FROM python:3.10-slim WORKDIR /app RUN apt-get update && apt-get install -y build-essential curl && rm -rf /var/lib/apt/lists/* COPY requirements.txt . # THE FIX: Download the pre-compiled CPU wheel. This reduces install time from hours to seconds! RUN pip install --no-cache-dir -r requirements.txt --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu COPY app.py . EXPOSE 7860 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]