test_structured_prompt_kwargs() — langchain Function Reference

Architecture documentation for the test_structured_prompt_kwargs() function in test_structured.py from the langchain codebase.

Function python CoreAbstractions Serialization

Entity Profile

CoreAbstractions→ Serialization→ test_structured_prompt_kwargs() — langchain Function Reference

Dependency Diagram

graph TD
  e8c7d980_9212_b371_2da0_bdf60c6ef6d8["test_structured_prompt_kwargs()"]
  3513030b_4904_ecfd_7a0d_cc92be4dda69["test_structured.py"]
  e8c7d980_9212_b371_2da0_bdf60c6ef6d8 -->|defined in| 3513030b_4904_ecfd_7a0d_cc92be4dda69
  style e8c7d980_9212_b371_2da0_bdf60c6ef6d8 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/prompts/test_structured.py lines 87–121

def test_structured_prompt_kwargs() -> None:
    prompt = StructuredPrompt(
        [
            ("human", "I'm very structured, how about you?"),
        ],
        {
            "name": "yo",
            "description": "a structured output",
            "parameters": {
                "name": {"type": "string"},
                "value": {"type": "integer"},
            },
        },
        value=7,
    )
    model = FakeStructuredChatModel(responses=[])
    chain = prompt | model
    assert chain.invoke({"hello": "there"}) == {"name": 1, "value": 7}  # type: ignore[comparison-overlap]
    assert loads(dumps(prompt)).model_dump() == prompt.model_dump()
    chain = loads(dumps(prompt)) | model
    assert chain.invoke({"hello": "there"}) == {"name": 1, "value": 7}

    class OutputSchema(BaseModel):
        name: str
        value: int

    prompt = StructuredPrompt(
        [("human", "I'm very structured, how about you?")], OutputSchema, value=7
    )

    model = FakeStructuredChatModel(responses=[])

    chain = prompt | model

    assert chain.invoke({"hello": "there"}) == OutputSchema(name="yo", value=7)  # type: ignore[comparison-overlap]