World's most used 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.
Vector database superset
Choose a vector database based on the vector search experience you want to build.
Some vector databases
Elasticsearch
Store embeddings
full support
full support (free)
Generate embeddings
some support
full support (paid)
Search embeddings
full support
full support (free)
Search BM25
some support
full support (free)
Hybrid search (BM25 + Vectors)
full support
full support (free)
Filtering, faceting, aggregations
full support
full support (free)
Search autocomplete
no support
full support (free)
Optimized for multiple data type (text, vector, geo)
some support
full support (free)
Support for several embedding models
full support
full support (paid)
Built-in semantic search model
no support
full support (paid)
Data inference pipelines
some support
full support (paid)
Ingest tools (web crawler*, connectors*, API framework, beats, fleet, agent)
some support
full support (*paid)
Document and field level security
no support
full support (paid)
Observability tools (Kibana)
no support
full support (free)
Search UI components
no support
full support (free)
Start with a few lines of code
Generate embeddings, store embeddings, and run vector search using the familiar Elasticsearch API.
POST /_ml/trained_models/sentence-transformers__all-minilm-l6-v2/_infer
{
"docs": {
"text_field": "Jamaica's tropical climate brings warmth all year round"
}
}
Take your first steps to vector search today
Blogs
Webinars
Demo projects