# Knn query

## Serverless

### Stack

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_vector`s or [`semantic_text`](/content/docs/reference/elasticsearch/mapping-reference/semantic-text/index.html) fields which use `dense_vector` under the hood. For `dense_vector` fields, you can also use the [top level knn section](/content/docs/solutions/search/vector/knn/index.html) of a search request.

### Note

The top-level `knn` option does not support `semantic_text` fields. To run a kNN search on a `semantic_text` field, use the `knn` query described on this page. You can also query `semantic_text` fields using a [`match` query](/content/docs/reference/query-languages/query-dsl/query-dsl-match-query/index.html), which is the simplest approach.

## Example request

```apiheader
PUT my-image-index
{
  "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.

```apiheader
POST my-image-index/_bulk?refresh=true
{ "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.

```apiheader
POST my-image-index/_search
{
 "size" : 3,
 "query" : {
   "knn": {
     "field": "image-vector",
     "query_vector": [-5, 9, -12],
     "k": 10
   }
 }
}
```

3. Stack9.0-9.3

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`.

```apiheader
POST my-image-index/_search
{
 "size" : 3,
 "query" : {
   "knn": {
     "field": "image-vector",
     "query_vector": "fb09f4",
     "k": 10
   }
 }
}
```

4. Stack9.4+

You can also provide a base64-encoded query vector string. For example, `[-5, 9, -12]` encoded as float32 big-endian bytes is `wKAAAEEQAADBQAAA`.

```apiheader
POST my-image-index/_search
{
 "size" : 3,
 "query" : {
   "knn": {
     "field": "image-vector",
     "query_vector": "wKAAAEEQAADBQAAA",
     "k": 10
   }
 }
}
```

## Top-level parameters for `knn`

`field`(Required, string) The name of the vector field to search against. Must be a [`dense_vector` field with indexing enabled](/content/docs/reference/elasticsearch/mapping-reference/dense-vector#index-vectors-knn-search/index.html), or a [`semantic_text` field](/content/docs/reference/elasticsearch/mapping-reference/semantic-text/index.html) with a compatible dense vector inference model.

`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).

Stack9.0-9.3

- A base64-encoded vector string. Base64 supports `float` and `bfloat16` (big-endian), `byte`, and `bit` encodings depending on the target field type.

Stack9.4+

Either this or `query_vector_builder` must be provided.

`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. Refer to [Query vector builder types](/content/docs/reference/query-languages/query-dsl/query-dsl-knn-query#query-vector-builders-parameters/index.html) for parameter details and [Query vector builder examples](/content/docs/reference/query-languages/query-dsl/query-dsl-knn-query#query-vector-builders-overview/index.html) for usage examples.

`k`(Optional, integer) The number of nearest neighbors to return from each shard. Elasticsearch collects `k` (or `k * oversample` if conditions for [`rescore_vector`](/content/docs/solutions/search/vector/knn#the-rescore_vector-option/index.html) 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.

`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`](/content/docs/solutions/search/vector/knn#the-rescore_vector-option/index.html) are met) is applied, `num_candidates` is set to `max(num_candidates, k * oversample)`

`visit_percentage`(Stack9.2+
(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.

`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.

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.

`similarity`(Optional, float) The minimum similarity required for a document to be considered a match. The similarity value calculated relates to the raw [`similarity`](/content/docs/reference/elasticsearch/mapping-reference/dense-vector#dense-vector-similarity/index.html) used. Not the document score. The matched documents are then scored according to [`similarity`](/content/docs/reference/elasticsearch/mapping-reference/dense-vector#dense-vector-similarity/index.html) and the provided `boost` is applied.

`boost`(Optional, float) Floating point number used to multiply the scores of matched documents. This value cannot be negative. Defaults to `1.0`.

`_name`(Optional, string) Name field to identify the query

`rescore_vector`(StackGA9.1+
(Optional, object) Apply oversampling and rescoring to quantized vectors.

### Parameters for `rescore_vector`

`oversample`(Required, float)

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.

### 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](/content/docs/manage-data/data-store/aliases#filter-alias/index.html) 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.

```apiheader
POST my-image-index/_search
{
  "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.

```apiheader
POST my-image-index/_search
{
  "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](/content/docs/solutions/search/vector/knn#nested-knn-search/index.html):

- 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

### 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

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)

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

Note

The top-level `knn` search option does not support `semantic_text` fields. Use the `knn` query shown below to run a kNN search on a `semantic_text` field which uses `dense_vector` under the hood. For simpler use cases, you can also use a [`match` query](/content/docs/reference/query-languages/query-dsl/query-dsl-match-query/index.html) directly on the `semantic_text` field.

Elasticsearch supports knn queries over a [`semantic_text` field](/content/docs/reference/elasticsearch/mapping-reference/semantic-text/index.html).

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.

## Build query vectors for knn search

Query vector builders let you generate vectors directly from inputs such as text or base64-encoded images at search time.

Elasticsearch provides three query vector builders. Each builder generates a query vector from a different type of input or source.

- [`text_embedding`](/content/docs/reference/query-languages/query-dsl/query-dsl-knn-query#knn-query-builder-text-embedding/index.html): Generates a query vector from text input. This is useful when your application sends raw text, such as a search query, and you want Elasticsearch to convert it into an embedding automatically instead of generating the vector in advance.
- [`embedding`](/content/docs/reference/query-languages/query-dsl/query-dsl-knn-query#embedding-builder/index.html): Generates a query vector from multimodal input, such as text or base64-encoded images. Use this when you want to generate embeddings dynamically from different types of input without creating them in advance.
- [`lookup`](/content/docs/reference/query-languages/query-dsl/query-dsl-knn-query#lookup-builder/index.html): Retrieves an existing vector from a stored document to use as the query vector. This is useful when you want to find documents similar to an existing document, without generating a new embedding at search time.

### Query vector builder types

`lookup`

Build the query vector by looking up an existing document's vector. For an example, refer to [`lookup`](/content/docs/reference/query-languages/query-dsl/query-dsl-knn-query#lookup-builder/index.html).

### 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.

`text_embedding`

Build the query vector by generating an embedding from input text. For an example, refer to [`text_embedding`](/content/docs/reference/query-languages/query-dsl/query-dsl-knn-query#text-embedding-builder/index.html).

### Parameters for `text_embedding`

`model_id`: (Optional, string) Identifier of the text embedding model that generates the query vector. Use the same model that produced vectors in your index.

Note

When you query only [semantic_text](/content/docs/reference/elasticsearch/mapping-reference/semantic-text/index.html) fields, you can omit `model_id` because Elasticsearch uses the `inference_id` from the `semantic_text` field mapping (for example the search-time inference endpoint configured on the field).

For [`dense_vector`](/content/docs/reference/elasticsearch/mapping-reference/dense-vector/index.html) fields or when you need a different model than the one mapped on `semantic_text`, set `model_id` explicitly.

`model_text`: (Required, string) The query text passed to the model to produce the embedding.

### Example requests for query vector builders
#### Lookup builder

```apiheader
{
  "knn": {
    "field": "dense-vector-field",
    "k": 10,
    "num_candidates": 100,
    "query_vector_builder": {
      "lookup": {
        "index": "my-index",
        "id": "document-1",
        "path": "my_vector"
      }
    }
  }
}
```

#### Text embedding builder

```apiheader
{
  "knn": {
    "field": "dense-vector-field",
    "k": 10,
    "num_candidates": 100,
    "query_vector_builder": {
      "text_embedding": {
        "model_id": "my-text-embedding-model",
        "model_text": "The opposite of blue"
      }
    }
  }
}
```

#### Embedding builder

```apiheader
{
  "knn": {
    "field": "dense-vector-field",
    "k": 10,
    "num_candidates": 100,
    "query_vector_builder": {
      "embedding": {
        "inference_id": "my-embedding-endpoint",
        "input": {
          "type": "image",
          "format": "base64",
          "value": "data:image/jpeg;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA
AAAAFCAIAAAACDbGyAAAAHElEQVQI12P4
//8/w38GIAXDIBKE0DHxgljNBAAO
9TXL0Y4OHwAAAABJRU5ErkJggg=="
        }
      }
    }
  }
}
```