fix nltk averaged_perceptron_tagger download and fix score limit is none (#7582)

Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
This commit is contained in:
Jyong 2024-08-26 15:14:05 +08:00 committed by GitHub
parent a7743a4f47
commit 7ae728a9a3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 1 deletions

View File

@ -12,5 +12,6 @@
</component> </component>
<component name="VcsDirectoryMappings"> <component name="VcsDirectoryMappings">
<mapping directory="" vcs="Git" /> <mapping directory="" vcs="Git" />
<mapping directory="$PROJECT_DIR$/.." vcs="Git" />
</component> </component>
</project> </project>

View File

@ -65,7 +65,7 @@ COPY --from=packages ${VIRTUAL_ENV} ${VIRTUAL_ENV}
ENV PATH="${VIRTUAL_ENV}/bin:${PATH}" ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
# Download nltk data # Download nltk data
RUN python -c "import nltk; nltk.download('punkt')" RUN python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger')"
# Copy source code # Copy source code
COPY . /app/api/ COPY . /app/api/

View File

@ -616,6 +616,7 @@ class DatasetRetrieval:
for document in all_documents: for document in all_documents:
if score_threshold is None or document.metadata['score'] >= score_threshold: if score_threshold is None or document.metadata['score'] >= score_threshold:
filter_documents.append(document) filter_documents.append(document)
if not filter_documents: if not filter_documents:
return [] return []
filter_documents = sorted(filter_documents, key=lambda x: x.metadata['score'], reverse=True) filter_documents = sorted(filter_documents, key=lambda x: x.metadata['score'], reverse=True)