Update app.py

app.py

@@ -187,7 +187,7 @@ def chat_with_model(prompt, document_section, model_choice='Llama-2-7b-chat-hf')
                     res_box.markdown(f'*{result}*')
                     
             except:
-                st.write('Stream llm issue')
+                st.write('.')
     
         full_reply_content = result
         st.write("Elapsed time:")
@@ -198,9 +198,6 @@ def chat_with_model(prompt, document_section, model_choice='Llama-2-7b-chat-hf')
         readitaloud(full_reply_content)
         return result
       
-    except:
-        st.write('Llama model is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).')
-    
 # Chat and Chat with files
 def chat_with_model2(prompt, document_section, model_choice='gpt-3.5-turbo'):
     model = model_choice
@@ -236,6 +233,7 @@ def chat_with_model2(prompt, document_section, model_choice='gpt-3.5-turbo'):
                 res_box.markdown(f'*{result}*') 
         except:
             st.write(' ')
+            
     full_reply_content = all_content
     st.write("Elapsed time:")
     st.write(time.time() - start_time)