move stopword data package from code to Dockerfile

api/Dockerfile

@@ -73,7 +73,8 @@ COPY --from=packages ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 
 # Download nltk data
-RUN python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger')"
+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')" \
+    && chmod -R 755 /usr/local/share/nltk_data
 
 ENV TIKTOKEN_CACHE_DIR=/app/api/.tiktoken_cache
 
@@ -86,7 +87,15 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh
 
+# Create non-root user and set permissions
+RUN groupadd -r -g 1001 dify && \
+    useradd -r -u 1001 -g 1001 -s /bin/bash dify && \
+    mkdir -p /home/dify && \
+    chown -R 1001:1001 /app /home/dify ${TIKTOKEN_CACHE_DIR} /entrypoint.sh
+
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}
+ENV NLTK_DATA=/usr/local/share/nltk_data
+USER 1001
 
 ENTRYPOINT ["/bin/bash", "/entrypoint.sh"]

api/core/rag/datasource/vdb/oracle/oraclevector.py

@@ -302,8 +302,7 @@ class OracleVector(BaseVector):
                     nltk.data.find("tokenizers/punkt")
                     nltk.data.find("corpora/stopwords")
                 except LookupError:
-                    nltk.download("punkt")
+                    raise LookupError("Unable to find the required NLTK data package: punkt and stopwords")
-                    nltk.download("stopwords")
                 e_str = re.sub(r"[^\w ]", "", query)
                 all_tokens = nltk.word_tokenize(e_str)
                 stop_words = stopwords.words("english")