Dockerfile

# Hugging Face Spaces Dockerfile for Document Conversion
# Optimized for minimal size and fast startup

FROM python:3.10-slim

# Install ONLY essential packages (no GUI, no unnecessary libraries)
RUN apt-get update && apt-get install -y --no-install-recommends \
    # LibreOffice headless only (no GUI components)
    libreoffice-writer-nogui \
    libreoffice-calc-nogui \
    libreoffice-impress-nogui \
    # Tesseract OCR (English only)
    tesseract-ocr \
    tesseract-ocr-eng \
    # Minimal Java runtime for LibreOffice
    default-jre-headless \
    # OpenCV system dependencies (minimal)
    libgl1 \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender1 \
    # Aggressive cleanup to reduce image size
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/* \
    && rm -rf /tmp/* /var/tmp/* \
    # Remove LibreOffice bloat (galleries, extra fonts, docs)
    && rm -rf /usr/lib/libreoffice/share/gallery \
    && rm -rf /usr/share/fonts/truetype/liberation \
    && rm -rf /usr/share/doc \
    && rm -rf /usr/share/man \
    && rm -rf /usr/share/locale

# Set working directory
WORKDIR /app

# Copy requirements and install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY app.py .

# Create temp directory for conversions
RUN mkdir -p /tmp/conversions

# Expose port 7860 (Hugging Face Spaces default)
EXPOSE 7860

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV PORT=7860

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD python -c "import requests; requests.get('http://localhost:7860/health')"

# Run the application
CMD ["gunicorn", "--bind", "0.0.0.0:7860", "--workers", "2", "--timeout", "60", "app:app"]