_merge_test_outputs() — langchain Function Reference

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

Function python LangChainCore ApiManagement called by 1

Entity Profile

LangChainCore→ ApiManagement→ _merge_test_outputs() — langchain Function Reference

Dependency Diagram

graph TD
  bb416a9d_32e6_298b_d0bd_82d7d53d9821["_merge_test_outputs()"]
  3aaa6e94_b6a8_1c13_86d0_1709a1d93909["_DatasetRunContainer"]
  bb416a9d_32e6_298b_d0bd_82d7d53d9821 -->|defined in| 3aaa6e94_b6a8_1c13_86d0_1709a1d93909
  7bd0a459_a7f0_719c_faf9_2cf0ffd65a8c["_collect_test_results()"]
  7bd0a459_a7f0_719c_faf9_2cf0ffd65a8c -->|calls| bb416a9d_32e6_298b_d0bd_82d7d53d9821
  style bb416a9d_32e6_298b_d0bd_82d7d53d9821 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/smith/evaluation/runner_utils.py lines 1104–1124

    def _merge_test_outputs(
        self,
        batch_results: list,
        all_eval_results: dict[str, _RowResult],
    ) -> dict:
        results: dict = {}
        for example, output in zip(self.examples, batch_results, strict=False):
            row_result = all_eval_results.get(str(example.id), {})
            results[str(example.id)] = {
                "input": example.inputs,
                "feedback": row_result.get("feedback", []),
                "execution_time": row_result.get("execution_time"),
                "run_id": row_result.get("run_id"),
            }
            if isinstance(output, EvalError):
                results[str(example.id)]["Error"] = output.Error
            else:
                results[str(example.id)]["output"] = output
            if example.outputs:
                results[str(example.id)]["reference"] = example.outputs
        return results