binary-husky/gpt_academic · error · RuntimeError

请配置 DASHSCOPE_API_KEY

Error message

请配置 DASHSCOPE_API_KEY

What it means

Constructor guard of QwenRequestInstance in the DashScope (Tongyi Qianwen) client: __init__ reads DASHSCOPE_API_KEY via get_conf and raises RuntimeError('请配置 DASHSCOPE_API_KEY') when it is empty, before assigning dashscope.api_key. Any predict entry in bridge_qwen.py that instantiates this class will fail immediately.

Source

Thrown at request_llms/com_qwenapi.py:21

import threading

timeout_bot_msg = '[Local Message] Request timeout. Network error.'
model_prefix_to_remove = 'dashscope-'

class QwenRequestInstance():
    def __init__(self):
        import dashscope
        self.time_to_yield_event = threading.Event()
        self.time_to_exit_event = threading.Event()
        self.result_buf = ""

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

        if not validate_key():
            raise RuntimeError('请配置 DASHSCOPE_API_KEY')
        dashscope.api_key = get_conf("DASHSCOPE_API_KEY")

    def format_reasoning(self, reasoning_content:str, main_content:str):
        if reasoning_content:
            reasoning_content_paragraphs = ''.join([f'<p style="margin: 1.25em 0;">{line}</p>' for line in reasoning_content.split('\n')])
            formatted_reasoning_content = f'<div class="reasoning_process">{reasoning_content_paragraphs}</div>\n\n---\n\n'
            return formatted_reasoning_content + main_content
        else:
            return main_content

    def generate(self, inputs, llm_kwargs, history, system_prompt):
        # import _thread as thread
        from dashscope import Generation
        top_p = llm_kwargs.get('top_p', 0.8)
        if top_p == 0: top_p += 1e-5
        if top_p == 1: top_p -= 1e-5

        model_name = llm_kwargs['llm_model']

View on GitHub (pinned to d6bde0fa54)

Solutions

1. Get a key from DashScope (bailian.console.aliyun.com) and set DASHSCOPE_API_KEY in config_private.py or env, then restart
2. If config was changed at runtime, clear the get_conf LRU cache or restart the process
3. For docker deployments, add DASHSCOPE_API_KEY to docker-compose.yml environment

Example fix

# before
DASHSCOPE_API_KEY = ''

# after (config_private.py)
DASHSCOPE_API_KEY = 'sk-xxxxxxxxxxxxxxxx'

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

try:
    from request_llms.com_qwenapi import QwenRequestInstance
    q = QwenRequestInstance()
except RuntimeError as e:
    if 'DASHSCOPE_API_KEY' in str(e):
        raise ConfigurationError(str(e)) from e
    raise

When it happens

Trigger: Instantiating QwenRequestInstance (request_llms/com_qwenapi.py:21) while DASHSCOPE_API_KEY == '' in the resolved configuration. Triggered by selecting a qwen model in the UI or any plugin that spawns the qwen bridge.

Common situations: DASHSCOPE_API_KEY missing from config.py/config_private.py; aliyun DashScope key not propagated into docker container; key added after process start without restart (get_conf uses an LRU cache).

Related errors

• 程序终止。
• 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ZHIPUAI_API_KEY
• 请配置讯飞星火大模型的XFYUN_APPID, XFYUN_API_KEY, XFYUN_API_SECRET

AI-assisted analysis of binary-husky/gpt_academic@d6bde0fa54 (2026-08-14). Data as JSON: /api/errors/88ef163544af16b0. Report an issue: GitHub.