World's most downloaded vector database — Elasticsearch

Elasticsearch's vector database offers you an efficient way to create, store, and search vector embeddings at scale.

Combine text search and vector search for hybrid retrieval, resulting in the best of both capabilities for greater relevance and accuracy.


A vector database is your starting point...

You need more than a vector database for a great search experience. Elasticsearch includes a full vector database, multiple types of retrieval (text, sparse and dense vector, hybrid), and your choice of machine learning model architectures.

Build your search experience with aggregations, filtering and faceting, and auto-complete. Run your search in the cloud, on-prem, or air gapped.

  • Generate embeddings

    Capture meaning, context, and associations of data in dense vectors, with flexibility of picking embedding models. Run machine learning inference as you index data.

  • Store embeddings

    Elasticsearch's vector storage is based on Lucene's HNSW. The approach performs well on comparative benchmarks (see luceneknn) for vector search algorithms.

  • Search embeddings

    Run kNN search to fit your use case — ANN for speed and scale using Lucene's HNSW index or exact match for ultimate accuracy.

  • A rich framework of filtering and faceting capabilities that Elasticsearch developers rely on, available for vector search.

  • With hybrid retrieval, pick from a combination of retrieval methods that works for you: BM25, our trained sparse model (ELSER), and dense vectors.

  • Apply document level security & compliance policies

    Assign granular role-based access controls with document & field level security. Know you have coverage across widely adopted compliance frameworks.

Why use a vector database?

Vector database superset

Choose a vector database based on the vector search experience you want to build.

Some vector databases



Store embeddings

full support

full support (free)

Generate embeddings

some support

full support (paid)