- Add ML-powered lead scoring endpoint with demographic, behavioral,
engagement, and intent signal analysis
- Add QR code and barcode reading endpoints using pyzbar
- Add OCR text extraction endpoint using pytesseract
- Add comprehensive image analysis endpoint combining all features
- Fix describe_video endpoint path (underscore to hyphen)
- Add endpoint listing to root API response
Replace Azure Functions architecture with a modern FastAPI-based REST
API providing image, video, speech, and vision capabilities for General
Bots.
Key changes:
- Add FastAPI app with versioned API endpoints and OpenAPI docs
- Implement services for Stable Diffusion, Zeroscope, TTS/Whisper, BLIP2
- Add pydantic schemas for request/response validation
- Configure structured logging with structlog
- Support lazy model loading and GPU acceleration
- Update dependencies from Azure/TensorFlow stack to PyTorch/diffusers
