test_tool_choice_bool() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_tool_choice_bool() — langchain Function Reference

Dependency Diagram

graph TD
  1dd6c118_5a65_f062_71d3_f7b1ac76b8e6["test_tool_choice_bool()"]
  af57ae60_607e_c138_9ab0_fb8bb1c5916a["test_chat_models.py"]
  1dd6c118_5a65_f062_71d3_f7b1ac76b8e6 -->|defined in| af57ae60_607e_c138_9ab0_fb8bb1c5916a
  style 1dd6c118_5a65_f062_71d3_f7b1ac76b8e6 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/groq/tests/integration_tests/test_chat_models.py lines 434–455

def test_tool_choice_bool() -> None:
    """Test that tool choice is respected just passing in True."""
    llm = ChatGroq(model=DEFAULT_MODEL_NAME)

    class MyTool(BaseModel):
        name: str
        age: int

    with_tool = llm.bind_tools([MyTool], tool_choice=True)

    resp = with_tool.invoke("Who was the 27 year old named Erick? Use the tool.")
    assert isinstance(resp, AIMessage)
    assert resp.content == ""  # should just be tool call
    tool_calls = resp.additional_kwargs["tool_calls"]
    assert len(tool_calls) == 1
    tool_call = tool_calls[0]
    assert tool_call["function"]["name"] == "MyTool"
    assert json.loads(tool_call["function"]["arguments"]) == {
        "age": 27,
        "name": "Erick",
    }
    assert tool_call["type"] == "function"