requirements.txt

# Core web framework
streamlit>=1.28.0

# AI/ML libraries
transformers>=4.35.0
torch>=2.0.0
tokenizers>=0.14.0

# PDF processing
PyPDF2>=3.0.1

# Text processing and utilities
regex>=2023.10.3
numpy>=1.24.0
pandas>=2.0.0

# Additional dependencies for transformers
accelerate>=0.24.0
safetensors>=0.4.0

# Optional: For better performance
sentencepiece>=0.1.99

# Development and testing (optional)
pytest>=7.4.0
black>=23.0.0
flake8>=6.0.0