FROM python:3.12-slim WORKDIR /app COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt COPY src/ ./src/ ENV PYTHONUNBUFFERED=1 \ PORT=8090 \ LITELLM_BASE_URL=http://litellm.ai-inference.svc:4000 \ REQUEST_TIMEOUT=120 EXPOSE 8090 HEALTHCHECK --interval=30s --timeout=10s --start-period=15s --retries=3 \ CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8090/health')" CMD ["python", "src/server.py"]