test_system_invoke() — langchain Function Reference

Architecture documentation for the test_system_invoke() function in test_chat_models.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_system_invoke() — langchain Function Reference

Dependency Diagram

graph TD
  6b9dd7fa_2c9e_9ee1_da83_5f971422746e["test_system_invoke()"]
  f27640dd_3870_5548_d153_f9504ae1021f["test_chat_models.py"]
  6b9dd7fa_2c9e_9ee1_da83_5f971422746e -->|defined in| f27640dd_3870_5548_d153_f9504ae1021f
  style 6b9dd7fa_2c9e_9ee1_da83_5f971422746e fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/anthropic/tests/integration_tests/test_chat_models.py lines 262–280

def test_system_invoke() -> None:
    """Test invoke tokens with a system message."""
    llm = ChatAnthropic(model_name=MODEL_NAME)  # type: ignore[call-arg, call-arg]

    prompt = ChatPromptTemplate.from_messages(
        [
            (
                "system",
                "You are an expert cartographer. If asked, you are a cartographer. "
                "STAY IN CHARACTER",
            ),
            ("human", "Are you a mathematician?"),
        ],
    )

    chain = prompt | llm

    result = chain.invoke({})
    assert isinstance(result.content, str)