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

WORKDIR /app

# System dependencies
RUN apt-get update && apt-get install -y \
    python3.11 \
    python3-pip \
    curl \
    git \
    && rm -rf /var/lib/apt/lists/*

# Python dependencies
COPY requirements.txt .
RUN pip3 install --no-cache-dir -r requirements.txt

# App code
COPY app/ ./app/

EXPOSE 8892

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD curl -f http://localhost:8892/health || exit 1

CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8892"]