_acall() — langchain Function Reference

Architecture documentation for the _acall() function in string_run_evaluator.py from the langchain codebase.

Function python LangChainCore Runnables calls 2

Entity Profile

LangChainCore→ Runnables→ _acall() — langchain Function Reference

Dependency Diagram

graph TD
  45efc57d_2b9e_96a6_a608_68913f941b40["_acall()"]
  96e174c1_4107_a88b_8d98_3f22e5d7fb20["StringRunEvaluatorChain"]
  45efc57d_2b9e_96a6_a608_68913f941b40 -->|defined in| 96e174c1_4107_a88b_8d98_3f22e5d7fb20
  2ca03f02_b9e1_8677_eda6_1008a8b4b7d4["_prepare_input()"]
  45efc57d_2b9e_96a6_a608_68913f941b40 -->|calls| 2ca03f02_b9e1_8677_eda6_1008a8b4b7d4
  463340b6_4fd0_8a0a_5cee_c0ea5a3163a4["_prepare_output()"]
  45efc57d_2b9e_96a6_a608_68913f941b40 -->|calls| 463340b6_4fd0_8a0a_5cee_c0ea5a3163a4
  style 45efc57d_2b9e_96a6_a608_68913f941b40 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/smith/evaluation/string_run_evaluator.py lines 343–357

    async def _acall(
        self,
        inputs: dict[str, str],
        run_manager: AsyncCallbackManagerForChainRun | None = None,
    ) -> dict[str, Any]:
        """Call the evaluation chain."""
        evaluate_strings_inputs = self._prepare_input(inputs)
        _run_manager = run_manager or AsyncCallbackManagerForChainRun.get_noop_manager()
        callbacks = _run_manager.get_child()
        chain_output = await self.string_evaluator.aevaluate_strings(
            **evaluate_strings_inputs,
            callbacks=callbacks,
            include_run_info=True,
        )
        return self._prepare_output(chain_output)