Dockerfile

FROM nvidia/cuda:12.2.2-cudnn8-devel-ubuntu22.04

ARG DEBIAN_FRONTEND=noninteractive

RUN apt-get update && apt-get install --no-install-recommends -y \
  build-essential \
  ffmpeg \
  python3-pip \
  python3-dev \
  python3-venv \
  ninja-build \
  libreoffice \
  git \
  unzip \
  wget \
  curl \
  && apt-get clean && rm -rf /var/lib/apt/lists/*

WORKDIR /data

RUN curl https://sh.rustup.rs -sSf | bash -s -- -y

ENV VIRTUAL_ENV=/opt/venv

RUN python3 -m venv $VIRTUAL_ENV
ENV PATH="$VIRTUAL_ENV/bin:${PATH}"
ENV PATH="/root/.cargo/bin:${PATH}"

COPY ./requirements.txt /data/requirements.txt
RUN pip3 install --no-cache-dir --upgrade -r /data/requirements.txt

RUN python3 -m spacy download en_core_web_sm

COPY pip.conf $VIRTUAL_ENV/pip.conf

RUN pip3 install onnxruntime-gpu==1.17.1

RUN useradd -m -u 1000 user
USER user

ENV HOME=/home/user \
	PATH=/home/user/.local/bin:$PATH \
    PYTHONPATH=$HOME/app \
    PYTHONUNBUFFERED=1 \
    NVIDIA_VISIBLE_DEVICES=all \
    NVIDIA_DRIVER_CAPABILITIES=compute,utility \
	SYSTEM=spaces \
    HF_HOME=/data \
    NLTK_DATA=$HF_HOME \
    TOKENIZERS_PARALLELISM=false \
    PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True

WORKDIR $HOME/data

COPY --chown=user . $HOME/data

EXPOSE 8501

CMD streamlit run app.py \
    --server.headless true \
    --server.enableCORS false \
    --server.enableXsrfProtection false \
    --server.maxUploadSize 1000 \
    --server.fileWatcherType watchdog \
    --theme.backgroundColor "#EEE3D3" \
    --theme.secondaryBackgroundColor "#CCC8C2" \
    --theme.primaryColor "#EF792D" \
    --theme.textColor "#7D6654"