Dockerfile

FROM python:3.11-slim
WORKDIR /app
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential cmake git ninja-build && rm -rf /var/lib/apt/lists/*
COPY . .
ENV CMAKE_BUILD_PARALLEL_LEVEL=4
ENV FORCE_CMAKE=1
RUN pip install --no-cache-dir fastapi uvicorn pydantic huggingface_hub
RUN pip install --no-cache-dir --prefer-binary llama-cpp-python \
    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
ENV HF_HOME=/app/hf_cache
EXPOSE 7860
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]