Home icon

Manage access controls in generative AI-powered search applications using Amazon OpenSearch Service and Amazon Cognito

Big Data Blog



This article discusses a solution for managing access controls in generative AI-powered document search applications using Amazon OpenSearch Service and Amazon Cognito.

  • Key problem: Ensuring users can only access documents they are authorized to view
  • Solution uses custom user attributes in Amazon Cognito to control document access
  • Workflow involves:
    • User authentication through Cognito
    • Retrieving user custom attributes
    • Filtering OpenSearch search results based on user attributes
    • Generating answers using retrieval augmented generation (RAG)
  • Supports various use cases across departments like R&D, HR, Finance, and Sales
  • Implemented using AWS CDK with a sample fictional company dataset

The solution provides a scalable and flexible approach to managing document access in generative AI search applications, allowing organizations to control information sharing while maintaining confidentiality.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Nov 5
2024
Implement effective data authorization mechanisms to secure your data used in generative AI applications
Aug 27
2025
Implement fine-grained access control using Amazon OpenSearch Service and JSON Web Tokens
Oct 14
2024
Design secure generative AI application workflows with Amazon Verified Permissions and Amazon Bedrock Agents
Aug 22
2025
Unlock the power of Amazon OpenSearch Service: Your learning guide for search, analytics, and generative AI solutions

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.