Update app.py

app.py

@@ -64,7 +64,10 @@ def chat_inf(system_prompt,prompt,history,client_choice,seed,temp,tokens,top_p,r
         hist_len=len(history)
         print(hist_len)
     if hist_len>4000:
+        yield [(prompt,"Wait. I need to compress our Chat history...")]
         history=compress_history(history,client_choice,seed,temp,tokens,top_p,rep_p)
+        yield [(prompt,"History has been compressed, processing request...")]
+            
     generate_kwargs = dict(
         temperature=temp,
         max_new_tokens=tokens,