Dockerfile

FROM python:3.12-slim

# Install system dependencies for tesseract OCR and image processing
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    libtesseract-dev \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy requirements first for better Docker layer caching
COPY requirements.txt .

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

# Copy application files
COPY . .

# Expose Streamlit port (HF Spaces default)
EXPOSE 7860

# Set environment variables for Streamlit
ENV STREAMLIT_SERVER_PORT=7860
ENV STREAMLIT_SERVER_ADDRESS=0.0.0.0
ENV STREAMLIT_SERVER_HEADLESS=true
ENV STREAMLIT_SERVER_ENABLE_CORS=false
ENV STREAMLIT_SERVER_ENABLE_XSRF_PROTECTION=false

# Health check
HEALTHCHECK CMD curl --fail http://localhost:7860/_stcore/health || exit 1

# Run the application
CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]