Langchain-Chatchat 前一天晚上配置好能跑之后，第二天重新启动就报错了，，，

这是啥问题啊，拒绝访问了

Feb 17 '24 02:02 Nikolahuang

🤖

嘿，@AndersonHuangEDU！好久不见，又遇到一些技术挑战了吗？😄 抱歉听说你遇到了问题，别担心，我正在查看，很快就会回复你具体的解决方案。

Feb 17 '24 02:02 dosubot[bot]

2024-02-17 10:18:41,010 - utils.py[line:95] - ERROR: ConnectError: error when post /llm_model/list_running_models: [WinError 10061] 由于目标计算机积极拒绝，无法连接。 2024-02-17 10:18:43,028 - utils.py[line:95] - ERROR: ConnectError: error when post /llm_model/list_running_models: [WinError 10061] 由于目标计算机积极拒绝，无法连接。 2024-02-17 10:18:45,041 - utils.py[line:95] - ERROR: ConnectError: error when post /llm_model/list_running_models: [WinError 10061] 由于目标计算机积极拒绝，无法连接。 2024-02-17 10:18:47,155 - utils.py[line:95] - ERROR: ConnectError: error when post /llm_model/list_running_models: [WinError 10061] 由于目标计算机积极拒绝，无法连接。 2024-02-17 10:18:49,173 - utils.py[line:95] - ERROR: ConnectError: error when post /llm_model/list_running_models: [WinError 10061] 由于目标计算机积极拒绝，无法连接。 2024-02-17 10:18:51,190 - utils.py[line:95] - ERROR: ConnectError: error when post /llm_model/list_running_models: [WinError 10061] 由于目标计算机积极拒绝，无法连接。 2024-02-17 10:18:51.190 Uncaught app exception Traceback (most recent call last): File "C:\Users\17769.conda\envs\env\Lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 535, in _run_script exec(code, module.dict) File "D:\BaiduNetdiskDownload\langchain_chatchatv2_anderson\webui.py", line 64, in pages[selected_page]["func"](api=api, is_lite=is_lite) File "D:\BaiduNetdiskDownload\langchain_chatchatv2_anderson\webui_pages\dialogue\dialogue.py", line 163, in dialogue_page running_models = list(api.list_running_models()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: 'NoneType' object is not iterable

Feb 17 '24 02:02 Nikolahuang

🤖

Based on the error message you provided, it seems like the Langchain-Chatchat software is unable to establish a connection to the target computer, and the function api.list_running_models() is returning a None object when it's expected to return an iterable object.

The error "ConnectError: error when post /llm_model/list_running_models: [WinError 10061] 由于目标计算机积极拒绝，无法连接" indicates that the program is unable to establish a connection to the target computer. This could be due to several reasons such as the server not running, firewall blocking the connection, or network issues. You can check if the server is running and accessible, check your firewall settings, and ensure that you have a stable network connection.

The TypeError: 'NoneType' object is not iterable error usually occurs when you try to iterate over a None object. This could be due to a function returning None when you're expecting it to return an iterable object. In this case, you need to check the function api.list_running_models() to make sure it is returning an iterable object and not None. You can add print statements or use a debugger to check the return values of your functions.

running_models = list(api.list_running_models())

If the function is returning None, you need to debug the function to find out why it is not returning the expected result.

The api.list_running_models() function in the Langchain-Chatchat codebase is used to retrieve a list of currently loaded models and their configurations from the Fastchat controller. If an error occurs during this process, it logs the error and returns a BaseResponse with an error message.

Here is the function for your reference:

def list_running_models(
    controller_address: str = Body(None, description="Fastchat controller服务器地址", examples=[fschat_controller_address()]),
    placeholder: str = Body(None, description="该参数未使用，占位用"),
) -> BaseResponse:
    '''
    从fastchat controller获取已加载模型列表及其配置项
    '''
    try:
        controller_address = controller_address or fschat_controller_address()
        with get_httpx_client() as client:
            r = client.post(controller_address + "/list_models")
            models = r.json()["models"]
            data = {m: get_model_config(m).data for m in models}
            return BaseResponse(data=data)
    except Exception as e:
        logger.error(f'{e.__class__.__name__}: {e}',
                        exc_info=e if log_verbose else None)
        return BaseResponse(
            code=500,
            data={},
            msg=f"failed to get available models from controller: {controller_address}。错误信息是： {e}")

You can find this function in the server/llm_api.py file.

I hope this helps! If you have any other questions or need further clarification, feel free to ask.

Sources

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

Feb 17 '24 02:02 dosubot[bot]

重启程序