requirements.txt

# Knowledge Bank Tools - Python Dependencies

# Core dependencies
yt-dlp>=2023.0.0                    # YouTube metadata extraction (no API key needed)
youtube-transcript-api>=0.6.0       # Transcript/caption extraction
chromadb>=0.4.0                     # Vector database for semantic search
sentence-transformers>=2.2.0        # Embedding models

# PDF processing
pdfplumber>=0.10.0                  # PDF text extraction with layout analysis
PyPDF2>=3.0.0                       # PDF parsing (fallback)
anthropic>=0.40.0                   # Claude API for LLM-based metadata extraction

# Text processing
python-dateutil>=2.8.0              # Date parsing and manipulation

# CLI framework
click>=8.0.0                        # Command-line interface

# Server (for persistent mode)
fastapi>=0.100.0                    # REST API framework
uvicorn>=0.23.0                     # ASGI server
requests>=2.31.0                    # HTTP client (for CLI → server communication)

# Testing
pytest>=7.0.0                       # Testing framework
pytest-cov>=4.0.0                   # Coverage reporting
pytest-mock>=3.10.0                 # Mocking utilities
httpx>=0.24.0                       # Async HTTP client for API testing

# Future dependencies (commented out):
# pandas>=2.0.0          # Data manipulation for analytics
# pyarrow>=10.0.0        # Parquet file support
# pydantic>=2.0.0        # Data validation