_generate() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ _generate() — langchain Function Reference

Dependency Diagram

graph TD
  20d02b68_6434_8e38_551a_725af032988d["_generate()"]
  f3181e26_0568_4993_612c_5b8d73ad3c37["ChatDeepSeek"]
  20d02b68_6434_8e38_551a_725af032988d -->|defined in| f3181e26_0568_4993_612c_5b8d73ad3c37
  style 20d02b68_6434_8e38_551a_725af032988d fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/deepseek/langchain_deepseek/chat_models.py lines 370–393

    def _generate(
        self,
        messages: list[BaseMessage],
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        **kwargs: Any,
    ) -> ChatResult:
        try:
            return super()._generate(
                messages,
                stop=stop,
                run_manager=run_manager,
                **kwargs,
            )
        except JSONDecodeError as e:
            msg = (
                "DeepSeek API returned an invalid response. "
                "Please check the API status and try again."
            )
            raise JSONDecodeError(
                msg,
                e.doc,
                e.pos,
            ) from e