AI Fabric- Using Pipeline

[akshay616 (Akshay Kulkarni)]

while using pipeline in AI Fabric, what is the role of parameters and how to use them?

[Pablito (Pawel Wozniak)]

Hi @akshay616,
Welcome to the Community!
Please check out the documentation:

AI Center

As well as this topic might be useful for you:

UiPath AI Fabric: Apply AI to Your RPA Workflows

UiPath AI Fabric: Apply AI to Your RPA Workflows About this event: AI Fabric is UiPath’s machine learning platform. It allows enterprises to expand their automation scope to more business processes—complex and cognitive ones, which wouldn’t be possible without AI. AI Fabric standardizes, integrates, and streamlines all moving pieces of AI. It makes it easier for our customers to automate business processes using machine learning models. To join the virtual meetup, RSVP via ou…

And this:

AI Fabric On-premise GA

Today, we are excited to announce the launch of the long-awaited AI Fabric – ON PREMISE in general availability! This will be our first fully-featured version of AI Fabric on-premise which is a single node configuration. With this launch, customers can deploy, run and improve machine learning models locally on VM instances provided by cloud providers such as AWS, Azure, and GCP. Installation on bare metal machines is not yet officially supported. With this release, customers enjoy the deploymen…

[nashrahkhan]

@Pablito I am also posting my questions related to AI Fabrics. I am really facing issue of slowness. Even for the data that has only 50 rows. ML package in the pipeline took 111m. Sometimes the package got failed also. moreover the ML Logs are not providing enough information of failing the package.

Kindly also provide my answers as well related to AIFabrics.

[Pablito (Pawel Wozniak)]

Are you able to provide some screenshots of such issue? I something fails you should have any error which you could share.

[bob_schmid]

…any updates?

[Pablito (Pawel Wozniak)]

Hi @bob_schmid,
Let me notify someone who could help here.
@AntonMcG

[Andra_Buica]

Hi all,

Behind are deep learning architectures running for multiple number of epochs on CPU. This is the expected time to run - pipeline can take between 1 hr and 7 days while ran on CPU. This is the time spent for the model to get trained, to learn from the data.

If you want faster processing, we recommend attaching GPU to the pipelines. GPU provides 5-10x faster processing. You can get a GPU by purchasing an AI Robot Pro licenses on Cloud.

Hope this helps.
Thanks,
Andra