# IMPORTANT: On modern Debian/Ubuntu systems (Python 3.12+), you MUST use a virtual environment
# before installing these packages. Run: python3 -m venv venv && source venv/bin/activate
# Or use the automated setup script: ./setup.sh

torch>=2.0.0
transformers>=4.30.0
numpy>=1.24.0
tqdm>=4.65.0
tensorboard>=2.13.0
matplotlib>=3.7.0

# Optional dependencies for data processing
# Install these if you want to process PDFs or images:
# For PDF processing (choose one - pdfplumber is recommended for better quality):
pdfplumber>=0.9.0  # Recommended: better text extraction quality
# PyPDF2>=3.0.0  # Alternative PDF library (lighter weight but less accurate)

# For image OCR (requires Tesseract OCR engine installed on system):
# pytesseract>=0.3.10  # For OCR
# Pillow>=10.0.0  # Required for image processing with pytesseract
# 
# To install Tesseract OCR engine:
#   Ubuntu/Debian: sudo apt-get install tesseract-ocr
#   macOS: brew install tesseract
#   Windows: Download from https://github.com/UB-Mannheim/tesseract/wiki

# For downloading datasets from Hugging Face (used by download_large_data.py):
datasets>=2.14.0  # Optional: for downloading WikiText, OpenWebText, BookCorpus, etc.