Rodrigo Rodriguez (Pragmatismo)
5a43dc81c7
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
44 lines
691 B
Text
44 lines
691 B
Text
# Core Framework
|
|
fastapi==0.115.0
|
|
uvicorn[standard]==0.30.6
|
|
pydantic==2.9.0
|
|
pydantic-settings==2.5.2
|
|
|
|
# Logging
|
|
structlog==25.5.0
|
|
python-json-logger==2.0.7
|
|
|
|
# Generation Libraries
|
|
diffusers==0.30.3
|
|
torch==2.5.1
|
|
torchaudio==2.5.1
|
|
torchvision==0.20.1
|
|
transformers==4.46.0
|
|
accelerate==1.1.1
|
|
safetensors==0.4.5
|
|
Pillow==11.0.0
|
|
|
|
# Audio Generation & Processing
|
|
openai-whisper==20231117
|
|
TTS==0.22.0
|
|
scipy==1.14.1
|
|
|
|
# Video Processing
|
|
imageio==2.36.0
|
|
imageio-ffmpeg==0.5.1
|
|
opencv-python==4.10.0.84
|
|
|
|
# Vision & Multimodal
|
|
timm==1.0.12
|
|
|
|
# HTTP & API
|
|
httpx==0.27.2
|
|
aiofiles==24.1.0
|
|
python-multipart==0.0.12
|
|
|
|
# Monitoring
|
|
prometheus-client==0.21.0
|
|
|
|
# Utils
|
|
python-dotenv==1.0.1
|
|
typing-extensions==4.12.2
|