Skip to main content

Guidance for Creating Low-Cost Semantic Search on AWS

Go to sample code

Overview

This Guidance demonstrates how you can implement cost-effective retrieval-augmented generation (RAG) solutions for your AI needs. It provides practical tools and methodologies for creating accessible, small-scale RAG implementations that remain effective without the high costs typically associated with vector database solutions. Making advanced AI techniques more accessible, this approach will enable your small business to personalize generative AI applications and use AI capabilities within budget constraints.

How it works

Document ingestion and vectorization flow

This architecture diagram shows how to effectively create a low-cost vector store using Amazon DynamoDB. It shows the key components and their interactions, providing an overview of the architecture’s structure and functionality. This diagram illustrates document ingestion and vectorization flow.

Download the architecture diagram
Creating Low-Cost Semantic Search on AWS - Document ingestion and vectorization flow

Inference flow

This architecture diagram shows how to effectively create a low-cost vector store using Amazon DynamoDB. It shows the key components and their interactions, providing an overview of the architecture’s structure and functionality. This diagram illustrates inference flow. 

Download the architecture diagram
Creating Low-Cost Semantic Search on AWS - Inference Flow

Deploy with confidence

Ready to deploy? Review the sample code on GitHub for detailed deployment instructions to deploy as-is or customize to fit your needs. 

Go to sample code

Benefits

Implement a retrieval-augmented generation solution capabilities using DynamoDB as a cost-effective vector store, eliminating the need for expensive dedicated vector databases while maintaining performance for small to medium workloads.

Empower your applications with intelligent document understanding and semantic search capabilities. Improve user experiences by providing relevant, context-aware responses based on your organization's specific knowledge base.

Quickly implement advanced AI techniques using pre-built workflows and managed services. Focus on creating value from your data while AWS handles the underlying infrastructure and AI model management.

Disclaimer

The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.

References to third-party services or organizations in this Guidance do not imply an endorsement, sponsorship, or affiliation between Amazon or AWS and the third party. Guidance from AWS is a technical starting point, and you can customize your integration with third-party services when you deploy the architecture.

Did you find what you were looking for today?

Let us know so we can improve the quality of the content on our pages