Not working with QWen's qwen-max-longcontext model

[lidh15]

Describe the bug A clear and concise description of what the bug is.

if we modify the model in qwen example config from qwen-max to qwen-max-longcontext, it will raise an error saying response which is of type generator didn't have attributes status_code nor error.

To Reproduce Steps to reproduce the behavior:

modify the model in qwen example config from qwen-max to qwen-max-longcontext whatever query, it's not about the contents in my case

Expected behavior A clear and concise description of what you expected to happen. NA if feel not applicable.

I expect it run without raising the error

Screenshots If applicable, add screenshots to help explain your problem.

N/A but I can tell you it is at taskweaver/llm/qwen.py line 86 or nearby

Environment Information (please complete the following information):

• OS: WSL
• Python Version 3.10
• LLM that you're using: qwen

Additional context Add any other context about the problem here.

I think it is related to the different return types of the qwen models, maybe need some adaption

[zhangxu0307]

Hi, @lidh15 ! Thanks for your point out this problem. We have fixed this issue in #164. After bug fix, I had a try on Qwen-max-longcontext and it reported the throttling error from the server side. So it could be problem on Qwen API. You can pull the latest code and reproduce this issue to check which kind of error emerged in Qwen API.

[liqul]

Close inactive issues.