Dockerfile

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

# Set the working directory inside the container
WORKDIR /app

# Install system dependencies (required for PyMuPDF and other tools)
RUN apt-get update && apt-get install -y \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Copy only the requirements first to leverage Docker caching
COPY requirements.txt .

# Install Python dependencies
RUN pip install --no-cache-dir --default-timeout=1000 --retries 5 -i https://pypi.org/simple/ --extra-index-url https://download.pytorch.org/whl/cpu -r requirements.txt

# Copy the rest of your application code
COPY . .

# Expose the port Streamlit runs on
EXPOSE 8501

# Command to run the application
CMD ["streamlit", "run", "main.py", "--server.port=8501", "--server.address=0.0.0.0"]