Update app.py

app.py

@@ -50,7 +50,7 @@ Now begin. You can make the descriptions a bit more verbose than in the examples
 
 Description: {text}
 Thought:"""
-    return llm_client.text_generation(prompt, max_new_tokens=2000, stream=True, stop_sequences=[end_sequence])
+    return llm_client.chat_completion([{"role": "user", "content": prompt}], max_new_tokens=2096, stream=True, stop_sequences=[end_sequence])
 
 
 def parse_llm_output(output):