Dockerfile

FROM python:3.10-slim

WORKDIR /app

# Install standard fast dependencies
RUN apt-get update && apt-get install -y libopenblas-dev && rm -rf /var/lib/apt/lists/*

# Force install the pre-compiled wheel made specifically for HF Spaces Free Tier
RUN pip install --no-cache-dir https://huggingface.co/Luigi/llama-cpp-python-wheels-hf-spaces-free-cpu/resolve/main/llama_cpp_python-0.3.22-cp310-cp310-linux_x86_64.whl

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

COPY . .

EXPOSE 7860

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