| Couchbase Adds Vector Search |
| Written by Kay Ewbank |
| Thursday, 07 March 2024 |
|
Couchbase is adding support for vector search across its entire product line including Capella, Enterprise Server, and Mobile. Support has also been added for retrieval-augmented generation (RAG) techniques through large language models (LLMs) via LangChain and LlamaIndex interfaces. Couchbase is a distributed NoSQL cloud database that grew from a merger between Membase and CouchOne, with the aim of creating a scalable, high-performance document-oriented database system. Couchbase combines the properties of a distributed document database (JSON) with features of a traditional DBMS including distributed SQL, transactions, and ACID guarantees.
Capella is Couchbase's managed service that was launched at the end of 2021 with support for AWS, GCP and Azure. The vector search has been added to the native natural language search service in Couchbase Enterprise Edition Server 7.6, the Capella fully-managed database, and Couchbase Lite, the embeddable mobile database. The addition of vector search adds the ability to carry out similarity and hybrid search, combining text, vector, range and geospatial search capabilities in one. The developers say it also improves performance because all search patterns can be supported within a single index to lower response latency. The second part of the announcement is the support for LangChain and LlamaIndex across Couchbase's language-specific SDKs. Both are frameworks designed to simplify the creation of applications using large language models, and the Couchbase team says the support will boost developer productivity in using whatever GenAI models they choose within their application. Underpinning this is support for Retrieval-Augmented Generation (RAG) techniques with vector search to improve response accuracy due to the large language model having access to more accurate and relevant information than it would have otherwise. RAG can also provide domain-specific information and its models can be fine-tuned for specific tasks. Developers will have full vector search support in REST API, SDK and SQL++. Other improvements to Capella and the forthcoming Enterprise Server 7.6 include support for graph-like relationship traversals using recursive common table expressions in SQL++; and file-based index rebalancing. These new capabilities are expected to be available in the first quarter of Couchbase’s fiscal year 2025 in Capella and Couchbase Server and in beta for mobile and edge.
More InformationRelated ArticlesCouchbase 7 Adds Relational Support Model Insights From Couchbase Connect Couchbase Launches JSON Analytics Couchbase Mobile Version Adds Sync Gateway Couchbase Server 4.0 Now With N1QL What Happens To Couchbase Now?
To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin. 
Comments
or email your comment to: comments@i-programmer.info |
