VectorIndexConfiguration class abstract final Query Enterprise Edition
A specification of a vector Index from a SQL++ expression.
This feature is only available in the Enterprise Edition.
Vector Search is a technique to retrieve semantically similar items based on vector embedding representations of the items in a multi-dimensional space. You can use vector search to find the top N items similar to a given item based on their vector representations. Vector Search is an essential component of generative AI and predictive AI applications.
Vector search is a sophisticated data retrieval technique that focuses on matching the contextual meanings of search queries and data entries, rather than simple text matching. Vectors are represented by arrays of numbers known as an embedding, which are generated by Large Language Models (LLMs) to depict objects such as text, images, and audio.
Once you choose the LLM you wish to integrate in your application, you can create vector indexes that will store these embeddings for improved search performance and start querying against them.
- Implemented types
Constructors
- VectorIndexConfiguration.new(String expression, {required int dimensions, required int centroids, bool? lazy, VectorEncoding? encoding, DistanceMetric? metric, int? minTrainingSize, int? maxTrainingSize, int? numProbes})
-
Creates a specification of a vector Index from a SQL++
expression.factory
Properties
- centroids ↔ int
-
The number of centroids to use for the index.
getter/setter pair
- dimensions ↔ int
-
The number of vector dimensions to use for the index.
getter/setter pair
- encoding ↔ VectorEncoding
-
The vector encoding type to use for the index.
getter/setter pair
- expression ↔ String
-
The SQL++ expression to use to create the index.
getter/setter pair
-
expressions
↔ List<
String> -
The list of SQL++ expressions to use to create the index, which must
contain a single expression for a vector index.
getter/setter pairoverride
- hashCode → int
-
The hash code for this object.
no setterinherited
- lazy ↔ bool
-
Whether index is lazy or not.
getter/setter pair
- maxTrainingSize ↔ int?
-
The maximum number of vectors used for training the index.
getter/setter pair
- metric ↔ DistanceMetric
-
The distance metric to use for the index.
getter/setter pair
- minTrainingSize ↔ int?
-
The minimum number of vectors for training the index.
getter/setter pair
- numProbes ↔ int?
-
The number of centroids that will be scanned during a query.
getter/setter pair
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited