Update app.py

app.py

@@ -29,7 +29,7 @@ def format_prompt(message, history, system_prompt, bot_name):
   for user_prompt, bot_response in history:
     prompt += f"User: {user_prompt}\n"
     prompt += f"{bot_name}: {bot_response}\n"
-  prompt += f"""User: {message}\n{bot_name}:"""
+  prompt += f"""User: {message}\n{bot_name}: """
   return prompt
 
 seed = 42
@@ -68,24 +68,23 @@ def generate(
         bot_name = "Assistant"
     
     formatted_prompt = format_prompt(prompt, history, system_prompt, bot_name)
+    output = ""
     
     try:
         stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-        output = ""
-
+        
         for response in stream:
             output += response.token.text
-    
             for stop_str in STOP_SEQUENCES:
                 if output.endswith(stop_str):
                     output = output[:-len(stop_str)]
 #                    output = output.rstrip()
                     yield output
             yield output
+        return output
     except Exception as e:
-        raise gr.Error(f"Client error while generating: {e}")
-    return output
-
+        raise gr.Error(f"Error: {e}. Please retry!")
+        
 additional_inputs=[
     gr.Textbox("", label="Optional system prompt"),
     gr.Slider(
@@ -134,5 +133,5 @@ with gr.Blocks() as demo:
         additional_inputs=additional_inputs,
     ) 
 
-#demo.queue(concurrency_count=100, api_open=False).launch(show_api=False)
-demo.queue(concurrency_count=100).launch()
+demo.queue(concurrency_count=100, api_open=False).launch(show_api=False)
+#demo.queue(concurrency_count=100).launch()