---
title: Knn query
description: Finds the k nearest vectors to a query vector, as measured by a similarity metric. knn query finds nearest vectors through approximate search on indexed...
url: https://www.elastic.co/elastic/docs-builder/docs/3028/reference/query-languages/query-dsl/query-dsl-knn-query
products:
  - Elasticsearch
applies_to:
  - Elastic Cloud Serverless: Generally available
  - Elastic Stack: Generally available
---

# Knn query
Finds the *k* nearest vectors to a query vector, as measured by a similarity metric. *knn* query finds nearest vectors through approximate search on indexed dense_vectors. The preferred way to do approximate kNN search is through the [top level knn section](https://docs-v3-preview.elastic.dev/elastic/docs-builder/docs/3028/solutions/search/vector/knn) of a search request. *knn* query is reserved for expert cases, where there is a need to combine this query with other queries, or perform a kNN search against a [semantic_text](https://www.elastic.co/elastic/docs-builder/docs/3028/reference/elasticsearch/mapping-reference/semantic-text) field.

## Example request

```json

{
  "mappings": {
    "properties": {
       "image-vector": {
        "type": "dense_vector",
        "dims": 3,
        "index": true,
        "similarity": "l2_norm"
      },
      "file-type": {
        "type": "keyword"
      },
      "title": {
        "type": "text"
      }
    }
  }
}
```

1. Index your data.
   ```json

   { "index": { "_id": "1" } }
   { "image-vector": [1, 5, -20], "file-type": "jpg", "title": "mountain lake" }
   { "index": { "_id": "2" } }
   { "image-vector": [42, 8, -15], "file-type": "png", "title": "frozen lake"}
   { "index": { "_id": "3" } }
   { "image-vector": [15, 11, 23], "file-type": "jpg", "title": "mountain lake lodge" }
   ```
   
2. Run the search using the `knn` query, asking for the top 10 nearest vectors from each shard, and then combine shard results to get the top 3 global results.
   ```json

   {
     "size" : 3,
     "query" : {
       "knn": {
         "field": "image-vector",
         "query_vector": [-5, 9, -12],
         "k": 10
       }
     }
   }
   ```
   
3. <applies-to>Elastic Stack: Generally available from 9.0 to 9.3</applies-to> You can also provide a hex-encoded query vector string. Hex query vectors are byte-oriented (one byte per dimension, represented as two hex characters). For example, `[-5, 9, -12]` as signed bytes is `fb09f4`.
   ```json

   {
     "size" : 3,
     "query" : {
       "knn": {
         "field": "image-vector",
         "query_vector": "fb09f4",
         "k": 10
       }
     }
   }
   ```
   
4. <applies-to>Elastic Stack: Planned</applies-to> You can also provide a base64-encoded query vector string. For example, `[-5, 9, -12]` encoded as float32 big-endian bytes is `wKAAAEEQAADBQAAA`.
   ```json

   {
     "size" : 3,
     "query" : {
       "knn": {
         "field": "image-vector",
         "query_vector": "wKAAAEEQAADBQAAA",
         "k": 10
       }
     }
   }
   ```
   


## Top-level parameters for `knn`

<definitions>
  <definition term="field">
    (Required, string) The name of the vector field to search against. Must be a [`dense_vector` field with indexing enabled](/elastic/docs-builder/docs/3028/reference/elasticsearch/mapping-reference/dense-vector#index-vectors-knn-search), or a [`semantic_text` field](https://www.elastic.co/elastic/docs-builder/docs/3028/reference/elasticsearch/mapping-reference/semantic-text) with a compatible dense vector inference model.
  </definition>
  <definition term="query_vector">
    (Optional, array of floats or string) Query vector. Must have the same number of dimensions as the vector field you are searching against.
    Must be one of:
    - An array of floats
    - A hex-encoded byte vector (one byte per dimension; for `bit`, one byte per 8 dimensions). <applies-to>Elastic Stack: Generally available from 9.0 to 9.3</applies-to>
    - A base64-encoded vector string. Base64 supports `float` and `bfloat16` (big-endian), `byte`, and `bit` encodings depending on the target field type. <applies-to>Elastic Stack: Planned</applies-to> <applies-to>Elastic Cloud Serverless: Generally available</applies-to>
      Either this or `query_vector_builder` must be provided.
  </definition>
  <definition term="query_vector_builder">
    (Optional, object) Query vector builder. A configuration object indicating how to build a query_vector before executing the request. You must provide either a `query_vector_builder` or `query_vector`, but not both.
    <definitions>
      <definition term="Parameters for query_vector_builder:">
        (Optional, object) Build the query vector by looking up an existing document's vector.
      </definition>
    </definitions>
    **Parameters for `lookup`**:
    `id`
    :   (Required, string) The ID of the document to look up.
    `path`
    :   (Required, string) The name of the vector field in the document to use as the query vector.
    `index`
    :   (Required, string) The name of the index containing the document to look up
    `routing`
    :   (Optional, string) The routing value to use when looking up the document.
    <definitions>
      <definition term="text_embedding">
        (Optional, object) Build the query vector by generating an embedding from input text. Refer to [Perform semantic search](https://docs-v3-preview.elastic.dev/elastic/docs-builder/docs/3028/solutions/search/vector/knn#knn-semantic-search) to learn more.
        If all queried fields are of type [semantic_text](https://www.elastic.co/elastic/docs-builder/docs/3028/reference/elasticsearch/mapping-reference/semantic-text), the inference ID associated with the `semantic_text` field may be inferred.
      </definition>
    </definitions>
  </definition>
  <definition term="k">
    (Optional, integer) The number of nearest neighbors to return from each shard. Elasticsearch collects `k` (or `k * oversample` if conditions for [`rescore_vector`](https://docs-v3-preview.elastic.dev/elastic/docs-builder/docs/3028/solutions/search/vector/knn#the-rescore_vector-option) are met) results from each shard, then merges them to find the global top `k` results. This value must be less than or equal to `num_candidates`. Defaults to search request size.
  </definition>
  <definition term="num_candidates">
    (Optional, integer) The number of nearest neighbor candidates to consider per shard while doing knn search. Cannot exceed 10,000. Increasing `num_candidates` tends to improve the accuracy of the final results. Defaults to `1.5 * k` if `k` is set, or `1.5 * size` if `k` is not set. When [`rescore_vector`](https://docs-v3-preview.elastic.dev/elastic/docs-builder/docs/3028/solutions/search/vector/knn#the-rescore_vector-option) are met) is applied, `num_candidates` is set to `max(num_candidates, k * oversample)`
  </definition>
  <definition term="visit_percentage Elastic Stack: Generally available since 9.2">
    (Optional, float) The percentage of vectors to explore per shard while doing knn search with `bbq_disk`. Must be between 0 and 100.  0 will default to using `num_candidates` for calculating the percent visited. Increasing `visit_percentage` tends to improve the accuracy of the final results.  If `visit_percentage` is set for `bbq_disk`, `num_candidates` is ignored. Defaults to ~1% per shard for every 1 million vectors.
  </definition>
  <definition term="filter">
    (Optional, query object) Query to filter the documents that can match. The kNN search will return the top documents that also match this filter. The value can be a single query or a list of queries. If `filter` is not provided, all documents are allowed to match.
  </definition>
</definitions>

The filter is a pre-filter, meaning that it is applied **during** the approximate kNN search to ensure that `num_candidates` matching documents are returned.
<definitions>
  <definition term="similarity">
    (Optional, float) The minimum similarity required for a document to be considered a match. The similarity value calculated relates to the raw [`similarity`](/elastic/docs-builder/docs/3028/reference/elasticsearch/mapping-reference/dense-vector#dense-vector-similarity) used. Not the document score. The matched documents are then scored according to [`similarity`](/elastic/docs-builder/docs/3028/reference/elasticsearch/mapping-reference/dense-vector#dense-vector-similarity) and the provided `boost` is applied.
  </definition>
  <definition term="boost">
    (Optional, float) Floating point number used to multiply the scores of matched documents. This value cannot be negative. Defaults to `1.0`.
  </definition>
  <definition term="_name">
    (Optional, string) Name field to identify the query
  </definition>
  <definition term="rescore_vector Elastic Stack: Generally available since 9.1, Elastic Stack: Preview in 9.0">
    (Optional, object) Apply oversampling and rescoring to quantized vectors.
    **Parameters for `rescore_vector`**:
    <definitions>
      <definition term="oversample">
        (Required, float)
      </definition>
    </definitions>
    Applies the specified oversample factor to `k` on the approximate kNN search. The approximate kNN search will:
    - Retrieve `num_candidates` candidates per shard.
    - From these candidates, the top `k * oversample` candidates per shard will be rescored using the original vectors.
    - The top `k` rescored candidates will be returned. Must be one of the following values:
      - >= 1f to indicate the oversample factor
    - Exactly `0` to indicate that no oversampling and rescoring should occur. <applies-to>Elastic Stack: Generally available since 9.1</applies-to>
    See [oversampling and rescoring quantized vectors](https://docs-v3-preview.elastic.dev/elastic/docs-builder/docs/3028/solutions/search/vector/knn#dense-vector-knn-search-rescoring) for details.
    <note>
      Rescoring only makes sense for [quantized](/elastic/docs-builder/docs/3028/reference/elasticsearch/mapping-reference/dense-vector#dense-vector-quantization) vectors. The `rescore_vector` option will be ignored for non-quantized `dense_vector` fields, because the original vectors are used for scoring.
    </note>
  </definition>
</definitions>


## Pre-filters and post-filters in knn query

There are two ways to filter documents that match a kNN query:
1. **pre-filtering** – filter is applied during the approximate kNN search to ensure that `k` matching documents are returned.
2. **post-filtering** – filter is applied after the approximate kNN search completes, which results in fewer than k results, even when there are enough matching documents.

Pre-filtering is supported through the `filter` parameter of the `knn` query. Also filters from [aliases](https://docs-v3-preview.elastic.dev/elastic/docs-builder/docs/3028/manage-data/data-store/aliases#filter-alias) are applied as pre-filters.
All other filters found in the Query DSL tree are applied as post-filters. For example, `knn` query finds the top 3 documents with the nearest vectors (k=3), which are combined with  `term` filter, that is post-filtered. The final set of documents will contain only a single document that passes the post-filter.
```json

{
  "size" : 10,
  "query" : {
    "bool" : {
      "must" : {
        "knn": {
          "field": "image-vector",
          "query_vector": [-5, 9, -12],
          "k": 3
        }
      },
      "filter" : {
        "term" : { "file-type" : "png" }
      }
    }
  }
}
```


## Hybrid search with knn query

Knn query can be used as a part of hybrid search, where knn query is combined with other lexical queries. For example, the query below finds documents with `title` matching `mountain lake`, and combines them with the top 10 documents that have the closest image vectors to the `query_vector`. The combined documents are then scored and the top 3 top scored documents are returned.
```json

{
  "size" : 3,
  "query": {
    "bool": {
      "should": [
        {
          "match": {
            "title": {
              "query": "mountain lake",
              "boost": 1
            }
          }
        },
        {
          "knn": {
            "field": "image-vector",
            "query_vector": [-5, 9, -12],
            "k": 10,
            "boost": 2
          }
        }
      ]
    }
  }
}
```


## Knn query inside a nested query

The `knn` query can be used inside a nested query. The behaviour here is similar to [top level nested kNN search](https://docs-v3-preview.elastic.dev/elastic/docs-builder/docs/3028/solutions/search/vector/knn#nested-knn-search):
- kNN search over nested `dense_vector`s diversifies the top results over the top-level document
- `filter` both over the top-level document metadata and `nested` is supported and acts as a pre-filter

To ensure correct results: each individual filter must be either over:
- Top-level metadata
- `nested` metadata <applies-to>Elastic Stack: Generally available since 9.2</applies-to>
  <note>
  A single knn query supports multiple filters, where some filters can be over the top-level metadata and some over nested.
  </note>


### Basic nested knn search

This query performs a basic nested knn search:
```js
{
  "query" : {
    "nested" : {
      "path" : "paragraph",
        "query" : {
          "knn": {
            "query_vector": [0.45, 0.50],
            "field": "paragraph.vector"
        }
      }
    }
  }
}
```


### Filter over nested metadata

<applies-to>
  - Elastic Stack: Generally available since 9.2
</applies-to>

This query filters over nested metadata. For scoring parent documents, this query only considers vectors that
have "paragraph.language" set to "EN":
```js
{
  "query" : {
    "nested" : {
      "path" : "paragraph",
        "query" : {
          "knn": {
            "query_vector": [0.45, 0.50],
            "field": "paragraph.vector",
            "filter": {
              "match": {
                "paragraph.language": "EN"
              }
            }
        }
      }
    }
  }
}
```


### Multiple filters (nested and top-level metadata)

<applies-to>
  - Elastic Stack: Generally available since 9.2
</applies-to>

This query uses multiple filters: one over nested metadata and another over the top level metadata. For scoring parent documents,
this query only considers vectors whose parent's title contain "essay"
word and have "paragraph.language" set to "EN":
```js
{
  "query" : {
    "nested" : {
      "path" : "paragraph",
      "query" : {
        "knn": {
          "query_vector": [0.45, 0.50],
          "field": "paragraph.vector",
          "filter": [
            {
              "match": {
                "paragraph.language": "EN"
              }
            },
            {
              "match": {
                "title": "essay"
              }
            }
          ]
        }
      }
    }
  }
}
```

Note that nested `knn` only supports `score_mode=max`.

## Knn query on a semantic_text field

Elasticsearch supports knn queries over a [
`semantic_text` field](https://www.elastic.co/elastic/docs-builder/docs/3028/reference/elasticsearch/mapping-reference/semantic-text).
Here is an example using the `query_vector_builder`:
```js
{
  "query": {
    "knn": {
      "field": "inference_field",
      "k": 10,
      "num_candidates": 100,
      "query_vector_builder": {
        "text_embedding": {
          "model_text": "test"
        }
      }
    }
  }
}
```

Note that for `semantic_text` fields, the `model_id` does not have to be
provided as it can be inferred from the `semantic_text` field mapping.
Knn search using query vectors over `semantic_text` fields is also supported,
with no change to the API.

## Knn query with vector lookup

<applies-to>
  - Elastic Stack: Planned
</applies-to>

Elasticsearch supports knn queries with a vector that is stored within an index.
Here is an example utilizing lookup. It gets the document with id `vector_doc_0` from index `some_vector_index` and uses the field `vector_field` as the query vector for the `knn` search.
```js
{
  "query": {
    "knn": {
      "field": "vector_field",
      "query_vector_builder": {
        "lookup": {
          "id": "vector_doc_0",
          "index": "some_vector_index",
          "path": "vector_field"
        }
      }
    }
  }
}
```

%NOTCONSOLE

## Knn query with aggregations

`knn` query calculates aggregations on top `k` documents from each shard. Thus, the final results from aggregations contain `k * number_of_shards` documents. This is different from the [top level knn section](https://docs-v3-preview.elastic.dev/elastic/docs-builder/docs/3028/solutions/search/vector/knn) where aggregations are calculated on the global top `k` nearest documents.