Skip to main content

By

Aditya Tripathi,

Hemant Malik

pawel-czerwinski-dlVvDJmqf-Q-unsplash.jpg

Elastic now integrates with the NVIDIA Enterprise AI Factory validated design to provide users with a recommended vector database for their on-premises AI Factories. The validated design provides enterprises with a framework for building and deploying AI Factories on-premises.

Reference design with Elasticsearch vector database for multimodal retrieval augmented generation (RAG) use case
Elasticsearch vector database for multimodal retrieval augmented generation (RAG) use case

Elasticsearch: The enterprise-ready vector database for NVIDIA AI Factory

Validated design combines NVIDIA accelerated computing and AI software for optimized AI model deployment, multimodal data extraction, and embedding generation with Elasticsearch — a proven-at-scale vector database for storing and searching all of your AI data. Customers can use Elasticsearch on NVIDIA AI Factories for agentic AI applications using the validated design.

NVIDIA Enterprise AI Factory validated design with Elasticsearch helps enterprises accelerate AI applications by providing a full-stack pre-engineered blueprint.

But there is more to the collaboration — think GPU-accelerated vector search!

What’s next?

Elastic will use NVIDIA cuVS, an open source GPU-accelerated vector search library, to create a new Elasticsearch plugin to bring in GPU acceleration in two key areas:

  1. Index build times: By using NVIDIA GPUs, you can reduce the time required for building and updating vector indices in Elasticsearch.

  2. Query performance: By utilizing GPU acceleration for kNN vector searches, the goal is to achieve lower latency and higher throughput for similarity queries within Elasticsearch, supporting real-time AI applications.


This collaboration with NVIDIA for GPU acceleration will build upon the Elastic team's previous work to optimize vector search performance through techniques such as CPU SIMD, Better Binary Quantization (BBQ), and faster filtered HNSW, making Elasticsearch the vector database of choice for users. Stay tuned for more updates on Elasticsearch Labs.

The release and timing of any features or functionality described in this post remain at Elastic's sole discretion. Any features or functionality not currently available may not be delivered on time or at all.

In this blog post, we may have used or referred to third party generative AI tools, which are owned and operated by their respective owners. Elastic does not have any control over the third party tools and we have no responsibility or liability for their content, operation or use, nor for any loss or damage that may arise from your use of such tools. Please exercise caution when using AI tools with personal, sensitive or confidential information. Any data you submit may be used for AI training or other purposes. There is no guarantee that information you provide will be kept secure or confidential. You should familiarize yourself with the privacy practices and terms of use of any generative AI tools prior to use. 

Elastic, Elasticsearch, and associated marks are trademarks, logos, or registered trademarks of Elasticsearch N.V. in the United States and other countries. All other company and product names are trademarks, logos, or registered trademarks of their respective owners.

Sign up for Elastic Cloud free trial

Spin up a fully loaded deployment on the cloud provider you choose. As the company behind Elasticsearch, we bring our features and support to your Elastic clusters in the cloud.

Start free trial