[Bug]: response_format.type

[mr-Lime197]

Do you need to file an issue?

• I have searched the existing issues and this bug is not already filed.
• I believe this is a legitimate bug, not just a question or feature request.

Describe the bug

I successfully deployed the model gemma-4-e2b in LM Studio, and the chat is working properly.
I can't make visualization, error:
openai.BadRequestError: Error code: 400 - {'error': "'response_format.type' must be 'json_schema' or 'text'"}
I'm looking at the logs, I saw that the request for the model is:
"response_format": { "type": "json_object" }
I haven't checked the other functions, maybe they have this problem too.

Steps to reproduce

No response

Expected Behavior

The visualization function is working properly

Related Module

API/Backend

Configuration Used

No response

Logs and screenshots

No response

Additional Information

• DeepTutor Version:
• Operating System:
• Python Version:
• Node.js Version:
• Browser (if applicable):
• Related Issues:

[pancacake]

Thanks! Nice issue~

[mr-Lime197]

Hello!
Unfortunately, fix didn't help. I decided to try the mistralai/ministerial-3-3b model from LM Studio. And the mistake was repeated. I'm testing this on the Internet information search function, as there was the same error at this point. However, if you specify custom rather than LM Studio in Settings->Profile->Provider, the error disappears.

[pancacake]

Ahh... Thanks for the feedbacks! Will try to do this. btw, are you deployed via docker?

[mr-Lime197]

No, I only use Option A — Setup Tour (Recommended)

[pancacake]

https://github.com/HKUDS/DeepTutor/releases/tag/v1.2.2 Try this version~