test_loads_runnable_sequence_prompt_model() — langchain Function Reference

Architecture documentation for the test_loads_runnable_sequence_prompt_model() function in test_load.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_loads_runnable_sequence_prompt_model() — langchain Function Reference

Dependency Diagram

graph TD
  471c1e06_f950_803a_69e2_9f44e8fb75cd["test_loads_runnable_sequence_prompt_model()"]
  f594231b_8e8d_61b8_e688_99b6f31430d1["test_load.py"]
  471c1e06_f950_803a_69e2_9f44e8fb75cd -->|defined in| f594231b_8e8d_61b8_e688_99b6f31430d1
  style 471c1e06_f950_803a_69e2_9f44e8fb75cd fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/tests/unit_tests/test_load.py lines 67–102

def test_loads_runnable_sequence_prompt_model() -> None:
    """Test serialization/deserialization of a chain:

    `prompt | model (RunnableSequence)`
    """
    prompt = ChatPromptTemplate.from_messages([("user", "Hello, {name}!")])
    model = ChatOpenAI(model="gpt-4o-mini", temperature=0.5, openai_api_key="hello")  # type: ignore[call-arg]
    chain = prompt | model

    # Verify the chain is a RunnableSequence
    assert isinstance(chain, RunnableSequence)

    # Serialize
    chain_string = dumps(chain)

    # Deserialize
    # (ChatPromptTemplate contains HumanMessagePromptTemplate and PromptTemplate)
    chain2 = loads(
        chain_string,
        secrets_map={"OPENAI_API_KEY": "hello"},
        allowed_objects=[
            RunnableSequence,
            ChatPromptTemplate,
            HumanMessagePromptTemplate,
            PromptTemplate,
            ChatOpenAI,
        ],
    )

    # Verify structure
    assert isinstance(chain2, RunnableSequence)
    assert isinstance(chain2.first, ChatPromptTemplate)
    assert isinstance(chain2.last, ChatOpenAI)

    # Verify round-trip serialization
    assert dumps(chain2) == chain_string