_generate() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase calls 2 called by 1

Entity Profile

LangChainCore→ LanguageModelBase→ _generate() — langchain Function Reference

Dependency Diagram

graph TD
  1958c025_da10_4021_3597_57eb74b3eae7["_generate()"]
  b2c7d2a5_0852_93df_c3e1_828c36a88999["LLM"]
  1958c025_da10_4021_3597_57eb74b3eae7 -->|defined in| b2c7d2a5_0852_93df_c3e1_828c36a88999
  41e472cf_86b5_9da0_e470_4a679091bba9["_generate()"]
  41e472cf_86b5_9da0_e470_4a679091bba9 -->|calls| 1958c025_da10_4021_3597_57eb74b3eae7
  862f8f36_13e4_466c_ffc2_266e2e8b78e4["_call()"]
  1958c025_da10_4021_3597_57eb74b3eae7 -->|calls| 862f8f36_13e4_466c_ffc2_266e2e8b78e4
  41e472cf_86b5_9da0_e470_4a679091bba9["_generate()"]
  1958c025_da10_4021_3597_57eb74b3eae7 -->|calls| 41e472cf_86b5_9da0_e470_4a679091bba9
  style 1958c025_da10_4021_3597_57eb74b3eae7 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/language_models/llms.py lines 1493–1510

    def _generate(
        self,
        prompts: list[str],
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        **kwargs: Any,
    ) -> LLMResult:
        # TODO: add caching here.
        generations = []
        new_arg_supported = inspect.signature(self._call).parameters.get("run_manager")
        for prompt in prompts:
            text = (
                self._call(prompt, stop=stop, run_manager=run_manager, **kwargs)
                if new_arg_supported
                else self._call(prompt, stop=stop, **kwargs)
            )
            generations.append([Generation(text=text)])
        return LLMResult(generations=generations)