Package io.objectbox.model

Class HnswParams

  • public final class HnswParams
extends Table
    Parameters to configure HNSW-based approximate nearest neighbor (ANN) search. Some of the parameters can influence index construction and searching. Changing these values causes re-indexing, which can take a while due to the complex nature of HNSW.

    • Constructor Detail

      • HnswParams

        public HnswParams()

    • Method Detail

      • ValidateVersion

        public static void ValidateVersion()

      • getRootAsHnswParams

        public static HnswParams getRootAsHnswParams​(java.nio.ByteBuffer _bb)

      • getRootAsHnswParams

        public static HnswParams getRootAsHnswParams​(java.nio.ByteBuffer _bb,
                                             HnswParams obj)

      • __init

        public void __init​(int _i,
                   java.nio.ByteBuffer _bb)

      • __assign

        public HnswParams __assign​(int _i,
                           java.nio.ByteBuffer _bb)

      • dimensions

        public long dimensions()
        Dimensions of vectors; vector data with less dimensions are ignored. Vectors with more dimensions than specified here are only evaluated up to the given dimension value. Changing this value causes re-indexing.

      • neighborsPerNode

        public long neighborsPerNode()
        Aka "M": the max number of connections per node (default: 30). Higher numbers increase the graph connectivity, which can lead to more accurate search results. However, higher numbers also increase the indexing time and resource usage. Try e.g. 16 for faster but less accurate results, or 64 for more accurate results. Changing this value causes re-indexing.

      • indexingSearchCount

        public long indexingSearchCount()
        Aka "efConstruction": the number of neighbor searched for while indexing (default: 100). The higher the value, the more accurate the search, but the longer the indexing. If indexing time is not a major concern, a value of at least 200 is recommended to improve search quality. Changing this value causes re-indexing.

      • flags

        public long flags()

      • distanceType

        public int distanceType()
        The distance type used for the HNSW index; if none is given, the default Euclidean is used. Changing this value causes re-indexing.

      • reparationBacklinkProbability

        public float reparationBacklinkProbability()
        When repairing the graph after a node was removed, this gives the probability of adding backlinks to the repaired neighbors. The default is 1.0 (aka "always") as this should be worth a bit of extra costs as it improves the graph's quality.

      • vectorCacheHintSizeKb

        public long vectorCacheHintSizeKb()
        A non-binding hint at the maximum size of the vector cache in KB (default: 2097152 or 2 GB/GiB). The actual size max cache size may be altered according to device and/or runtime settings. The vector cache is used to store vectors in memory to speed up search and indexing. Note 1: cache chunks are allocated only on demand, when they are actually used. Thus, smaller datasets will use less memory. Note 2: the cache is for one specific HNSW index; e.g. each index has its own cache. Note 3: the memory consumption can temporarily exceed the cache size, e.g. for large changes, it can double due to multi-version transactions.

      • createHnswParams

        public static int createHnswParams​(FlatBufferBuilder builder,
                                   long dimensions,
                                   long neighborsPerNode,
                                   long indexingSearchCount,
                                   long flags,
                                   int distanceType,
                                   float reparationBacklinkProbability,
                                   long vectorCacheHintSizeKb)

      • startHnswParams

        public static void startHnswParams​(FlatBufferBuilder builder)

      • addDimensions

        public static void addDimensions​(FlatBufferBuilder builder,
                                 long dimensions)

      • addNeighborsPerNode

        public static void addNeighborsPerNode​(FlatBufferBuilder builder,
                                       long neighborsPerNode)

      • addIndexingSearchCount

        public static void addIndexingSearchCount​(FlatBufferBuilder builder,
                                          long indexingSearchCount)

      • addDistanceType

        public static void addDistanceType​(FlatBufferBuilder builder,
                                   int distanceType)

      • addReparationBacklinkProbability

        public static void addReparationBacklinkProbability​(FlatBufferBuilder builder,
                                                    float reparationBacklinkProbability)

      • addVectorCacheHintSizeKb

        public static void addVectorCacheHintSizeKb​(FlatBufferBuilder builder,
                                            long vectorCacheHintSizeKb)