Struct cuvsCagraCompressionParams 

#[repr(C)]
pub struct cuvsCagraCompressionParams {
    pub pq_bits: u32,
    pub pq_dim: u32,
    pub vq_n_centers: u32,
    pub kmeans_n_iters: u32,
    pub vq_kmeans_trainset_fraction: f64,
    pub pq_kmeans_trainset_fraction: f64,
}

Parameters for VPQ compression.

Fields

pq_bits: u32

The bit length of the vector element after compression by PQ.

Possible values: [4, 5, 6, 7, 8].

Hint: the smaller the ‘pq_bits’, the smaller the index size and the better the search performance, but the lower the recall.

pq_dim: u32

The dimensionality of the vector after compression by PQ. When zero, an optimal value is selected using a heuristic.

TODO: at the moment dim must be a multiple pq_dim.

vq_n_centers: u32

Vector Quantization (VQ) codebook size - number of “coarse cluster centers”. When zero, an optimal value is selected using a heuristic.

kmeans_n_iters: u32

The number of iterations searching for kmeans centers (both VQ & PQ phases).

vq_kmeans_trainset_fraction: f64

The fraction of data to use during iterative kmeans building (VQ phase). When zero, an optimal value is selected using a heuristic.

pq_kmeans_trainset_fraction: f64

The fraction of data to use during iterative kmeans building (PQ phase). When zero, an optimal value is selected using a heuristic.

Trait Implementations

impl Clone for cuvsCagraCompressionParams

fn clone(&self) -> cuvsCagraCompressionParams

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for cuvsCagraCompressionParams

impl Debug for cuvsCagraCompressionParams

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

Formats the value using the given formatter.