_arun_llm_or_chain() — langchain Function Reference

Architecture documentation for the _arun_llm_or_chain() function in runner_utils.py from the langchain codebase.

Function python LangChainCore Runnables calls 2

Entity Profile

LangChainCore→ Runnables→ _arun_llm_or_chain() — langchain Function Reference

Dependency Diagram

graph TD
  f3487723_0da7_fd94_b3c8_cdac21cf7e23["_arun_llm_or_chain()"]
  8253c602_7d0c_9195_a7e1_3e9b19304131["runner_utils.py"]
  f3487723_0da7_fd94_b3c8_cdac21cf7e23 -->|defined in| 8253c602_7d0c_9195_a7e1_3e9b19304131
  5dad9d8a_ecf9_b785_9a01_d927f6bea73e["_arun_llm()"]
  f3487723_0da7_fd94_b3c8_cdac21cf7e23 -->|calls| 5dad9d8a_ecf9_b785_9a01_d927f6bea73e
  9b0e22db_68ee_87da_3140_8fa034a95ee3["_arun_chain()"]
  f3487723_0da7_fd94_b3c8_cdac21cf7e23 -->|calls| 9b0e22db_68ee_87da_3140_8fa034a95ee3
  style f3487723_0da7_fd94_b3c8_cdac21cf7e23 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/smith/evaluation/runner_utils.py lines 803–855

async def _arun_llm_or_chain(
    example: Example,
    config: RunnableConfig,
    *,
    llm_or_chain_factory: MCF,
    input_mapper: Callable[[dict], Any] | None = None,
) -> dict | str | LLMResult | ChatResult:
    """Asynchronously run the Chain or language model.

    Args:
        example: The example to run.
        config: The configuration for the run.
        llm_or_chain_factory: The Chain or language model constructor to run.
        input_mapper: Optional function to map the input to the expected format.

    Returns:
        A list of outputs.
    """
    chain_or_llm = (
        "LLM" if isinstance(llm_or_chain_factory, BaseLanguageModel) else "Chain"
    )
    result = None
    try:
        if isinstance(llm_or_chain_factory, BaseLanguageModel):
            output: Any = await _arun_llm(
                llm_or_chain_factory,
                example.inputs or {},
                tags=config["tags"],
                callbacks=config["callbacks"],
                input_mapper=input_mapper,
                metadata=config.get("metadata"),
            )
        else:
            chain = llm_or_chain_factory()
            output = await _arun_chain(
                chain,
                example.inputs or {},
                tags=config["tags"],
                callbacks=config["callbacks"],
                input_mapper=input_mapper,
                metadata=config.get("metadata"),
            )
        result = output
    except Exception as e:  # noqa: BLE001
        logger.warning(
            "%s failed for example %s with inputs %s\n%s",
            chain_or_llm,
            example.id,
            example.inputs,
            e,
        )
        result = EvalError(Error=e)
    return result