Elastic announced Search AI Lake, a first-of-its-kind, cloud-native architecture optimized for real-time, low-latency applications including search, retrieval augmented generation (RAG), observability and security.

The Search AI Lake also powers the new Elastic Cloud Serverless offering, which removes operational overhead to automatically scale and manage workloads.

With the expansive storage capacity of a data lake and the powerful search and AI relevance capabilities of Elasticsearch, Search AI Lake delivers low-latency query performance without sacrificing scalability, relevance, or affordability.

Search AI Lake benefits include:

- Boundless scale, decoupled compute and storage: Fully decoupling storage and compute enables effortless scalability and reliability using object storage, dynamic caching supports high throughput, frequent updates, and interactive querying of large data volumes. This eliminates the need for replicating indexing operations across multiple servers, cutting indexing costs and reducing data duplication.

- Real-time, low latency: Multiple enhancements maintain excellent query performance even when the data is safely persisted on object stores. This includes the introduction of smart caching and segment-level query parallelization to reduce latency by enabling faster data retrieval and allowing more requests to be processed quickly.

- Independently scale indexing and querying: By separating indexing and search at a low level, the platform can independently and automatically scale to meet the needs of a wide range of workloads.

- GAI optimized native inference and vector search: Users can leverage a native suite of powerful AI relevance, retrieval, and reranking capabilities, including a native vector database fully integrated into Lucene, open inference APIs, semantic search, and first- and third-party transformer models, which work seamlessly with the array of search functionalities.

- Powerful query and analytics: Elasticsearch’s powerful query language, ES|QL, is built in to transform, enrich, and simplify investigations with fast concurrent processing irrespective of data source and structure. Full support for precise and efficient full-text search and time series analytics to identify patterns in geospatial analysis are also included.

- Native machine learning: Users can build, deploy, and optimize machine learning directly on all data for superior predictions. For security analysts, prebuilt threat detection rules can easily run across historical information, even years back. Similarly, unsupervised models perform near-real-time anomaly detections retrospectively on data spanning much longer time periods than other SIEM platforms.

- Truly distributed - cross-region, cloud, or hybrid: Query data in the region or data center where it was generated from one interface. Cross-cluster search (CCS) avoids the requirement to centralize or synchronize. It means within seconds of being ingested, any data format is normalized, indexed, and optimized to allow for extremely fast querying and analytics. All while reducing data transfer and storage costs.

Search AI Lake powers a new Elastic Cloud Serverless offering that harnesses the innovative architecture’s speed and scale to remove operational overhead so users can quickly and seamlessly start and scale workloads. All operations, from monitoring and backup to configuration and sizing, are managed by Elastic – users just bring their data and choose Elasticsearch, Elastic Observability, or Elastic Security on Serverless.

“To meet the requirements of more AI and real-time workloads, it’s clear a new architecture is needed that can handle compute and storage at enterprise speed and scale – not one or the other,” said Ken Exner, chief product officer at Elastic. “Search AI Lake pours cold water on traditional data lakes that have tried to fill this need but are simply incapable of handling real-time applications. This new architecture and the serverless projects it powers are precisely what’s needed for the search, observability, and security workloads of tomorrow.”

Search AI Lake and Elastic Cloud Serverless are currently available in tech preview.