setup.sh

#!/bin/bash

# Update package lists
sudo apt-get update

# Install Poppler utilities (for pdf2image)
sudo apt-get install -y poppler-utils

# Install Tesseract-OCR (for pytesseract)
sudo apt-get install -y tesseract-ocr

# Optional: Install language packs for Tesseract if needed (e.g., for English)
# sudo apt-get install -y tesseract-ocr-eng

echo "System dependencies installed successfully."