FROM python:3.11-slim

WORKDIR /app

# Install system dependencies for PDF, Image, and DOCX processing
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-deu \
    poppler-utils \
    libpoppler-cpp-dev \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements
COPY requirements.txt .

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

# Copy application code
COPY . .

# Create necessary directories
RUN mkdir -p /app/temp /app/uploads

# Expose port
EXPOSE 8004

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:8004/health || exit 1

# Start FastAPI server
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8004"]