BettaFish [Query Engine Streamlit App] 研究过程中发生错误: Error code: 400

错误信息

研究过程中发生错误: Error code: 400 - {'error': {'message': 'Content Exists Risk', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_request_error'}}

错误详情

Traceback (most recent call last):
  File "/app/SingleEngineApp/query_engine_streamlit_app.py", line 149, in execute_research
    agent._initial_search_and_summary(i)
  File "/app/SingleEngineApp/../QueryEngine/agent.py", line 301, in _initial_search_and_summary
    self.state = self.first_summary_node.mutate_state(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/SingleEngineApp/../QueryEngine/nodes/summary_node.py", line 199, in mutate_state
    raise e
  File "/app/SingleEngineApp/../QueryEngine/nodes/summary_node.py", line 185, in mutate_state
    summary = self.run(input_data, **kwargs)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/SingleEngineApp/../QueryEngine/nodes/summary_node.py", line 116, in run
    raise e
  File "/app/SingleEngineApp/../QueryEngine/nodes/summary_node.py", line 103, in run
    response = self.llm_client.stream_invoke_to_string(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/SingleEngineApp/../QueryEngine/llms/base.py", line 148, in stream_invoke_to_string
    for chunk in self.stream_invoke(system_prompt, user_prompt, **kwargs):
  File "/app/SingleEngineApp/../QueryEngine/llms/base.py", line 132, in stream_invoke
    raise e
  File "/app/SingleEngineApp/../QueryEngine/llms/base.py", line 118, in stream_invoke
    stream = self.client.chat.completions.create(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_utils/_utils.py", line 286, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/resources/chat/completions/completions.py", line 1156, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1259, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1047, in request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'Content Exists Risk', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_request_error'}}

环境信息

应用: Query Engine Streamlit App
时间: 2025-11-09 17:31:10

Nov 09 '25 17:11 xangelwing

Hi @xangelwing! I'm Dosu and I’m helping the BettaFish team.

这个 400 - "Content Exists Risk" 错误是由 LLM 服务商（如 DeepSeek 或部分 OpenAI 兼容 API）内容风控机制触发的，通常是因为请求内容包含敏感词（如新闻、涉政、加密货币、PDF 标题等）或被判定为高风险，导致 API 拒绝响应。该错误直接由 LLM API 返回，BettaFish 本地代码没有预处理或绕过机制，重试也无法解决，因为内容本身会持续触发风控相关说明。

目前 Query Engine Streamlit App 没有自动断点续跑或自动保存进度的功能，遇到此类错误只能重新跑流程。建议如下：

优先切换到内容审查更宽松的 LLM（如 Qwen、Bocha、OpenAI 等），只需在 .env 或配置文件中修改 base_url、model 和 API key，然后重启服务即可操作指引。
避免 prompt 或输入内容中出现敏感词或重复内容，降低触发风控概率。
如需减少损失，可手动保存中间 state 文件，出错后用 load_state 恢复进度（需一定代码操作）详细说明。

如果你用的是 DeepSeek，注意 base_url 需带 /v1 后缀，否则会导致请求失败，但这不是 "Content Exists Risk" 的直接原因配置说明。

如需进一步规避此类问题，建议关注后续版本是否支持自动断点续跑或更细致的内容预检测。

To reply, just mention @dosu.

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}