-

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 Named a Leader in the IDC MarketScape: Worldwide SIEM 2026

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC), the Search AI Company, today announced that it has been named a Leader in the IDC MarketScape: Worldwide SIEM 2026 Vendor Assessment (Doc# US54126826, June 2026). Download the complimentary excerpt here. The IDC MarketScape’s assessment highlights several key strengths of Elastic Security, including: Elastic Common Schema and the underlying Elasticsearch engine allow customers to query security and operational data using a single language. C...

Elastic Named a Strong Performer in Extended Detection And Response Platforms, Q2 2026

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC), the Search AI Company, today announced that it has been named a Strong Performer in The Forrester Wave™: Extended Detection And Response Platforms, Q2 2026. The report recognized Elastic Security’s SIEM-replacement capabilities, open data architecture, AI innovation, and endpoint protection. Access the complimentary report here. Elastic Security is an agentic security operations platform that unifies SIEM, XDR, and native automation. Elastic...

Elastic Observability Gives SREs a Head Start on Kubernetes Incident Investigations

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC), the Search AI Company, today introduced an agentic Kubernetes investigation workflow and MCP-based observability skills that diagnose incidents the moment an alert fires. By the time an SRE opens the alert, the root cause has already been identified, evidence has been assembled, and recommended next steps have been surfaced. For teams running Kubernetes at scale, the gap between alert and answer costs time, compounds outages, and wears down...
Back to Newsroom