Dockerfile

FROM python:3.8.9

# Set environment variables for Java
ENV JAVA_HOME /usr/lib/jvm/java-11-openjdk-amd64
ENV PATH $JAVA_HOME/bin:$PATH

# Install OpenJDK 11
RUN apt-get update && \
    apt-get install -y openjdk-11-jdk && \
    apt-get clean;

# Install Gradle
ENV GRADLE_HOME /opt/gradle
ENV PATH $GRADLE_HOME/bin:$PATH
ENV GRADLE_VERSION 7.3

RUN wget -q https://services.gradle.org/distributions/gradle-${GRADLE_VERSION}-bin.zip -P /tmp && \
    unzip -q /tmp/gradle-${GRADLE_VERSION}-bin.zip -d /opt && \
    ln -s /opt/gradle-${GRADLE_VERSION} /opt/gradle && \
    rm /tmp/gradle-${GRADLE_VERSION}-bin.zip

RUN apt-get update && \
    apt-get -y --no-install-recommends install unzip

WORKDIR /app

RUN git clone https://github.com/kermitt2/grobid.git
RUN cd grobid && \
    ./gradlew clean install && \
    bash -c "./gradlew run &" && \
    cd ..

COPY ./requirements.txt /app/requirements.txt
COPY ./packages.txt /app/packages.txt

RUN apt-get update && xargs -r -a /app/packages.txt apt-get install -y && rm -rf /var/lib/apt/lists/*
RUN pip3 install --no-cache-dir -r /app/requirements.txt

RUN git clone https://github.com/kermitt2/grobid_client_python && \
    cd grobid_client_python && \
    python3 setup.py install && \
    cd ..

# User
RUN useradd -m -u 1000 user
USER user
ENV HOME /home/user
ENV PATH $HOME/.local/bin:$PATH

WORKDIR $HOME
RUN mkdir app
WORKDIR $HOME/app
COPY . $HOME/app

EXPOSE 8501
CMD streamlit run app.py \
    --server.headless true \
    --server.enableCORS false \
    --server.enableXsrfProtection false \
    --server.fileWatcherType none