Update app.py

app.py

@@ -42,7 +42,6 @@ def answer_question(prompt):
     generated_answer = hub_chain.run(input_data)  
     return generated_answer
 
-    
 def calculate_similarity(word, other_words, model, threshold=0.5):
     embeddings_word = model.encode([word])
     embeddings_other_words = model.encode(other_words)
@@ -106,7 +105,7 @@ def highlight_words_within_cluster(sentences, model, exclude_words):
 
 exclude_words = {"a", "the", "for", "from", "of", "in","over", "as", "on", "is", "am", "have", "an","has", "had", "and", "by", "it", "its", "those", "these", "was", "were", "their", "them", "I", "you", "also", "your", "me", "after"}
 
-def cluster_sentences(sentences, model, num_clusters=1):
+def cluster_sentences(sentences, model, num_clusters=3):
     embeddings = model.encode(sentences)
     kmeans = KMeans(n_clusters=num_clusters)
     kmeans.fit(embeddings)
@@ -123,6 +122,8 @@ sentences = ["In a quaint little town nestled in the heart of the mountains, a s
 
 "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."]
 
+# Step 1: Cluster the sentences
+num_clusters = 1
 sentence_clusters = cluster_sentences(sentences, model, num_clusters)
 
 # Step 2: Highlight similar words within each cluster
@@ -133,7 +134,7 @@ for sentence, cluster_id in zip(sentences, sentence_clusters):
 highlighted_clustered_sentences = []
 for cluster in clustered_sentences:
     highlighted_clustered_sentences.extend(highlight_words_within_cluster(cluster, model, exclude_words))
-
+    
     
 text_list = []