Understand this story
AWS announced the general availability of Amazon Textract Insights, a new generative AI feature for Amazon Textract. Users can define fields using natural language and use a new API to extract structured results—with confidence scores and page-level traceability—from a single document or a mixed document package, without training a model. The feature can split files of up to 3,000 pages and match them to the appropriate blueprint, supporting PDF, PNG, JPEG, and TIFF formats and six languages. At the same time, Amazon Textract Core has improved its handling of dense tables and handwritten content and expanded language coverage for the DetectDocumentText and AnalyzeDocument APIs to 40 languages. There are currently no other developments supported by factual evidence.
AI-generated from public reports
Latest development · Report
AWS Launches Amazon Textract Insights for Verifiable Generative AI Document ProcessingDevelopments
1 confirmed developments
AWS Announces General Availability of Amazon Textract Insights
Source:AWS Machine Learning
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 21
AWS Machine LearningFirst-partySelected
AWS Launches Amazon Textract Insights for Verifiable Generative AI Document Processing
AWS announced the general availability of Amazon Textract Insights. Users can define fields in natural language and use the new API to obtain structured results with confidence scores and page-level traceability from individual documents or mixed-document packages, without training a model. The feature can split files of up to 3,000 pages and match them to the appropriate blueprint. Supported input formats include PDF, PNG, JPEG, and TIFF, with support for six languages. Amazon Textract Core has also improved its handling of dense tables and handwritten content, while expanding language coverage for the DetectDocumentText and AnalyzeDocument APIs to 40 languages.
AI Trends