Update app.py

app.py

@@ -51,7 +51,7 @@ def generate(
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": "### Instruction: \n" + "根据巨杉数据库SequoiaDB的相关问题进行回答。\n" + "### Input:\n" + message + "\n ### Response:"})
 
-    chat = tokenizer.apply_chat_template(conversation, tokenize=False)
+    chat = tokenizer.apply_chat_template([{"role": "user", "content": "### Instruction: \n" + "根据巨杉数据库SequoiaDB的相关问题进行回答。\n" + "### Input:\n" + message + "\n ### Response:"}], tokenize=False)
     inputs = tokenizer(chat, return_tensors="pt", add_special_tokens=False).to("cuda")
     if len(inputs) > MAX_INPUT_TOKEN_LENGTH:
         inputs = inputs[-MAX_INPUT_TOKEN_LENGTH:]