Struct IndexConfig 

pub struct IndexConfig {
    pub nbits: usize,
    pub batch_size: usize,
    pub seed: Option<u64>,
    pub kmeans_niters: usize,
    pub max_points_per_centroid: usize,
    pub n_samples_kmeans: Option<usize>,
    pub start_from_scratch: usize,
}

Configuration for index creation

Fields

nbits: usize

Number of bits for quantization (typically 2 or 4)

batch_size: usize

Batch size for processing

seed: Option<u64>

Random seed for reproducibility

kmeans_niters: usize

Number of K-means iterations (default: 4)

max_points_per_centroid: usize

Maximum number of points per centroid for K-means (default: 256)

n_samples_kmeans: Option<usize>

Number of samples for K-means training. If None, uses heuristic: min(1 + 16 * sqrt(120 * num_documents), num_documents)

start_from_scratch: usize

Threshold for start-from-scratch mode (default: 999). When the number of documents is <= this threshold, raw embeddings are saved to embeddings.npy for potential rebuilds during updates.

Trait Implementations

impl Clone for IndexConfig

fn clone(&self) -> IndexConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for IndexConfig

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

Formats the value using the given formatter.

impl Default for IndexConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for IndexConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for IndexConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.