_resolve_prompt() — langchain Function Reference

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

Function python LangChainCore ApiManagement calls 1 called by 1

Entity Profile

LangChainCore→ ApiManagement→ _resolve_prompt() — langchain Function Reference

Dependency Diagram

graph TD
  d7b47090_5602_93cf_8322_76a617b649a4["_resolve_prompt()"]
  530b536b_29e3_b2c0_9528_f38501e896c1["LabeledCriteriaEvalChain"]
  d7b47090_5602_93cf_8322_76a617b649a4 -->|defined in| 530b536b_29e3_b2c0_9528_f38501e896c1
  b7bf8076_06ca_7d01_49db_01bbd3e75d24["_resolve_prompt()"]
  b7bf8076_06ca_7d01_49db_01bbd3e75d24 -->|calls| d7b47090_5602_93cf_8322_76a617b649a4
  b7bf8076_06ca_7d01_49db_01bbd3e75d24["_resolve_prompt()"]
  d7b47090_5602_93cf_8322_76a617b649a4 -->|calls| b7bf8076_06ca_7d01_49db_01bbd3e75d24
  style d7b47090_5602_93cf_8322_76a617b649a4 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/evaluation/criteria/eval_chain.py lines 522–534

    def _resolve_prompt(
        cls,
        prompt: BasePromptTemplate | None = None,
    ) -> BasePromptTemplate:
        expected_input_vars = {"input", "output", "criteria", "reference"}
        prompt_ = prompt or PROMPT_WITH_REFERENCES
        if expected_input_vars != set(prompt_.input_variables):
            msg = (
                f"Input variables should be {expected_input_vars}, "
                f"but got {prompt_.input_variables}"
            )
            raise ValueError(msg)
        return prompt_