changed output to only bot message

app.py

@@ -56,7 +56,7 @@ def gpt_respond(tab_name, message, chat_history, max_convo_length = 10):
     return "", chat_history
 
 def vicuna_respond(tab_name, message, chat_history):
-    formatted_prompt = f'''Generate the output only for the assistant. Please output any {tab_name} in the following sentence one per line without any additional text: {message}'''
+    formatted_prompt = f'''Generate the output only for the assistant. Please output any <{tab_name}> in the following sentence one per line without any additional text: <{message}>'''
     print('Prompt + Context:')
     print(formatted_prompt)
     input_ids = vicuna_tokenizer.encode(formatted_prompt, return_tensors="pt")
@@ -66,10 +66,10 @@ def vicuna_respond(tab_name, message, chat_history):
         
     chat_history.append((formatted_prompt, bot_message))
     time.sleep(2)
-    return tab_name, "", chat_history
+    return tab_name, "", bot_message
 
 def llama_respond(tab_name, message, chat_history):
-    formatted_prompt = f'''Generate the output only for the assistant. Please output any {tab_name} in the following sentence one per line without any additional text: {message}'''
+    formatted_prompt = f'''Generate the output only for the assistant. Please output any <{tab_name}> in the following sentence one per line without any additional text: <{message}>'''
     print('Prompt + Context:')
     print(formatted_prompt)
     input_ids = llama_tokenizer.encode(formatted_prompt, return_tensors="pt")
@@ -79,7 +79,7 @@ def llama_respond(tab_name, message, chat_history):
         
     chat_history.append((formatted_prompt, bot_message))
     time.sleep(2)
-    return tab_name, "", chat_history
+    return tab_name, "", bot_message
 
 def interface():
         gr.Markdown(" Description ")