evaluate() — langchain Function Reference

Architecture documentation for the evaluate() function in eval_chain.py from the langchain codebase.

Function python LangChainCore MessageInterface calls 1 called by 1

Entity Profile

LangChainCore→ MessageInterface→ evaluate() — langchain Function Reference

Dependency Diagram

graph TD
  521b9488_9033_0706_ed4d_2effaa66f023["evaluate()"]
  6b783916_2e41_8d2a_dba2_81813096b7c4["ContextQAEvalChain"]
  521b9488_9033_0706_ed4d_2effaa66f023 -->|defined in| 6b783916_2e41_8d2a_dba2_81813096b7c4
  28c54882_f371_ef45_e599_5af436fe1f65["evaluate()"]
  28c54882_f371_ef45_e599_5af436fe1f65 -->|calls| 521b9488_9033_0706_ed4d_2effaa66f023
  28c54882_f371_ef45_e599_5af436fe1f65["evaluate()"]
  521b9488_9033_0706_ed4d_2effaa66f023 -->|calls| 28c54882_f371_ef45_e599_5af436fe1f65
  style 521b9488_9033_0706_ed4d_2effaa66f023 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/evaluation/qa/eval_chain.py lines 281–301

    def evaluate(
        self,
        examples: list[dict],
        predictions: list[dict],
        question_key: str = "query",
        context_key: str = "context",
        prediction_key: str = "result",
        *,
        callbacks: Callbacks = None,
    ) -> list[dict]:
        """Evaluate question answering examples and predictions."""
        inputs = [
            {
                "query": example[question_key],
                "context": example[context_key],
                "result": predictions[i][prediction_key],
            }
            for i, example in enumerate(examples)
        ]

        return self.apply(inputs, callbacks=callbacks)