Enum Quantization 

pub enum Quantization {
    F32,
    F16,
    BF16,
    I8,
}

Scalar quantization for index storage.

Lower precision reduces memory usage but may affect recall:

• F32: Full precision (4 bytes per dimension)
• F16: Half precision (2 bytes per dimension, ~1% recall loss)
• BF16: Brain float (2 bytes, better for ML models)
• I8: 8-bit quantization (1 byte, ~3-5% recall loss)

Variants

F32

32-bit float (full precision, largest index size).

F16

16-bit float (half precision, good balance).

BF16

Brain float 16 (better for ML model outputs).

I8

8-bit integer (smallest index, some recall loss).

Implementations

impl Quantization

pub fn bytes_per_element(self) -> usize

Get bytes per scalar element.

Trait Implementations

impl Clone for Quantization

fn clone(&self) -> Quantization

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Quantization

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Quantization

fn default() -> Quantization

Returns the “default value” for a type.

impl PartialEq for Quantization

fn eq(&self, other: &Quantization) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for Quantization

impl Eq for Quantization

impl StructuralPartialEq for Quantization