Home / Function/ test_openai_pdf_tool_messages() — langchain Function Reference

test_openai_pdf_tool_messages() — langchain Function Reference

Architecture documentation for the test_openai_pdf_tool_messages() function in test_responses_standard.py from the langchain codebase.

Entity Profile

Dependency Diagram

graph TD
  19509b4b_da10_d2cd_31b9_8ced23add686["test_openai_pdf_tool_messages()"]
  25cafc0a_8f3b_2d49_7e58_88f79aca1167["TestOpenAIResponses"]
  19509b4b_da10_d2cd_31b9_8ced23add686 -->|defined in| 25cafc0a_8f3b_2d49_7e58_88f79aca1167
  style 19509b4b_da10_d2cd_31b9_8ced23add686 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py lines 87–127

    def test_openai_pdf_tool_messages(self, model: BaseChatModel) -> None:
        """Test that the model can process PDF inputs in `ToolMessage` objects."""
        url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
        pdf_data = base64.b64encode(httpx.get(url).content).decode("utf-8")

        tool_message = ToolMessage(
            content_blocks=[
                {
                    "type": "file",
                    "base64": pdf_data,
                    "mime_type": "application/pdf",
                    "extras": {"filename": "my-pdf"},  # specify filename
                },
            ],
            tool_call_id="1",
            name="random_pdf",
        )

        messages = [
            HumanMessage(
                "Get a random PDF using the tool and relay the title verbatim."
            ),
            AIMessage(
                [],
                tool_calls=[
                    {
                        "type": "tool_call",
                        "id": "1",
                        "name": "random_pdf",
                        "args": {},
                    }
                ],
            ),
            tool_message,
        ]

        def random_pdf() -> str:
            """Return a random PDF."""
            return ""

        _ = model.bind_tools([random_pdf]).invoke(messages)

Domain

Subdomains

Frequently Asked Questions

What does test_openai_pdf_tool_messages() do?
test_openai_pdf_tool_messages() is a function in the langchain codebase, defined in libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py.
Where is test_openai_pdf_tool_messages() defined?
test_openai_pdf_tool_messages() is defined in libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py at line 87.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free