# Core document processing libraries
PyMuPDF==1.23.8
python-docx==0.8.11
beautifulsoup4==4.12.2
pandas==2.1.4
requests==2.31.0

# OCR and image processing
pytesseract==0.3.10
Pillow==10.1.0
opencv-python==4.8.1.78
pdf2image==1.16.3

# Table extraction libraries
tabula-py==2.8.2
camelot-py[cv]==0.11.0

# LangChain for text splitting (using compatible versions)
langchain>=0.1.0,<0.2.0
langchain-text-splitters>=0.0.1
langchain-community>=0.0.20

# Testing dependencies
pytest==7.4.3
pytest-cov==4.1.0

# Additional utilities
numpy==1.24.3
lxml==4.9.3