是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

已经修改llm_for_openai_api.py为openai接口，并且已经通过本地测试。使用docker启动(命令为“bash ./run.sh -c cloud -i 0”),streaming=False,服务启动正常，前端展示正常，可以正常新建知识库。
但是在问问题后，会一直反复调用sanic_api.py中local_doc_chat接口，前端一开始没有报错，然后查询sanic_api.log, 可以看到openai正常返回了结果(ChatCompletion(id='cmpl-782b8d6783034163b48abec915a07346',包含了content的正常结果 )。然后报下面错误：

Exception ignored in: <generator object OpenAILLM._call at 0x7f881c11b610>
Traceback (most recent call last):
  File "/workspace/qanything_local/qanything_kernel/core/local_doc_qa.py", line 265, in get_knowledge_based_answer
    yield response, history
RuntimeError: generator ignored GeneratorExit

然后程序继续调用local_doc_chat接口，重新调用openai接口并且结果返回正常，RuntimeError: generator ignored GeneratorExit报错继续出现，前端也没有报错。然后程序继续重复以上调用，直到出现如下错误：
Error code: 429 - {'error': {'message': 'Your account ************* request reached max concurrency: 1, please try again after 1 seconds', 'type': 'rate_limit_reached_error'}}
请问大家怎么解决！!

期望行为 | Expected Behavior

• No response*

运行环境 | Environment

- OS:
- NVIDIA Driver:
- CUDA:
- docker:
- docker-compose:
- NVIDIA GPU:
- NVIDIA GPU Memory:

QAnything日志 | QAnything logs

Exception ignored in: <generator object OpenAILLM._call at 0x7f881c11aea0>
Traceback (most recent call last):
File "/workspace/qanything_local/qanything_kernel/core/local_doc_qa.py", line 265, in get_knowledge_based_answer
yield response, history
RuntimeError: generator ignored GeneratorExit

复现方法 | Steps To Reproduce

1. 适配llm_for_openai_api.py为openai接口
2. docker 启动 bash ./run.sh -c cloud -i 0
3. 前端提问

备注 | Anything else?

• No response*