Rethinking access control for RAG with Amazon Quick and Amazon Bedrock
Enterprise organizations are adopting Retrieval Augmented Generation (RAG) to unlock insights from company knowledge sources like Microsoft SharePoint, Google Drive, and Atlassian Confluence.
Key points
- Making sure that AI-generated answers respect those permissions is one of the hardest challenges in enterprise AI.
- In this post, we explore how Amazon Quick and Amazon Bedrock Knowledge Bases solve this challenge through real-time access control list (ACL) enforcement, verifying permissions directly with authoritative sources at query time.
- Consider this scenario: A SharePoint site owner creates a knowledge base for their organization.
- A common approach to RAG access control uses a replicate-and-filter approach to enforce document-level permissions.
Sources (1)
- [1]Rethinking access control for RAG with Amazon Quick and Amazon BedrockAWS Machine Learning Blog · Oct 7, 06:34 PM
Enterprise organizations are adopting Retrieval Augmented Generation (RAG) to unlock insights from company knowledge sources like Microsoft SharePoint, Google Drive, and Atlassian Confluence.
Making sure that AI-generated answers respect those permissions is one of the hardest challenges in enterprise AI.
Extractive summary: sentences quoted from the sources.