[BUG] WebDemo中使用Few Shot功能，如果不传图片无法正常使用

[gongjimin]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

在WebDemo2.6中使用Few Shot功能，如果不传图片，生成时页面报错。

期望行为 | Expected Behavior

正常看到经过Few Shot学习后的回答内容

复现方法 | Steps To Reproduce

使用web_demo_2.6.py加载int4模型，打开页面后切换到Frew Shot页签。填写用户问题和助手回答，但是不上传图片，点击add example，然后再次填写用户问题，点击Generate.

运行环境 | Environment

无关

备注 | Anything else?

查看日志能看到是格式校验错误。

msgs: [{'role': 'user', 'content': ['你是谁？']}, {'role': 'assistant', 'content': ['我是XXX']}]
answer: 你好！我是XXX，一个由OpenAI训练的大型语言模型。我被设计用来理解和生成自然语言文本，并可以回答各种问题或参与对话。今天有什么我可以帮助你的吗？
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/gradio/queueing.py", line 624, in process_events
    response = await route_utils.call_process_api(
  File "/usr/local/lib/python3.10/dist-packages/gradio/route_utils.py", line 323, in call_process_api
    output = await app.get_blocks().process_api(
  File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 2028, in process_api
    data = await self.postprocess_data(block_fn, result["prediction"], state)
  File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1834, in postprocess_data
    prediction_value = block.postprocess(prediction_value)
  File "/usr/local/lib/python3.10/dist-packages/modelscope_studio/components/Chatbot/__init__.py", line 351, in postprocess
    list)) else self._postprocess_chat_messages(message))
  File "/usr/local/lib/python3.10/dist-packages/modelscope_studio/components/Chatbot/__init__.py", line 285, in _postprocess_chat_messages
    chat_message = MultimodalMessage(**chat_message)
  File "/usr/local/lib/python3.10/dist-packages/pydantic/main.py", line 212, in __init__
    validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)
pydantic_core._pydantic_core.ValidationError: 4 validation errors for MultimodalMessage
files.0.FileMessage
  Input should be a valid dictionary or instance of FileMessage [type=model_type, input_value=None, input_type=NoneType]
    For further information visit https://errors.pydantic.dev/2.9/v/model_type
files.0.dict[any,any]
  Input should be a valid dictionary [type=dict_type, input_value=None, input_type=NoneType]
    For further information visit https://errors.pydantic.dev/2.9/v/dict_type
files.0.FileData
  Input should be a valid dictionary or instance of FileData [type=model_type, input_value=None, input_type=NoneType]
    For further information visit https://errors.pydantic.dev/2.9/v/model_type
files.0.str
  Input should be a valid string [type=string_type, input_value=None, input_type=NoneType]
    For further information visit https://errors.pydantic.dev/2.9/v/string_type