Document Understanding
latest
false
  • Release Notes
Banner background image
Document Understanding Release Notes
Last updated May 9, 2024

June 2022

General Release Notes - ML Packages

27 June 2022

Release in Endpoints

What's New

The ML Classification endpoint is now available in -Preview.

20 June 2022

Release Chinese Japanese Korean OCR in Endpoints

What's New

The Chinese Japanese Korean OCR public endpoint has become generally available.

16 June 2022 | V22.5.0

Released in AI Center Cloud, for Data Extraction ML Packages

Improvements

Performance has been improved for all Data Extraction ML Packages.

6 June 2022

Release date in AI Center Cloud | Data Extraction ML Packages

What's New

A new OCR method, UiPath Chinese, Japanese, Korean OCR, is now available and can be applied to new or already created projects from Document Understanding, Cloud only.

3 June 2022 | V22.4.1

Release date in AI Center Cloud | Data Extraction ML Packages

Bug Fixes

Fixed a bug occurring when running an evaluation pipeline on a model trained with the special line_detection mode, causing predictions to be different than when called from the ML skill.

28 June 2022

Known Issues

In some situations, the extracted fields are shown on the wrong page in Validation Station.

General Release Notes - Document Understanding

22 June 2022

Bug Fixes

A hotfix was done for Document Manager due to an error that occurred when labelled documents were exported from Document Manager. The bug was fixed and the labelled documents are now exported without problems.

20 June 2022

Improvements

Overall improvements for Document Understanding: Document Manager and Forms AI.

9 June 2022

What's New

A new feature, Dataset Diagnostics, is now available to help you build effective datasets by providing visual and written guidance throughout the whole process of training a new model.

Was this page helpful?

Get The Help You Need
Learning RPA - Automation Courses
UiPath Community Forum
Uipath Logo White
Trust and Security
© 2005-2024 UiPath. All rights reserved.