binary-husky/gpt_academic · error · RuntimeError

请配置 TAICHU_API_KEY

Error message

请配置 TAICHU_API_KEY

What it means

Configuration guard of the Taichu (太极/taichu) LLM bridge: predict_no_ui_long_connection raises RuntimeError('请配置 TAICHU_API_KEY') when validate_key() finds the TAICHU_API_KEY config value empty. It fires before TaichuChatInit is imported, so no network traffic has occurred.

Source

Thrown at request_llms/bridge_taichu.py:28

def validate_key():
    TAICHU_API_KEY = get_conf("TAICHU_API_KEY")
    if TAICHU_API_KEY == '': return False
    return True

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"] == "taichu":
    #     llm_kwargs["llm_model"] = "taichu"

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

    # 开始接收回复
    from .com_taichu import TaichuChatInit
    zhipu_bro_init = TaichuChatInit()
    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. Obtain an API key from the Taichu open platform and set TAICHU_API_KEY in config_private.py (or env / docker-compose), then restart
2. Confirm the loaded value: from toolbox import get_conf; assert get_conf('TAICHU_API_KEY') != ''
3. If using docker, add TAICHU_API_KEY to the container environment

Example fix

# before
TAICHU_API_KEY = ''

# after (config_private.py)
TAICHU_API_KEY = 'your-taichu-key'

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

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

When it happens

Trigger: Calling request_llms/bridge_taichu.py:28 predict_no_ui_long_connection() (used by background/plugin threads) with TAICHU_API_KEY == '' as resolved by get_conf from config.py, config_private.py or the environment.

Common situations: Default config.py ships with an empty TAICHU_API_KEY; user selected the taichu model without registering on the Taichu open platform; key placed in config.py but a config_private.py or env var overrides it with an empty string.

Related errors

• 请配置讯飞星火大模型的XFYUN_APPID, XFYUN_API_KEY, XFYUN_API_SECRET
• 请配置ZHIPUAI_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/b44d6e59461b6e37. Report an issue: GitHub.