Dockerfile

# Hugging Face Spaces Dockerfile for Document Conversion
# This installs LibreOffice for Word to PDF conversion

FROM python:3.10-slim

# Install LibreOffice, Tesseract OCR, and required system dependencies
RUN apt-get update && apt-get install -y \
    libreoffice \
    libreoffice-writer \
    libreoffice-calc \
    libreoffice-impress \
    tesseract-ocr \
    tesseract-ocr-eng \
    default-jre-headless \
    libgl1 \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# 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"]