map() — langchain Function Reference

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

Function python LangChainCore Runnables calls 3 called by 4

Entity Profile

LangChainCore→ Runnables→ map() — langchain Function Reference

Dependency Diagram

graph TD
  eeef200b_d96b_43d0_3074_30604390fe0c["map()"]
  8b074a3f_8729_0bb7_fe7d_db473df331ce["LLMStringRunMapper"]
  eeef200b_d96b_43d0_3074_30604390fe0c -->|defined in| 8b074a3f_8729_0bb7_fe7d_db473df331ce
  18ce5ec1_b967_6417_c994_9209a57f1c14["map()"]
  18ce5ec1_b967_6417_c994_9209a57f1c14 -->|calls| eeef200b_d96b_43d0_3074_30604390fe0c
  b8c4bf91_87d7_ce69_1350_1bcdf1bccbbb["map()"]
  b8c4bf91_87d7_ce69_1350_1bcdf1bccbbb -->|calls| eeef200b_d96b_43d0_3074_30604390fe0c
  975f5b09_3562_1764_4468_c7cb070bbfd3["map()"]
  975f5b09_3562_1764_4468_c7cb070bbfd3 -->|calls| eeef200b_d96b_43d0_3074_30604390fe0c
  b15ccccb_1344_8d38_767a_922bd0d352ca["map()"]
  b15ccccb_1344_8d38_767a_922bd0d352ca -->|calls| eeef200b_d96b_43d0_3074_30604390fe0c
  132c0c4d_93e7_fc60_9da8_46f58df87075["serialize_inputs()"]
  eeef200b_d96b_43d0_3074_30604390fe0c -->|calls| 132c0c4d_93e7_fc60_9da8_46f58df87075
  df0ac8ee_9864_89bc_2b10_585085211119["serialize_outputs()"]
  eeef200b_d96b_43d0_3074_30604390fe0c -->|calls| df0ac8ee_9864_89bc_2b10_585085211119
  b8c4bf91_87d7_ce69_1350_1bcdf1bccbbb["map()"]
  eeef200b_d96b_43d0_3074_30604390fe0c -->|calls| b8c4bf91_87d7_ce69_1350_1bcdf1bccbbb
  style eeef200b_d96b_43d0_3074_30604390fe0c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/smith/evaluation/string_run_evaluator.py lines 132–153

    def map(self, run: Run) -> dict[str, str]:
        """Maps the Run to a dictionary."""
        if run.run_type != "llm":
            msg = "LLM RunMapper only supports LLM runs."
            raise ValueError(msg)
        if not run.outputs:
            if run.error:
                msg = f"Cannot evaluate errored LLM run {run.id}: {run.error}"
                raise ValueError(msg)
            msg = f"Run {run.id} has no outputs. Cannot evaluate this run."
            raise ValueError(msg)
        try:
            inputs = self.serialize_inputs(run.inputs)
        except Exception as e:
            msg = f"Could not parse LM input from run inputs {run.inputs}"
            raise ValueError(msg) from e
        try:
            output_ = self.serialize_outputs(run.outputs)
        except Exception as e:
            msg = f"Could not parse LM prediction from run outputs {run.outputs}"
            raise ValueError(msg) from e
        return {"input": inputs, "prediction": output_}