-

Elasticsearch Open Inference API Supports Cohere Rerank 3

Developers can now boost semantic search retrieval for greater accuracy in GenAI use cases

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC), the company behind Elasticsearch®, today announced the Elasticsearch open inference API supports Cohere’s Rerank 3 model. As the first vector database to support Cohere Rerank 3, Elasticsearch now enables developers to benefit from greater semantic relevance to keyword and vector search retrieval for prompting large language models (LLMs).

“The combination of the Elasticsearch open inference API and Cohere Rerank 3 gives developers stronger ‘top n’ results, without requiring any changes to the model or data indexes – which are both expensive operations – providing better search results to ground LLMs,” said Shay Banon, founder and chief technology officer at Elastic. “As part of our ongoing partnership with Cohere, we’ve already made it easy for Elasticsearch developers to use Cohere’s embeddings. Adding Cohere’s incredible reranking capabilities to refine results past the first stage of retrieval was a natural evolution to our partnership.”

With this first-of-its-kind integration available today, developers with data stored in existing Elasticsearch indexes benefit from Cohere’s enhanced last-stage reranking capabilities. Users can also leverage the Elasticsearch vector database and hybrid search capabilities for embeddings from other third-party models with Cohere Rerank 3.

“We continue to be impressed by the speed of innovation from Elasticsearch. They offer powerful search and retrieval capabilities and are leading the way with investments into their vector database and hybrid search offerings,” said Jaron Waldman, chief product officer at Cohere. “We are excited to deepen our partnership by enabling developers to use Elasticsearch with Cohere’s state-of-the-art Rerank 3 model from day one.”

Support for Cohere’s Rerank 3 model is available today, read the Elastic blog to get started.

About Elastic

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

Contacts

Candace Metoyer
Elastic PR
PR-Team@elastic.co

Elastic N.V.

NYSE:ESTC

Release Versions

Contacts

Candace Metoyer
Elastic PR
PR-Team@elastic.co

More News From Elastic N.V.

Elastic to Announce Fourth Quarter and Fiscal 2026 Earnings Results on Thursday, May 28, 2026

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC), the Search AI Company, announced that it will release its financial results for its fourth quarter and fiscal 2026 ended April 30, 2026, after the U.S. market close on Thursday, May 28, 2026. The company will host a conference call at 2:00 p.m. PT / 5:00 p.m. ET that day to review its financial results and business outlook. A live webcast of the conference call will be accessible from the Elastic investor relations website at ir.elastic.co....

Elastic Introduces Jina v5 Omni Family: Two Models to Power Text, Image, Video, and Audio Search

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC), the Search AI Company, today announced jina-embeddings-v5-omni, a new family of multimodal embedding models with the ability to represent text, images, video, and audio as vectors. Developers can now perform search, classification, clustering, and deduplication across different media types, giving users powerful new ways to understand and organize multimodal data. Available in two sizes, small and nano, the new omni models share the exact sa...

Elastic Jina Embeddings v3 Now Available in Gemini Enterprise Agent Platform Model Garden

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC), the Search AI Company, announced that Jina Embeddings v3 is now available as a self-deployable partner model in Gemini Enterprise Agent Platform Model Garden. As the first Jina model available on the platform, it enables organizations to deploy high-performance retrieval models directly within their own cloud environments. With Jina Embeddings v3 deployed directly inside their Google Cloud projects and Virtual Private Clouds (VPCs), enterpri...
Back to Newsroom