Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.9-slim

# Set the working directory to /app
WORKDIR /app

# make directory /app/files/
RUN mkdir /app/files/
RUN mkdir /app/ckpt/
# grant permission to write to /app/files/
RUN chmod 777 /app/files/ 
RUN chmod 777 /app/ckpt/

# Copy the requirements file into the container
COPY requirements.txt .
COPY serve_grobid.sh .

# JAVA
RUN apt-get update && \
    apt-get install -y openjdk-11-jre-headless && \
    apt-get clean;
ENV JAVA_HOME /usr/lib/jvm/java-11-openjdk-amd64/
ENV PATH $JAVA_HOME/bin:$PATH


# Install any needed packages specified in requirements.txt
RUN pip install --no-cache-dir -r requirements.txt

# Copy the current directory contents into the container at /app
COPY . /app

# Expose port 7860 for the streamlit app to listen on
EXPOSE 5000
EXPOSE 7860

# open the grobid server
RUN apt-get update && \
    apt-get install -y wget unzip
RUN chmod +x serve_grobid.sh
RUN ./serve_grobid.sh 

# open the backend server and streamlit app
RUN chmod +x run.sh
CMD ["bash" ,"run.sh"]