Amazon Textract is a machine learning service that automatically extracts printed text, handwriting, and data from any document or image. Layout is a new Textract feature that enables users to extract layout elements such as paragraphs, titles, lists, headers, footers, and more from documents.

Layout will be a new feature type in the Analyze Document API. Users can use Layout as a stand-alone feature or in combination with other Analyze Document feature types.

Layout is pre-trained on a wide variety of documents from the financial services, legal, insurance, medical, media and other industries.

With Layout, users will be able to directly extract layout elements from documents reducing their reliance on developing and maintaining complex post-processing code.

In turn, Amazon expects Layout to improve efficiencies for document processing operations such as creating search indices, embeddings for Retrieval Augmented Generation (RAG) applications, and more.

Rahul Gupta, Head of Product and Tech at AWS, said: “Congrats to the team for launching Amazon Textract Layout, which makes it a breeze to extract reading order, additional elements and metadata to expedite document understanding.”

This feature is  available in Asia Pacific (Mumbai, Seoul, Singapore, Sydney).

To get started, log on to the Amazon Textract console to try out the new feature. To learn more about Textract capabilities, visit the Amazon Textract website, developer guide, or resources page.