Struct ProductQuantizerOptions 

pub struct ProductQuantizerOptions {
    pub training_samples: usize,
    pub seed: u64,
    pub rerank_factor: usize,
}

Product-quantizer training parameters. Used only when AnnQuantization::Product is selected; the representation (subvector count, bits) is declared on the variant.

Fields

training_samples: usize

Cap on training samples drawn from the pinned read generation. Default 256_000. Training cost is bounded by this value.

seed: u64

Deterministic training seed. Same seed + same training data yields byte-identical codebooks (checkpoint reproducibility).

rerank_factor: usize

Rerank factor: the top k * rerank_factor ADC candidates are reranked using reconstructed approximate vectors (centroid concatenation) for improved ranking quality. 0 disables rerank (ADC only). Default 5. This is not a true exact rerank — see pq_backend.rs docs.

Trait Implementations

impl Clone for ProductQuantizerOptions

fn clone(&self) -> ProductQuantizerOptions

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ProductQuantizerOptions

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

Formats the value using the given formatter.

impl Default for ProductQuantizerOptions

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ProductQuantizerOptions

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for ProductQuantizerOptions

impl PartialEq for ProductQuantizerOptions

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for ProductQuantizerOptions

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ProductQuantizerOptions