Update app.py

app.py

@@ -10,6 +10,12 @@ from transformers import AutoTokenizer, AutoModel
 from sklearn.metrics.pairwise import cosine_similarity
 
 
+def average_pool(last_hidden_states: Tensor,
+                 attention_mask: Tensor) -> Tensor:
+    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
+    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+
+
 df = pd.read_csv('rjokes.csv')
 data_embeddings = np.load("rjokes-embeddings.npy")
 
@@ -43,7 +49,7 @@ with gr.Blocks() as demo:
         # Get corresponding 'text' for top k similar points
         top_k_text = df['text'].iloc[top_k_idx].tolist()
     
-        chat_history.extend(f"{i+1}. {top_k_text[i]}" for i in range(len(top_k_text))))
+        chat_history.extend([f"{i+1}. {top_k_text[i]}" for i in range(len(top_k_text))])
         return "", chat_history
 
     msg.submit(respond, [msg, chatbot], [msg, chatbot])