Update app.py

app.py

@@ -33,13 +33,13 @@ def vector_search(query):
     # Calculate cosine similarity between the query and all embeddings
     similarities = cosine_similarity([query_embedding], embeddings)
 
-    # Adjust similarity scores based on ratings
-    ratings = np.array([item["rating"] for item in data_list])
-    adjusted_similarities = similarities * ratings.reshape(-1, 1)
+    # # Adjust similarity scores based on ratings
+    # ratings = np.array([item["rating"] for item in data_list])
+    # adjusted_similarities = similarities * ratings.reshape(-1, 1)
 
     # Get top N most similar items (e.g., top 3)
     top_n = 3
-    top_indices = adjusted_similarities[0].argsort()[-top_n:][::-1]  # Get indices of the top N results
+    top_indices = similarities[0].argsort()[-top_n:][::-1]  # Get indices of the top N results
     top_items = [data_list[i] for i in top_indices]
     
     # Format the output for display