Dockerfile

# Use a base Python image
FROM python:3.10-slim

# Install system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-mar \
    libtesseract-dev \
    poppler-utils \
    && apt-get clean

# Set up application
WORKDIR /app
COPY . /app

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Expose port for Gradio app
EXPOSE 7860

# Run the application
CMD ["python", "app.py"]