Dockerfile

# Grab a fresh copy of the Python image
FROM python:3.11-slim

# Install build and runtime dependencies
RUN apt-get update && \
    apt-get install -y \
    libopenblas-dev \
    ninja-build \
    build-essential \
    pkg-config \
    curl

RUN pip install -U pip setuptools wheel && \
    CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" FORCE_CMAKE=1 pip install --verbose llama-cpp-python[server]

# Download model
RUN mkdir model && \
    curl -L https://huggingface.co/TheBloke/Yarn-Mistral-7B-128k-GGUF/resolve/main/yarn-mistral-7b-128k.Q6_K.gguf -o model/gguf-model.bin

COPY ./start_server.sh ./
COPY ./main.py ./
COPY ./index.html ./

# Make the server start script executable
RUN chmod +x ./start_server.sh

# Set environment variable for the host
ENV HOST=0.0.0.0
ENV PORT=7860

# Expose a port for the server
EXPOSE ${PORT}

# Run the server start script
CMD ["/bin/sh", "./start_server.sh"]