Update app.py

app.py

@@ -141,16 +141,16 @@ def talk(prompt, history):
     import pprint
     stream = model.create_chat_completion(messages = [{"role":"system","content":SYS_PROMPT},{"role":"user","content":formatted_prompt}], max_tokens=1000, stop=["</s>"], stream=True)
 #   print(output['choices'][0]['message']['content'])
-    print(f"{stream}")
-    pprint.pprint(stream)
     text = []
     for output in stream:
-#       text += output['choices'][0]   
+#       text += output['choices'][0]  
+        print(f"{output}")
+        print("check3H")
+
         text.append(output['choices'][0])
         print(f"{text}")
         yield "".join(text)
         print(text)
-        print("check3H")
     
     # preparing tokens for model input
     # add_generation_prompt argument tells the template to add tokens that indicate the start of a bot response