Elasticsearch — the best open source vector database for AI

Start free trial

What's new BBQ

What should your vector database do for you?

Start tutorial

Vector search: Context, intent, relationships
Similarity search can return the right results — even when the words don't quite match.
Hybrid search: Precision + flexibility
Keyword search is precision. Vector search is nuanced. Hybrid search brings both together.
Sparse vs. dense vectors: Fast and efficient
Sparse text expansion and dense meaning matches are perfect for open-ended, real-world search.
Filters, ranking, reranking: Relevance with context
Filters reduce scope, ranking finds the signal — both hard problems, but pure delight when done right.

Elasticsearch: More than just vectors, loved by developers

No gaps or compromises — it all works together, because it was built this way

Hybrid search that understands everything
Elasticsearch's hybrid search blends keywords, vectors, geo data, metadata, and more in a single API call. Rank results by meaning, precision, and context.
Facets and filters, without the lag
Filters and facets that run fast, even at scale — no slowdowns, no full index scans. Elastic blends aNN retrieval with filters to create the right scope, no matter the scale.
OpenAI, Anthropic, Hugging Face … all native
Inference APIs execute native inference with popular LLMs or built-in models for text embeddings, classification, Q&A, and more — no external ML infrastructure needed.
More vectors. Less memory. No trade-offs.
Better Binary Quantization (BBQ) reduces memory footprint up by to 95% while delivering great accuracy. Optimized distance calculations and aNN recall accelerate vector search at scale.
Semantic search, fewer steps
The semantic_text field handles mappings, embeddings, and chunking automatically — delivering truly seamless dense retrieval in a single query.
Test RAG fast — no setup needed
Stop the guess work. AI Playground lets you test hybrid retrieval, relevance ranking, and chunking strategies in real time, so you can fine-tune and ship tested queries with confidence.

Go hosted on AWS, Azure, or Google Cloud — or try serverless and let Elastic handle the rest.

Try now See pricing

One call, that's all

Index, search, filter, apply RBAC — on text, embeddings, geo, timeseries, or metadata

Create inference endpoint

Use a machine learning model and apply it to your data at ingestion time.

Learn more about inference API & E5 model.

PUT _inference/text_embedding/my-e5-endpoint
{
  "service": "elasticsearch",
  "service_settings": {
    "num_allocations": 1,
    "num_threads": 1,
    "model_id": ".multilingual-e5-small"
  }
}

Generate embeddings
Capture meaning, context, and associations by transforming data into data in dense vectors. Create embeddings blog
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 (see 'luceneknn').

Our vector search approach

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.

Explore ANN and KNN.


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.

Read about kNN filtering

Learn more about faceting

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.

Watch video about hybrid search


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.

Set up authorization

Set up compliance

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": {...}
}

PUT _inference/text_embedding/my-e5-endpoint
{
  "service": "elasticsearch",
  "service_settings": {
    "num_allocations": 1,
    "num_threads": 1,
    "model_id": ".multilingual-e5-small"
  }
}

Best in class? Built right in

Native integrations to all the leading AI products — so your apps go further, faster

A high quality neighborhood

From prompt to product, these organizations trust Elastic to build next-gen search

Customer spotlight
Reed, the UK's largest recruiter, brings job searchers and employers together using vector embeddings in Elasticsearch.
Learn more
Customer spotlight
Stack Overflow combines the power of human experts with generative AI to accelerate the retrieval of trusted information from developer knowledge bases.
Learn more
Customer spotlight
Adobe scales, manages multiple use cases, and puts machine learning features to work with Elastic.
Learn more

Vector database superset

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

Some vector databases

Elasticsearch

Embeddings

Store embeddings

full support

full support (free)

Generate embeddings

some support

full support (paid)

Retrieval

Machine learning

Search experience tools

Elastic tools

Frequently asked questions

What is a vector database and how does it work?

A vector database stores information as vectors, which are numerical representations of data objects, also known as vector embeddings. It uses vector embeddings for multi-modal search across a massive data set of structured, unstructured, and semi-structured data, such as images, text, videos and audio. Vector databases are built to manage vector embeddings and therefore offer a complete solution for data management.

Elasticsearch — the best open source vector database for AI

What should your vector database do for you?

Vector search: Context, intent, relationships

Hybrid search: Precision + flexibility

Sparse vs. dense vectors: Fast and efficient

Filters, ranking, reranking: Relevance with context

Elasticsearch: More than just vectors, loved by developers

Hybrid search that understands everything

Facets and filters, without the lag

OpenAI, Anthropic, Hugging Face … all native

More vectors. Less memory. No trade-offs.

Semantic search, fewer steps

Test RAG fast — no setup needed

Go hosted on AWS, Azure, or Google Cloud — or try serverless and let Elastic handle the rest.

One call, that's all

Best in class? Built right in

A high quality neighborhood

Customer spotlight

Customer spotlight

Customer spotlight

Vector database superset

Some vector databases

Elasticsearch

Embeddings

Retrieval

Machine learning

Search experience tools

Elastic tools

Frequently asked questions

What is a vector database and how does it work?

What are vector embeddings?

What are the benefits of a vector database?

Is Elasticsearch a vector database?

Why choose Elastic as your vector database?

Follow us

About us

Join us

Partners

Trust & Security

Investor relations

Excellence Awards