Update app/main.py

app/main.py

@@ -32,7 +32,7 @@ def ask_llama(llm: Llama, question: str, max_new_tokens=200, temperature=0.5, re
   prompt = f"""<|begin_of_text|>
 <|start_header_id|> user  <|end_header_id|> {question} <|eot_id|>
 <|start_header_id|> assistant <|end_header_id|>"""
-  result = extract_restext(llm.complete(prompt, max_tokens=max_new_tokens, temperature=temperature, repeat_penalty=repeat_penalty, stop=["<|eot_id|>", "<|end_of_text|>"])).replace("<|eot_id|>", "").replace("<|end_of_text|>", "")
+  result = extract_restext(llm(prompt, max_tokens=max_new_tokens, temperature=temperature, repeat_penalty=repeat_penalty, stop=["<|eot_id|>", "<|end_of_text|>"])).replace("<|eot_id|>", "").replace("<|end_of_text|>", "")
   return result
 
 # def chat_llama(llm: Llama, chat_history: dict, max_new_tokens=200, temperature=0.5, repeat_penalty=2.0):