Python: Add PDF file support to OpenAI content parser with filename mapping (#1121)

* Add mapping for application media type in OpenAI responses client * Enhance multimodal input samples: Add PDF testing functionality and fix image sample * Standardize filename handling and add multimodal samples - Standardized filename extraction logic between chat and responses clients - Both clients now omit filename when not provided (no default fallback) - Added Azure Responses API multimodal sample with PDF support - Cleaned up Azure Chat sample to focus on supported features only - Fixed test comment placement for better code documentation - Updated README with clear API capability differences * Enhance multimodal input samples with image and PDF handling - Refactor image and PDF handling in `azure_chat_multimodal.py` and `openai_chat_multimodal.py` to use new utility functions. - Add `load_sample_pdf` and `create_sample_image` functions for better test asset management. - Remove redundant code for creating sample images and PDFs. - Introduce a sample PDF file in `sample_assets` for testing purposes. * Fix formatting in OpenAI chat client --------- Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>
2026-06-16 21:04:09 +08:00 · 2025-10-07 19:04:33 +02:00
parent 1d27b57672
commit 8bb1266020
8 changed files with 268 additions and 77 deletions
@@ -419,27 +419,24 @@ class OpenAIBaseChatClient(OpenAIBase, BaseChatClient):
                        "format": audio_format,
                    },
                }
-            case DataContent() | UriContent() if content.media_type and content.media_type.startswith("application/"):
-                if content.media_type == "application/pdf":
-                    if content.uri.startswith("data:"):
-                        filename = (
-                            getattr(content, "filename", None)
-                            or content.additional_properties.get("filename", "document.pdf")
-                            if hasattr(content, "additional_properties") and content.additional_properties
-                            else "document.pdf"
-                        )
-                        return {
-                            "type": "file",
-                            "file": {
-                                "file_data": content.uri,  # Send full data URI
-                                "filename": filename,
-                            },
-                        }
-
-                    return content.to_dict(exclude_none=True)
-
-                return content.to_dict(exclude_none=True)
+            case DataContent() | UriContent() if content.has_top_level_media_type(
+                "application"
+            ) and content.uri.startswith("data:"):
+                # All application/* media types should be treated as files for OpenAI
+                filename = getattr(content, "filename", None) or (
+                    content.additional_properties.get("filename")
+                    if hasattr(content, "additional_properties") and content.additional_properties
+                    else None
+                )
+                file_obj = {"file_data": content.uri}
+                if filename:
+                    file_obj["filename"] = filename
+                return {
+                    "type": "file",
+                    "file": file_obj,
+                }
            case _:
+                # Default fallback for all other content types
                return content.to_dict(exclude_none=True)

    @override
@@ -454,6 +454,19 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                            "format": format,
                        },
                    }
+                if content.has_top_level_media_type("application"):
+                    filename = getattr(content, "filename", None) or (
+                        content.additional_properties.get("filename")
+                        if hasattr(content, "additional_properties") and content.additional_properties
+                        else None
+                    )
+                    file_obj = {
+                        "type": "input_file",
+                        "file_data": content.uri,
+                    }
+                    if filename:
+                        file_obj["filename"] = filename
+                    return file_obj
                return {}
            case FunctionCallContent():
                return {
@@ -756,7 +756,12 @@ def test_openai_content_parser_data_content_image(openai_unit_test_env: dict[str
    assert result["input_audio"]["data"] == "//uQAAAAWGluZwAAAA8AAAACAAACcQ=="
    assert result["input_audio"]["format"] == "mp3"

-    # Test DataContent with PDF file
+
+def test_openai_content_parser_document_file_mapping(openai_unit_test_env: dict[str, str]) -> None:
+    """Test _openai_content_parser converts document files (PDF, DOCX, etc.) to OpenAI file format."""
+    client = OpenAIChatClient()
+
+    # Test PDF without filename - should omit filename in OpenAI payload
    pdf_data_content = DataContent(
        uri="data:application/pdf;base64,JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9UeXBlL0NhdGFsb2cvUGFnZXMgMiAwIFI+PgplbmRvYmoKMiAwIG9iago8PC9UeXBlL1BhZ2VzL0tpZHNbMyAwIFJdL0NvdW50IDE+PgplbmRvYmoKMyAwIG9iago8PC9UeXBlL1BhZ2UvTWVkaWFCb3ggWzAgMCA2MTIgNzkyXS9QYXJlbnQgMiAwIFIvUmVzb3VyY2VzPDwvRm9udDw8L0YxIDQgMCBSPj4+Pi9Db250ZW50cyA1IDAgUj4+CmVuZG9iago0IDAgb2JqCjw8L1R5cGUvRm9udC9TdWJ0eXBlL1R5cGUxL0Jhc2VGb250L0hlbHZldGljYT4+CmVuZG9iago1IDAgb2JqCjw8L0xlbmd0aCA0ND4+CnN0cmVhbQpCVApxCjcwIDUwIFRECi9GMSA4IFRmCihIZWxsbyBXb3JsZCEpIFRqCkVUCmVuZHN0cmVhbQplbmRvYmoKeHJlZgowIDYKMDAwMDAwMDAwMCA2NTUzNSBmIAowMDAwMDAwMDA5IDAwMDAwIG4gCjAwMDAwMDAwNTggMDAwMDAgbiAKMDAwMDAwMDExNSAwMDAwMCBuIAowMDAwMDAwMjQ1IDAwMDAwIG4gCjAwMDAwMDAzMDcgMDAwMDAgbiAKdHJhaWxlcgo8PC9TaXplIDYvUm9vdCAxIDAgUj4+CnN0YXJ0eHJlZgo0MDUKJSVFT0Y=",
        media_type="application/pdf",
@@ -764,14 +769,15 @@ def test_openai_content_parser_data_content_image(openai_unit_test_env: dict[str

    result = client._openai_content_parser(pdf_data_content)  # type: ignore

-    # Should convert to OpenAI file format
+    # Should convert to OpenAI file format without filename
    assert result["type"] == "file"
-    assert result["file"]["filename"] == "document.pdf"
+    assert "filename" not in result["file"]  # No filename provided, so none should be set
    assert "file_data" in result["file"]
    # Base64 data should be the full data URI (OpenAI requirement)
    assert result["file"]["file_data"].startswith("data:application/pdf;base64,")
+    assert result["file"]["file_data"] == pdf_data_content.uri

-    # Test DataContent with PDF and custom filename
+    # Test PDF with custom filename via additional_properties
    pdf_with_filename = DataContent(
        uri="data:application/pdf;base64,JVBERi0xLjQ=",
        media_type="application/pdf",
@@ -783,17 +789,75 @@ def test_openai_content_parser_data_content_image(openai_unit_test_env: dict[str
    # Should use custom filename
    assert result["type"] == "file"
    assert result["file"]["filename"] == "report.pdf"
+    assert result["file"]["file_data"] == "data:application/pdf;base64,JVBERi0xLjQ="

+    # Test different application/* media types - all should now be mapped to file format
+    test_cases = [
+        {
+            "media_type": "application/json",
+            "filename": "data.json",
+            "base64": "eyJrZXkiOiJ2YWx1ZSJ9",
+        },
+        {
+            "media_type": "application/xml",
+            "filename": "config.xml",
+            "base64": "PD94bWwgdmVyc2lvbj0iMS4wIj8+",
+        },
+        {
+            "media_type": "application/octet-stream",
+            "filename": "binary.bin",
+            "base64": "AQIDBAUGBwgJCg==",
+        },
+    ]

-def test_openai_chat_client_with_callable_api_key() -> None:
-    """Test OpenAIChatClient initialization with callable API key."""
+    for case in test_cases:
+        # Test without filename
+        doc_content = DataContent(
+            uri=f"data:{case['media_type']};base64,{case['base64']}",
+            media_type=case["media_type"],
+        )

-    async def get_api_key() -> str:
-        return "test-api-key-123"
+        result = client._openai_content_parser(doc_content)  # type: ignore

-    client = OpenAIChatClient(model_id="gpt-4o", api_key=get_api_key)
+        # All application/* types should now be mapped to file format
+        assert result["type"] == "file"
+        assert "filename" not in result["file"]  # Should omit filename when not provided
+        assert result["file"]["file_data"] == doc_content.uri

-    # Verify client was created successfully
-    assert client.model_id == "gpt-4o"
-    # OpenAI SDK now manages callable API keys internally
-    assert client.client is not None
+        # Test with filename - should now use file format with filename
+        doc_with_filename = DataContent(
+            uri=f"data:{case['media_type']};base64,{case['base64']}",
+            media_type=case["media_type"],
+            additional_properties={"filename": case["filename"]},
+        )
+
+        result = client._openai_content_parser(doc_with_filename)  # type: ignore
+
+        # Should now use file format with filename
+        assert result["type"] == "file"
+        assert result["file"]["filename"] == case["filename"]
+        assert result["file"]["file_data"] == doc_with_filename.uri
+
+    # Test edge case: empty additional_properties dict
+    pdf_empty_props = DataContent(
+        uri="data:application/pdf;base64,JVBERi0xLjQ=",
+        media_type="application/pdf",
+        additional_properties={},
+    )
+
+    result = client._openai_content_parser(pdf_empty_props)  # type: ignore
+
+    assert result["type"] == "file"
+    assert "filename" not in result["file"]
+
+    # Test edge case: None filename in additional_properties
+    pdf_none_filename = DataContent(
+        uri="data:application/pdf;base64,JVBERi0xLjQ=",
+        media_type="application/pdf",
+        additional_properties={"filename": None},
+    )
+
+    result = client._openai_content_parser(pdf_none_filename)  # type: ignore
+
+    assert result["type"] == "file"
+    assert "filename" not in result["file"]  # None filename should be omitted