Update app.py

app.py

@@ -45,19 +45,28 @@ def setTextVisibility(cbg, model_name_input):
     sentences = []
     result = []
     model = SentenceTransformer('all-mpnet-base-v2')
-    exclude_words = {"a", "the", "for", "from", "of", "in", "over", "as", "on", "is", "am", "have", "an", "has", "had", "and", "by", "it", "its", "those", "these", "above", "to", "However"}
+    exclude_words = {"a", "the", "for", "from", "of", "in", "over", "as", "on", "is", "am", "have", "an", "has", "had", "and", "by", "it", "its", "those", "these", "above", "to"}
     sentences_org = ["In a quaint little town nestled in the heart of the mountains, a small bakery famous for its artisanal breads and pastries had a line of customers stretching out the door, eagerly waiting to savor the freshly baked goods that were known far and wide for their delightful flavors.",
                 "Within a picturesque mountain village, there stood a renowned bakery, celebrated for its handcrafted bread and sweet treats, attracting a long queue of patrons each morning, all keen to enjoy the baked delicacies that had gained widespread acclaim for their exceptional taste.",
                 "A charming bakery, located in a small mountainous hamlet, renowned for producing exquisite handmade pastries and bread, was bustling with a crowd of eager customers lined up outside, each anticipating the chance to indulge in the famous baked items celebrated for their extraordinary deliciousness.",
                 "In a cozy, mountain-encircled village, a beloved bakery was the center of attraction, known for its traditional baking methods and delightful pastries, drawing a consistent stream of people waiting outside, all desiring to experience the renowned flavors that made the bakery's products distinctively mouth-watering."]
     for text in cbg:
          sentences.append(answer_question(text, model_name_input))
+    
+    # Step 1: Cluster the sentences
+    num_clusters = 1
+    sentence_clusters = cluster_sentences(sentences, model, num_clusters)
+
+    # Step 2: Highlight similar words within each cluster
+    clustered_sentences = [[] for _ in range(num_clusters)]
+
+    for sentence, cluster_id in zip(sentences, sentence_clusters):
+        clustered_sentences[cluster_id].append(sentence)
+    
+    highlighted_clustered_sentences = []
 
-    highlighted_sentences = []
-    for i, sentence in enumerate(sentences):
-        other_sentences = sentences[:i] + sentences[i+1:]
-        highlighted_sentence = highlight_words(sentence, other_sentences, model, exclude_words)
-        highlighted_sentences.append(highlighted_sentence)
+    for cluster in clustered_sentences:
+        highlighted_clustered_sentences.extend(highlight_words_within_cluster(cluster, model, exclude_words))
         
     for idx, sentence in enumerate(highlighted_sentences):
         result.append("<p><strong>"+ cbg[idx] +"</strong></p><p>"+ sentence +"</p><br/>")