- Release Notes
- General Availability
- Getting Started
- Data Labeling
- ML Packages
- Out of the Box Packages
- AI Computer Vision
- Communications Mining
- UiPath Document Understanding
- ML Skills
- ML Logs
- Document Understanding in AI Center™
- AI Center API
- AI Solutions Templates
- How To
- Basic Troubleshooting Guide
ML Skills and Pipelines reports
You can now download a report for ML Skills and pipelines. This report gathers all the necessary information required to debug an issue, including account ID, tenant ID, AI Units, and the respective package, pipeline or ML Skill information.
We recommend attaching this report when submitting an issue for easier troubleshooting.
Data Labeling General Availability
We are excited to announce that Data Labeling is now in general availability.
The Data Labeling page enables you to view all data labeling sessions within a project, along with their name, dataset, status, and creation time. The data uploaded for labeling can be stored in an existing dataset, or into a new dataset. Data labels can be deployed or deleted.
To learn more on how to use Data Labeling with human-in-the-loop, check the Using Data Labeling with Human-in-the-Loop page.
Multilabel Text Classification 23.5.0
- Model is moved to Python 3.9.
- Fixed Python dependency.
- This release brings general security and accessibility fixes.
- Project creation is retried in case of failure because of SQL connection drop.
- An error is now displayed when trying to send files with Validation failed status to Action Center.
- Model version list sorting is improved. The models are now sorted based on custom version first. Among the same custom version, they are sorted based on the auto-incremented version.
- The character length for the user display name is now 128 characters.
- Fixed an issue where the AI Center tenant was not accessible for certain users.
- Fixed an issue where datasets could be deleted when used without displaying an error.
- Fixed an issue where ML Skills were occasionally stuck in the Updating state on failure.
- Fixed an issue where ML Skills were occassionally not available.
- Fixed an issue where the
granularity="word"tag was missing in the Data Labeling configuration.
- Fix an issue related to ML Packages validation.
- Fixed an issue related to AI Units consumption for non-Document Understanding skills.
- ML Skills can no longer be resumed when AI Units are depleted.
- Fixed an issue where the ML Skill hardware configuration could not be viewed in Edit mode.
- Fixed an issue related to pipeline status.
- Fixed an issue where a skill deployment request could be made after the project was deleted.
- Fixed an issue where the skill version would sometimes get stuck at
VALIDATING_DEPLOYMENTstatus during deployment.
- Fixed an issue causing training pipeline failures.
The date when a change is first announced in the release notes is the date when it first becomes available.If you don't see the change yet, you can expect to see it soon, after we roll out changes to all the regions.