Dockerfile

FROM python:3.11-slim

# Set metadata
LABEL maintainer="MLOps Team"
LABEL description="MLOps Pipeline Application"
LABEL version="1.0"

# Set working directory
WORKDIR /app

# Set environment variables
ENV PYTHONPATH=/app
ENV FLASK_APP=app.py
ENV FLASK_ENV=production
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1

# Install system dependencies
RUN apt-get update && apt-get install -y \
    gcc \
    g++ \
    curl \
    && rm -rf /var/lib/apt/lists/* \
    && apt-get clean

# Create non-root user for security
RUN groupadd -r mlops && useradd -r -g mlops mlops

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

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

# Copy application code
COPY . .

# Create necessary directories with proper permissions
RUN mkdir -p artifacts/model_trainer \
    artifacts/data_transformation \
    artifacts/data_validation \
    artifacts/feature_engineering \
    artifacts/model_evaluation \
    artifacts/data_ingestion \
    logs \
    static \
    templates && \
    chown -R mlops:mlops /app

# Switch to non-root user
USER mlops

# Expose port
EXPOSE 5000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:5000/health || exit 1

# Run the application
CMD ["python", "app.py"]