Posted On: Oct 12, 2023
HAQM SageMaker Canvas is a service for business analysts to generate machine learning (ML) and artificial intelligence (AI) predictions without having to write a single line of code. As announced on October 5, customers can access and evaluate foundation models (FMs) to generate and summarize content.
Starting today, HAQM SageMaker Canvas expands content summarization and information extraction capabilities of data specifically from customer-provided documents.
To get started, customers index a set of documents in HAQM Kendra that they would like to extract information from, and then simply select this document index for use in HAQM SageMaker Canvas. The new capabilities are available in all AWS regions where HAQM SageMaker Canvas, HAQM Kendra, HAQM Bedrock, and HAQM SageMaker JumpStart are supported today. To learn more, see the SageMaker Canvas service documentation. Customers are charged for their HAQM Kendra use, see the HAQM Kendra pricing for details. Customers using FMs from HAQM Bedrock are charged based on the volume of input tokens and output tokens. For more information, see HAQM Bedrock pricing page. Public FMs are deployed on HAQM SageMaker instances. Customers are charged for the duration of usage based on the instance type used. For more information, see the HAQM SageMaker Pricing for Hosting: Real-Time Inference.