Redis, Inc. announced it is furthering developers’ ability to harness Redis Cloud as a vector database alongside Amazon Bedrock through a range of enablement resources to aid in the development and deployment of Retrieval Augmented Generation (RAG) architectures that deliver more relevant context with greater speed, cost- effectively. Amazon Bedrock is a fully managed service from Amazon Web Services (AWS) that makes foundation models (FMs) from leading AI companies accessible via an API to build and scale generative AI applications.
The integration of Redis Cloud and Amazon Bedrock is designed to address the key challenges developers face with large language models (LLMs) and building generative AI applications:
– Cost of associated hardware, repetitive operations, and API usage
– Quality of broad versus specialized LLMs and the risks of “hallucinations”
– Performance time of responses
– Security leaks of sensitive or proprietary information or a need for role-based data access
Redis has worked with AWS to create resources ranging from reference architectures, step-by-step guides, community examples, and more to guide you through the complexities of building or augmenting generative AI applications in the cloud. These resources, supplemented by in-person and virtual workshops, lead developers through integrating Redis Cloud with Amazon Bedrock from the initial subscription setup in AWS Marketplace, extending through configuring and connecting Redis Cloud as an external knowledge base.
“Redis is committed to empowering developers with new levels of efficiency, scalability, and performance capabilities for their generative AI applications in the cloud with AWS,“ said Ash Vijay, Senior Vice President of global Strategic Alliances at Redis. “The technical integration of Redis Cloud and Amazon Bedrock is just the beginning of our work to streamline generative AI application development workflows so that companies’ most critical applications will be powered by Redis Cloud on AWS.“
“Many organisations want to leverage RAG to extend the power of foundation models (FMs) to produce more accurate responses using their proprietary data in a secure way,” said Atul Deo, general manager of Amazon Bedrock at AWS. “We look forward to helping customers seamlessly use Redis Cloud as a vector database with Amazon Bedrock to implement RAG, enabling end-users to derive meaningful value from generative AI.”
The companies are also working to address industry-specific challenges for AI developers. Redis has crafted an end-to-end solution demonstration that explains how to leverage the integration to manage and search vast arrays of public financial documents. The demonstration illustrates how Redis Cloud, with Amazon Bedrock, can extract and leverage pertinent contextual information using vector similarity search (VSS) to enrich a sample RAG pipeline.
AWS Data and Analytics Competency Status Achievement
Redis also announced it has achieved Amazon Web Services (AWS) Data and Analytics Competency status. This designation recognises Redis Cloud’s demonstrated success in helping customers collect, store, govern, and analyze data at any scale.
“By leveraging vector similarity search with Redis Cloud on AWS, we’ve been able to provide our customers with vector search with the confidence that it’s reliable and extremely fast. We saw an improvement of 80% in latency compared to our initial Lucene-based implementation.
We’re glad to work with a trusted brand and a team at Redis that makes working with these technologies seamless,” said Jacky Koh, CEO of Relevance AI.
Achieving the AWS Data and Analytics Competency differentiates Redis as an AWS Partner Network (APN) member that provides specialized software solutions designed to help enterprises adopt, develop, and deploy complex projects on AWS. To receive the designation, APN members must possess deep AWS expertise and deliver solutions seamlessly on AWS.
