Update app.py

app.py

@@ -114,6 +114,7 @@ def talk(prompt, history):
     print(messages)
     # binding the system context and new prompt for LLM
     # the chat template structure should be based on text generation model format
+    print("check 6")
 
 # indicates the end of a sequence
     stream = model.create_chat_completion(messages = messages, max_tokens=1000, stop=["</s>"], stream=False)