The most widely deployed, open source vector database

Elasticsearch is more than just a vector database — it supports dense and sparse vectors and hybrid retrieval, and it works with your preferred machine learning models.

Try it free

Best experienced on Elastic Cloud Serverless

"We can scale as the business scales and as the data scales with Elastic and maintain that level of reliability and performance."

Logan PashbyPrincipal Engineer, Cypris

Not all vector databases are equal

Build the vector search experience you need with a vector database that supports hybrid retrieval, text search, and vector embeddings — all in one stack.

Other vector databases

Elasticsearch

Ingest, parse, and index

Flexible document model

some support

full support (free)

Secure storage (document- and field-level security)

some support

full support (paid)

Process structured and unstructured data

some support

full support (free)

Ingest tools (clients, web crawler,* connectors,* inference pipelines*)

some support

full support (*paid)

Real-time document and metadata updates

some support

full support (free)

Semantic text for optimized vector storage

some support

full support (free)

Embeddings

Retrieval

Machine learning

Elastic tools

Your data, instantly searchable

Skip the complexity. Use Elasticsearch's proven API to generate, store, and search vector embeddings at scale.

Generate embeddings

Capture meaning, context, and associations by transforming data into dense vectors.

POST _inference/my-e5-endpoint
{
  "input": "How many adult mallard ducks fit in an american football field?"
}

Index embeddings

Elasticsearch's vector storage is based on Lucene's HNSW algorithm, which exceeds comparative benchmarks.

PUT my-index
{
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector"
      },
      "my_text" : {
        "type" : "text"
      },
      "category": {
        "type": "text"
      }
    }
  }
}



# Index a document
PUT my-index/_doc/2
{
  "my_vector" : [
        0.018743202,
        -0.011059246,
   …
        0.05155631,
        0.04044561
      ],
  "my_text" :"57,000 average sized mallard ducks fit on an American football field",
"category" : "weird_stats"
}

Search embeddings

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

GET /my-index/_search
{
  "retriever": {
    "knn": { 
      "field": "my_vector", 
      "query_vector_builder":{
      "text_embedding": {
        "model_id": "my-e5-endpoint",
        "model_text": "How many adult mallard ducks fit in an american football field??"
      }
    }, 
      "k": 10, 
      "num_candidates": 10 
    }
  }
}

Use filters and faceting to refine search

Rely on Elasticsearch's rich framework of filtering and faceting capabilities available for vector search for building intuitive end-user applications.

GET /my-index/_search
{
  "retriever": {
    "knn": {
      "field": "my_vector",
      "query_vector_builder":{
      "text_embedding": {
        "model_id": "my-e5-endpoint",
        "model_text": "How many adult mallard ducks fit in an american football field??"
      }
    }, 
      "k": 10,
      "num_candidates": 10,
      "filter": [
        {
          "term": {
            "category": "weird_stats"
          }
        }
      ]
    }
  }
}

Combine retrieval methods with hybrid search

With hybrid retrieval, pick from retrieval methods that deliver the best results for your use case: BM25, Elastic's trained sparse encoder model (ELSER), or dense vectors.

GET /my-index/_search
{
  "retriever": {
    "rrf": {
      "retrievers": [
        {
          "standard": {
            "query": {
              "bool": {
                "filter": [
                  {
                    "term": {
                      "category": "weird_stats"
                    }
                  }
                ]
              }
            }
          }
        },
        {
          "knn": {
            "field": "vector",
            "query_vector_builder": {
              "text_embedding": {
                "model_id": "my-e5-endpoint",
                "model_text": "How many adult mallard ducks fit in an american football field??"
              }
            },
            "k": 10,
            "num_candidates": 10
          }
        }
      ],
      "rank_constant": 1,
      "rank_window_size": 50
    }
  }
}

Apply document-level security and compliance authorization

Assign granular role-based access controls with document- and field-level security with coverage across widely adopted compliance frameworks.

POST /_security/role/employee_role {
  "indices": [
    {
      "names": [ "example-index" ],
      "privileges": [ "read" ],
      "field_security" : {
        "grant" : [ "state", "name.first", "name.last" ]
      }
    }
  ]
}


GET example-index/_search {
  "query": {...},
  "knn" = {...},
  "aggs": {...}
}

POST _inference/my-e5-endpoint
{
  "input": "How many adult mallard ducks fit in an american football field?"
}

Take a vector-y lap

Your search experience built your way. Deploy in your favorite cloud — no credit card required. Take Elastic for a test drive now.

Start free trial