test_with_structured_output() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_with_structured_output() — langchain Function Reference

Dependency Diagram

graph TD
  3fbbcc9f_87ea_a4f8_b052_d840d29525fd["test_with_structured_output()"]
  48232d20_f8c1_b597_14fa_7dc407e9bfe5["test_base.py"]
  3fbbcc9f_87ea_a4f8_b052_d840d29525fd -->|defined in| 48232d20_f8c1_b597_14fa_7dc407e9bfe5
  style 3fbbcc9f_87ea_a4f8_b052_d840d29525fd fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/tests/unit_tests/chat_models/test_base.py lines 924–936

def test_with_structured_output(
    schema: type | dict[str, Any] | None,
    method: Literal["function_calling", "json_mode", "json_schema"],
    include_raw: bool,
    strict: bool | None,
) -> None:
    """Test passing in manually construct tool call message."""
    if method == "json_mode":
        strict = None
    llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
    llm.with_structured_output(
        schema, method=method, strict=strict, include_raw=include_raw
    )