Amazon Textract Insights is now generally available
Understand this story
AWS announces the general availability of Amazon Textract Insights. This is a new generative AI feature of Amazon Textract, offered through a new API: users describe the fields they need in natural language, submit a single document or a mixed multi-document package, and receive structured results with confidence scores and page-level provenance, with no model training required. In use, users submit a single file from their own S3 bucket, up to 3,000 pages, and enable splitting. The feature supports PDF, PNG, JPEG, and TIFF input, processes documents in English, French, German, Italian, Portuguese, and Spanish, and is billed per page rather than per token, with no minimum commitment. AWS says the feature is not yet available in some AWS Regions.
AI overview based on source reports · Updated 59 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogAnnouncing Amazon Textract Insights: Verifiable generative AI for documents
Amazon announced the general availability of Amazon Textract Insights, a generative AI feature available through a new API within Amazon Textract that lets users describe desired fields in natural language and submit a document or mixed multi-document packet to receive structured results with confidence scores and page-level grounding, with no model training required. Users define extraction in JSON Schema blueprints with natural language field descriptions and inference types, can start from AWS public blueprints or author custom ones, and can enable splitting on files up to 3,000 pages from Amazon S3. The service supports PDF, PNG, JPEG, and TIFF inputs in English, French, German, Italian, Portuguese, and Spanish, and is priced per page.
Activity for this story
Not enough continuous observations to show a trend yet.