AI Fabric - No Data Manager Documentation

[Lahiru.Fernando]

Hi guys,

Along the lines of Document Understanding new capabilities offered through AI Fabric:

Document Understanding AI - 5 new models in Preview (Cloud and On prem)

New ML Models in Public preview! UiPath Document Understanding is launching 5 more ML Models in Preview on both Cloud and On Premises deployments. All models are retrainable (except for OCR engine), so their objective is two-fold. First, you get new, Out-Of-the-Box, Document Understanding capability. But perhaps more importantly, you get a leg-up for training a custom ML model for your specific usecase, by using these models as Base Models in AI Fabric (both On Premises and in the Cloud). For…

I tried to use these models through the Enterprise Trial, however the model deployment is failing. I figured that it could be because these models require training before deploying the skill. I wanted to go through the documentation to understand how I can train these models through Data Manager that comes in as a part of AI Fabric. However, I was unable to find any link to Data Manager.

Have anyone used the Data Manager for enterprise trial? If so, what is the link that I can use to access it?
and if you have any documentation, it would be great if you can share the link for it…

[alexcabuz]

Hello @Lahiru.Fernando,

Data Manager is for now only available on premises, so you would have to request an On Premises Trial through your Sales representative. The documentation is here: https://docs.uipath.com/ai-fabric/v2020.4/docs/about-data-manager

However, which model are you trying to deploy, and how is it failing? Are you using AI Fabric in the Cloud through Automation Cloud?

Alex.

[alexcabuz]

Additionally, @Lahiru.Fernando deploying Out of the Box models (Invoices, Receipts, Utility Bills, etc) does NOT require retraining unless you want to optimize/fine tune them on your own data. You should be able to deploy the models without any retraining. Please let me know if you run into any issues.

Thanks,
Alex.