query encoding refactored

app.py

@@ -206,12 +206,8 @@ if 'paragraph_sentence_encodings' in st.session_state:
         if 'prev_query' not in st.session_state or st.session_state.prev_query != query:
             st.session_state.prev_query = query
             st.session_state.premise = query
-            query_tokens = st.session_state.bert_tokenizer(query, return_tensors="pt", padding=True, truncation=True).to(
-                'cuda')
-            with torch.no_grad():  # Disable gradient calculation for inference
-                query_encoding = st.session_state.bert_model(**query_tokens).last_hidden_state[:, 0,
-                                 :].cpu().numpy()  # Move the result to CPU and convert to NumPy
 
+            query_encoding = encode_sentence(query)
             paragraph_scores = []
             sentence_scores = []
             total_count = len(st.session_state.paragraph_sentence_encodings)