Q: How can this task be solved with the packaged app? (Improve AI task pickup speed)

[luckow]

Connecting Nextcloud to an LLM is the number 1 wish of NC users. The Cloudron app is far too slow for daily work.
The Nextcloud documentation explains how to speed things up. Do you have any idea how to solve the tasks with the Cloudron app package?

---

To avoid task processing execution delay, setup at 4 background job workers in the main server (where Nextcloud is installed). The setup process is documented here: https://docs.nextcloud.com/server/latest/admin_manual/ai/overview.html#improve-ai-task-pickup-speed

[girish]

My understanding is we have to convert the cron job (every 5 mins) to this background worker. I have created a task internally to do this in the package .

[girish]

@luckow worker is implemented in the latest package. Can you please check?

[giofonseca]

Thanks for this improvement!

I just updated our test environment and I can see those logs. Also, the time-reaction on AI assistant reduced as expected. Is there a way to set the -t parameter through the terminal? What was the value you used?

[girish]

@giofonseca it was set to 60. what is -t ? cc @vladimir.d

[luckow]

The next big ai thing may break the current idea of a Cloudron nextcloud app.

AppAPI and External Apps

Previously, Nextcloud only supported applications written in the PHP programming language. In order to support a wider range of use cases, an ecosystem for ExApps (short for “External Apps”) was introduced, allowing for the installation of apps as Docker containers.

https://docs.nextcloud.com/server/latest/admin_manual/exapps_management/AppAPIAndExternalApps.html#ai-app-api