Struct HnswVectorIndex 

pub struct HnswVectorIndex { /* private fields */ }

Production-ready vector index backed by HNSW from sochdb-index.

This provides O(log N) search performance vs O(N) for brute-force. Each collection maps to a separate HNSW index.

Implementations

impl HnswVectorIndex

pub fn new() -> Self

Create a new HNSW-backed vector index

pub fn create_collection(&self, name: &str, dimension: usize)

Create a collection with specified dimension and HNSW parameters

pub fn insert( &self, collection: &str, id: String, vector: Vec<f32>, content: String, metadata: HashMap<String, SochValue>, ) -> Result<(), String>

Insert a vector with metadata

pub fn vector_count(&self, collection: &str) -> Option<usize>

Get collection count for a specific collection

Trait Implementations

impl Default for HnswVectorIndex

fn default() -> Self

Returns the “default value” for a type.

impl VectorIndex for HnswVectorIndex

fn search_by_embedding( &self, collection: &str, embedding: &[f32], k: usize, min_score: Option<f32>, ) -> Result<Vec<VectorSearchResult>, String>

Search for k nearest neighbors to the query vector

fn search_by_text( &self, _collection: &str, _text: &str, _k: usize, _min_score: Option<f32>, ) -> Result<Vec<VectorSearchResult>, String>

Search by text (index handles embedding generation)

fn stats(&self, collection: &str) -> Option<VectorIndexStats>

Get index statistics