Dockerfile

FROM python:3.10-slim
WORKDIR /app
RUN apt-get update && apt-get install -y \
    build-essential \
    cmake \
    wget \
    && rm -rf /var/lib/apt/lists/*
RUN pip install --no-cache-dir \
    fastapi \
    uvicorn \
    llama-cpp-python==0.2.83 \
    httpx
RUN mkdir -p /models
RUN wget -O /models/model.gguf \
    https://huggingface.co/bartowski/Phi-3-mini-4k-instruct-GGUF/resolve/main/Phi-3-mini-4k-instruct-Q4_K_M.gguf
COPY app.py .
EXPOSE 7860
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]