Update app.py

app.py

@@ -2,9 +2,11 @@ import gradio as gr
 from transformers import pipeline, AutoTokenizer
 from sentence_transformers import SentenceTransformer, util
 import nltk
-nltk.download('punkt')
 from nltk.tokenize import sent_tokenize
 
+# Download NLTK data
+nltk.download('punkt')
+
 # Translation models
 translation_models = {
     'Vietnamese': "Helsinki-NLP/opus-mt-en-vi",
@@ -27,8 +29,11 @@ def get_translator(language):
 
 # Helper function to generate bullet points
 def generate_bullet_points(text):
-    model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+    print("Original Text:", text)
     sentences = sent_tokenize(text)
+    print("Sentences:", sentences)
+    
+    model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
     embeddings = model.encode(sentences, convert_to_tensor=True)
     clusters = util.community_detection(embeddings, threshold=0.75)
     
@@ -38,7 +43,10 @@ def generate_bullet_points(text):
         main_sentence = cluster_sentences[0] if cluster_sentences else ""
         bullet_points.append(main_sentence.strip())
     
-    return "\n".join(f"- {point}" for point in bullet_points)
+    result = "\n".join(f"- {point}" for point in bullet_points)
+    print("Bullet Points:", result)
+    
+    return result
 
 # Helper function to split text into chunks
 def split_text(text, max_tokens=1024):
@@ -113,3 +121,4 @@ iface.launch()
 
 
 
+