Class OffHeapQuantizedByteVectorValues.DenseOffHeapVectorValues
java.lang.Object
org.apache.lucene.index.KnnVectorValues
org.apache.lucene.index.ByteVectorValues
org.apache.lucene.util.quantization.QuantizedByteVectorValues
org.apache.lucene.backward_codecs.lucene99.OffHeapQuantizedByteVectorValues
org.apache.lucene.backward_codecs.lucene99.OffHeapQuantizedByteVectorValues.DenseOffHeapVectorValues
- All Implemented Interfaces:
HasIndexSlice
- Enclosing class:
OffHeapQuantizedByteVectorValues
public static class OffHeapQuantizedByteVectorValues.DenseOffHeapVectorValues
extends OffHeapQuantizedByteVectorValues
Dense vector values that are stored off-heap. This is the most common case when every doc has a
vector.
-
Nested Class Summary
Nested classes/interfaces inherited from class org.apache.lucene.backward_codecs.lucene99.OffHeapQuantizedByteVectorValues
OffHeapQuantizedByteVectorValues.DenseOffHeapVectorValuesNested classes/interfaces inherited from class org.apache.lucene.index.KnnVectorValues
KnnVectorValues.DocIndexIterator -
Constructor Summary
ConstructorsConstructorDescriptionDenseOffHeapVectorValues(int dimension, int size, ScalarQuantizer scalarQuantizer, boolean compress, VectorSimilarityFunction similarityFunction, FlatVectorsScorer vectorsScorer, IndexInput slice) Create dense off-heap vector values -
Method Summary
Modifier and TypeMethodDescriptioncopy()getAcceptOrds(Bits acceptDocs) iterator()scorer(float[] target) Methods inherited from class org.apache.lucene.backward_codecs.lucene99.OffHeapQuantizedByteVectorValues
dimension, getScalarQuantizer, getScoreCorrectionConstant, getSlice, getVectorByteLength, size, vectorValueMethods inherited from class org.apache.lucene.index.ByteVectorValues
checkField, fromBytes, getEncoding, rescorer, scorerMethods inherited from class org.apache.lucene.index.KnnVectorValues
createDenseIterator, createSparseIterator, fromDISI, ordToDoc
-
Constructor Details
-
DenseOffHeapVectorValues
public DenseOffHeapVectorValues(int dimension, int size, ScalarQuantizer scalarQuantizer, boolean compress, VectorSimilarityFunction similarityFunction, FlatVectorsScorer vectorsScorer, IndexInput slice) Create dense off-heap vector values- Parameters:
dimension- vector dimensionsize- number of vectorsscalarQuantizer- the scalar quantizercompress- whether the vectors are compressedsimilarityFunction- the similarity functionvectorsScorer- the vectors scorerslice- the index input slice containing the vector data
-
-
Method Details
-
copy
- Overrides:
copyin classQuantizedByteVectorValues- Throws:
IOException
-
getAcceptOrds
- Overrides:
getAcceptOrdsin classKnnVectorValues
-
scorer
- Overrides:
scorerin classQuantizedByteVectorValues- Throws:
IOException
-
iterator
- Overrides:
iteratorin classKnnVectorValues
-