Amazon Textract launches Custom Queries to improve information extraction for business-specific documents

Amazon Textract is a machine learning service that automatically extracts printed text, handwriting, and data from any document or image. Today, we are pleased to announce Custom Queries, a new Amazon Textract feature that enables customers to adapt the Queries feature and improve extraction accuracy for their business-specific documents. Queries is a feature within the Analyze Document API that lets you extract specific pieces of information from documents using natural language questions. Custom Queries allows customers to quickly adapt the Queries feature to meet their business-specific needs without requiring them to have machine learning expertise. Through the AWS Console, customers can upload sample documents, label the data, and generate a customized artifact called an adapter. Customers have full control of their data and the adapter that Custom Queries generates. To use the adapter, customers can simply call the Analyze Document API along with the adapter identifier and enjoy all the benefits of a managed service including low latency, high availability and usage-based pricing, without worrying about managing custom models or inference resources. This feature will be available in US East (Ohio, N. Virginia), US West (N. California), US West (Oregon), Asia Pacific (Mumbai, Seoul, Singapore, Sydney), Canada (Central), Europe (Frankfurt, Ireland, London, Paris), and the AWS GovCloud (US-East, US-West) Regions starting October 12, 2023\. To get started, log on to the Amazon Textract console to try out the new feature. To learn more about Textract capabilities, please visit the [Amazon Textract website](https://aws.amazon.com/textract/), [developer guide](https://docs.aws.amazon.com/textract/latest/dg/getting-started.html), or [resources page](https://aws.amazon.com/textract/resources/).