core/org.gnit.lucenekmp.index/VectorEncoding/BYTE

BYTE

BYTE

Encodes vector using 8 bits of precision per sample. Values provided with higher precision (eg: queries provided as float) must be in the range -128, 127. NOTE: this can enable significant storage savings and faster searches, at the cost of some possible loss of precision.

Properties

Link copied to clipboard
val byteSize: Int

The number of bytes required to encode a scalar in this format. A vector will nominally require dimension * byteSize bytes of storage.

Link copied to clipboard
expect val name: String
Link copied to clipboard
expect val ordinal: Int
Generated by Dokka
© 2026 Copyright