[update]add main

main.py

@@ -98,6 +98,8 @@ def chat_with_llm_non_stream(question: str,
     utterances.append(question)
 
     encoded_utterances = tokenizer.__call__(utterances, add_special_tokens=False)
+    encoded_utterances = encoded_utterances["input_ids"]
+
     for encoded_utterance in encoded_utterances:
         input_ids.extend(encoded_utterance)
         if model.config.model_type == "chatglm":
@@ -150,6 +152,8 @@ def chat_with_llm_streaming(question: str,
     utterances.append(question)
 
     encoded_utterances = tokenizer.__call__(utterances, add_special_tokens=False)
+    encoded_utterances = encoded_utterances["input_ids"]
+
     for encoded_utterance in encoded_utterances:
         input_ids.extend(encoded_utterance)
         if model.config.model_type == "chatglm":