_select_eval_results() — langchain Function Reference

Architecture documentation for the _select_eval_results() function in evaluation.py from the langchain codebase.

Function python Observability Tracers called by 1

Entity Profile

Observability→ Tracers→ _select_eval_results() — langchain Function Reference

Dependency Diagram

graph TD
  b0dc41a9_2b64_0617_60e8_135a3bffaff5["_select_eval_results()"]
  d98d30f4_d5fd_24fc_54d0_e2f82eecc3cd["EvaluatorCallbackHandler"]
  b0dc41a9_2b64_0617_60e8_135a3bffaff5 -->|defined in| d98d30f4_d5fd_24fc_54d0_e2f82eecc3cd
  9cdfe3a0_d3ac_e744_24ad_fa3959981970["_log_evaluation_feedback()"]
  9cdfe3a0_d3ac_e744_24ad_fa3959981970 -->|calls| b0dc41a9_2b64_0617_60e8_135a3bffaff5
  style b0dc41a9_2b64_0617_60e8_135a3bffaff5 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/tracers/evaluation.py lines 163–176

    def _select_eval_results(
        results: EvaluationResult | EvaluationResults,
    ) -> list[EvaluationResult]:
        if isinstance(results, EvaluationResult):
            results_ = [results]
        elif isinstance(results, dict) and "results" in results:
            results_ = results["results"]
        else:
            msg = (
                f"Invalid evaluation result type {type(results)}."
                " Expected EvaluationResult or EvaluationResults."
            )
            raise TypeError(msg)
        return results_