Couchbase 8.0 Introduces AI-Focused Vector Indexing and Security Enhancements

Oct 21, 2025
Couchbase has released version 8.0 of its database platform, adding new vector indexing features and enhanced security for AI-driven applications. The update supports billion-scale vector searches and introduces natural language querying for developers.

Couchbase, Inc. has released Couchbase 8.0, a major update to its database platform designed to support large-scale AI and agentic applications, announced in a press release.

The new version introduces three vector indexing and retrieval options—Hyperscale, Composite, and Search Vector Indexes—allowing developers to handle diverse vector workloads and optimize for speed, scale, or accuracy. Couchbase 8.0 supports billion-scale vector searches with millisecond latency and tunable recall accuracy, available for both self-managed and Capella deployments.

Couchbase 8.0 adds built-in encryption through native data-at-rest encryption and support for the Key Management Interoperability Protocol for key handling. It also enhances cross data center replication with bidirectional conflict detection and mobile bucket support, helping meet regional compliance requirements. New intelligent auto-failover capabilities maintain availability during system disruptions.

For developers, the update introduces natural language querying for users unfamiliar with SQL++, a query workload repository for performance insights, and improved search relevance with user-defined synonyms. Couchbase 8.0 is now generally available across on-premises, cloud, and edge environments.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.