Dockerfile

FROM nvidia/cuda:11.7.1-cudnn8-devel-ubuntu22.04
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && \
    apt-get upgrade -y && \
    apt-get install -y --no-install-recommends \
    git \
    git-lfs \
    wget \
    curl \
    # python build dependencies \
    build-essential \
    libssl-dev \
    zlib1g-dev \
    libbz2-dev \
    libreadline-dev \
    libsqlite3-dev \
    libncursesw5-dev \
    xz-utils \
    tk-dev \
    libxml2-dev \
    libxmlsec1-dev \
    libffi-dev \
    liblzma-dev \
    # gradio dependencies \
    ffmpeg \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

RUN curl -fsSL https://ollama.com/install.sh | sh
ARG OLLAMA_MODEL

RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user \
PATH=/home/user/.local/bin:${PATH}
WORKDIR ${HOME}/app

RUN curl https://pyenv.run | bash
ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
ARG PYTHON_VERSION=3.10.12
RUN pyenv install ${PYTHON_VERSION} && \
pyenv global ${PYTHON_VERSION} && \
pyenv rehash && \
pip install --no-cache-dir -U pip setuptools wheel && \
pip install packaging ninja

COPY --chown=1000 ./requirements.txt /tmp/requirements.txt
RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt && \
    pip install flash-attn --no-build-isolation

    COPY --chown=1000 src ${HOME}/app
    
COPY ollama_init.sh .
RUN sh ./ollama_init.sh ${OLLAMA_MODEL}
EXPOSE 8501
CMD ollama serve & \
    streamlit run app.py \
    --server.headless true \
    --server.enableCORS false \
    --server.enableXsrfProtection false \
    --server.fileWatcherType none \
    --server.address 0.0.0.0 \
    --logger.level debug