_persist_run() — langchain Function Reference

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

Function python Observability Tracers calls 1

Entity Profile

Observability→ Tracers→ _persist_run() — langchain Function Reference

Dependency Diagram

graph TD
  f8b5f1f4_e3b0_be12_bf7c_561a99a6e105["_persist_run()"]
  d98d30f4_d5fd_24fc_54d0_e2f82eecc3cd["EvaluatorCallbackHandler"]
  f8b5f1f4_e3b0_be12_bf7c_561a99a6e105 -->|defined in| d98d30f4_d5fd_24fc_54d0_e2f82eecc3cd
  0c53e289_4919_bbc6_c165_0a9bf3c71d14["_evaluate_in_project()"]
  f8b5f1f4_e3b0_be12_bf7c_561a99a6e105 -->|calls| 0c53e289_4919_bbc6_c165_0a9bf3c71d14
  style f8b5f1f4_e3b0_be12_bf7c_561a99a6e105 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/tracers/evaluation.py lines 205–222

    def _persist_run(self, run: Run) -> None:
        """Run the evaluator on the run.

        Args:
            run: The run to be evaluated.
        """
        if self.skip_unfinished and not run.outputs:
            logger.debug("Skipping unfinished run %s", run.id)
            return
        run_ = run_copy(run)
        run_.reference_example_id = self.example_id
        for evaluator in self.evaluators:
            if self.executor is None:
                self._evaluate_in_project(run_, evaluator)
            else:
                self.futures.add(
                    self.executor.submit(self._evaluate_in_project, run_, evaluator)
                )