yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-12-28 07:33:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

ci: update dockerfile to also add models and nltk (#418)

Browse Source
This commit is contained in:
ryannikolaidis 2023-03-29 20:48:06 -07:00 committed by GitHub
parent 7f6e094c1f
commit 77b6fb2792
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile
View File

@ -78,4 +78,8 @@ RUN python3.8 -m pip install pip==${PIP_VERSION} && \
COPY example-docs example-docs
COPY unstructured unstructured
RUN python3.8 -c "import nltk; nltk.download('punkt')" && \
python3.8 -c "import nltk; nltk.download('averaged_perceptron_tagger')" && \
python3.8 -c "from unstructured.ingest.doc_processor.generalized import initialize; initialize()"
CMD ["/bin/bash"]