16.07, Webinar Securing AI Agents: where threats hide in agentic systems
Webinar

AWS-native multi-tenant RAG

AI that works in production starts with the right architecture. In this webinar, we’ll walk through RAG fundamentals, AWS services, vector stores, and multi-tenant patterns with guidance on how to match them for scale, performance, and cost.

Share

Agenda

  1. Introduction to RAG
    What Retrieval-Augmented Generation is and why it matters
  2. The AWS stack for RAG
    Overview of AWS services (Amazon Bedrock, Amazon Knowledge Bases, AWS Lambda, etc.)
  3. Vector stores on AWS
    Comparison of available options and their benefits
  4. Multi-tenant patterns
    Overview of Pool, Bridge, Silo patterns for RAG systems
  5. Pattern-Vector store matching
    Best practices
  6. Conclusions and Q&A

Key topics

  • what RAG is and how it defines the way we design AI applications;
  • AWS services for building RAG solutions, including Amazon Bedrock, Amazon Knowledge Bases, and serverless compute;
  • how Amazon OpenSearch Serverless, Amazon Aurora, and Amazon S3 Vectors compare as vector stores options;
  • multitenancy patterns for RAG systems: Pool, Bridge, and Silo approaches and their trade-offs;
  • how to match the right vector store with your multitenancy requirements, performance, and cost goals.

Speaker

Paweł Grabiński

Paweł Grabiński

AI Engineer

He builds generative AI solutions, from chatbots and agentic assistants to intelligent document processing systems.

He holds all 4 AWS ML/AI certifications, including AWS Certified Generative AI Developer – Professional. A background in Physics, Data Science, backend development, IaC, and cloud gives him a unique perspective on cloud system design for AI workloads.

Amazon Bedrock

Amazon Bedrock

The platform for secure and private agentic AI services

Enter the world of generative AI with Amazon Bedrock — a fully managed service offering top of the line foundation models, such as Anthropic's Claude and OpenAI's GPT.

Thanks to its serverless design, Amazon Bedrock eliminates the complexity of running AI at scale, and lets you seamlessly integrate agentic AI into your applications using familiar AWS services — whether it's your first steps with AI, or you are already revolutionizing the market.

Agentic AI services

AWS is trusted by…