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 \
  curl \
  ffmpeg \
  libsm6 \
  libxext6 \
  python3-pip \
  python3-dev \
  python3-venv \
  python3-wheel \
  ninja-build \
  libmagic-dev \
  pandoc>=2.14.2 \
  libreoffice \
  tesseract-ocr \
  poppler-utils \
  git \
  && apt-get clean && rm -rf /var/lib/apt/lists/*

WORKDIR /data

ENV VIRTUAL_ENV=/opt/venv

RUN python3 -m venv $VIRTUAL_ENV
ENV PATH="$VIRTUAL_ENV/bin:$PATH"

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

RUN pip3 install --no-cache-dir llama-cpp-python \
    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu122

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

WORKDIR $HOME/data

COPY --chown=user . $HOME/data

RUN curl -sfL https://raw.githubusercontent.com/milvus-io/milvus/master/scripts/standalone_embed.sh -o standalone_embed.sh

RUN chmod +x standalone_embed.sh

EXPOSE 8501 19530

CMD ["bash", "-c", "./standalone_embed.sh start & streamlit run app.py --server.headless true --server.enableCORS false --server.enableXsrfProtection false --server.fileWatcherType watchdog"]