-

Elasticsearch Open Inference API Now Supports Mistral AI Embeddings

Mistral AI embeddings on Elasticsearch benefit from native chunking via a single API call

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC), the Search AI Company, today announced the Elasticsearch vector database now stores and automatically chunks embeddings from mistral-embed, with native integrations to the Open Inference API and the semantic_text field. This reduces time to market for RAG applications and simplifies the development process by eliminating the need to architect bespoke chunking strategies and combining chunking with vector storage.

“We are invested in delivering open-first, enterprise-grade GenAI tools to help developers build next generation search applications,” said Shay Banon, founder and chief technology officer at Elastic. “Through our collaboration with the Mistral AI team, we’re simplifying the process of storing and chunking embeddings in Elasticsearch to a single API call.”

“Mistral AI has always been committed to open-weights and making AI accessible to all,” said Arthur Mensch, co-founder and CEO of Mistral AI. “Working with Elastic allows us to bring Mistral’s tools to more developers through the Elastic open inference API, and gives us the opportunity to work with a company that shares our value of accessibility. We’re excited to see what developers will create.”

Support for Mistral’s AI embedding model is available today, read the Elastic blog to get started.

About Elastic

Elastic (NYSE: ESTC), the Search AI Company, enables everyone to find the answers they need in real-time using all their data, at scale. Elastic’s solutions for search, observability and security are built on the Elastic Search AI Platform, the development platform used by thousands of companies, including more than 50% of the Fortune 500. Learn more at elastic.co.

Elastic and associated marks are trademarks or registered trademarks of Elastic N.V. and its subsidiaries. All other company and product names may be trademarks of their respective owners.

Contacts

Elastic PR
PR-team@elastic.co

Industry:

Elastic N.V.

NYSE:ESTC
Release Versions
English

Contacts

Elastic PR
PR-team@elastic.co

More News From Elastic N.V.

Elastic Announces General Availability of Cross-Project Search for Querying Across Serverless Projects Without Moving Data

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC) today announced the general availability of cross-project search (CPS) for Elastic Cloud Serverless, enabling teams to query across multiple serverless projects without moving or duplicating data. Security analysts, SREs and app engineers get a unified search experience across regions, cloud providers and project types, without the operational overhead of centralizing data. Organizations keep data in separate projects for good reasons, such a...

Elastic Security Achieves the Only Perfect Score in the 2026 AV-Comparatives Endpoint Prevention and Response Test

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC) today announced that Elastic Security achieved the only perfect protection score in AV-Comparatives' 2026 Endpoint Prevention and Response (EPR) Test, earning Certified Leader status, the highest distinction AV-Comparatives awards in the test. Elastic sits at the very top of this year’s Certified Leader group, with 100% Active and 100% Passive Response scores and the lowest modeled operational footprint of any product tested. This is the seco...

Elastic Introduces Serverless Vector Database: Ship in Minutes, Scale Affordably to Hundreds of Billions of Vectors

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC) today announced Elasticsearch Vector Database, a new serverless offering purpose-built for large-scale vector search and AI applications. Elasticsearch is already one of the most widely used platforms for vector workloads worldwide and now developers get an optimized database with expert-tuned defaults to build high-quality vector search applications quickly. Developers bring their documents and queries, and Elastic handles the embeddings, tu...
Back to Newsroom