binary-husky/gpt_academic · error · RuntimeError

请配置ZHIPUAI_API_KEY

Error message

请配置ZHIPUAI_API_KEY

What it means

Configuration guard of the Zhipu GLM bridge: predict_no_ui_longconnection raises RuntimeError('请配置ZHIPUAI_API_KEY') when validate_key() reports the ZHIPUAI_API_KEY config empty. Note it fires after normalizing llm_kwargs['llm_model'] to the default zhipuai model, before any API call.

Source

Thrown at request_llms/bridge_zhipu.py:33

def make_media_input(inputs, image_paths):
    for image_path in image_paths:
        inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
    return inputs

def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
                                  observe_window:list=[], console_silence:bool=False):
    """
        ⭐多线程方法
        函数的说明请见 request_llms/bridge_all.py
    """
    watch_dog_patience = 5
    response = ""

    if llm_kwargs["llm_model"] == "zhipuai":
        llm_kwargs["llm_model"] = zhipuai_default_model

    if validate_key() is False:
        raise RuntimeError('请配置ZHIPUAI_API_KEY')

    # 开始接收回复
    from .com_zhipuglm import ZhipuChatInit
    zhipu_bro_init = ZhipuChatInit()
    for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, sys_prompt):
        if len(observe_window) >= 1:
            observe_window[0] = response
        if len(observe_window) >= 2:
            if (time.time() - observe_window[1]) > watch_dog_patience:
                raise RuntimeError("程序终止。")
    return response


def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
    """
        ⭐单线程方法
        函数的说明请见 request_llms/bridge_all.py

View on GitHub (pinned to d6bde0fa54)

Solutions

1. Set ZHIPUAI_API_KEY in config_private.py (or docker-compose env), restart the service
2. Verify: from toolbox import get_conf; assert get_conf('ZHIPUAI_API_KEY')
3. Ensure the key comes from open.bigmodel.cn and is active (no quota/binding issues)

Example fix

# before
ZHIPUAI_API_KEY = ''

# after (config_private.py)
ZHIPUAI_API_KEY = 'your-zhipuai-key'

from toolbox import get_conf
assert get_conf('ZHIPUAI_API_KEY'), 'ZHIPUAI_API_KEY not configured'

try:
    predict_no_ui_long_connection(...)
except RuntimeError as e:
    if 'ZHIPUAI_API_KEY' in str(e):
        raise ConfigurationError(str(e)) from e
    raise

When it happens

Trigger: Calling request_llms/bridge_zhipu.py:33 predict_no_ui_long_connection() with ZHIPUAI_API_KEY == '' from get_conf (config.py / config_private.py / env).

Common situations: Fresh install with placeholder config; user switched the model dropdown to zhipuai without a key; key set only in the shell that launched a different process (systemd/docker missing the env var).

Related errors

• 请配置讯飞星火大模型的XFYUN_APPID, XFYUN_API_KEY, XFYUN_API_SECRET
• 请配置 TAICHU_API_KEY
• 请配置 DASHSCOPE_API_KEY
• 请配置讯飞星火大模型的XFYUN_APPID, XFYUN_API_KEY, XFYUN_API_SECRET
• 文件大小 ({file_size_mb:.1f}MB) 超过限制 {max_size_mb}MB

AI-assisted analysis of binary-husky/gpt_academic@d6bde0fa54 (2026-08-14). Data as JSON: /api/errors/1e83d0c482cee872. Report an issue: GitHub.