运行demo，将模型换成本地Ollama部署的模型会报错404 Not Found

[qingqinghu1026]

执行examples/parallel_doc_qa.py demo， 将llm换成
bot = ParallelDocQA(llm={'model': 'gs_qwen:7b-chat',
'model_server': 'http://IP:11433',
'api_key': 'EMPTY',
# Use a model service compatible with the OpenAI API, such as vLLM or Ollama:
# 'model': 'Qwen2-7B-Chat',
# 'model_server': 'http://localhost:8000/v1', # base_url, also known as api_base
# 'api_key': 'EMPTY',
# 'generate_cfg': {
# 'max_retries': 10}
}
)
执行会报错
Traceback (most recent call last):
File "/home/qqhu/workdir/ml/OpenAI/Qwen-Agent/qwen_agent/llm/oai.py", line 77, in _chat_stream
response = self._chat_complete_create(model=self.model, messages=messages, stream=True, **generate_cfg)
File "/home/qqhu/workdir/ml/OpenAI/Qwen-Agent/qwen_agent/llm/oai.py", line 63, in _chat_complete_create
return client.chat.completions.create(*args, **kwargs)
File "/home/qqhu/anaconda3/envs/py39/lib/python3.9/site-packages/openai/_utils/_utils.py", line 303, in wrapper
return func(*args, **kwargs)
File "/home/qqhu/anaconda3/envs/py39/lib/python3.9/site-packages/openai/resources/chat/completions.py", line 645, in create
return self._post(
File "/home/qqhu/anaconda3/envs/py39/lib/python3.9/site-packages/openai/_base_client.py", line 1088, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
File "/home/qqhu/anaconda3/envs/py39/lib/python3.9/site-packages/openai/_base_client.py", line 853, in request
return self._request(
File "/home/qqhu/anaconda3/envs/py39/lib/python3.9/site-packages/openai/_base_client.py", line 930, in _request
raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError:

<title>404 Not Found</title>

404 Not Found

---

nginx/1.18.0 (Ubuntu) 是什么原因呢

该链接使用client是可以正常使用的，正常使用代码
client = Client(host='http://IP:11433')
load_dotenv()

def llmresponse(messages):
try:
response = client.chat(
model = 'qwen2:7b', #llama3:latest gs_qwen:7b-chat yi:9b qwen2:7b
messages = messages,
)
out = response['message']['content'].strip()
except Exception as e:
print(e)
out = 'llmresponse error'
return out