_agenerate_helper() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase calls 1 called by 1

Entity Profile

LangChainCore→ LanguageModelBase→ _agenerate_helper() — langchain Function Reference

Dependency Diagram

graph TD
  b5b0ca06_5826_6cbb_e9a3_9ad03072565c["_agenerate_helper()"]
  ce4aa464_3868_179e_5d99_df48bc307c5f["BaseLLM"]
  b5b0ca06_5826_6cbb_e9a3_9ad03072565c -->|defined in| ce4aa464_3868_179e_5d99_df48bc307c5f
  99297396_752a_7590_6d2b_c4757fc5a9d8["agenerate()"]
  99297396_752a_7590_6d2b_c4757fc5a9d8 -->|calls| b5b0ca06_5826_6cbb_e9a3_9ad03072565c
  70d0ab8e_d34a_ffec_e962_7f1649597664["_agenerate()"]
  b5b0ca06_5826_6cbb_e9a3_9ad03072565c -->|calls| 70d0ab8e_d34a_ffec_e962_7f1649597664
  style b5b0ca06_5826_6cbb_e9a3_9ad03072565c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/language_models/llms.py lines 1072–1113

    async def _agenerate_helper(
        self,
        prompts: list[str],
        stop: list[str] | None,
        run_managers: list[AsyncCallbackManagerForLLMRun],
        *,
        new_arg_supported: bool,
        **kwargs: Any,
    ) -> LLMResult:
        try:
            output = (
                await self._agenerate(
                    prompts,
                    stop=stop,
                    run_manager=run_managers[0] if run_managers else None,
                    **kwargs,
                )
                if new_arg_supported
                else await self._agenerate(prompts, stop=stop)
            )
        except BaseException as e:
            await asyncio.gather(
                *[
                    run_manager.on_llm_error(e, response=LLMResult(generations=[]))
                    for run_manager in run_managers
                ]
            )
            raise
        flattened_outputs = output.flatten()
        await asyncio.gather(
            *[
                run_manager.on_llm_end(flattened_output)
                for run_manager, flattened_output in zip(
                    run_managers, flattened_outputs, strict=False
                )
            ]
        )
        if run_managers:
            output.run = [
                RunInfo(run_id=run_manager.run_id) for run_manager in run_managers
            ]
        return output