ToolStringRunMapper Class — langchain Architecture

Architecture documentation for the ToolStringRunMapper class in string_run_evaluator.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  715da39e_ae7e_bf18_46f6_cebdd3d81437["ToolStringRunMapper"]
  6513456f_be2b_21ef_06af_21023f648595["StringRunMapper"]
  715da39e_ae7e_bf18_46f6_cebdd3d81437 -->|extends| 6513456f_be2b_21ef_06af_21023f648595
  2f0b23f2_7760_d68c_7feb_721c5231c4ec["string_run_evaluator.py"]
  715da39e_ae7e_bf18_46f6_cebdd3d81437 -->|defined in| 2f0b23f2_7760_d68c_7feb_721c5231c4ec
  975f5b09_3562_1764_4468_c7cb070bbfd3["map()"]
  715da39e_ae7e_bf18_46f6_cebdd3d81437 -->|method| 975f5b09_3562_1764_4468_c7cb070bbfd3

Relationship Graph

Source Code

libs/langchain/langchain_classic/smith/evaluation/string_run_evaluator.py lines 214–222

class ToolStringRunMapper(StringRunMapper):
    """Map an input to the tool."""

    @override
    def map(self, run: Run) -> dict[str, str]:
        if not run.outputs:
            msg = f"Run {run.id} has no outputs to evaluate."
            raise ValueError(msg)
        return {"input": run.inputs["input"], "prediction": run.outputs["output"]}