Dockerfile

# Stage 1: Builder
FROM python:3.10-slim as builder

WORKDIR /app
COPY requirements.txt .

RUN apt-get update && \
    apt-get install -y --no-install-recommends gcc python3-dev && \
    pip install --no-cache-dir gunicorn==21.2.0 uvicorn==0.23.2 && \
    pip install --no-cache-dir -r requirements.txt && \
    apt-get remove -y gcc python3-dev && \
    apt-get autoremove -y

# Stage 2: Runtime
FROM python:3.10-slim

WORKDIR /app

# Install system dependencies AS ROOT (before switching user)
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    ffmpeg \
    tesseract-ocr \
    libtesseract-dev \
    tesseract-ocr-eng \
    tesseract-ocr-fra \
    tesseract-ocr-spa \
    curl && \
    rm -rf /var/lib/apt/lists/*

# Copy Python dependencies from system locations
COPY --from=builder /usr/local/lib/python3.10/site-packages /usr/local/lib/python3.10/site-packages
COPY --from=builder /usr/local/bin/gunicorn /usr/local/bin/
COPY --from=builder /usr/local/bin/uvicorn /usr/local/bin/
COPY . .

# Create non-root user and set permissions
RUN useradd -m appuser && \
    chown -R appuser:appuser /app && \
    mkdir -p /tmp/uploads && \
    chown appuser:appuser /tmp/uploads

# Switch to non-root user
USER appuser

# Health check with longer intervals and start period for model loading
HEALTHCHECK --interval=60s --timeout=30s --start-period=300s --retries=5 \
    CMD curl -f http://localhost:7860/health || exit 1

EXPOSE 7860

# Use port 7860 which is standard for Hugging Face Spaces
CMD ["gunicorn", "-k", "uvicorn.workers.UvicornWorker", "-b", "0.0.0.0:7860", "--timeout", "300", "--worker-connections", "10", "app.main:app"]