Skip to main content
Login
Start free trialContact Sales

Announcing the Microsoft Semantic Kernel Elasticsearch connector

By

Srikanth Manvi

142234_-_Blog_header_image_Bridging_IT_intelligence_and_business-02.jpg

In collaboration with the Microsoft Semantic Kernel team, we are announcing the availability of Semantic Kernel Elasticsearch Vector Store connector for Microsoft Semantic Kernel (.NET) users. Semantic Kernel simplifies building enterprise-grade AI agents, including the capability to enhance large language models (LLMs) with more relevant, data-driven responses from a vector store. Semantic Kernel provides an abstraction layer for interacting with various vector stores like Elasticsearch, offering essential features, such as creating, listing, and deleting records.

With Elasticsearch now available as an out-of-the-box connector, Semantic Kernel developers can seamlessly plug in the Elasticsearch vector database with their new or existing AI agents using Semantic Kernel Elasticsearch vector store connector.

Microsoft Semantic Kernel and Elasticsearch

Semantic Kernel offers developers a flexible framework for building AI agents that enhance LLMs with custom workflows and data. It enables developers to build context-aware, intelligent agents by providing tools for memory storage, skill management, and orchestration across various tasks. With its support for modular and extensible plugins, Semantic Kernel can be adapted to a wide range of applications, making it a great choice for creating robust, scalable AI agents.

The Elasticsearch vector database is essential for developers building AI agents with Microsoft Semantic Kernel as it provides efficient storage, retrieval, and similarity search for high-dimensional data, such as embeddings. In Semantic Kernel — which enables AI agents to process and interpret complex text data — Elasticsearch allows for quick access to similar or related concepts, boosting relevance in search and retrieval tasks. This is critical for applications like recommendation engines, question-answering, or context-aware responses, where AI agents need to handle large amounts of unstructured data and serve accurate results in real time. Elasticsearch vector database allows developers building Semantic Kernel-powered agents to manage large data sets with robust indexing and scalability

Elasticsearch has strong roots in the open source community, recently adding the AGPL license. With the open source availability of Microsoft Semantic Kernel, this creates a powerful combination of enterprise-ready tools. This setup supports building AI agents for production workloads that are adaptable to various deployment and licensing needs.

You can quickly get started with Elasticsearch locally using start-local for experimentation and move to Elastic Cloud for low-cost infrastructure or on-prem deployment. Whether you’re working with a local, self-hosted, or cloud hosted instance of Elasticsearch, Semantic Kernel’s integration makes using Elasticsearch with Semantic kernel effortless.

The Elasticsearch Connector can be used against Serverless or 8.x versions (signup for Elastic cloud). The connector is valuable not only for basic storage and retrieval use cases but also potentially for future advanced applications. Elasticsearch users have had access to great hybrid search, such as RRF in retrievers (now GA in 8.16). As Semantic Kernel expands its support for sophisticated features in the future, the full suite of what Elastic has to offer will be fully manifested in the Semantic Kernel experience.

What's next?

  • Stay tuned for upcoming Semantic Kernel Elasticsearch connectors for Python and Java in the coming months.

  • We’re thrilled to partner with Microsoft to bring features like hybrid search and advanced retrieval strategies to Semantic Kernel developers in the near future. 

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, ESRE, Elasticsearch Relevance Engine 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