm._generate(
            prompts=[llm_input], stop=stop, run_manager=run_manager, **kwargs
        )
        return self._to_chat_result(llm_result)