requirements.txt

# Core dependencies
# LlamaIndex: RAG framework
llama-index-core>=0.12.0
llama-index-cli>=0.4.0
llama-index-vector-stores-faiss>=0.4.0
llama-index-retrievers-bm25>=0.6.0
llama-index-embeddings-huggingface>=0.4.0
llama-index-readers-file>=0.5.4

# Docling: Advanced document parsing and processing
docling~=2.61.1

# Embeddings: State-of-the-art text embeddings
sentence-transformers~=5.1.2

# MCP framework: Model Context Protocol server
fastmcp~=2.13.0
pydantic~=2.12.4
fastapi~=0.121.1
uvicorn[standard]~=0.38.0

# Data processing: Core data manipulation libraries
beautifulsoup4~=4.14.2
pandas~=2.3.3
tiktoken~=0.12.0
joblib~=1.5.2

# Web scraping and automation: Browser automation tools
selenium~=4.38.0
selenium-wire~=5.1.0
requests~=2.32.5

# Configuration: Environment and settings management
pyyaml>=6.0.0
python-dotenv>=1.0.0

# Vector storage: FAISS for efficient similarity search
faiss-cpu~=1.12.0

# Development: Testing and language detection
pytest~=9.0.0
pytest-mock~=3.15.1
langdetect~=1.0.9