Select your cookie preferences

We use essential cookies and similar tools that are necessary to provide our site and services. We use performance cookies to collect anonymous statistics, so we can understand how customers use our site and make improvements. Essential cookies cannot be deactivated, but you can choose “Customize” or “Decline” to decline performance cookies.

If you agree, AWS and approved third parties will also use cookies to provide useful site features, remember your preferences, and display relevant content, including relevant advertising. To accept or decline all non-essential cookies, choose “Accept” or “Decline.” To make more detailed choices, choose “Customize.”

AWS Logo
Menu
Building SaaS on AWS - Multi-tenant GenAI architecture patterns

Building SaaS on AWS - Multi-tenant GenAI architecture patterns

Exciting times as I launch into a new season and episode of 🔨 Building SaaS on AWS 🛠!

Anthony McClure
Amazon Employee
Published Aug 2, 2024
Last Modified Aug 6, 2024
Season 7 of Building SaaS on AWS starts off where we left last season, speaking about SaaS and Generative AI (GenAI). In this episode I was joined by Mehran Najafi, PhD and Ujwal Bukka as we dive deep into suggested architectures for including GenAI capabilities into multi-tenant SaaS solutions. Specifically we discuss how GenAI can integrate into either silo or pooled model SaaS. Using Amazon Bedrock capabilities in calling Large Language Models (LLM) and Amazon Bedrock Knowledge Bases to hold tenant specific content, we show how tenant isolation can exist when using Retrieval-augmented Generation techniques.
 To learn more about Building SaaS on AWS be sure to check out our community.aws page by clicking here: Building SaaS on AWS
 

Any opinions in this post are those of the individual author and may not reflect the opinions of AWS.

Comments