# Core dependencies for PhD Deep Read Workflow
PyMuPDF>=1.24.0           # Fast PDF text extraction
pytesseract>=0.3.10       # Python wrapper for Tesseract OCR
Pillow>=10.0.0            # Image processing for OCR

# Note: Tesseract OCR engine must be installed separately:
# macOS: brew install tesseract
# Ubuntu/Debian: sudo apt install tesseract-ocr
# Windows: https://github.com/UB-Mannheim/tesseract/wiki