Dockerfile

FROM python:3.9-slim

WORKDIR /app

# Install system dependencies for document processing
RUN apt-get update && apt-get install -y \
    ffmpeg \
    libmagic1 \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first for better caching
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Create a non-root user (better security for Hugging Face)
RUN useradd -m -u 1000 user
RUN chown -R user:user /app
USER user

# Create temp directory for file processing
RUN mkdir -p /tmp/materials

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV TRANSFORMERS_CACHE=/tmp/transformers_cache

# Expose port (Hugging Face uses port 7860 by default)
EXPOSE 7860

# Health check command (Hugging Face Spaces requirement)
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:7860/health')"

# Start the application with gunicorn for production
CMD uvicorn app:app --host 0.0.0.0 --port 7860 --workers 1