MongoDB to integrate Atlas Vector Search with Amazon Bedrock on AWS

MongoDB has unveiled plans to integrate MongoDB Atlas Vector Search with Amazon Bedrock. This collaboration will enable organisations to build the next-generation applications on Amazon Web Services (AWS), AWS's leading cloud infrastructure.

The integration promises ease for developers creating applications on AWS that use generative AI to complete complex tasks for a variety of use cases. It will also ensure up-to-the-minute responses based on proprietary data processed by MongoDB Atlas Vector Search.

MongoDB Atlas Vector Search utilises an organisation's operational data to simplify the integration of semantic search capabilities and generative AI into applications, resulting in tailored end-user experiences. Amazon Bedrock, on the other hand, is a fully managed service from AWS offering a choice of top-performing foundation models via a single API. It also provides a wide range of capabilities for building generative AI applications with security and privacy at the forefront.

Azam Sahir, Chief Product Officer at MongoDB, reiterated the value that this partnership holds for its customers. "Customers of all sizes from startups to enterprises tell us they want to use generative AI to build next-generation applications and future-proof their businesses," said Azam. "Many customers express concern about ensuring the accuracy of AI-powered systems' outputs whilst also protecting their proprietary data. We're easing this process for our joint-AWS customers with the integration of MongoDB Atlas Vector Search and Amazon Bedrock. This will enable them to use various foundation models hosted in their AWS environments to build generative AI applications, so they can securely use proprietary data to improve accuracy and provide enhanced end-user experiences."

Vasi Philomin, Vice President of Generative AI at AWS, also shared his excitement about the merger. "The MongoDB Atlas Vector Search integration with Amazon Bedrock will help customers tightly align their data strategies to develop and scale generative AI innovations. With a relationship that's evolved over more than a decade, we are eager to continue working with MongoDB to enable our joint customers to make the most of generative AI."

The scope of applications for this new system stretches across various industries and use cases. Customers can privately customise foundation models with their data, convert data into vector embeddings, and process these embeddings using MongoDB Atlas Vector Search. Applications responding to user queries can do so with relevant, contextualised responses, eliminating the need to manually code. For instance, a retail apparel organisation can develop a generative AI application to simplify the processing of inventory requests in real-time or personalise customer returns and exchanges with in-stock, similar merchandise suggestions. Fully managed capabilities from the upcoming integration offer secure use of generative AI throughout organisations with lower operational overheads.

Elio Narciso, Co-founder and CEO at Scalestack—an all-in-one data enrichment, prioritisation, and activation platform—expressed anticipation for the integration. "We're really excited about the integration between MongoDB Atlas Vector Search and Amazon Bedrock—this fully managed system will let our developers focus on innovating on behalf of customers."

It's expected that the integration of MongoDB Atlas Vector Search with Amazon Bedrock will be available on AWS in the coming months.