Dense Vector Search
Solr’s Dense Vector Search adds support for indexing and searching dense numerical vectors.
Deep learning can be used to produce a vector representation of both the query and the documents in a corpus of information.
These neural network-based techniques are usually referred to as neural search, an industry derivation from the academic field of Neural information Retrieval.
Important Concepts
Dense Vector Representation
A traditional tokenized inverted index can be considered to model text as a "sparse" vector, in which each term in the corpus corresponds to one vector dimension. In such a model, the number of dimensions is generally quite high (corresponding to the term dictionary cardinality), and the vector for any given document contains mostly zeros (hence it is sparse, as only a handful of terms that exist in the overall index will be present in any given document).
Dense vector representation contrasts with term-based sparse vector representation in that it distills approximate semantic meaning into a fixed (and limited) number of dimensions.
The number of dimensions in this approach is generally much lower than the sparse case, and the vector for any given document is dense, as most of its dimensions are populated by non-zero values.
In contrast to the sparse approach (for which tokenizers are used to generate sparse vectors directly from text input) the task of generating vectors must be handled in application logic external to Apache Solr.
There may be cases where it makes sense to directly search data that natively exists as a vector (e.g., scientific data); but in a text search context, it is likely that users will leverage deep learning models such as BERT to encode textual information as dense vectors, supplying the resulting vectors to Apache Solr explicitly at index and query time.
For additional information you can refer to this blog post.
Dense Retrieval
Given a dense vector v
that models the information need, the easiest approach for providing dense vector retrieval would be to calculate the distance (euclidean, dot product, etc.) between v
and each vector d
that represents a document in the corpus of information.
This approach is quite expensive, so many approximate strategies are currently under active research.
The strategy implemented in Apache Lucene and used by Apache Solr is based on Navigable Small-world graph.
It provides efficient approximate nearest neighbor search for high dimensional vectors.
Index Time
This is the Apache Solr field type designed to support dense vector search:
DenseVectorField
The dense vector field gives the possibility of indexing and searching dense vectors of float elements.
For example:
[1.0, 2.5, 3.7, 4.1]
Here’s how DenseVectorField
should be configured in the schema:
<fieldType name="knn_vector" class="solr.DenseVectorField" vectorDimension="4" similarityFunction="cosine"/>
<field name="vector" type="knn_vector" indexed="true" stored="true"/>
vectorDimension
-
Required
Default: none
The dimension of the dense vector to pass in.
Accepted values: Any integer.
similarityFunction
-
Optional
Default:
euclidean
Vector similarity function; used in search to return top K most similar vectors to a target vector.
Accepted values:
euclidean
,dot_product
orcosine
.-
euclidean
: Euclidean distance -
dot_product
: Dot product
-
this similarity is intended as an optimized way to perform cosine similarity. In order to use it, all vectors must be of unit length, including both document and query vectors. Using dot product with vectors that are not unit length can result in errors or poor search results. |
-
cosine
: Cosine similarity
the preferred way to perform cosine similarity is to normalize all vectors to unit length, and instead use DOT_PRODUCT. You should only use this function if you need to preserve the original vectors and cannot normalize them in advance. |
To use the following advanced parameters that customise the codec format and the hyperparameter of the HNSW algorithm, make sure the Schema Codec Factory, is in use.
Here’s how DenseVectorField
can be configured with the advanced hyperparameters:
<fieldType name="knn_vector" class="solr.DenseVectorField" vectorDimension="4" similarityFunction="cosine" knnAlgorithm="hnsw" hnswMaxConnections="10" hnswBeamWidth="40"/>
<field name="vector" type="knn_vector" indexed="true" stored="true"/>
knnAlgorithm
-
Optional
Default:
hnsw
(advanced) Specifies the underlying knn algorithm to use
Accepted values:
hnsw
.
Please note that the knnAlgorithm
accepted values may change in future releases.
vectorEncoding
-
Optional
Default:
FLOAT32
(advanced) Specifies the underlying encoding of the dense vector elements. This affects memory/disk impact for both the indexed and stored fields (if enabled)
Accepted values:
FLOAT32
,BYTE
. hnswMaxConnections
-
Optional
Default:
16
(advanced) This parameter is specific for the
hnsw
knn algorithm:Controls how many of the nearest neighbor candidates are connected to the new node.
It has the same meaning as
M
from the 2018 paper.Accepted values: Any integer.
hnswBeamWidth
-
Optional
Default:
100
(advanced) This parameter is specific for the
hnsw
knn algorithm:It is the number of nearest neighbor candidates to track while searching the graph for each newly inserted node.
It has the same meaning as
efConstruction
from the 2018 paper.Accepted values: Any integer.
DenseVectorField
supports the attributes: indexed
, stored
.
currently multivalue is not supported |
Here’s how a DenseVectorField
should be indexed:
JSON
[{ "id": "1",
"vector": [1.0, 2.5, 3.7, 4.1]
},
{ "id": "2",
"vector": [1.5, 5.5, 6.7, 65.1]
}
]
XML
<add>
<doc>
<field name="id">1</field>
<field name="vector">1.0</field>
<field name="vector">2.5</field>
<field name="vector">3.7</field>
<field name="vector">4.1</field>
</doc>
<doc>
<field name="id">2</field>
<field name="vector">1.5</field>
<field name="vector">5.5</field>
<field name="vector">6.7</field>
<field name="vector">65.1</field>
</doc>
</add>
SolrJ
final SolrClient client = getSolrClient();
final SolrInputDocument d1 = new SolrInputDocument();
d1.setField("id", "1");
d1.setField("vector", Arrays.asList(1.0f, 2.5f, 3.7f, 4.1f));
final SolrInputDocument d2 = new SolrInputDocument();
d2.setField("id", "2");
d2.setField("vector", Arrays.asList(1.5f, 5.5f, 6.7f, 65.1f));
client.add(Arrays.asList(d1, d2));
Query Time
This is the Apache Solr query approach designed to support dense vector search:
knn Query Parser
The knn
k-nearest neighbors query parser allows to find the k-nearest documents to the target vector according to indexed dense vectors in the given field.
The score for a retrieved document is the approximate distance to the target vector(defined by the similarityFunction configured at indexing time).
It takes the following parameters:
f
-
Required
Default: none
The
DenseVectorField
to search in. topK
-
Optional
Default: 10
How many k-nearest results to return.
Here’s how to run a KNN search:
&q={!knn f=vector topK=10}[1.0, 2.0, 3.0, 4.0]
The search results retrieved are the k-nearest to the vector in input [1.0, 2.0, 3.0, 4.0]
, ranked by the similarityFunction configured at indexing time.
Usage with Filter Queries
The knn
query parser can be used in filter queries:
&q=id:(1 2 3)&fq={!knn f=vector topK=10}[1.0, 2.0, 3.0, 4.0]
The knn
query parser can be used with filter queries:
&q={!knn f=vector topK=10}[1.0, 2.0, 3.0, 4.0]&fq=id:(1 2 3)
Filter queries are executed as pre-filters: the main query refines the sub-set of search results derived from the application of all the filter queries combined as 'MUST' clauses(boolean AND). This means that in
The results are prefiltered by the topK knn retrieval and then only the documents from this subset, matching the query 'q=id:(1 2 3)' are returned. In
The results are prefiltered by the fq=id:(1 2 3) and then only the documents from this subset are considered as candidates for the topK knn retrieval. If you want to run some of the filter queries as post-filters you can follow the standard approach for post-filtering in Apache Solr, using the cache and cost local parameters. e.g.
|
Usage as Re-Ranking Query
The knn
query parser can be used to rerank first pass query results:
&q=id:(3 4 9 2)&rq={!rerank reRankQuery=$rqq reRankDocs=4 reRankWeight=1}&rqq={!knn f=vector topK=10}[1.0, 2.0, 3.0, 4.0]
When using The second pass score(deriving from knn) is calculated only if the document This means the second pass The final ranked list of results will have the first pass score(main query Details about using the ReRank Query Parser can be found in the Query Re-Ranking section. |