Dockerfile

FROM python:3.11-slim

WORKDIR /app

ENV PYTHONUNBUFFERED=1
ENV PIP_NO_CACHE_DIR=1
ENV PIP_EXTRA_INDEX_URL=https://abetlen.github.io/llama-cpp-python/whl/cpu

RUN apt-get update && apt-get install -y --no-install-recommends \
    libgomp1 \
    && rm -rf /var/lib/apt/lists/*

COPY requirements.txt .

RUN pip install --upgrade pip \
    && pip install --prefer-binary --only-binary=llama-cpp-python -r requirements.txt

COPY app.py .

EXPOSE 7860

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