Dockerfile

FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV OMP_NUM_THREADS=4
ENV MKL_NUM_THREADS=4
ENV OPENBLAS_NUM_THREADS=4

# Install Python and dependencies
RUN apt-get update && apt-get install -y \
    python3.10 \
    python3-pip \
    git \
    wget \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

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

# Install Python packages
RUN pip3 install --no-cache-dir -r requirements.txt

# Copy application code
COPY app.py .

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

# Expose port
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python3 -c "import requests; requests.get('http://localhost:7860/health')"

# Run the application
CMD ["python3", "app.py"]