test_image_tool_calling() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_image_tool_calling() — langchain Function Reference

Dependency Diagram

graph TD
  58e8797b_ef8c_878c_3aa7_227f18f1d802["test_image_tool_calling()"]
  f27640dd_3870_5548_d153_f9504ae1021f["test_chat_models.py"]
  58e8797b_ef8c_878c_3aa7_227f18f1d802 -->|defined in| f27640dd_3870_5548_d153_f9504ae1021f
  style 58e8797b_ef8c_878c_3aa7_227f18f1d802 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/anthropic/tests/integration_tests/test_chat_models.py lines 1218–1276

def test_image_tool_calling() -> None:
    """Test tool calling with image inputs."""

    class color_picker(BaseModel):  # noqa: N801
        """Input your fav color and get a random fact about it."""

        fav_color: str

    human_content: list[dict] = [
        {
            "type": "text",
            "text": "what's your favorite color in this image",
        },
    ]
    image_url = "https://raw.githubusercontent.com/langchain-ai/docs/4d11d08b6b0e210bd456943f7a22febbd168b543/src/images/agentic-rag-output.png"
    image_data = b64encode(httpx.get(image_url).content).decode("utf-8")
    human_content.append(
        {
            "type": "image",
            "source": {
                "type": "base64",
                "media_type": "image/png",
                "data": image_data,
            },
        },
    )
    messages = [
        SystemMessage("you're a good assistant"),
        HumanMessage(human_content),  # type: ignore[arg-type]
        AIMessage(
            [
                {"type": "text", "text": "Hmm let me think about that"},
                {
                    "type": "tool_use",
                    "input": {"fav_color": "purple"},
                    "id": "foo",
                    "name": "color_picker",
                },
            ],
        ),
        HumanMessage(
            [
                {
                    "type": "tool_result",
                    "tool_use_id": "foo",
                    "content": [
                        {
                            "type": "text",
                            "text": "purple is a great pick! that's my sister's favorite color",  # noqa: E501
                        },
                    ],
                    "is_error": False,
                },
                {"type": "text", "text": "what's my sister's favorite color"},
            ],
        ),
    ]
    llm = ChatAnthropic(model=MODEL_NAME)  # type: ignore[call-arg]
    _ = llm.bind_tools([color_picker]).invoke(messages)