Package org.apache.lucene.util.hnsw

Class HnswGraphBuilder

java.lang.Object
org.apache.lucene.util.hnsw.HnswGraphBuilder
All Implemented Interfaces:
HnswBuilder
Direct Known Subclasses:
InitializedHnswGraphBuilder, MergingHnswGraphBuilder
public class HnswGraphBuilder extends Object implements HnswBuilder
Builder for HNSW graph. See HnswGraph for a gloss on the algorithm and the meaning of the hyper-parameters.

  • Field Details

    • DEFAULT_MAX_CONN

      public static final int DEFAULT_MAX_CONN
      Default number of maximum connections per node
      See Also:

    • DEFAULT_BEAM_WIDTH

      public static final int DEFAULT_BEAM_WIDTH
      Default number of the size of the queue maintained while searching during a graph construction.
      See Also:

    • HNSW_COMPONENT

      public static final String HNSW_COMPONENT
      A name for the HNSW component for the info-stream *
      See Also:

    • randSeed

      public static long randSeed
      Random seed for level generation; public to expose for testing *

    • scorerSupplier

      protected final RandomVectorScorerSupplier scorerSupplier

    • hnsw

      protected final OnHeapHnswGraph hnsw

    • hnswLock

      protected final org.apache.lucene.util.hnsw.HnswLock hnswLock

    • infoStream

      protected InfoStream infoStream

    • frozen

      protected boolean frozen

  • Constructor Details

    • HnswGraphBuilder

      protected HnswGraphBuilder(RandomVectorScorerSupplier scorerSupplier, int M, int beamWidth, long seed, int graphSize) 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:
      scorerSupplier - a supplier to create vector scorer from ordinals.
      M - – graph fanout parameter used to calculate the maximum number of connections a node can have – M on upper layers, and M * 2 on the lowest level.
      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.
      graphSize - size of graph, if unknown, pass in -1
      Throws:
      IOException

    • HnswGraphBuilder

      protected HnswGraphBuilder(RandomVectorScorerSupplier scorerSupplier, int M, int beamWidth, long seed, OnHeapHnswGraph hnsw) throws IOException
      Throws:
      IOException

    • HnswGraphBuilder

      protected HnswGraphBuilder(RandomVectorScorerSupplier scorerSupplier, int M, int beamWidth, long seed, OnHeapHnswGraph hnsw, org.apache.lucene.util.hnsw.HnswLock hnswLock, HnswGraphSearcher graphSearcher) 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:
      scorerSupplier - a supplier to create vector scorer from ordinals.
      M - – graph fanout parameter used to calculate the maximum number of connections a node can have – M on upper layers, and M * 2 on the lowest level.
      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.
      hnsw - the graph to build, can be previously initialized
      Throws:
      IOException

  • Method Details