able to load sample insurance

app.py

@@ -74,7 +74,11 @@ if 'is_initialized' not in st.session_state:
 
     nltk.download('punkt')
     nltk.download('stopwords')
-    st.session_state.stop_words = set(stopwords.words('english'))
+    # print("stop words start")
+    # print(stopwords.words('english'))
+    # print("stop words end")
+    stop_words_list = stopwords.words('english')
+    st.session_state.stop_words = set(stop_words_list)
     st.session_state.bert_tokenizer = BertTokenizer.from_pretrained("bert-base-uncased", )
     st.session_state.bert_model = BertModel.from_pretrained("bert-base-uncased", ).to('cuda')
     st.session_state.paraphrase_tokenizer = AutoTokenizer.from_pretrained("Vamsi/T5_Paraphrase_Paws")
@@ -94,7 +98,7 @@ if 'list_count' in st.session_state:
             read_progress_bar.progress(progress_percentage)
 
             sentence_encodings = []
-            sentences = sent_tokenize(paragraph['text'])
+            sentences = sent_tokenize(paragraph['paragraph'])
             for sentence in sentences:
                 if sentence.strip().endswith('?'):
                     sentence_encodings.append(None)