Dense vector field type

Serverless Stack

The dense_vector field type stores dense vectors of numeric values. Dense vector fields are primarily used for k-nearest neighbor (kNN) search.

The dense_vector type does not support aggregations or sorting.

You add a dense_vector field as an array of numeric values based on element_type with float by default:

				PUT my-index
					{
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector",
        "dims": 3
      },
      "my_text" : {
        "type" : "keyword"
      }
    }
  }
}
				PUT my-index/_doc/1
					{
  "my_text" : "text1",
  "my_vector" : [0.5, 10, 6]
}
				PUT my-index/_doc/2
					{
  "my_text" : "text2",
  "my_vector" : [-0.5, 10, 10]
}
		

A k-nearest neighbor (kNN) search finds the k nearest vectors to a query vector, as measured by a similarity metric.

Dense vector fields can be used to rank documents in script_score queries. This lets you perform a brute-force kNN search by scanning all documents and ranking them by similarity.

In many cases, a brute-force kNN search is not efficient enough. For this reason, the dense_vector type supports indexing vectors into a specialized data structure to support fast kNN retrieval through the knn option in the search API

Unmapped array fields of float elements with size between 128 and 4096 are dynamically mapped as dense_vector with a default similarity of cosine. You can override the default similarity by explicitly mapping the field as dense_vector with the desired similarity.

Indexing is enabled by default for dense vector fields and indexed as bbq_hnsw if dimensions are greater than or equal to 384, otherwise they are indexed as int8_hnsw. Stack 9.1.0

When indexing is enabled, you can define the vector similarity to use in kNN search:

				PUT my-index-2
					{
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector",
        "dims": 3,
        "similarity": "dot_product"
      }
    }
  }
}
		

You can disable indexing by setting the index parameter to false:

				PUT my-index-2
					{
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector",
        "dims": 3,
        "index": false
      }
    }
  }
}
		

Elasticsearch uses the HNSW algorithm to support efficient kNN search. Like most kNN algorithms, HNSW is an approximate method that sacrifices result accuracy for improved speed.

Serverless Stack 9.2.0

By default, dense_vector fields are not included in _source in responses from the _search, _msearch, _get, and _mget APIs. This helps reduce response size and improve performance, especially in scenarios where vectors are used solely for similarity scoring and not required in the output.

To retrieve vector values explicitly, you can use:

• The fields option to request specific vector fields directly:

  				POST my-index-2/_search
  					{
    "fields": ["my_vector"]
  }
  		

• The _source.exclude_vectors flag to re-enable vector inclusion in _source responses:

  				POST my-index-2/_search
  					{
    "_source": {
      "exclude_vectors": false
    }
  }
  		

By default, dense_vector fields are not stored in _source on disk. This is also controlled by the index setting index.mapping.exclude_source_vectors. This setting is enabled by default for newly created indices and can only be set at index creation time.

When enabled:

• dense_vector fields are removed from _source and the rest of the _source is stored as usual.
• If a request includes _source and vector values are needed (e.g., during recovery or reindex), the vectors are rehydrated from their internal format.

This setting is compatible with synthetic _source, where the entire _source document is reconstructed from columnar storage. In full synthetic mode, no _source is stored on disk, and all fields — including vectors — are rebuilt when needed.

When vector values are rehydrated (e.g., for reindex, recovery, or explicit _source requests), they are restored from their internal format. Internally, vectors are stored at float precision, so if they were originally indexed as higher-precision types (e.g., double or long), the rehydrated values will have reduced precision. This lossy representation is intended to save space while preserving search quality.

If you want to preserve the original vector values exactly as they were provided, you can re-enable vector storage in _source:

				PUT my-index-include-vectors
					{
  "settings": {
    "index.mapping.exclude_source_vectors": false
  },
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector"
      }
    }
  }
}
		

When this setting is disabled:

• dense_vector fields are stored as part of the _source, exactly as indexed.
• The index will store both the original _source value and the internal representation used for vector search, resulting in increased storage usage.
• Vectors are once again returned in _source by default in all relevant APIs, with no need to use exclude_vectors or fields.

This configuration is appropriate when full source fidelity is required, such as for auditing or round-tripping exact input values.

The dense_vector type supports quantization to reduce the memory footprint required when searching float vectors. The three following quantization strategies are supported:

• int8 - Quantizes each dimension of the vector to 1-byte integers. This reduces the memory footprint by 75% (or 4x) at the cost of some accuracy.
• int4 - Quantizes each dimension of the vector to half-byte integers. This reduces the memory footprint by 87% (or 8x) at the cost of accuracy.
• bbq - Better binary quantization which reduces each dimension to a single bit precision. This reduces the memory footprint by 96% (or 32x) at a larger cost of accuracy. Generally, oversampling during query time and reranking can help mitigate the accuracy loss.

When using a quantized format, you may want to oversample and rescore the results to improve accuracy. See oversampling and rescoring for more information.

To use a quantized index, you can set your index type to int8_hnsw, int4_hnsw, or bbq_hnsw. When indexing float vectors, the current default index type is bbq_hnsw for vectors with greater than or equal to 384 dimensions, otherwise it's int8_hnsw.

Quantized vectors can use oversampling and rescoring to improve accuracy on approximate kNN search results.

Here is an example of how to create a byte-quantized index:

				PUT my-byte-quantized-index
					{
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector",
        "dims": 3,
        "index": true,
        "index_options": {
          "type": "int8_hnsw"
        }
      }
    }
  }
}
		

Here is an example of how to create a half-byte-quantized index:

				PUT my-byte-quantized-index
					{
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector",
        "dims": 4,
        "index": true,
        "index_options": {
          "type": "int4_hnsw"
        }
      }
    }
  }
}
		

Here is an example of how to create a binary quantized index:

				PUT my-byte-quantized-index
					{
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector",
        "dims": 64,
        "index": true,
        "index_options": {
          "type": "bbq_hnsw"
        }
      }
    }
  }
}
		

The following mapping parameters are accepted:

element_type

(Optional, string) The data type used to encode vectors. The supported data types are float (default), byte, and bit.

dims

(Optional, integer) Number of vector dimensions. Can’t exceed 4096. If dims is not specified, it will be set to the length of the first vector added to the field.

index

(Optional, Boolean) If true, you can search this field using the knn query or knn in _search . Defaults to true.

similarity

(Optional¹, string) The vector similarity metric to use in kNN search. Documents are ranked by their vector field’s similarity to the query vector. The _score of each document will be derived from the similarity, in a way that ensures scores are positive and that a larger score corresponds to a higher ranking. Defaults to l2_norm when element_type: bit otherwise defaults to cosine.

¹ This parameter can only be specified when index is true.

Note

bit vectors only support l2_norm as their similarity metric.

index_options

(Optional², object) An optional section that configures the kNN indexing algorithm. The HNSW algorithm has two internal parameters that influence how the data structure is built. These can be adjusted to improve the accuracy of results, at the expense of slower indexing speed.

² This parameter can only be specified when index is true.

dense_vector fields support synthetic _source .

When using element_type: bit, this will treat all vectors as bit vectors. Bit vectors utilize only a single bit per dimension and are internally encoded as bytes. This can be useful for very high-dimensional vectors or models.

When using bit, the number of dimensions must be a multiple of 8 and must represent the number of bits. Additionally, with bit vectors, the typical vector similarity values are effectively all scored the same, e.g. with hamming distance.

Let’s compare two byte[] arrays, each representing 40 individual bits.

[-127, 0, 1, 42, 127] in bits 1000000100000000000000010010101001111111 [127, -127, 0, 1, 42] in bits 0111111110000001000000000000000100101010

When comparing these two bit, vectors, we first take the hamming distance.

xor result:

1000000100000000000000010010101001111111
^
0111111110000001000000000000000100101010
=
1111111010000001000000010010101101010101
		

Then, we gather the count of 1 bits in the xor result: 18. To scale for scoring, we subtract from the total number of bits and divide by the total number of bits: (40 - 18) / 40 = 0.55. This would be the _score between these two vectors.

Here is an example of indexing and searching bit vectors:

				PUT my-bit-vectors
					{
  "mappings": {
    "properties": {
      "my_vector": {
        "type": "dense_vector",
        "dims": 40,
        "element_type": "bit"
      }
    }
  }
}
		

1. The number of dimensions that represents the number of bits

				POST /my-bit-vectors/_bulk?refresh
					{"index": {"_id" : "1"}}
{"my_vector": [127, -127, 0, 1, 42]}
{"index": {"_id" : "2"}}
{"my_vector": "8100012a7f"}
		

1. 5 bytes representing the 40 bit dimensioned vector
2. A hexidecimal string representing the 40 bit dimensioned vector

Then, when searching, you can use the knn query to search for similar bit vectors:

				POST /my-bit-vectors/_search?filter_path=hits.hits
					{
  "query": {
    "knn": {
      "query_vector": [127, -127, 0, 1, 42],
      "field": "my_vector"
    }
  }
}
		

{
  "hits": {
    "hits": [
      {
        "_index": "my-bit-vectors",
        "_id": "1",
        "_score": 1,
        "_source": {
          "my_vector": [
            127,
            -127,
            0,
            1,
            42
          ]
        }
      },
      {
        "_index": "my-bit-vectors",
        "_id": "2",
        "_score": 0.55,
        "_source": {
          "my_vector": "8100012a7f"
        }
      }
    ]
  }
}
		

To better accommodate scaling and performance needs, updating the type setting in index_options is possible with the Update Mapping API, according to the following graph (jumps allowed):

flat --> int8_flat --> int4_flat --> bbq_flat --> hnsw --> int8_hnsw --> int4_hnsw --> bbq_hnsw
		

flat --> int8_flat --> int4_flat --> hnsw --> int8_hnsw --> int4_hnsw
		

For updating all HNSW types (hnsw, int8_hnsw, int4_hnsw, bbq_hnsw) the number of connections m must either stay the same or increase. For the scalar quantized formats int8_flat, int4_flat, int8_hnsw and int4_hnsw the confidence_interval must always be consistent (once defined, it cannot change).

Updating type in index_options will fail in all other scenarios.

Switching types won’t re-index vectors that have already been indexed (they will keep using their original type), vectors being indexed after the change will use the new type instead.

For example, it’s possible to define a dense vector field that utilizes the flat type (raw float32 arrays) for a first batch of data to be indexed.

				PUT my-index-000001
					{
    "mappings": {
        "properties": {
            "text_embedding": {
                "type": "dense_vector",
                "dims": 384,
                "index_options": {
                    "type": "flat"
                }
            }
        }
    }
}
		

Changing the type to int4_hnsw makes sure vectors indexed after the change will use an int4 scalar quantized representation and HNSW (e.g., for KNN queries). That includes new segments created by merging previously created segments.

				PUT /my-index-000001/_mapping
					{
    "properties": {
        "text_embedding": {
            "type": "dense_vector",
            "dims": 384,
            "index_options": {
                "type": "int4_hnsw"
            }
        }
    }
}
		

Vectors indexed before this change will keep using the flat type (raw float32 representation and brute force search for KNN queries).

In order to have all the vectors updated to the new type, either reindexing or force merging should be used.

For debugging purposes, it’s possible to inspect how many segments (and docs) exist for each type with the Index Segments API.