Knowledge Bases for Amazon Bedrock now supports multiple data sources
Knowledge Bases for Amazon Bedrock is a fully managed Retrieval-Augmented Generation (RAG) capability that allows you to connect foundation models (FMs) to internal company data sources to deliver more relevant and accurate responses. Knowledge Bases now supports adding multiple data sources, across accounts.
Knowledge Bases for Amazon Bedrock is a fully managed Retrieval-Augmented Generation (RAG) capability that allows you to connect foundation models (FMs) to internal company data sources to deliver more relevant and accurate responses. Knowledge Bases now supports adding multiple data sources, across accounts.
Knowledge Bases can ingest data from up to five data sources, increasing the comprehensiveness and relevancy of a knowledge base. You have the flexibility to choose S3 buckets associated with different AWS accounts in the same region as the knowledge base. This approach simplifies the ingestion process by making data more accessible and provides your RAG applications with a more comprehensive set of knowledge. Simply provide the necessary S3 bucket details and credentials to unlock a wider expanse of information for your knowledge base.
Lastly, we’re making improvements for deleting data sources. When setting up a data source in a knowledge base, you can specify whether the data belonging to that data source should be retained or deleted if the data source is deleted. Your knowledge base will remain up-to-date and free from obsolete or irrelevant data, maintaining the integrity and accuracy of your RAG process.
This feature is currently available in the US East (N. Virginia) and US West (Oregon) AWS Regions. To learn more about this feature and how to get started, refer to the Knowledge Bases for Amazon Bedrock documentation and visit the Amazon Bedrock console.