chore(docker): update nltk data download process to include unstructured download_nltk_packages (#28876)

This commit is contained in:
Lework 2026-01-05 15:50:33 +08:00 committed by GitHub
parent a99ac3fe0d
commit 34f3b288a7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions

View File

@ -79,7 +79,8 @@ COPY --from=packages --chown=dify:dify ${VIRTUAL_ENV} ${VIRTUAL_ENV}
ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
# Download nltk data
RUN mkdir -p /usr/local/share/nltk_data && NLTK_DATA=/usr/local/share/nltk_data python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('stopwords')" \
RUN mkdir -p /usr/local/share/nltk_data \
&& NLTK_DATA=/usr/local/share/nltk_data python -c "import nltk; from unstructured.nlp.tokenize import download_nltk_packages; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('stopwords'); download_nltk_packages()" \
&& chmod -R 755 /usr/local/share/nltk_data
ENV TIKTOKEN_CACHE_DIR=/app/api/.tiktoken_cache