paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Bakes the NLTK data into the image (~60mb)

Browse Source
This commit is contained in:
Trenton H
2022-12-02 12:02:56 -08:00
parent 3f6e3a2750
commit 8da3ae2c53
3 changed files with 5 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile
View File

@@ -228,6 +228,10 @@ RUN set -eux \
&& python3 -m pip install --no-cache-dir --upgrade wheel \
&& echo "Installing Python requirements" \
&& python3 -m pip install --default-timeout=1000 --no-cache-dir --requirement requirements.txt \
&& echo "Installing NLTK data" \
&& python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/local/share/nltk_data" snowball_data \
&& python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/local/share/nltk_data" stopwords \
&& python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/local/share/nltk_data" punkt \
&& echo "Cleaning up image" \
&& apt-get -y purge ${BUILD_PACKAGES} \
&& apt-get -y autoremove --purge \