Dockerfile

# Multi-stage build for OCR Agent
# Stage 1: Builder
FROM python:3.12-slim as builder

WORKDIR /build

# Install system dependencies for building
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    git \
    && rm -rf /var/lib/apt/lists/*

# Copy project files
COPY pyproject.toml setup.py* ./
COPY src ./src

# Build wheels for dependencies
RUN pip install --upgrade pip setuptools wheel && \
    pip wheel --no-cache-dir --no-deps --wheel-dir /build/wheels -e .

# Stage 2: Runtime
FROM python:3.12-slim

WORKDIR /app

# Install runtime dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

# Copy wheels from builder
COPY --from=builder /build/wheels /wheels

# Install wheels
RUN pip install --upgrade pip && \
    pip install --no-cache /wheels/* && \
    rm -rf /wheels

# Copy application code
COPY src ./src
COPY docs ./docs
COPY examples ./examples

# Create directories for uploads and outputs
RUN mkdir -p /app/uploads /app/outputs

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1

# Expose port for web service
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
    CMD python -c "import requests; requests.get('http://localhost:8000/api/v1/health')" || exit 1

# Default command: start web service
CMD ["ocr-agent", "serve", "--host", "0.0.0.0", "--port", "8000"]