Dockerfile

FROM python:3.10-slim

WORKDIR /app

RUN apt-get update && apt-get install -y \
    build-essential \
    cmake \
    && rm -rf /var/lib/apt/lists/*

RUN CMAKE_ARGS="-DLLAMA_NATIVE=OFF" \
    pip install --no-cache-dir \
    fastapi \
    uvicorn \
    llama-cpp-python==0.2.90 \
    httpx

COPY app.py /app/app.py
COPY model.gguf /models/model.gguf

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