Dockerfile

# Multi-stage build for ML Service
FROM python:3.11-slim as builder

# Install system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    libgomp1 \
    && rm -rf /var/lib/apt/lists/*

# Create app directory
WORKDIR /app

# Copy requirements first for better caching
COPY requirements.txt .

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

# Production stage
FROM python:3.11-slim

# Install runtime dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    libgomp1 \
    && rm -rf /var/lib/apt/lists/*

# Create non-root user for security
RUN useradd -m -u 1000 mluser && \
    mkdir -p /app && \
    chown -R mluser:mluser /app

# Set working directory
WORKDIR /app

# Copy Python packages from builder
COPY --from=builder /usr/local/lib/python3.11/site-packages /usr/local/lib/python3.11/site-packages
COPY --from=builder /usr/local/bin /usr/local/bin

# Copy application code
COPY --chown=mluser:mluser . .

# Switch to non-root user
USER mluser

# Expose port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python -c "import requests; requests.get('http://localhost:8000/health')"

# Run the application
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]