Dense vector field type
editDense vector field type
editThe 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:
response = client.indices.create( index: 'my-index', body: { mappings: { properties: { my_vector: { type: 'dense_vector', dims: 3 }, my_text: { type: 'keyword' } } } } ) puts response response = client.index( index: 'my-index', id: 1, body: { my_text: 'text1', my_vector: [ 0.5, 10, 6 ] } ) puts response response = client.index( index: 'my-index', id: 2, body: { my_text: 'text2', my_vector: [ -0.5, 10, 10 ] } ) puts response
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] }
Unlike most other data types, dense vectors are always single-valued.
It is not possible to store multiple values in one dense_vector
field.
Index vectors for kNN search
editA 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 similariy 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 int8_hnsw
.
When indexing is enabled, you can define the vector similarity to use in kNN search:
response = client.indices.create( index: 'my-index-2', body: { mappings: { properties: { my_vector: { type: 'dense_vector', dims: 3, similarity: 'dot_product' } } } } ) puts response
PUT my-index-2 { "mappings": { "properties": { "my_vector": { "type": "dense_vector", "dims": 3, "similarity": "dot_product" } } } }
Indexing vectors for approximate kNN search is an expensive process. It
can take substantial time to ingest documents that contain vector fields with
index
enabled. See k-nearest neighbor (kNN) search to
learn more about the memory requirements.
You can disable indexing by setting the index
parameter to false
:
response = client.indices.create( index: 'my-index-2', body: { mappings: { properties: { my_vector: { type: 'dense_vector', dims: 3, index: false } } } } ) puts response
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.
Automatically quantize vectors for kNN search
editThe dense_vector
type supports quantization to reduce the memory footprint required when searching float
vectors.
Currently the only quantization method supported is int8
and provided vectors element_type
must be float
. To use
a quantized index, you can set your index type to int8_hnsw
. When indexing float
vectors, the current default
index type is int8_hnsw
.
When using the int8_hnsw
index, each of the float
vectors' dimensions are quantized to 1-byte integers. This can
reduce the memory footprint by as much as 75% at the cost of some accuracy. However, the disk usage can increase by
25% due to the overhead of storing the quantized and raw vectors.
response = client.indices.create( index: 'my-byte-quantized-index', body: { mappings: { properties: { my_vector: { type: 'dense_vector', dims: 3, index: true, index_options: { type: 'int8_hnsw' } } } } } ) puts response
PUT my-byte-quantized-index { "mappings": { "properties": { "my_vector": { "type": "dense_vector", "dims": 3, "index": true, "index_options": { "type": "int8_hnsw" } } } } }
Parameters for dense vector fields
editThe following mapping parameters are accepted:
-
element_type
-
(Optional, string)
The data type used to encode vectors. The supported data types are
float
(default) andbyte
.float
indexes a 4-byte floating-point value per dimension.byte
indexes a 1-byte integer value per dimension. Usingbyte
can result in a substantially smaller index size with the trade off of lower precision. Vectors usingbyte
require dimensions with integer values between -128 to 127, inclusive for both indexing and searching. -
dims
-
(Optional, integer)
Number of vector dimensions. Can’t exceed
4096
. Ifdims
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 search API. Defaults totrue
.
-
similarity
-
(Optional*, 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 tocosine
.* This parameter can only be specified when
index
istrue
.Valid values for
similarity
-
l2_norm
-
Computes similarity based on the L2 distance (also known as Euclidean
distance) between the vectors. The document
_score
is computed as1 / (1 + l2_norm(query, vector)^2)
. -
dot_product
-
Computes the dot product of two unit vectors. This option provides an optimized way to perform cosine similarity. The constraints and computed score are defined by
element_type
.When
element_type
isfloat
, all vectors must be unit length, including both document and query vectors. The document_score
is computed as(1 + dot_product(query, vector)) / 2
.When
element_type
isbyte
, all vectors must have the same length including both document and query vectors or results will be inaccurate. The document_score
is computed as0.5 + (dot_product(query, vector) / (32768 * dims))
wheredims
is the number of dimensions per vector. -
cosine
-
Computes the cosine similarity. During indexing Elasticsearch automatically
normalizes vectors with
cosine
similarity to unit length. This allows to internally usedot_product
for computing similarity, which is more efficient. Original un-normalized vectors can be still accessed through scripts. The document_score
is computed as(1 + cosine(query, vector)) / 2
. Thecosine
similarity does not allow vectors with zero magnitude, since cosine is not defined in this case. -
max_inner_product
-
Computes the maximum inner product of two vectors. This is similar to
dot_product
, but doesn’t require vectors to be normalized. This means that each vector’s magnitude can significantly effect the score. The document_score
is adjusted to prevent negative values. Formax_inner_product
values< 0
, the_score
is1 / (1 + -1 * max_inner_product(query, vector))
. For non-negativemax_inner_product
results the_score
is calculatedmax_inner_product(query, vector) + 1
.
-
Although they are conceptually related, the similarity
parameter is
different from text
field similarity
and accepts
a distinct set of options.
-
index_options
-
(Optional*, 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.
* This parameter can only be specified when
index
istrue
.Properties of
index_options
-
type
-
(Required, string) The type of kNN algorithm to use. Can be either any of:
-
hnsw
- This utilizes the HNSW algorithm for scalable approximate kNN search. This supports allelement_type
values. -
int8_hnsw
- The default index type for float vectors. This utilizes the HNSW algorithm in addition to automatically scalar quantization for scalable approximate kNN search withelement_type
offloat
. This can reduce the memory footprint by 4x at the cost of some accuracy. See Automatically quantize vectors for kNN search. -
flat
- This utilizes a brute-force search algorithm for exact kNN search. This supports allelement_type
values. -
int8_flat
- This utilizes a brute-force search algorithm in addition to automatically scalar quantization. Only supportselement_type
offloat
.
-
-
m
-
(Optional, integer)
The number of neighbors each node will be connected to in the HNSW graph.
Defaults to
16
. Only applicable tohnsw
andint8_hnsw
index types. -
ef_construction
-
(Optional, integer)
The number of candidates to track while assembling the list of nearest
neighbors for each new node. Defaults to
100
. Only applicable tohnsw
andint8_hnsw
index types. -
confidence_interval
-
(Optional, float)
Only applicable to
int8_hnsw
andint8_flat
index types. The confidence interval to use when quantizing the vectors, can be any value between and including0.90
and1.0
. This value restricts the values used when calculating the quantization thresholds. For example, a value of0.95
will only use the middle 95% of the values when calculating the quantization thresholds (e.g. the highest and lowest 2.5% of values will be ignored). Defaults to1/(dims + 1)
.
-
Synthetic _source
editSynthetic _source
is Generally Available only for TSDB indices
(indices that have index.mode
set to time_series
). For other indices
synthetic _source
is in technical preview. Features in technical preview may
be changed or removed in a future release. Elastic will work to fix
any issues, but features in technical preview are not subject to the support SLA
of official GA features.
dense_vector
fields support synthetic _source
.