Dockerfile

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

FROM python:3.11-slim

ENV LANG=C.UTF-8

ARG ARCH="cpu"

RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
    build-essential \
    default-jre \
    libgl1-mesa-glx \
    libjemalloc-dev \
    libreoffice \
    poppler-utils \
    tesseract-ocr \
    libpq-dev \
    libcairo2 \
    wget

# Install ffmpeg static build
RUN cd /root && wget https://johnvansickle.com/ffmpeg/builds/ffmpeg-git-amd64-static.tar.xz && \
mkdir ffmpeg-git-amd64-static && tar -xvf ffmpeg-git-amd64-static.tar.xz -C ffmpeg-git-amd64-static --strip-components 1 && \
export PATH=/root/ffmpeg-git-amd64-static:$PATH && \
cp /root/ffmpeg-git-amd64-static/ffmpeg /usr/local/bin/


RUN useradd -m -s /bin/bash user && \
    mkdir -p /home/user && \
    chown -R user /home/user/

COPY comps /home/user/comps

RUN pip install --no-cache-dir --upgrade pip setuptools && \
    if [ ${ARCH} = "cpu" ]; then \
        PIP_EXTRA_INDEX_URL="--extra-index-url https://download.pytorch.org/whl/cpu"; \
    else \
        PIP_EXTRA_INDEX_URL=""; \
    fi && \
    pip install --no-cache-dir torch torchvision ${PIP_EXTRA_INDEX_URL} && \
    pip install --no-cache-dir ${PIP_EXTRA_INDEX_URL} -r /home/user/comps/dataprep/src/requirements.txt && \
    pip install opentelemetry-api==1.29.0 opentelemetry-exporter-otlp==1.29.0 opentelemetry-sdk==1.29.0

ENV PYTHONPATH=$PYTHONPATH:/home/user

RUN mkdir -p /home/user/comps/dataprep/src/uploaded_files && chown -R user /home/user/comps/dataprep/src/uploaded_files

USER user
ENV NLTK_DATA=/home/user/nltk_data

WORKDIR /home/user/comps/dataprep/src

ENTRYPOINT ["sh", "-c", "python $( [ \"$MULTIMODAL_DATAPREP\" = \"true\" ] && echo 'opea_dataprep_multimodal_microservice.py' || echo 'opea_dataprep_microservice.py')"]