AI Center User Guide

DELIVERY:

Last updated Jun 26, 2025

Managing ML Skills

Creating ML Skills

In the ML Skills page, select Create New. The Create New ML Skill page is displayed.
Enter a name for the new skill. The name should contain only characters, numbers, and underscores and should not start with number.
Select a package from the dropdown list.
Select package major and minor versions.
Optional: Add a description for the new skill.
Choose whether or not to enable auto-update. If this is set to true, the model is automatically updated with the latest retrained version of the model (same ML Package version, but new minor version).
Choose whether or not to make the ML Skill public.
Toggle the Advanced Infra Settings if you want to further configure your deployment, for example enabling GPU.
- Choose whether or not to enable a GPU on the environment running this skill.
- Choose the number of replicas.
Note:
A replica is an instance of a model. More replicas lead to more instances of the same deployed model. This is helpful in:
- High Availability (HA) - We cannot guarantee uninterrupted operation for instances with a single replica as there is frequent automated maintenance of backend services. In rare circumstances, the skill might encounter unexpected downtime. For production environments, we strongly advise having at least two replicas, and for test instances, one replica.
- Parallel Processing - If you expect a high volume of requests in parallel, increase the number of replicas. As a general guideline, you can use one to three robots as a starting point for each replica the ML Skill has.
- Choose how many resources you want to allocate per replica.
  Note: If you are using advanced infra settings, make sure that the requestMemory parameter is set to one of the following values:
  - 0.5 CPU 2 GB RAM
  - 1 CPU 4 GB RAM
  - 2 CPU 8 GB RAM
  - 4 CPU 16 GB RAM
  - 6 CPU 24 GB RAM
  If you specify any other value, ML Skills will not be available in the interface.
Choose when to undeploy the Skill after a period of inactivity from the dropdown.
Select Create. The Create New ML Skill page is closed and the ML Skills page is displayed, containing the new skill with Deploying status.

The model is wrapped in UiPath®'s serving framework and deployed within a namespace on UiPath® AI Center's Kubernetes cluster that is only accessible by your tenant.
Note: We made optimizations to node availability for skill deployments. Starting with October, time taken for skill deployments is reduced.
If the deployment is successful, the status of the skill changes from Deploying to Available.

Stopping ML Skills

To stop an ML Skill, use the following procedure:

In the ML Skills page, select the skill you want to stop.
Select the Stop button from the top.

Redeploying stopped ML Skills

To redeploy an ML Package, use the following procedure:

In the ML Skills page, select the stopped Skill on the grid.
Select the Resume button from the top.

Managing package versions

The ML Skill Details page enables you to manage the package version used within the deployed skill. You can update the skill to use a specific package version, or you can perform a rollback to the previously used version.

Updating package version

In the ML Skill Details page, select the Update ⇅ button next to the package version you want to use. The button is disabled for the version that is currently in use, marked as Current. The Update skill window is displayed.
In the Update skill window, select Confirm to update the skill to use the selected package version.

Rolling back to previous version

In the ML Skill Details page, select Rollback. The Update Skill window is displayed.
In the Update Skill window, select OK to update the skill to use the previous used package version.

Modifying current deployment

In addition to updating a skill to a different version, a deployed skill can be kept at the same version, but modified to use a GPU or not. To do that, select Modify current deployment in the ML Skill Details page > Update skill window.

Note: If you are using advanced infra settings, make sure that the requestMemory parameter is set to one of the following values:

0.5 CPU 2 GB RAM
1 CPU 4 GB RAM
2 CPU 8 GB RAM
4 CPU 16 GB RAM
6 CPU 24 GB RAM

If you specify any other value, ML Skills will not be available in the interface.

Make ML Skill public/private

You have the possibility to make an ML Skill public. Doing so, the ML Skill will be accessible via an endpoint from outside of UiPath environment. This means that you can call it without the need to go through a robot connected to the specific tenant.

To do that, select Modify current deployment in the ML Skill Details page > Update skill window.

Note this will redeploy the ML Skill, once the ML Skill is available you will see the corresponding url in the ML Skill Details and a button will help you copying the URL. Depending of base ML Package an API Key will also be exposed to be used with this Skill in ML Skill activity.

Deleting ML Skills

In the ML Skills page, select the Cancel or Remove button, depending on the status, next to a deployed or failed skill. A confirmation window is displayed.
Depending on the ML Skill status, use one of the following buttons to delete it:
- Cancel: use this button to delete a failed ML Skill.
- Remove: use this button to delete a successfully deployed ML Skill.
Select OK to remove or cancel the skill. The selected skill is undeployed and it disappears from the ML Skills page.

Note: Deleting a skill could affect its consumers. However, a skill with the same name can be re-created at any point restoring dependents of this service.

ML Skills report

You can download a report of ML Skill by selecting the Download ML Skills Report button.

We recommend attaching this report when submitting an issue for faster troubleshooting.

This report gathers all the necessary information required to debug an issue, including account ID, tenant ID, AI Units, and the respective package and ML Skill information.

Check the following screenshot for an ML Skills report example: