Fix: fix nltk tokenizer breaking change

This commit is contained in:
shamoon
2024-08-22 19:37:34 -07:00
parent bc0e420d67
commit 813233a8a9

View File

@@ -246,7 +246,7 @@ RUN --mount=type=cache,target=/root/.cache/pip/,id=pip-cache \
&& echo "Installing NLTK data" \
&& python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" snowball_data \
&& python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" stopwords \
&& python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" punkt \
&& python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" punkt_tab \
&& echo "Cleaning up image" \
&& apt-get --yes purge ${BUILD_PACKAGES} \
&& apt-get --yes autoremove --purge \