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 or cosine.

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.
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

&q=id:(1 2 3)&fq={!knn f=vector topK=10}[1.0, 2.0, 3.0, 4.0]

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

&q={!knn f=vector topK=10}[1.0, 2.0, 3.0, 4.0]&fq=id:(1 2 3)

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.

&q={!knn f=vector topK=10}[1.0, 2.0, 3.0, 4.0]&fq={!frange cache=false l=0.99}$q

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 knn in re-ranking pay attention to the topK parameter.

The second pass score(deriving from knn) is calculated only if the document d from the first pass is within the k-nearest neighbors(in the whole index) of the target vector to search.

This means the second pass knn is executed on the whole index anyway, which is a current limitation.

The final ranked list of results will have the first pass score(main query q) added to the second pass score(the approximated similarityFunction distance to the target vector to search) multiplied by a multiplicative factor(reRankWeight).

Details about using the ReRank Query Parser can be found in the Query Re-Ranking section.