Benchmarks across four datasets show how one index setting applies bfloat16 vector quantization, cache preloading and parallel merges to improve vector search throughput and decrease storage. We’re introducing one setting for production-ready vector search. The new vectordb_document index mode stores raw vectors as bfloat16 to halve their disk footprint and preloads vector data structures into the filesystem cache. It also lets segment merges run unthrottled and in parallel.
In our benchmarks, it delivered up to 2× the queries per second (QPS) at high recall with bbq_hnsw and cut time to a search-ready index by roughly 20% with bbq_disk , with no tuning required. It’s available in Stateful Elasticsearch 9. 5 and in Elasticsearch Serverless today. Elasticsearch supports a diverse range of use cases, including observability metrics and logs and complex geospatial analysis. However, as vector search becomes a core component of modern architectures, the need for specialized optimization has grown.
Achieving peak performance for vector-heavy workloads often requires navigating a complex space of configuration knobs. To reduce this operational toil, we wanted to provide opinionated, high-performance defaults through a single setting that simplifies performance tuning for production environments. The vectordb_document index mode is designed specifically for optimal vector search workloads. Setup is a single setting. When you’re creating an index, define the following in the index settings: vectordb_document mode is available on all Elasticsearch subscription tiers, including Basic.
Most indices used for vector search also support other operations, such as aggregations or geo-search. They also support hybrid search. Because vector search is typically the most computationally demanding part of these mixed workloads, we recommend using the vectordb_document index mode to prioritize performance for your most intensive operations. An index in vectordb_document mode remains highly capable, supporting almost all operations available in the default standard mode, while optimizing specifically for the resource-heavy demands of vector search. The “_document” suffix represents our roadmap.