Dockerfile

FROM python:3.10.13-slim-bullseye

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

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

RUN pip install --no-cache-dir -U pip setuptools wheel && \
    pip install "huggingface-hub" "hf-transfer" "gradio[oauth]>=4.28.0" "gradio_huggingfacehub_search==0.0.7" "APScheduler" \
                bitsandbytes transformers

COPY --chown=1000 . ${HOME}/app

# clone from ngxson's fork to support tied embeddings models, see https://github.com/arcee-ai/mergekit/pull/483
RUN git clone https://github.com/ngxson/mergekit.git -b xsn/tied_embd && \
    cd mergekit && \
    pip install --upgrade pip && \
    pip install -e .

ENV PYTHONPATH=${HOME}/app \
    PYTHONUNBUFFERED=1 \
    HF_HUB_ENABLE_HF_TRANSFER=1 \
    GRADIO_ALLOW_FLAGGING=never \
    GRADIO_NUM_PORTS=1 \
    GRADIO_SERVER_NAME=0.0.0.0 \
    GRADIO_THEME=huggingface \
    TQDM_POSITION=-1 \
    TQDM_MININTERVAL=1 \
    SYSTEM=spaces \
    LD_LIBRARY_PATH=/usr/local/cuda/lib64:${LD_LIBRARY_PATH} \
    PATH=/usr/local/nvidia/bin:${PATH}


CMD ["python", "app.py"]