Update app.py

app.py

@@ -42,6 +42,7 @@ def respond(
     settings.stream = True
 
     messages = BasicChatHistory()
+    print("history")
     print(history)
 
     for msn in history:
@@ -50,13 +51,14 @@ def respond(
             'content': msn[1]
         }
         messages.add_message(dic)
+
+    print("messages")
+    print(messages)
     
-    stream = agent.get_chat_response(message, llm_sampling_settings=settings, chat_history=messages, returns_streaming_generator=True)
+    stream = agent.get_chat_response(message, llm_sampling_settings=settings, chat_history=messages, returns_streaming_generator=True, print_output=False)
     
     outputs = ""
     for output in stream:
-        print(output)
-        # if "content" in output["choices"][0]["delta"]:  
         outputs += output
         yield outputs
     # from llama_cpp import Llama