test_response_metadata() — langchain Function Reference

Architecture documentation for the test_response_metadata() function in test_base.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_response_metadata() — langchain Function Reference

Dependency Diagram

graph TD
  046ca79b_c13c_ca43_93ab_84968e8183e1["test_response_metadata()"]
  bd382a4e_442c_13ae_530c_6e34bc43623d["test_base.py"]
  046ca79b_c13c_ca43_93ab_84968e8183e1 -->|defined in| bd382a4e_442c_13ae_530c_6e34bc43623d
  style 046ca79b_c13c_ca43_93ab_84968e8183e1 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/tests/integration_tests/chat_models/test_base.py lines 427–442

def test_response_metadata() -> None:
    llm = ChatOpenAI()
    result = llm.invoke([HumanMessage(content="I'm PickleRick")], logprobs=True)
    assert result.response_metadata
    assert all(
        k in result.response_metadata
        for k in (
            "token_usage",
            "model_name",
            "logprobs",
            "system_fingerprint",
            "finish_reason",
            "service_tier",
        )
    )
    assert "content" in result.response_metadata["logprobs"]