Merge pull request #1088 from kermitt2/reduce-image-size

Reduce docker image size for the NN grobid version

Dockerfile.delft

@@ -67,12 +67,12 @@ FROM tensorflow/tensorflow:2.7.0-gpu
 ENV LANG C.UTF-8
 
 # update NVIDIA Cuda key (following a key rotation in April 2022)
-RUN apt-get install -y wget
-RUN apt-key del 7fa2af80
-RUN rm /etc/apt/sources.list.d/cuda.list
-RUN rm /etc/apt/sources.list.d/nvidia-ml.list
-RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb
-RUN dpkg -i cuda-keyring_1.0-1_all.deb
+RUN apt-get install -y wget && \
+    apt-key del 7fa2af80 && \
+    rm /etc/apt/sources.list.d/cuda.list && \
+    rm /etc/apt/sources.list.d/nvidia-ml.list && \
+    wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb && \
+    dpkg -i cuda-keyring_1.0-1_all.deb
 
 # Add Tini
 ENV TINI_VERSION v0.19.0
@@ -96,7 +96,7 @@ COPY --from=builder /opt/grobid .
 RUN python3 -m pip install pip --upgrade
 
 # install DeLFT via pypi
-RUN pip3 install requests delft==0.3.3
+RUN pip3 install requests delft==0.3.4
 # link the data directory to /data
 # the current working directory will most likely be /opt/grobid
 RUN mkdir -p /data \
@@ -112,13 +112,14 @@ ENV JAVA_OPTS=-Xmx4g
 
 # install jep (and temporarily the matching JDK)
 ENV JDK_URL=https://download.java.net/java/GA/jdk17.0.2/dfd4a8d0985749f896bed50d7138ee7f/8/GPL/openjdk-17.0.2_linux-x64_bin.tar.gz
-RUN curl --fail --show-error --location -q ${JDK_URL} -o /tmp/openjdk.tar.gz 
-RUN mkdir /tmp/jdk-17 
-RUN tar xvfz /tmp/openjdk.tar.gz --directory /tmp/jdk-17 --strip-components 1 --no-same-owner 
-RUN /tmp/jdk-17/bin/javac -version
-RUN JAVA_HOME=/tmp/jdk-17 pip3 install jep==4.0.2 
-RUN rm -f /tmp/openjdk.tar.gz 
-RUN rm -rf /tmp/jdk-17
+RUN curl --fail --show-error --location -q ${JDK_URL} -o /tmp/openjdk.tar.gz &&  \
+    mkdir /tmp/jdk-17 &&  \
+    tar xvfz /tmp/openjdk.tar.gz --directory /tmp/jdk-17 --strip-components 1 --no-same-owner && \
+    /tmp/jdk-17/bin/javac -version && \
+    JAVA_HOME=/tmp/jdk-17 pip3 install jep==4.0.2 &&  \
+    rm -f /tmp/openjdk.tar.gz && \
+    rm -rf /tmp/jdk-17
+
 ENV LD_LIBRARY_PATH=/usr/local/lib/python3.8/dist-packages/jep:grobid-home/lib/lin-64:grobid-home/lib/lin-64/jep:${LD_LIBRARY_PATH}
 # remove libjep.so because we are providing our own version in the virtual env above
 RUN rm /opt/grobid/grobid-home/lib/lin-64/jep/libjep.so
@@ -128,11 +129,11 @@ RUN rm /opt/grobid/grobid-home/lib/lin-64/jep/libjep.so
 
 COPY --from=builder /opt/grobid-source/grobid-home/scripts/preload_embeddings.py .
 COPY --from=builder /opt/grobid-source/grobid-home/config/resources-registry.json .
-RUN python3 preload_embeddings.py --registry ./resources-registry.json
-RUN ln -s /opt/grobid /opt/delft
+RUN python3 preload_embeddings.py --registry ./resources-registry.json &&  \
+    ln -s /opt/grobid /opt/delft
 
-RUN mkdir delft
-RUN cp ./resources-registry.json delft/
+RUN mkdir delft && \
+    cp ./resources-registry.json delft/
 
 ENV GROBID_SERVICE_OPTS "--add-opens java.base/java.lang=ALL-UNNAMED"