Package org.apache.lucene.util.hnsw

Class HnswGraphBuilder

java.lang.Object

org.apache.lucene.util.hnsw.HnswGraphBuilder

public final class HnswGraphBuilder
extends Object

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

Field Summary

Fields

Modifier and Type	Field	Description
static final String	HNSW_COMPONENT	A name for the HNSW component for the info-stream *
static long	randSeed	Random seed for level generation; public to expose for testing *

Constructor Summary

Constructors

Constructor	Description
HnswGraphBuilder(RandomAccessVectorValuesProducer vectors, VectorSimilarityFunction similarityFunction, int maxConn, int beamWidth, long seed)	Reads all the vectors from a VectorValues, 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
OnHeapHnswGraph	build(RandomAccessVectorValues vectors)	Reads all the vectors from two copies of a random access VectorValues.
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

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 *

Constructor Details

HnswGraphBuilder

public HnswGraphBuilder(RandomAccessVectorValuesProducer vectors,
 VectorSimilarityFunction similarityFunction,
 int maxConn,
 int beamWidth,
 long seed)

Reads all the vectors from a VectorValues, 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.

Method Details

build

public OnHeapHnswGraph build(RandomAccessVectorValues vectors)
                      throws IOException

Reads all the vectors from two copies of a random access VectorValues. 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 *