binary-husky/gpt_academic · critical · AssertionError

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

Error message

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. 长效解决方案：在config.py中配置。

What it means

AssertionError raised at the top of generate_payload in the main ChatGPT bridge: is_any_api_key(llm_kwargs['api_key']) returned False, meaning the key string is empty or contains no usable key (it checks for non-placeholder, non-'sk-'-missing values). The bridge builds Authorization: Bearer headers from this key, so it aborts before any request. The message offers both a quick fix (type the key in the chat box) and a durable one (config.py).

Source

Thrown at request_llms/bridge_chatgpt.py:456

        chatbot[-1] = (chatbot[-1][0], "[Local Message] API key has been deactivated. OpenAI以账户失效为由, 拒绝服务." + openai_website)
    elif "bad forward key" in error_msg:
        chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key.")
    elif "Not enough point" in error_msg:
        chatbot[-1] = (chatbot[-1][0], "[Local Message] Not enough point.")
    else:
        from toolbox import regular_txt_to_markdown
        tb_str = '```\n' + trimmed_format_exc() + '```'
        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
    return chatbot, history

def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:str, image_base64_array:list=[], has_multimodal_capacity:bool=False, stream:bool=True):
    """
    整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
    """
    from request_llms.bridge_all import model_info

    if not is_any_api_key(llm_kwargs['api_key']):
        raise AssertionError("你提供了错误的API_KEY。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。")

    if llm_kwargs['llm_model'].startswith('vllm-'):
        api_key = 'no-api-key'
    else:
        api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])

    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {api_key}"
    }
    if API_ORG.startswith('org-'): headers.update({"OpenAI-Organization": API_ORG})
    if llm_kwargs['llm_model'].startswith('azure-'):
        headers.update({"api-key": api_key})
        if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys():
            azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"]
            headers.update({"api-key": azure_api_key_unshared})

    if has_multimodal_capacity:

View on GitHub (pinned to d6bde0fa54)

Solutions

1. Temporary: type the API key directly into the gpt_academic input box and press Enter — it is picked up for the session.
2. Permanent: set API_KEY = "sk-..." (and if sharing, API_KEY_EXPOSE) in config_private.py at the repo root and restart.
3. Verify the variable spelling and that config_private.py is in the project root (it shadows config.py).
4. For vllm- models no key is needed — the code path assigns 'no-api-key' — so the error means you are on an OpenAI/Azure model that requires one.

Example fix

# config_private.py
API_KEY = "sk-your-real-key-here"
API_KEY_EXPOSE = 0

from toolbox import is_any_api_key
assert is_any_api_key(API_KEY), "API_KEY empty/placeholder — set it in config_private.py before starting"

try:
    payload = generate_payload(inputs, llm_kwargs, history, system_prompt)
except AssertionError as e:
    if 'API_KEY' in str(e):
        prompt_user_for_key_in_chat()  # the documented temporary fix
    else:
        raise

When it happens

Trigger: API_KEY/API_KEY_EXPOSE left empty or as the default placeholder in config.py and config_private.py; user selected an OpenAI-family model but never configured a key; env var override not picked up because config was already loaded; key typed into the UI but the model branch reads the config value instead.

Common situations: Fresh install where only config.py (template) exists; user filled config_private.py but misspelled the variable name; docker deployments missing the mounted config; selecting gpt models before any key was ever provided.

Related errors

• 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
• 请配置 GEMINI_API_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
• APIKEY为空,请检查配置文件的{APIKEY}

AI-assisted analysis of binary-husky/gpt_academic@d6bde0fa54 (2026-08-14). Data as JSON: /api/errors/c56c01a8e0ad0658. Report an issue: GitHub.