Module org.apache.lucene.backward_codecs

Package org.apache.lucene.backward_codecs.lucene90

Class Lucene90HnswGraphBuilder

java.lang.Object

org.apache.lucene.backward_codecs.lucene90.Lucene90HnswGraphBuilder

public final class Lucene90HnswGraphBuilder
extends Object

Builder for HNSW graph. See Lucene90OnHeapHnswGraph for a gloss on the algorithm and the meaning of the hyperparameters.

This class is preserved here only for tests.

Field Summary

Fields

Modifier and Type	Field	Description
private final int	beamWidth
private final Lucene90BoundsChecker	bound
private final RandomAccessVectorValues.Floats	buildVectors
private static final long	DEFAULT_RAND_SEED	Default random seed for level generation *
(package private) final Lucene90OnHeapHnswGraph	hnsw
static final String	HNSW_COMPONENT	A name for the HNSW component for the info-stream *
private InfoStream	infoStream
private final int	maxConn
private final SplittableRandom	random
static long	randSeed	Random seed for level generation; public to expose for testing *
private final Lucene90NeighborArray	scratch
private final VectorSimilarityFunction	similarityFunction
private final RandomAccessVectorValues.Floats	vectorValues

Constructor Summary

Constructors

Constructor	Description
Lucene90HnswGraphBuilder(RandomAccessVectorValues.Floats vectors, VectorSimilarityFunction similarityFunction, int maxConn, int beamWidth, long seed)	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
private void	addDiverseNeighbors(int node, NeighborQueue candidates)
(package private) void	addGraphNode(float[] value)	Inserts a doc with vector value to the graph
Lucene90OnHeapHnswGraph	build(RandomAccessVectorValues.Floats vectors)	Reads all the vectors from two copies of a RandomAccessVectorValues.
private boolean	diversityCheck(float[] candidate, float score, Lucene90NeighborArray neighbors, RandomAccessVectorValues.Floats vectorValues)
private void	diversityUpdate(Lucene90NeighborArray neighbors)
private int	findNonDiverse(Lucene90NeighborArray neighbors)
private void	popToScratch(NeighborQueue candidates)
private void	selectDiverse(Lucene90NeighborArray neighbors, Lucene90NeighborArray candidates)
void	setInfoStream(InfoStream infoStream)	Set info-stream to output debugging information *

Methods inherited from class java.lang.Object

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

Field Details

DEFAULT_RAND_SEED

private static final long DEFAULT_RAND_SEED

Default random seed for level generation *

See Also:

• Constant Field Values

HNSW_COMPONENT

public static final String HNSW_COMPONENT

A name for the HNSW component for the info-stream *

See Also:

• Constant Field Values

randSeed

public static long randSeed

Random seed for level generation; public to expose for testing *

maxConn

private final int maxConn

beamWidth

private final int beamWidth

scratch

private final Lucene90NeighborArray scratch

similarityFunction

private final VectorSimilarityFunction similarityFunction

vectorValues

private final RandomAccessVectorValues.Floats vectorValues

random

private final SplittableRandom random

bound

private final Lucene90BoundsChecker bound

hnsw

final Lucene90OnHeapHnswGraph hnsw

infoStream

private InfoStream infoStream

buildVectors

private final RandomAccessVectorValues.Floats buildVectors

Constructor Details

Lucene90HnswGraphBuilder

public Lucene90HnswGraphBuilder(RandomAccessVectorValues.Floats vectors,
 VectorSimilarityFunction similarityFunction,
 int maxConn,
 int beamWidth,
 long seed)
                         throws IOException

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:

vectors - 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.

maxConn - the number of connections to make when adding a new graph node; roughly speaking the graph fanout.

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

seed - the seed for a random number generator used during graph construction. Provide this to ensure repeatable construction.

Throws:

IOException

Method Details

build

public Lucene90OnHeapHnswGraph build(RandomAccessVectorValues.Floats vectors)
                              throws IOException

Reads all the vectors from two copies of a RandomAccessVectorValues. Providing two copies enables efficient retrieval without extra data copying, while avoiding collision of the returned values.

Parameters:

vectors - the vectors for which to build a nearest neighbors graph. Must be an independet accessor for the vectors

Throws:

IOException

setInfoStream

public void setInfoStream(InfoStream infoStream)

Set info-stream to output debugging information *

addGraphNode

void addGraphNode(float[] value)
           throws IOException

Inserts a doc with vector value to the graph

Throws:

IOException

addDiverseNeighbors

private void addDiverseNeighbors(int node,
 NeighborQueue candidates)
                          throws IOException

Throws:

IOException

selectDiverse

private void selectDiverse(Lucene90NeighborArray neighbors,
 Lucene90NeighborArray candidates)
                    throws IOException

Throws:

IOException

popToScratch

private void popToScratch(NeighborQueue candidates)

diversityCheck

private boolean diversityCheck(float[] candidate,
 float score,
 Lucene90NeighborArray neighbors,
 RandomAccessVectorValues.Floats vectorValues)
                        throws IOException

Parameters:

candidate - the vector of a new candidate neighbor of a node n

score - the score of the new candidate and node n, to be compared with scores of the candidate and n's neighbors

neighbors - the neighbors selected so far

vectorValues - source of values used for making comparisons between candidate and existing neighbors

Returns:

whether the candidate is diverse given the existing neighbors

Throws:

IOException

diversityUpdate

private void diversityUpdate(Lucene90NeighborArray neighbors)
                      throws IOException

Throws:

IOException

findNonDiverse

private int findNonDiverse(Lucene90NeighborArray neighbors)
                    throws IOException

Throws:

IOException