Python: Fix Multimodal input bug (#799)

* fix multimodal bug python

* update file names

* precommit fixes

* Update python/samples/getting_started/multimodal_input/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* udpate readme

* add copyright line, remove audio example function

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

python/samples/getting_started/multimodal_input/README.md

@@ -0,0 +1,85 @@
+# Multimodal Input Examples
+
+This folder contains examples demonstrating how to send multimodal content (images, audio, PDF files) to AI agents using the Agent Framework.
+
+## Examples
+
+### OpenAI Chat Client
+
+- **File**: `openai_chat_multimodal.py`
+- **Description**: Shows how to send images, audio, and PDF files to OpenAI's Chat Completions API
+- **Supported formats**: PNG/JPEG images, WAV/MP3 audio, PDF documents
+
+### Azure Chat Client
+
+- **File**: `azure_chat_multimodal.py`
+- **Description**: Shows how to send multimodal content to Azure OpenAI service
+- **Supported formats**: PNG/JPEG images, WAV/MP3 audio, PDF documents
+
+## Running the Examples
+
+1. Set your API keys:
+
+   ```bash
+   export OPENAI_API_KEY="your-openai-key"
+   export AZURE_OPENAI_API_KEY="your-azure-key"
+   export AZURE_OPENAI_ENDPOINT="your-azure-endpoint"
+   ```
+
+2. Run an example:
+   ```bash
+   python openai_chat_client_multimodal.py
+   python azure_chat_client_multimodal.py
+   ```
+
+## Using Your Own Files
+
+The examples include small embedded test files for demonstration. To use your own files:
+
+### Method 1: Data URIs (recommended)
+
+```python
+import base64
+
+# Load and encode your file
+with open("path/to/your/image.jpg", "rb") as f:
+    image_data = f.read()
+    image_base64 = base64.b64encode(image_data).decode('utf-8')
+    image_uri = f"data:image/jpeg;base64,{image_base64}"
+
+# Use in DataContent
+DataContent(
+    uri=image_uri,
+    media_type="image/jpeg"
+)
+```
+
+### Method 2: Raw bytes
+
+```python
+# Load raw bytes
+with open("path/to/your/image.jpg", "rb") as f:
+    image_bytes = f.read()
+
+# Use in DataContent
+DataContent(
+    data=image_bytes,
+    media_type="image/jpeg"
+)
+```
+
+## Supported File Types
+
+| Type      | Formats              | Notes                          |
+| --------- | -------------------- | ------------------------------ |
+| Images    | PNG, JPEG, GIF, WebP | Most common image formats      |
+| Audio     | WAV, MP3             | For transcription and analysis |
+| Documents | PDF                  | Text extraction and analysis   |
+
+## API Differences
+
+- **Chat Completions API**: Supports images, audio, and PDF files
+- **Assistants API**: Only supports text and images (no audio/PDF)
+- **Responses API**: Similar to Chat Completions
+
+Choose the appropriate client based on your multimodal needs.

python/samples/getting_started/multimodal_input/azure_chat_multimodal.py

@@ -0,0 +1,36 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+import base64
+import requests
+from agent_framework import ChatMessage, DataContent, Role, TextContent
+from agent_framework.azure import AzureChatClient
+
+async def test_image():
+    """Test image analysis with Azure."""
+    client = AzureChatClient()
+
+    # Fetch image from httpbin
+    image_url = "https://httpbin.org/image/jpeg"
+    response = requests.get(image_url)
+    image_b64 = base64.b64encode(response.content).decode()
+    image_uri = f"data:image/jpeg;base64,{image_b64}"
+
+    message = ChatMessage(
+        role=Role.USER,
+        contents=[
+            TextContent(text="What's in this image?"),
+            DataContent(uri=image_uri, media_type="image/jpeg")
+        ]
+    )
+
+    response = await client.get_response(message)
+    print(f"Image Response: {response}")
+
+
+async def main():
+    print("=== Testing Azure Multimodal ===")
+    await test_image() 
+
+if __name__ == "__main__":
+    asyncio.run(main())

python/samples/getting_started/multimodal_input/openai_chat_multimodal.py

@@ -0,0 +1,63 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+import base64
+import requests
+import struct
+from agent_framework import ChatMessage, DataContent, Role, TextContent
+from agent_framework.openai import OpenAIChatClient
+
+async def test_image():
+    """Test image analysis with OpenAI."""
+    client = OpenAIChatClient(ai_model_id="gpt-4o")
+
+    # Fetch image from httpbin
+    image_url = "https://httpbin.org/image/jpeg"
+    response = requests.get(image_url)
+    image_b64 = base64.b64encode(response.content).decode()
+    image_uri = f"data:image/jpeg;base64,{image_b64}"
+
+    message = ChatMessage(
+        role=Role.USER,
+        contents=[
+            TextContent(text="What's in this image?"),
+            DataContent(uri=image_uri, media_type="image/jpeg")
+        ]
+    )
+
+    response = await client.get_response(message)
+    print(f"Image Response: {response}")
+
+async def test_audio():
+    """Test audio analysis with OpenAI."""
+    client = OpenAIChatClient(ai_model_id="gpt-4o-audio-preview")
+
+    # Create minimal WAV file (0.1 seconds of silence)
+    wav_header = (
+        b'RIFF' + struct.pack('<I', 44) +  # file size
+        b'WAVEfmt ' + struct.pack('<I', 16) +  # fmt chunk
+        struct.pack('<HHIIHH', 1, 1, 8000, 16000, 2, 16) +  # PCM, mono, 8kHz
+        b'data' + struct.pack('<I', 1600) +  # data chunk
+        b'\x00' * 1600  # 0.1 sec silence
+    )
+    audio_b64 = base64.b64encode(wav_header).decode()
+    audio_uri = f"data:audio/wav;base64,{audio_b64}"
+
+    message = ChatMessage(
+        role=Role.USER,
+        contents=[
+            TextContent(text="What do you hear in this audio?"),
+            DataContent(uri=audio_uri, media_type="audio/wav")
+        ]
+    )
+
+    response = await client.get_response(message)
+    print(f"Audio Response: {response}")
+
+async def main():
+    print("=== Testing OpenAI Multimodal ===")
+    await test_image()
+    await test_audio()
+
+if __name__ == "__main__":
+    asyncio.run(main())