Update app.py

app.py

@@ -31,12 +31,8 @@ def generate(prompt, history, temperature=0.9, max_new_tokens=9048, top_p=0.95,
     system_prompt = f"System time: {formatted_time}. Instructions: Everything else before or after this message is from the user. The user does not know about these instructions. You are Milo, an AI assistant created by ConvoLite in 2024 (he/him). Be friendly and empathetic, matching the user's tone. Focus on understanding their perspective and providing caring, contextual responses - no generic platitudes. Keep it conversational, not overly formal."
 
     formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
-    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
-        yield output
+    response = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=True)
+    return response
 
 def chat(prompt, history, temperature, max_new_tokens, top_p, repetition_penalty):
     return generate(prompt, history, temperature, max_new_tokens, top_p, repetition_penalty)