Not working with local installed llama.cpp (without docker, LocalAI, HARP and etc.)

[svedbox]

Which version of integration_openai are you using?

3.9.1

Which version of Nextcloud are you using?

32.02

Which browser are you using? In case you are using the phone App, specify the Android or iOS version and device please.

No response

Describe the Bug

Not working with local installed llama.cpp (same host) (without docker, LocalAI, HARP and etc.), app detects model right and not get any warning, but in assistant interface any request not receive answer.

Expected Behavior

Not answer in nextcloud assistant

To Reproduce

[kyteinsky]

hello,
that's a lot of hi's :)

are the backgroud job workers setup on your instance? They help with faster pickups of the tasks since these messages are scheduled as AI tasks and run in backgroud jobs/cron jobs.
https://docs.nextcloud.com/server/latest/admin_manual/ai/overview.html#improve-ai-task-pickup-speed

if the task fails, it would be nice to have a look at the server logs.

[kyteinsky]

closing the issue for a info.