binary-husky/gpt_academic · error · ValueError

Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:

Error message

Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:

What it means

verify_endpoint is an lru_cache-decorated guard in the ChatGPT bridge that rejects Azure OpenAI endpoints still containing the literal placeholder text '你亲手写的api名称' ('the api name you wrote by hand') from config.py's AZURE_ENDPOINT template. It throws ValueError to force the user to finish editing their Azure configuration before any HTTP request is made. The error exists because Azure deployments require a fully specified deployment URL and unfilled placeholders are a very common copy-paste mistake.

Source

Thrown at request_llms/bridge_chatgpt.py:125

    try:
        chunkjson = json.loads(chunk_decoded[6:])
        has_choices = 'choices' in chunkjson
        if has_choices: choice_valid = (len(chunkjson['choices']) > 0)
        if has_choices and choice_valid: has_content = ("content" in chunkjson['choices'][0]["delta"])
        if has_content: has_content = (chunkjson['choices'][0]["delta"]["content"] is not None)
        if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
    except:
        pass
    return chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role

from functools import lru_cache
@lru_cache(maxsize=32)
def verify_endpoint(endpoint):
    """
        检查endpoint是否可用
    """
    if "你亲手写的api名称" in endpoint:
        raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
    return endpoint

def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_silence:bool=False):
    """
    发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
    inputs：
        是本次问询的输入
    sys_prompt:
        系统静默prompt
    llm_kwargs：
        chatGPT的内部调优参数
    history：
        是之前的对话列表
    observe_window = None：
        用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
    """
    from request_llms.bridge_all import model_info

View on GitHub (pinned to d6bde0fa54)

Solutions

1. Open config_private.py and set AZURE_ENDPOINT (and the model's entry in AZURE_CFG_ARRAY) to your real deployment URL, e.g. https://your-resource.openai.azure.com/openai/deployments/your-deployment/chat/completions?api-version=2023-05-15.
2. Make sure the deployment name in the URL matches the deployment you created in the Azure portal.
3. Verify no AZURE_CFG_ARRAY key still holds the placeholder string '你亲手写的api名称'.
4. Restart gpt_academic after saving config_private.py so the lru_cache on verify_endpoint is cleared.

Example fix

# before
AZURE_ENDPOINT = "https://你亲手写的api名称.openai.azure.com/openai/deployments/你亲手写的api名称/chat/completions?api-version=2023-05-15"

# after
AZURE_ENDPOINT = "https://my-resource.openai.azure.com/openai/deployments/gpt35/chat/completions?api-version=2023-05-15"

from request_llms.bridge_chatgpt import verify_endpoint
endpoint = AZURE_CFG_ARRAY[model]["AZURE_ENDPOINT"]
assert "你亲手写的api名称" not in endpoint, "fill in the real Azure deployment URL first"

try:
    verify_endpoint(endpoint)
except ValueError as e:
    print(f"config incomplete: {e}"); exit(1)

When it happens

Trigger: Selecting an 'azure-*' model in gpt_academic while AZURE_ENDPOINT (or the AZURE_CFG_ARRAY entry for that model in config_private.py) still contains the placeholder string '你亲手写的api名称' that ships in the default config.py; verify_endpoint(endpoint) is then called before the request and raises.

Common situations: User copies config.py to config_private.py, fills in AZURE_API_KEY but forgets to replace the endpoint template; switching from OpenAI official API to an Azure deployment without reading the Azure config section; config upgraded and the old placeholder survived.

Related errors

• Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:
• AZURE_CFG_ARRAY中配置的模型必须以azure开头
• Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:{endpoint}
• OpenAI拒绝了请求:
• OpenAI拒绝了请求：

AI-assisted analysis of binary-husky/gpt_academic@d6bde0fa54 (2026-08-14). Data as JSON: /api/errors/9dc91df1c8a8f586. Report an issue: GitHub.