io.lettuce.core.search.arguments.hybrid

Class HybridVectorArgs.Knn

java.lang.Object

io.lettuce.core.search.arguments.hybrid.HybridVectorArgs.Knn

All Implemented Interfaces:

HybridVectorArgs.VectorSearchMethod

Enclosing class:

HybridVectorArgs<K,V>

public static class HybridVectorArgs.Knn
extends Object
implements HybridVectorArgs.VectorSearchMethod

KNN (K-Nearest Neighbors) search method implementation.

Finds the K most similar vectors to the query vector. This is the default and most common vector search method.

Method Summary

Modifier and Type	Method and Description
<K,V> void	build(CommandArgs<K,V> args) Build the method arguments into the command.
HybridVectorArgs.Knn	efRuntime(int efRuntime) Set the EF_RUNTIME parameter for HNSW search.
static HybridVectorArgs.Knn	of(int k) Static factory method to create a KNN search method.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

of

public static HybridVectorArgs.Knn of(int k)

Static factory method to create a KNN search method.

Parameters:

k - number of nearest neighbors to return

Returns:

new KNN search method

efRuntime

public HybridVectorArgs.Knn efRuntime(int efRuntime)

Set the EF_RUNTIME parameter for HNSW search.

The EF_RUNTIME parameter controls the size of the dynamic candidate list during HNSW search. Higher values improve recall but increase search time.

Parameters:

efRuntime - size of the dynamic candidate list for HNSW algorithm

Returns:

this KNN search method

build

public <K,V> void build(CommandArgs<K,V> args)

Description copied from interface: HybridVectorArgs.VectorSearchMethod

Build the method arguments into the command.

Specified by:

build in interface HybridVectorArgs.VectorSearchMethod

Type Parameters:

K - key type

V - value type

Parameters:

args - command arguments