test_returns_expected_results() — langchain Function Reference

Architecture documentation for the test_returns_expected_results() function in test_eval_chain.py from the langchain codebase.

Function python LangChainCore Runnables

Entity Profile

LangChainCore→ Runnables→ test_returns_expected_results() — langchain Function Reference

Dependency Diagram

graph TD
  752f3511_08b7_0b2c_f7b0_57b8f628c4cf["test_returns_expected_results()"]
  919cda35_c0f5_cbb5_866a_0591c5815209["test_eval_chain.py"]
  752f3511_08b7_0b2c_f7b0_57b8f628c4cf -->|defined in| 919cda35_c0f5_cbb5_866a_0591c5815209
  style 752f3511_08b7_0b2c_f7b0_57b8f628c4cf fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/evaluation/qa/test_eval_chain.py lines 77–90

def test_returns_expected_results(
    chain_cls: type[LLMChain],
) -> None:
    fake_llm = FakeLLM(
        queries={"text": "The meaning of life\nCORRECT"},
        sequential_responses=True,
    )
    chain = chain_cls.from_llm(fake_llm)  # type: ignore[attr-defined]
    results = chain.evaluate_strings(
        prediction="my prediction",
        reference="my reference",
        input="my input",
    )
    assert results["score"] == 1