Update app.py

app.py

@@ -64,27 +64,25 @@ def _parse_text(text):
 # Demo launching function
 def _launch_demo(args, model, tokenizer, config):
     def predict(_query, _chatbot, _task_history):
-    print(f"User: {_parse_text(_query)}")
-    _chatbot.append((_parse_text(_query), ""))
-    
-    # Tokenize the input
-    input_ids = tokenizer.encode(_query, return_tensors='pt')
-    
-    # Generate a response using the model
-    generated_ids = model.generate(input_ids, max_length=100)
-    
-    # Decode the generated IDs to text
-    full_response = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
-    
-    # Update the chatbot state
-    _chatbot[-1] = (_parse_text(_query), _parse_text(full_response))
-    yield _chatbot
-    
-    print(f"History: {_task_history}")
-    _task_history.append((_query, full_response))
-    print(f"OpenHermes: {_parse_text(full_response)}")
-
-    
+        print(f"User: {_parse_text(_query)}")
+        _chatbot.append((_parse_text(_query), ""))
+        
+        # Tokenize the input
+        input_ids = tokenizer.encode(_query, return_tensors='pt')
+        
+        # Generate a response using the model
+        generated_ids = model.generate(input_ids, max_length=100)
+        
+        # Decode the generated IDs to text
+        full_response = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
+        
+        # Update the chatbot state
+        _chatbot[-1] = (_parse_text(_query), _parse_text(full_response))
+        yield _chatbot
+        
+        print(f"History: {_task_history}")
+        _task_history.append((_query, full_response))
+        print(f"OpenHermes: {_parse_text(full_response)}")
 
     def regenerate(_chatbot, _task_history):
         if not _task_history: