Class Lucene92HnswVectorsFormat

  • All Implemented Interfaces:
    NamedSPILoader.NamedSPI

    public class Lucene92HnswVectorsFormat
    extends KnnVectorsFormat
    Lucene 9.2 vector format, which encodes numeric vector values and an optional associated graph connecting the documents having values. The graph is used to power HNSW search. The format consists of three files:

    .vec (vector data) file

    For each field:

    .vex (vector index)

    Stores graphs connecting the documents for each field organized as a list of nodes' neighbours as following:

    • For each level:
      • For each node:
        • [int32] the number of neighbor nodes
        • array[int32] the neighbor ordinals
        • array[int32] padding if the number of the node's neighbors is less than the maximum number of connections allowed on this level. Padding is equal to ((maxConnOnLevel – the number of neighbours) * 4) bytes.

    .vem (vector metadata) file

    For each field:

    • [int32] field number
    • [int32] vector similarity function ordinal
    • [vlong] offset to this field's vectors in the .vec file
    • [vlong] length of this field's vectors, in bytes
    • [vlong] offset to this field's index in the .vex file
    • [vlong] length of this field's index data, in bytes
    • [int] dimension of this field's vectors
    • [int] the number of documents having values for this field
    • [int8] if equals to -1, dense – all documents have values for a field. If equals to 0, sparse – some documents missing values.
    • DocIds were encoded by IndexedDISI.writeBitSet(DocIdSetIterator, IndexOutput, byte)
    • OrdToDoc was encoded by DirectMonotonicWriter, note that only in sparse case
    • [int] the maximum number of connections (neigbours) that each node can have
    • [int] number of levels in the graph
    • Graph nodes by level. For each level
      • [int] the number of nodes on this level
      • array[int] for levels greater than 0 list of nodes on this level, stored as the the level 0th nodes ordinals.
    • Field Detail

      • DEFAULT_MAX_CONN

        public static final int DEFAULT_MAX_CONN
        Default number of maximum connections per node
        See Also:
        Constant Field Values
      • 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:
        Constant Field Values
      • VECTOR_DATA_CODEC_NAME

        static final java.lang.String VECTOR_DATA_CODEC_NAME
        See Also:
        Constant Field Values
      • VECTOR_INDEX_CODEC_NAME

        static final java.lang.String VECTOR_INDEX_CODEC_NAME
        See Also:
        Constant Field Values
      • VECTOR_DATA_EXTENSION

        static final java.lang.String VECTOR_DATA_EXTENSION
        See Also:
        Constant Field Values
      • VECTOR_INDEX_EXTENSION

        static final java.lang.String VECTOR_INDEX_EXTENSION
        See Also:
        Constant Field Values
      • maxConn

        final int maxConn
        Controls how many of the nearest neighbor candidates are connected to the new node. Defaults to maxConn. See HnswGraph for more details.
      • beamWidth

        final int beamWidth
        The number of candidate neighbors to track while searching the graph for each newly inserted node. Defaults to to DEFAULT_BEAM_WIDTH. See HnswGraph for details.
    • Constructor Detail

      • Lucene92HnswVectorsFormat

        public Lucene92HnswVectorsFormat()
        A constructor for vectors format with default parameters
      • Lucene92HnswVectorsFormat

        public Lucene92HnswVectorsFormat​(int maxConn,
                                         int beamWidth)
        Constructs a format for reading old indexes