Microsoft and Elastic partner to add Elasticsearch (preview) as an officially supported vector database and retrieval augmentation technology for Azure OpenAI On Your Data, enabling users to build chat experiences with advanced AI models grounded by enterprise data.

Build powerful conversational chat experiences, fast

How Elasticsearch vector database works with On Your Data

Elastic on Microsoft Azure: a proven combination

Try On Your Data with Elasticsearch vector database today

Introducing Elasticsearch vector database to Azure OpenAI Service On Your Data (preview)

Red Hat OpenShift users can now implement Elasticsearch for vector search & RAG applications via the Red Hat Ecosystem Catalog. Explore this integration here.

Elasticsearch vector database for generative AI and RAG apps

What is Red Hat OpenShift AI for generative AI apps

Get started with Red Hat and Elasticsearch

Red Hat OpenShift AI integration with Elasticsearch

Red Hat & Elastic: Red Hat OpenShift AI integration with Elasticsearch

Explore Elastic's Playground and learn how to use it to experiment with RAG applications using Bedrock Anthropic Models & Elasticsearch.

A/B test LLMs & retrieval with Playground inference via Amazon Bedrock

Using Elastic's Playground

Using retrievers and hybrid search for the best context

Use Playground to ship conversational search—quickly

Build, test, fun with Playground

Elastic's Playground is a low-code interface that enables developers to iterate and build production RAG applications by A/B testing LLMs, tuning prompts, and chunking data.

What is Elastic's Playground?

Elastic Playground: RAG with Bedrock Anthropic & Elasticsearch

Playground: Experiment with RAG using Bedrock Anthropic Models and Elasticsearch in minutes

With Elasticsearch Relevance Engine, you can create AI-powered search apps. Learn how Relativity uses Elastic & Azure Open AI for this goal.

About Relativity

eDiscovery's future with generative AI

Elasticsearch for the future of AI search experiences

Components of an AI-powered search experience

Architectural considerations for an AI-powered search experience

Cost

Scale and flexibility

Privacy and security

Industry-specific considerations: Compliance, air-gapped, private clouds

What will you build with Elastic and generative AI?

The building blocks of an AI-powered search experience are: natural language processing (NLP), vector database, vector search, and model flexibility with large language models integration.

What are the key components of an AI-powered search experience?

Users should consider the following factors when building an AI-search experience: cost, scale & flexibility, privacy and security. Also, keep in mind your industry-specific considerations (compliance, air-gapped, private clouds).

Which considerations should you keep in mind when building an AI-search experience?

Building AI search experiences with Elasticsearch & Azure OpenAI

Relativity uses Elasticsearch and Azure OpenAI to build AI search experiences

Author

Aditya Tripathi

Articles

Introducing Elasticsearch vector database to Azure OpenAI Service On Your Data (preview)

Red Hat & Elastic: Red Hat OpenShift AI integration with Elasticsearch

Playground: Experiment with RAG using Bedrock Anthropic Models and Elasticsearch in minutes

Relativity uses Elasticsearch and Azure OpenAI to build AI search experiences