# Document Processing Dependencies pandas PyPDF2 python-docx PyYAML nltk hazm arabic-reshaper python-bidi camelot-py opencv-python ghostscript pywin32; platform_system == "Windows" # Additional Dependencies for Table Processing openpyxl # For Excel files tabula-py # For PDF tables pdfminer.six # For PDF text extraction # Utility Dependencies tqdm # For progress bars python-magic # For MIME type detection chardet # For character encoding detection