requirements.txt

# Core dependencies
pyyaml>=6.0            # YAML configuration parsing
pytesseract>=0.3.10    # OCR text extraction 
pdf2image>=1.16.0      # PDF to image conversion
PyPDF2>=3.0.0          # PDF manipulation
Pillow>=10.0.0         # Image processing
numpy>=1.22.0          # Numerical operations
openai>=1.3.0          # OpenAI API integration

# Image processing and comparison
scikit-image>=0.19.0   # Image similarity comparison and processing
matplotlib>=3.5.0      # Optional: for visualization if needed

# Networking and HTTP
requests>=2.28.0       # HTTP requests

# Optional utilities for better PDF handling
pypdf>=3.15.0          # Advanced PDF operations (newer than PyPDF2)

# System requirements (not pip-installable, but document for reference)
# - Poppler (for pdf2image) - install via: 
#   macOS: brew install poppler
#   Linux: apt-get install poppler-utils
#   Windows: included in resources/poppler/bin
# 
# - Tesseract OCR - install via:
#   macOS: brew install tesseract tesseract-lang
#   Linux: apt-get install tesseract-ocr tesseract-ocr-deu
#   Windows: included in resources/tesseract