Package io.github.jbellis.jvector.graph

Class GraphIndexBuilder<T>

java.lang.Object

io.github.jbellis.jvector.graph.GraphIndexBuilder<T>

Type Parameters:

T - the type of vector

public class GraphIndexBuilder<T>
extends Object

Builder for Concurrent GraphIndex. See GraphIndex for a high level overview, and the comments to `addGraphNode` for details on the concurrent building approach.

Constructor Summary

Constructors

Constructor	Description
GraphIndexBuilder(RandomAccessVectorValues<T> vectorValues, VectorEncoding vectorEncoding, VectorSimilarityFunction similarityFunction, int M, int beamWidth, float neighborOverflow, float alpha)	Reads all the vectors from vector values, builds a graph connecting them by their dense ordinals, using the given hyperparameter settings, and returns the resulting graph.

Method Summary

Modifier and Type	Method	Description
long	addGraphNode(int node, RandomAccessVectorValues<T> vectors)	Inserts a node with the given vector value to the graph.
OnHeapGraphIndex<T>	build()
void	complete()
OnHeapGraphIndex<T>	getGraph()
int	insertsInProgress()	Number of inserts in progress, across all threads.
protected float	scoreBetween(T v1, T v2)

Methods inherited from class java.lang.Object

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

Constructor Details

GraphIndexBuilder

public GraphIndexBuilder(RandomAccessVectorValues<T> vectorValues,
 VectorEncoding vectorEncoding,
 VectorSimilarityFunction similarityFunction,
 int M,
 int beamWidth,
 float neighborOverflow,
 float alpha)

Reads all the vectors from vector values, builds a graph connecting them by their dense ordinals, using the given hyperparameter settings, and returns the resulting graph.

Parameters:

vectorValues - the vectors whose relations are represented by the graph - must provide a different view over those vectors than the one used to add via addGraphNode.

M - – the maximum number of connections a node can have

beamWidth - the size of the beam search to use when finding nearest neighbors.

neighborOverflow - the ratio of extra neighbors to allow temporarily when inserting a node. larger values will build more efficiently, but use more memory.

alpha - how aggressive pruning diverse neighbors should be. Set alpha > 1.0 to allow longer edges. If alpha = 1.0 then the equivalent of the lowest level of an HNSW graph will be created, which is usually not what you want.

Method Details

build

public OnHeapGraphIndex<T> build()

complete

public void complete()

getGraph

public OnHeapGraphIndex<T> getGraph()

insertsInProgress

public int insertsInProgress()

Number of inserts in progress, across all threads.

addGraphNode

public long addGraphNode(int node,
 RandomAccessVectorValues<T> vectors)

Inserts a node with the given vector value to the graph.

To allow correctness under concurrency, we track in-progress updates in a ConcurrentSkipListSet. After adding ourselves, we take a snapshot of this set, and consider all other in-progress updates as neighbor candidates.

Parameters:

node - the node ID to add

vectors - the set of vectors

Returns:

an estimate of the number of extra bytes used by the graph after adding the given node

scoreBetween

protected float scoreBetween(T v1,
 T v2)