can not use qwen-vl-max

[yyvhang]

Bug description

can not use the qwen-vl-max API
Bug solved method

Environment information

• LLM type and model name: dashscope, qwen-vl-max-latest
• System version: ubuntu22.04
• Python version: 3.10
• MetaGPT version or branch: 0.8.1

• packages version:
• installation method: pip

Screenshots or logs

Exception: Traceback (most recent call last):
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/utils/common.py", line 640, in wrapper
return await func(self, *args, **kwargs)
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/roles/role.py", line 550, in run
rsp = await self.react()
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/roles/role.py", line 519, in react
rsp = await self._act_by_order()
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/roles/role.py", line 473, in _act_by_order
rsp = await self._act()
File "/nas/shared/landmark_3dgen/yangyuhang/Agent/test.py", line 147, in _act
result = await todo.run(msg.content)
File "/nas/shared/landmark_3dgen/yangyuhang/Agent/test.py", line 36, in run
rsp = await self._aask(prompt)
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/actions/action.py", line 93, in _aask
return await self.llm.aask(prompt, system_msgs)
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/provider/base_llm.py", line 150, in aask
rsp = await self.acompletion_text(message, stream=stream, timeout=self.get_timeout(timeout))
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/tenacity/_asyncio.py", line 88, in async_wrapped
return await fn(*args, **kwargs)
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/tenacity/_asyncio.py", line 47, in call
do = self.iter(retry_state=retry_state)
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/tenacity/init.py", line 314, in iter
return fut.result()
File "/cpfs01/user/conda/envs/agent/lib/python3.10/concurrent/futures/_base.py", line 451, in result
return self.__get_result()
File "/cpfs01/user/conda/envs/agent/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
raise self._exception
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/tenacity/_asyncio.py", line 50, in call
result = await fn(*args, **kwargs)
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/provider/base_llm.py", line 200, in acompletion_text
return await self._achat_completion_stream(messages, timeout=self.get_timeout(timeout))
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/provider/dashscope_api.py", line 220, in _achat_completion_stream
self._check_response(chunk)
File "/cpfs01/user/conda/envs/agent/lib/python3.10/site-packages/metagpt/provider/dashscope_api.py", line 194, in _check_response
raise RuntimeError(f"code: {resp.code}, request_id: {resp.request_id}, message: {resp.message}")
RuntimeError: code: InvalidParameter, request_id: bd2b84b8-7989-93d3-b942-5f1af2ff129a, message: url error, please check url！

[iorisa]

Ok, I'll follow up on this issue.

[iorisa]

The follow config/config2.yaml configuration is working:

llm:
  api_type: "openai"
  model: "qwen-vl-max"
  base_url: "https://dashscope.aliyuncs.com/compatible-mode/v1"
  api_key: "sk-3b9e***"
  max_token: 1500
  temperature: 0.5

[github-actions]

This issue has no activity in the past 30 days. Please comment on the issue if you have anything to add.

[github-actions]

This issue was closed due to 45 days of inactivity. If you feel this issue is still relevant, please reopen the issue to continue the discussion.