FROM python:3.11-slim

WORKDIR /app

# Install system dependencies for Docling and OCR
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    libgl1 \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    poppler-utils \
    tesseract-ocr \
    libtesseract-dev \
    ffmpeg \
    && rm -rf /var/lib/apt/lists/*

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

# Download Docling models at build time (optional, reduces first-run latency)
RUN python -c "from docling.document_converter import DocumentConverter; DocumentConverter()" || true

# Copy application code
COPY server.py .

# Create non-root user
RUN useradd -m -u 1000 appuser && chown -R appuser:appuser /app
USER appuser

EXPOSE 8081

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8081/health')" || exit 1

CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8081"]