Dockerfile

FROM python:3.10-slim

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY llm_service.py .

RUN mkdir -p /app/cache

EXPOSE 7860
CMD ["uvicorn", "llm_service:app", "--host", "0.0.0.0", "--port", "7860"]