_create_chat_result() — langchain Function Reference

Architecture documentation for the _create_chat_result() function in chat_models.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ _create_chat_result() — langchain Function Reference

Dependency Diagram

graph TD
  e6815009_0080_e5e8_b723_9158ce500139["_create_chat_result()"]
  f3181e26_0568_4993_612c_5b8d73ad3c37["ChatDeepSeek"]
  e6815009_0080_e5e8_b723_9158ce500139 -->|defined in| f3181e26_0568_4993_612c_5b8d73ad3c37
  style e6815009_0080_e5e8_b723_9158ce500139 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/deepseek/langchain_deepseek/chat_models.py lines 281–311

    def _create_chat_result(
        self,
        response: dict | openai.BaseModel,
        generation_info: dict | None = None,
    ) -> ChatResult:
        rtn = super()._create_chat_result(response, generation_info)

        if not isinstance(response, openai.BaseModel):
            return rtn

        for generation in rtn.generations:
            if generation.message.response_metadata is None:
                generation.message.response_metadata = {}
            generation.message.response_metadata["model_provider"] = "deepseek"

        choices = getattr(response, "choices", None)
        if choices and hasattr(choices[0].message, "reasoning_content"):
            rtn.generations[0].message.additional_kwargs["reasoning_content"] = choices[
                0
            ].message.reasoning_content
        # Handle use via OpenRouter
        elif choices and hasattr(choices[0].message, "model_extra"):
            model_extra = choices[0].message.model_extra
            if isinstance(model_extra, dict) and (
                reasoning := model_extra.get("reasoning")
            ):
                rtn.generations[0].message.additional_kwargs["reasoning_content"] = (
                    reasoning
                )

        return rtn