# OCR
ocrmypdf>=16.0.0
pytesseract>=0.3.10

# Table extraction
camelot-py[cv]>=0.11.0
pdfplumber>=0.10.3

# PDF handling / marking
PyMuPDF>=1.23.0

# Data handling
pandas>=2.0.0
numpy>=1.24.0

# Image processing (Camelot dependency)
opencv-python>=4.8.0

# PDF utilities
ghostscript>=0.7


# pip install pymupdf pdf2image pillow pytesseract transformers torch sentencepiece tqdm reportlab opencv-python-headless