---
title: kNN search on Elasticsearch
description: Find semantically similar documents using k-nearest neighbor (kNN) vector search in Elasticsearch.
url: https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/knn
products:
  - Elasticsearch
applies_to:
  - Elastic Cloud Serverless: Generally available
  - Elastic Stack: Generally available
---

# kNN search on Elasticsearch
A *k-nearest neighbor* (kNN) search finds the *k* nearest vectors to a query vector using a similarity metric such as cosine or L2 norm. In Elasticsearch, kNN is the primary way to query [`dense_vector`](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/dense-vector) fields after you store embeddings.

## Common use cases for kNN vector similarity search

- **Search**
  - [Semantic text search](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/semantic-search): Find documents that match the meaning of a query, even when the wording differs.
- [Image and video similarity](/elastic/docs-content/pull/7138/solutions/search/vector/vector-search-use-cases#multimodal-search): Search across text, images, audio, or video to find visually or semantically similar content.
- **Recommendations**
  - [Product recommendations](/elastic/docs-content/pull/7138/solutions/search/vector/vector-search-use-cases#discovery-and-recommendations): Surface items similar to what a user is viewing or has interacted with.
- [Collaborative filtering](/elastic/docs-content/pull/7138/solutions/search/vector/vector-search-use-cases#discovery-and-recommendations): Match users or items based on shared behavior or preference patterns in vector space.
- [Personalized content discovery](/elastic/docs-content/pull/7138/solutions/search/vector/vector-search-use-cases#discovery-and-recommendations): Suggest articles, media, or other content tailored to individual user interests.
- **Analysis**
  - [Anomaly detection](/elastic/docs-content/pull/7138/solutions/search/vector/vector-search-use-cases#duplicate-detection-fraud-and-anomaly-detection): Flag records whose vectors sit unusually far from their nearest neighbors.
- [Pattern matching](/elastic/docs-content/pull/7138/solutions/search/vector/vector-search-use-cases#duplicate-detection-fraud-and-anomaly-detection): Find near-duplicates, suspicious matches, or other patterns that exact matching would miss.


## Prerequisites for kNN search

To run a kNN search in Elasticsearch:
- Your data must be vectorized. You can [use an NLP model in Elasticsearch](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/explore-analyze/machine-learning/nlp/ml-nlp-text-emb-vector-search-example) or generate vectors outside Elasticsearch.
  - Use the [`dense_vector`](https://docs-v3-preview.elastic.dev/elastic/elasticsearch/tree/main/reference/elasticsearch/mapping-reference/dense-vector) field type for dense vectors.
- Query vectors must have the same dimension and be created with the same model as the document vectors.
- Already have vectors? Refer to [Bring your own dense vectors](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/bring-own-vectors).
- Required [index privileges](https://docs-v3-preview.elastic.dev/elastic/elasticsearch/tree/main/reference/elasticsearch/security-privileges#privileges-list-indices):
  - `create_index` or `manage` to create an index with a `dense_vector` field
- `create`, `index`, or `write` to add data
- `read` to search the index

<tip>
  The default type of Elasticsearch Serverless project is suitable for this use case unless you plan to use uncompressed dense vectors (`int4` or `int8` quantization strategies) with high dimensionality.
  To learn more, refer to [General purpose and vector optimized projects](/elastic/docs-content/pull/7138/solutions/search/vector/dense-vector#vector-profiles).
</tip>


## kNN search methods

Elasticsearch provides several ways to perform kNN search. Which one you use depends on your field type and whether you need to combine kNN with other queries.
- **Approximate kNN**
  - Best for most production workloads where low latency and scale matter more than perfect recall.
- Uses graph-based or clustered index structures to find similar vectors quickly without scoring every document in the index.
- Refer to [Approximate kNN search](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/knn/approximate-knn) for mapping, indexing, and search examples.
- **Exact, brute-force kNN**
  - Best for small datasets, pre-filtered subsets, or when you need precise scoring without approximate indexing.
- Uses a [`script_score` query](https://docs-v3-preview.elastic.dev/elastic/elasticsearch/tree/main/reference/query-languages/query-dsl/query-dsl-script-score-query) with a vector function to compute similarity against each matching document.
- Refer to [Exact kNN search](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/knn/exact-knn) for search examples.

Approximate kNN offers low latency and good accuracy, while exact kNN guarantees accurate results but does not scale well for large datasets. With exact kNN, a `script_score` query must scan each matching document to compute the vector function, which can result in slow search speeds. However, you can improve latency by using a [query](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/explore-analyze/query-filter/languages/querydsl) to limit the number of matching documents passed to the function. If you filter your data to a small subset of documents, you can get good search performance using this approach.

## Resources

- [Approximate kNN search](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/knn/approximate-knn): Learn how to map, index, and query `dense_vector` fields for fast, scalable approximate kNN search.
- [Build search queries](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/knn/build-search-queries): Learn how to construct approximate kNN queries for filtering, hybrid retrieval, semantic search, multiple vector fields, and similarity thresholds.
- [Nested kNN search](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/knn/nested-knn-search): Learn how to run approximate kNN search on nested vectors for passage retrieval, filtering, inner hits, and chunked content.
- [Optimize performance and accuracy](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/knn/optimize-performance-accuracy): Learn how to tune search speed, recall, vector storage, quantization, and rescoring for approximate kNN search.
- [Exact kNN search](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector/knn/exact-knn): Learn how to run exact brute-force kNN search with `script_score` queries for small datasets or precise scoring.
- [Vector search in Elasticsearch](https://docs-v3-preview.elastic.dev/elastic/docs-content/pull/7138/solutions/search/vector): Learn the core concepts and terminology for vector search in Elasticsearch, including embeddings, field types, and how vector retrieval fits with other search strategies.
- [Knn query](https://docs-v3-preview.elastic.dev/elastic/elasticsearch/tree/main/reference/query-languages/query-dsl/query-dsl-knn-query): API reference for the `knn` query, including parameters, `query_vector_builder` options, and usage with `dense_vector` and `semantic_text` fields.