Class CreateVectorSearchIndexModel<TDocument>
Defines a vector index model for pre-embedded vector indexes using strongly-typed C# APIs.
public sealed class CreateVectorSearchIndexModel<TDocument> : CreateVectorSearchIndexModelBase<TDocument>Type Parameters
TDocument
- Inheritance
-
CreateVectorSearchIndexModelBase<TDocument>CreateVectorSearchIndexModel<TDocument>
- Inherited Members
Constructors
- CreateVectorSearchIndexModel(FieldDefinition<TDocument>, string, VectorSimilarity, int, params FieldDefinition<TDocument>[])
Initializes a new instance of the CreateVectorSearchIndexModel<TDocument> class for a vector index where the vector embeddings are created manually. The required options for VectorSimilarity and the number of vector dimensions are passed to the constructor.
- CreateVectorSearchIndexModel(Expression<Func<TDocument, object>>, string, VectorSimilarity, int, params Expression<Func<TDocument, object>>[])
Initializes a new instance of the CreateVectorSearchIndexModel<TDocument> class for a vector index where the vector embeddings are created manually. The required options for VectorSimilarity and the number of vector dimensions are passed to the constructor.
Properties
- Dimensions
Number of vector dimensions that vector search enforces at index-time and query-time.
- HnswMaxEdges
Maximum number of edges (or connections) that a node can have in the Hierarchical Navigable Small Worlds graph.
- HnswNumEdgeCandidates
Analogous to numCandidates at query-time, this parameter controls the maximum number of nodes to evaluate to find the closest neighbors to connect to a new node.
- Quantization
Type of automatic vector quantization for your vectors.
- Similarity
The VectorSimilarity to use to search for top K-nearest neighbors.