Dockerfile

# Build stage
FROM python:3.11-slim as builder

WORKDIR /app

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

# Copy requirements and install dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir --user -r requirements.txt

# Download NLTK data
RUN python -c "import nltk; nltk.download('punkt', quiet=True); nltk.download('punkt_tab', quiet=True); nltk.download('stopwords', quiet=True); nltk.download('wordnet', quiet=True)"

# Production stage
FROM python:3.11-slim

WORKDIR /app

# Copy Python packages from builder
COPY --from=builder /root/.local /root/.local
COPY --from=builder /root/nltk_data /root/nltk_data

# Make sure scripts in .local are usable
ENV PATH=/root/.local/bin:$PATH

# Set Python environment variables
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
ENV PYTHONPATH=/app

# Copy application code
COPY src/ ./src/
COPY data/ ./data/

# Create directories for model storage
RUN mkdir -p /app/src/models/serialized /app/visualizations

# Expose port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')" || exit 1

# Run the application
CMD ["uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000"]