Struct DenseVectorConfig 

pub struct DenseVectorConfig {
    pub dim: usize,
    pub index_type: VectorIndexType,
    pub quantization: DenseVectorQuantization,
    pub num_clusters: Option<usize>,
    pub nprobe: usize,
    pub build_threshold: Option<usize>,
    pub unit_norm: bool,
}

Configuration for dense vector fields using Flat, RaBitQ, IVF-RaBitQ, or ScaNN

Indexes operate in two states:

• Flat (accumulating): Brute-force search over raw vectors. Used when vector count is below build_threshold or before build_index is called.
• Built (ANN): Fast approximate nearest neighbor search using trained structures. Centroids and codebooks are trained from data and stored within the segment.

Fields

dim: usize

Dimensionality of vectors

index_type: VectorIndexType

Target vector index algorithm (Flat, RaBitQ, IVF-RaBitQ, or ScaNN) When in accumulating state, search uses brute-force regardless of this setting.

quantization: DenseVectorQuantization

Storage quantization for vector elements (f32, f16, uint8)

num_clusters: Option<usize>

Number of IVF clusters for IVF-RaBitQ and ScaNN (default: sqrt(n) capped at 4096) If None, automatically determined based on dataset size.

nprobe: usize

Number of clusters to probe during search (default: 32)

build_threshold: Option<usize>

Minimum number of vectors required before building ANN index. Below this threshold, brute-force (Flat) search is used. Default: 1000 for RaBitQ, 10000 for IVF-RaBitQ/ScaNN.

unit_norm: bool

Whether stored vectors are pre-normalized to unit L2 norm. When true, scoring skips per-vector norm computation (cosine = dot / ||q||), reducing compute by ~40%. Common for embedding models (e.g. OpenAI, Cohere). Default: true (most embedding models produce L2-normalized vectors).

Implementations

impl DenseVectorConfig

pub fn new(dim: usize) -> Self

pub fn with_ivf(dim: usize, num_clusters: Option<usize>, nprobe: usize) -> Self

Create IVF-RaBitQ configuration

pub fn with_scann( dim: usize, num_clusters: Option<usize>, nprobe: usize, ) -> Self

Create ScaNN configuration

pub fn flat(dim: usize) -> Self

Create Flat (brute-force) configuration - no ANN index

pub fn with_quantization(self, quantization: DenseVectorQuantization) -> Self

Set storage quantization

pub fn with_build_threshold(self, threshold: usize) -> Self

Set build threshold for auto-building ANN index

pub fn with_unit_norm(self) -> Self

Mark vectors as pre-normalized to unit L2 norm

pub fn with_num_clusters(self, num_clusters: usize) -> Self

Set number of IVF clusters

pub fn uses_ivf(&self) -> bool

Check if this config uses IVF

pub fn uses_scann(&self) -> bool

Check if this config uses ScaNN

pub fn is_flat(&self) -> bool

Check if this config is flat (brute-force)

pub fn default_build_threshold(&self) -> usize

Get the default build threshold for this index type

pub fn optimal_num_clusters(&self, num_vectors: usize) -> usize

Calculate optimal number of clusters for given vector count

Trait Implementations

impl Clone for DenseVectorConfig

fn clone(&self) -> DenseVectorConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DenseVectorConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DenseVectorConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for DenseVectorConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.