binary-husky/gpt_academic · error · RuntimeError

没有配置BAIDU_CLOUD_SECRET_KEY

Error message

没有配置BAIDU_CLOUD_SECRET_KEY

What it means

RuntimeError from get_access_token in bridge_qianfan: the BAIDU_CLOUD_SECRET_KEY read via get_conf is an empty string, so the OAuth client_credentials flow cannot be attempted. It fails before any network call; the companion check for BAIDU_CLOUD_API_KEY sits directly below. get_access_token is cached (timeout=3600), but a raise is not cached so fixing config takes effect on next call after restart.

Source

Thrown at request_llms/bridge_qianfan.py:39

                    return result

            # Call the function and cache the result
            result = func(*args, **kwargs)
            cache[key] = (result, datetime.now())
            return result
        return wrapper
    return decorator

@cache_decorator(timeout=3600)
def get_access_token():
    """
    使用 AK，SK 生成鉴权签名（Access Token）
    :return: access_token，或是None(如果错误)
    """
    # if (access_token_cache is None) or (time.time() - last_access_token_obtain_time > 3600):
    BAIDU_CLOUD_API_KEY, BAIDU_CLOUD_SECRET_KEY = get_conf('BAIDU_CLOUD_API_KEY', 'BAIDU_CLOUD_SECRET_KEY')

    if len(BAIDU_CLOUD_SECRET_KEY) == 0: raise RuntimeError("没有配置BAIDU_CLOUD_SECRET_KEY")
    if len(BAIDU_CLOUD_API_KEY) == 0: raise RuntimeError("没有配置BAIDU_CLOUD_API_KEY")

    url = "https://aip.baidubce.com/oauth/2.0/token"
    params = {"grant_type": "client_credentials", "client_id": BAIDU_CLOUD_API_KEY, "client_secret": BAIDU_CLOUD_SECRET_KEY}
    access_token_cache = str(requests.post(url, params=params).json().get("access_token"))
    return access_token_cache
    # else:
    #     return access_token_cache


def generate_message_payload(inputs, llm_kwargs, history, system_prompt):
    conversation_cnt = len(history) // 2
    if system_prompt == "": system_prompt = "Hello"
    messages = [{"role": "user", "content": system_prompt}]
    messages.append({"role": "assistant", "content": 'Certainly!'})
    if conversation_cnt:
        for index in range(0, 2*conversation_cnt, 2):
            what_i_have_asked = {}

View on GitHub (pinned to d6bde0fa54)

Solutions

1. Set BAIDU_CLOUD_SECRET_KEY in config_private.py (from Baidu Qianfan console > application credentials)
2. Also set BAIDU_CLOUD_API_KEY - both are required
3. Restart the process after config changes
4. If you did not intend to use Qianfan, switch the model back to an OpenAI-compatible one

Example fix

# config_private.py
# before
BAIDU_CLOUD_SECRET_KEY = ""

# after
BAIDU_CLOUD_SECRET_KEY = "your-qianfan-secret-key"

from shared_utils.config_loader import get_conf
api_key, secret = get_conf('BAIDU_CLOUD_API_KEY', 'BAIDU_CLOUD_SECRET_KEY')
assert api_key and secret, 'Baidu Qianfan credentials missing - set BAIDU_CLOUD_API_KEY and BAIDU_CLOUD_SECRET_KEY'

def qianfan_configured() -> bool:
    api_key, secret = get_conf('BAIDU_CLOUD_API_KEY', 'BAIDU_CLOUD_SECRET_KEY')
    return len(api_key) > 0 and len(secret) > 0

try:
    token = get_access_token()
except RuntimeError as e:
    if 'BAIDU_CLOUD_SECRET_KEY' in str(e):
        raise SystemExit('Set BAIDU_CLOUD_SECRET_KEY in config_private.py') from e

When it happens

Trigger: Using a qianfan (Baidu Qianfan/ERNIE) model without setting BAIDU_CLOUD_SECRET_KEY in config_private.py; key defined under the wrong variable name; Docker/env deployment missing the variable.

Common situations: Selecting an ERNIE Bot model in model dropdown before configuring Baidu credentials; copying config template and skipping Baidu section.

Related errors

• 没有配置BAIDU_CLOUD_API_KEY
• 请配置YUNQUE_SECRET_KEY
• 你提供了错误的API_KEY。 1. 临时解决方案：直接在输入区键入api_key，然后回车提交。 2. 长效解决方
• 你提供了错误的API_KEY。 1. 临时解决方案：直接在输入区键入api_key，然后回车提交。 2. 长效解决方
• 没有设置ANTHROPIC_API_KEY选项

AI-assisted analysis of binary-husky/gpt_academic@d6bde0fa54 (2026-08-14). Data as JSON: /api/errors/3957852c47e6e502. Report an issue: GitHub.