Update src/streamlit_app.py

src/streamlit_app.py

@@ -252,10 +252,10 @@ def extract_unique_names(content_list, field):
     return sorted(list(unique_names))
 
 @st.cache_data(ttl=3600)  # Cache feature vectors for 1 hour
-def prepare_content_features():
+def prepare_content_features(content_list):
     """Prepare and cache content features for similarity matching"""
     # Convert to DataFrame for easier processing
-    df = pd.DataFrame(all_content)
+    df = pd.DataFrame(content_list)
     
     # Create TF-IDF vectorizer for text features
     tfidf = TfidfVectorizer(
@@ -319,11 +319,11 @@ def get_content_clusters(features, n_clusters=50):
     kmeans = get_kmeans_model(n_clusters)
     return kmeans.fit_predict(features)
 
-def find_similar_content(content, n_clusters=50, n_recommendations=5):
+def find_similar_content(content, all_content_list, n_clusters=50, n_recommendations=5):
     """Find similar content using optimized k-means clustering"""
     try:
         # Get cached features and cluster assignments
-        features, df = prepare_content_features()
+        features, df = prepare_content_features(all_content_list)
         cluster_labels = get_content_clusters(features, n_clusters)
         
         # Find the index of the selected content
@@ -630,7 +630,7 @@ def main():
                     similar_button = st.button(f"🔍 Find Similar Content", key=f"similar_{i}")
                     if similar_button:
                         with st.spinner("Finding similar content..."):
-                            similar_content = find_similar_content(content)
+                            similar_content = find_similar_content(content, all_content)
                             
                             if similar_content:
                                 # Create tabs for different aspects of recommendations