Update Dockerfile

Dockerfile

@@ -16,20 +16,33 @@ RUN apt-get update && apt-get install -y \
 COPY requirements.txt ./
 RUN pip3 install --no-cache-dir -r requirements.txt
 
-# Download NLTK data
-RUN python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords'); nltk.download('vader_lexicon')"
+# Set NLTK data directory to a location with proper permissions
+ENV NLTK_DATA=/usr/local/share/nltk_data
+RUN mkdir -p $NLTK_DATA
+
+# Download NLTK data as root (with permissions) and handle SSL issues
+RUN python -c "import ssl; ssl._create_default_https_context = ssl._create_unverified_context; import nltk; nltk.download('stopwords', download_dir='/usr/local/share/nltk_data'); nltk.download('wordnet', download_dir='/usr/local/share/nltk_data'); nltk.download('omw-1.4', download_dir='/usr/local/share/nltk_data')"
 
 # Copy the application code
 COPY . .
 
-# Create necessary directories
-RUN mkdir -p models artifacts
+# Create necessary directories with proper permissions
+RUN mkdir -p models artifacts vectorizers
+RUN chmod -R 755 models artifacts vectorizers
+
+# Create a non-root user for security
+RUN useradd -m -u 1000 user
+RUN chown -R user:user /app
+USER user
+
+# Set environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    PYTHONPATH=/app \
+    NLTK_DATA=/usr/local/share/nltk_data
 
 # Expose the port that Streamlit runs on
 EXPOSE 8501
 
-# Add health check
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
 # Run the application
 CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]