_format_reference() — langchain Function Reference

Architecture documentation for the _format_reference() function in trajectory_eval_chain.py from the langchain codebase.

Function python LangChainCore MessageInterface called by 1

Entity Profile

LangChainCore→ MessageInterface→ _format_reference() — langchain Function Reference

Dependency Diagram

graph TD
  b7b9afe5_844f_287f_0e36_8a8d8d34e0a8["_format_reference()"]
  9066f65c_c5a3_1534_5336_72609f4ff02b["TrajectoryEvalChain"]
  b7b9afe5_844f_287f_0e36_8a8d8d34e0a8 -->|defined in| 9066f65c_c5a3_1534_5336_72609f4ff02b
  ccca4de6_6251_ea13_1af1_84bd1b80a9d4["prep_inputs()"]
  ccca4de6_6251_ea13_1af1_84bd1b80a9d4 -->|calls| b7b9afe5_844f_287f_0e36_8a8d8d34e0a8
  style b7b9afe5_844f_287f_0e36_8a8d8d34e0a8 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/evaluation/agents/trajectory_eval_chain.py lines 206–223

    def _format_reference(reference: str | None) -> str:
        """Format the reference text.

        Args:
            reference: The reference text.

        Returns:
            The formatted reference text.
        """
        if not reference:
            return ""
        return f"""

The following is the expected answer. Use this to measure correctness:
[GROUND_TRUTH]
{reference}
[END_GROUND_TRUTH]
"""