Struct NsgIndex 

pub struct NsgIndex { /* private fields */ }

NSG index structure

Implementations

impl NsgIndex

pub fn new(config: NsgConfig) -> Result<Self>

Create a new NSG index with given configuration

pub fn add(&mut self, uri: String, vector: Vector) -> Result<()>

Add a vector to the index (must call build() after adding all vectors)

pub fn build(&mut self) -> Result<()>

Build the NSG structure

This is a two-stage process:

1. Build initial kNN graph
2. Refine to create navigable monotonic graph

pub fn stats(&self) -> NsgStats

Get index statistics

pub fn len(&self) -> usize

Get number of vectors in the index

pub fn is_empty(&self) -> bool

Check if index is empty

pub fn is_built(&self) -> bool

Check if index is built

Trait Implementations

impl VectorIndex for NsgIndex

fn insert(&mut self, uri: String, vector: Vector) -> Result<()>

Insert a vector with associated URI

fn search_knn(&self, query: &Vector, k: usize) -> Result<Vec<(String, f32)>>

Find the k nearest neighbors, returned as (id, similarity) sorted by descending similarity (best match first). See the trait-level score contract: the score is a similarity, not a distance.

fn search_threshold( &self, query: &Vector, threshold: f32, ) -> Result<Vec<(String, f32)>>

Find all vectors whose similarity to query is >= threshold.

fn get_vector(&self, uri: &str) -> Option<&Vector>

Get a vector by its URI

fn remove_vector(&mut self, id: String) -> Result<()>

Remove a vector by its ID

fn add_vector( &mut self, id: VectorId, vector: Vector, _metadata: Option<HashMap<String, String>>, ) -> Result<()>

Add a vector with associated ID and metadata

fn update_vector(&mut self, id: VectorId, vector: Vector) -> Result<()>

Update an existing vector

fn update_metadata( &mut self, _id: VectorId, _metadata: HashMap<String, String>, ) -> Result<()>

Update metadata for a vector

fn iter_vectors(&self) -> Vec<(String, Vector)>

Iterate all stored (id, vector) pairs.

fn supports_enumeration(&self) -> bool

Whether VectorIndex::iter_vectors returns a real, complete enumeration of the vectors held by this index.