Unanswered

AI Builder - Continuous Improvement for custom models

Like (0) Share

Report

Posted on 12 Jan 2024 16:43:29 by reolan

Hi, I am using a custom AI model to scan documents and need to improve the model from time to time. I am not sure how the feedback loop for AI builder is meant to work.

The documentation recommends that AI models should be deployed in a production environment with managed solutions.

However the custom AI model cannot be edited in the production environment after it's been imported, so I am not quite sure how the feedback loop would be useful to improve the model in production. The documentation also mentions that feedback loop data can't transit between environments. Any thoughts on how to best use feedback loop to improve a model in the production environment after import? Thanks.

Categories:

AI Builder

All responses (2)

Answers (0)

cvulpe 5 on 12 Nov 2024 at 09:49:23

Like (0)

Report

AI Builder - Continuous Improvement for custom models

Hi Guys, I'm also facing a similar issue.

I have a project with 40 AI models created in a default environment since there, were all the credits assigned. Now we have decided to create a designated environment and exported all the models and flows as a unmanaged solution. The strange part is that even if all the flows can be updated in this environment, for my AI models the retrained / edit feature is locked. Is there a way we can export the models from the Default environment to a production one as a editable unmanaged solution ?
samiak Moderator on 16 Jan 2024 at 14:44:25

Like (0)

Report

Re: AI Builder - Continuous Improvement for custom models

Hi @reolan,

Would you please tell us which custom AI model are you using?

Samia