EmbeddingVector.QuantizedData

Kotlin |Java

@ExperimentalAppSearchApi
class EmbeddingVector.QuantizedData

Holds the pre-quantized embedding values along with the quantization parameters.

The original float values can be reconstructed from the quantized byte values using the formula: originalValue = (quantizedValue / scale) + minValue.

Summary

Public constructors
`QuantizedData( minValue: Float, scale: Float, quantizedValues: ByteArray<Byte> )` Creates a new `QuantizedData`.

Public functions
`Boolean`	`equals(o: Any?)`
`java-static EmbeddingVector.QuantizedData`	`fromUnquantizedValues(values: FloatArray<Float>)` Creates a new `QuantizedData` by quantizing the provided float values to 8-bit integers.
`Float`	`getMinValue()` Returns the minimum float value across all dimensions before quantization.
`Array<Byte>`	`getQuantizedValues()` Returns the pre-quantized int8 vector data.
`Float`	`getScale()` Returns the scaling factor used to quantize the vector.
`Int`	`hashCode()`

Public constructors

QuantizedData

Added in 1.2.0-alpha02

QuantizedData(
    minValue: Float,
    scale: Float,
    quantizedValues: ByteArray<Byte>
)

Creates a new QuantizedData.

The original float values can be reconstructed from the quantized byte values using the formula: originalValue = (quantizedValue / scale) + minValue.

Parameters
`minValue: Float`	The minimum float value across all dimensions before quantization.
`scale: Float`	The scaling factor used to quantize the vector.
`quantizedValues: ByteArray<Byte>`	The pre-quantized int8 vector data.

Throws
`java.lang.IllegalArgumentException`	if `quantizedValues` is empty.

Public functions

equals

fun equals(o: Any?): Boolean

fromUnquantizedValues

Added in 1.2.0-alpha02

java-static fun fromUnquantizedValues(values: FloatArray<Float>): EmbeddingVector.QuantizedData

Creates a new QuantizedData by quantizing the provided float values to 8-bit integers.

Storing 8-bit quantized values directly helps reduce memory and disk space usage by approximately 75% compared to storing full 32-bit floats.

Parameters
`values: FloatArray<Float>`	The float values to quantize.

Returns
`EmbeddingVector.QuantizedData`	The `QuantizedData` created by quantizing the float values.

Throws
`java.lang.IllegalArgumentException`	if `values` is empty.

getMinValue

Added in 1.2.0-alpha02

fun getMinValue(): Float

Returns the minimum float value across all dimensions before quantization.

getQuantizedValues

Added in 1.2.0-alpha02

fun getQuantizedValues(): Array<Byte>

Returns the pre-quantized int8 vector data.

getScale

Added in 1.2.0-alpha02

fun getScale(): Float

Returns the scaling factor used to quantize the vector.

hashCode

fun hashCode(): Int