## Added
- Multi-provider LLM support with factory pattern (8 providers):
* OpenAI, Z.AI, OpenCode Zen, OpenRouter, Anthropic, Google, Mistral, Azure
- Authentication system: JWT + API Key dual-mode
- Provider management API (/api/v1/providers)
- Docker containerization (Dockerfile + docker-compose.yml)
- Updated documentation in main.py
## Modified
- Documents API: added authentication
- Query API: support for provider/model selection
- RAG service: dynamic LLM provider selection
- Config: multi-provider settings
## Infrastructure
- Qdrant vector store integration
- Redis support (optional)
- Health check endpoints
🚀 Ready for production deployment
53 lines
978 B
Plaintext
53 lines
978 B
Plaintext
# AgenticRAG Requirements
|
|
# Core dependencies
|
|
|
|
# FastAPI and web framework
|
|
fastapi>=0.104.0
|
|
uvicorn[standard]>=0.24.0
|
|
python-multipart>=0.0.6
|
|
python-jose[cryptography]>=3.3.0
|
|
passlib[bcrypt]>=1.7.4
|
|
|
|
# Datapizza AI framework
|
|
datapizza-ai>=0.1.0
|
|
datapizza-ai-core>=0.1.0
|
|
|
|
# LLM Clients
|
|
datapizza-ai-clients-openai>=0.0.12
|
|
# Additional providers will be installed via pip in Dockerfile
|
|
|
|
# Embeddings
|
|
datapizza-ai-embedders-openai>=0.0.6
|
|
|
|
# Vector Store
|
|
datapizza-ai-vectorstores-qdrant>=0.0.9
|
|
qdrant-client>=1.7.0
|
|
|
|
# Document Processing
|
|
datapizza-ai-modules-parsers-docling>=0.0.1
|
|
|
|
# Tools
|
|
datapizza-ai-tools-duckduckgo>=0.0.1
|
|
|
|
# Configuration and utilities
|
|
pydantic>=2.5.0
|
|
pydantic-settings>=2.1.0
|
|
python-dotenv>=1.0.0
|
|
httpx>=0.25.0
|
|
aiofiles>=23.2.0
|
|
|
|
# Observability
|
|
opentelemetry-api>=1.21.0
|
|
opentelemetry-sdk>=1.21.0
|
|
opentelemetry-instrumentation-fastapi>=0.42b0
|
|
|
|
# Testing
|
|
pytest>=7.4.0
|
|
pytest-asyncio>=0.21.0
|
|
httpx>=0.25.0
|
|
|
|
# Development
|
|
black>=23.0.0
|
|
ruff>=0.1.0
|
|
mypy>=1.7.0
|