test_pdf_inputs() — langchain Function Reference

Architecture documentation for the test_pdf_inputs() function in chat_models.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_pdf_inputs() — langchain Function Reference

Dependency Diagram

graph TD
  52e8ff5d_3fd7_279c_6907_c4805cbd2b5f["test_pdf_inputs()"]
  971e928f_9c9b_ce7a_b93d_e762f2f5aa54["ChatModelIntegrationTests"]
  52e8ff5d_3fd7_279c_6907_c4805cbd2b5f -->|defined in| 971e928f_9c9b_ce7a_b93d_e762f2f5aa54
  style 52e8ff5d_3fd7_279c_6907_c4805cbd2b5f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/standard-tests/langchain_tests/integration_tests/chat_models.py lines 2533–2619

    def test_pdf_inputs(self, model: BaseChatModel) -> None:
        """Test that the model can process PDF inputs.

        This test should be skipped (see configuration below) if the model does not
        support PDF inputs. These will take the shape of the LangChain
        `FileContentBlock`:

        ```python
        {
            "type": "image",
            "base64": "<base64 image data>",
            "mime_type": "application/pdf",
        }
        ```

        Furthermore, for backward-compatibility, we must also support OpenAI chat
        completions file content blocks:

        ```python
        (
            {
                "type": "file",
                "file": {
                    "filename": "test_file.pdf",
                    "file_data": f"data:application/pdf;base64,{pdf_data}",
                },
            },
        )
        ```

        ??? note "Configuration"

            To disable this test, set `supports_pdf_inputs` to `False` in your
            test class:

            ```python
            class TestMyChatModelIntegration(ChatModelIntegrationTests):
                @property
                def supports_pdf_inputs(self) -> bool:
                    return False
            ```

        ??? question "Troubleshooting"

            If this test fails, check that the model can correctly handle messages
            with pdf content blocks, including base64-encoded files. Otherwise, set
            the `supports_pdf_inputs` property to `False`.

        """
        if not self.supports_pdf_inputs:
            pytest.skip("Model does not support PDF inputs.")

        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")

        message = HumanMessage(
            [
                {
                    "type": "text",
                    "text": "Summarize this document:",
                },
                {
                    "type": "file",
                    "base64": pdf_data,
                    "mime_type": "application/pdf",
                },
            ]
        )
        _ = model.invoke([message])

        # Test OpenAI Chat Completions format
        message = HumanMessage(
            [
                {
                    "type": "text",
                    "text": "Summarize this document:",
                },
                {
                    "type": "file",
                    "file": {
                        "filename": "test_file.pdf",