Omni API Gradio UI
A Gradio-based user interface for the Omni API that supports text, PDF, image, and audio file processing.
Features
- Text input for chat messages
- Multiple file upload support (PDF, images, audio)
- Configurable API base URL
- Real-time response display
- File ordering for multi-modal requests
Installation
# Install dependencies
uv sync
# Run the application
uv run python app.py
Development Mode (with auto-reload)
For development, you can use the auto-reload feature that will automatically restart the app when files change:
uv run python dev.py
This will monitor for changes in Python files, Markdown files, and TOML configuration files, automatically restarting the Gradio app when any of these files are modified.
Usage
- Configure the API base URL (defaults to https://api-omni.modelharbor.com)
- Enter your text message
- Upload files in the desired order (optional)
- Click "Send Request" to interact with the API
- View the response in the right panel
Supported File Types
- PDFs: Document processing
- Images: JPG, PNG, GIF, BMP, WEBP
- Audio: MP3, WAV, M4A, FLAC, OGG