General ML packages and public endpoints updates

UiPath DocPath public endpoints release

Release date: 28 November 2024

New document type

This release introduces a new document type, Receipts Japan. This new public endpoint can extract key details from a variety of document types such as regular cash register receipts, restaurants, hotels, train, parking, and other types of receipts written in Japanese.

Public endpoints for Invoices China and Invoices Japan based on UiPath DocPath

We are excited to announce the release of improved endpoints for Invoices China and Invoices Japan. This new generation of endpoints, based on UiPath DocPath, the new UiPath LLM, brings enhanced accuracy and performance.

Invoices Japan improvements

We have made significant improvements to the Invoices Japan public endpoint, adding new fields, such as:

• Regular fields:
  • Net amount reduced
  • Tax reduced
  • Net amount non-reduced
  • Tax non-reduced
  • Withholding tax amount
  • Deposit
• Column fields:
  • Item tax rate
  • Item registration tax
  • Item fee

Invoices Japan public endpoints release

Release date: 29 October 2024

Released in endpoints for Invoices Japan

Improvements

We've made significant improvements to our document digitization process. Now, when using the UiPath Extended Languages OCR or the Chinese, Korean, Japanese OCR, the output will be regular word boxes instead of individual characters.

New Invoices Japan public endpoints release

Release date: 15 October 2024

Released in endpoints for Invoices Japan

Improvements

• The accuracy of the Invoices Japan ML package has been improved.
• We've enhanced the spacing and word parsing when Chinese, Japanese, or Korean characters are mixed with Latin characters, punctuation, and numbers in documents.
• We've fixed an issue that was causing AI Center training pipelines to report inaccurately high scores for ID Number and Phone Number field types. This ensures that the reported scores match the actual scores.

UiPath Extended Languages OCR in general availability

Release date: 3 October 2024

We are excited to announce that our latest OCR engine, UiPath Extended Languages OCR, is now in general availability. The new OCR is capable of digitizing documents in over 200 languages, bringing a significant improvement over its predecessor, especially in regards to Chinese, Japanese, and Korean. Additionally, it can process documents in Thai, Vietnamese, all major languages from India, as well as languages using the Cyrilic alphabet, and Greek.

The UiPath Extended Languages OCR is currently only available as a public endpoint.

New public endpoints based on UiPath® DocPath

Release date: 17 September 2024

Improved performance and new model endpoints enrolled on UiPath DocPath

This release brings enhanced accuracy and performance for models based on UiPath DocPath, the new UiPath LLM. Furthermore, the following models are now based on UiPath DocPath as well:

• 709
• 941x
• 1040x
• 3949
• 3949a

Model endpoint redirected to the old generation

Due to performance issues, the Financial Statement model endpoint is redirected to the old generation.

Preview model removed

The 990 (Preview) model is removed from both public endpoints and Data Extraction ML packages.

UiPath Chinese, Japanese, Korean OCR deprecation

Release date: 8 July 2024

The UiPath Chinese, Japanese, Korean OCR will be deprecated starting with January 2025. We recommend using the UiPath Extended Languages OCR instead.

Check the Deprecation timeline page for more information about upcoming deprecations and removals.

Public endpoints for Invoices and Receipts based on UiPath® DocPath

Release date: 12 June 2024

We are excited to announce the release of improved endpoints for Invoices and Receipts. This new generation, based on UiPath DocPath, the new UiPath LLM, brings enhanced accuracy and performance.

We are gradually replacing our models with a new generation. For now, all public endpoints are based on DocPath, except for the following endpoints:

• 709
• 941x
• 1040x
• 3949a
• 9465
• Invoices China
• Invoices Hebrew
• Invoices Japan

Check the release notes for future announcements.

Public endpoints based on DocPath

Release date: 29 May 2024

We are excited to announce the release of improved endpoints for our pre-trained, out-of-the-box ML packages. This new generation, based on UiPath DocPath, the new UiPath® LLM, brings enhanced accuracy and performance.

We are gradually replacing our models with a new generation. For now, all public endpoints are based on DocPath, except for the following endpoints:

• 709
• 941x
• 1040x
• 3949a
• 9465
• Invoices
• Invoices China
• Invoices Hebrew
• Invoices Japan
• Receipts

Check the release notes for future announcements.

UiPath Extended Languages OCR in public preview

Release date: 28 March 2024

We are excited to announce that our latest OCR engine, UiPath Extended Languages OCR, is now in Public Preview. The new OCR is capable of digitizing documents in over 200 languages, bringing a significant improvement over its predecessor, especially in regards to Chinese, Japanese, and Korean. Additionally, it can process documents in Thai, Vietnamese, all major languages from India, as well as languages using the Cyrilic alphabet, and Greek.

The UiPath Extended Languages OCR is currently only available as a public endpoint.

Frozen Backbone training

Release date: 27 April 2023

The ML packages versions v23.4 and higher, now have the option to train using Frozen Backbone. This new approach trains faster and gives better results for small or low diversity training sets below 400 pages. You can override this behavior by using the new Training Pipeline environment variables documented in the official documentation.

Invoices Australia deprecation

Release date: 29 November 2022

An upcoming deprecation is announced for the Invoices Australia pre-trained ML package. We recommend using instead the Invoices ML package instead. Here you can find more details about it.

ML Classification endpoint public preview

Release date: 27 June 2022

Released in endpoints

The ML Classification endpoint is now available in public preview.

UiPath Chinese, Japanese, Korean OCR release

Endpoints

Release date: 20 June 2022

Released in endpoints

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

Data Extraction ML packages

Release date: 6 June 2022

Released in AI Center Cloud, for Data Extraction ML packages

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.