test_follow_up_custom() — langchain Function Reference

Architecture documentation for the test_follow_up_custom() function in test_self_ask.py from the langchain codebase.

Function python LangChainCore ApiManagement

Entity Profile

LangChainCore→ ApiManagement→ test_follow_up_custom() — langchain Function Reference

Dependency Diagram

graph TD
  3388af81_0de9_59df_670f_9647d32c99ac["test_follow_up_custom()"]
  fd5e49f7_25e9_e2c1_8142_fdd27d067ba1["test_self_ask.py"]
  3388af81_0de9_59df_670f_9647d32c99ac -->|defined in| fd5e49f7_25e9_e2c1_8142_fdd27d067ba1
  style 3388af81_0de9_59df_670f_9647d32c99ac fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/agents/output_parsers/test_self_ask.py lines 28–38

def test_follow_up_custom() -> None:
    """Test follow up parsing for custom followups."""
    parser = SelfAskOutputParser(followups=("Now:",))
    _input = "Now: what is two + 2"
    output = parser.invoke(_input)
    expected_output = AgentAction(
        tool="Intermediate Answer",
        tool_input="what is two + 2",
        log=_input,
    )
    assert output == expected_output