Skip to main content

VectorDbRead

vector::db

Trait VectorDbRead 

Source 
pub trait VectorDbRead {
    // Required methods
    fn search<'life0, 'life1, 'async_trait>(
        &'life0 self,
        query: &'life1 Query,
    ) -> Pin<Box<dyn Future<Output = Result<Vec<SearchResult>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait;
    fn search_with_nprobe<'life0, 'life1, 'async_trait>(
        &'life0 self,
        query: &'life1 Query,
        nprobe: usize,
    ) -> Pin<Box<dyn Future<Output = Result<Vec<SearchResult>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait;
    fn get<'life0, 'life1, 'async_trait>(
        &'life0 self,
        id: &'life1 str,
    ) -> Pin<Box<dyn Future<Output = Result<Option<Vector>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait;
}
Expand description

Trait for querying the vector db

Required Methods§

Source

fn search<'life0, 'life1, 'async_trait>( &'life0 self, query: &'life1 Query, ) -> Pin<Box<dyn Future<Output = Result<Vec<SearchResult>>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Search for k-nearest neighbors to a query vector.

This implements the SPANN-style query algorithm:

  1. Search HNSW for nearest centroids
  2. Load posting lists for those centroids
  3. Filter deleted vectors
  4. Score candidates and return top-k
§Arguments
  • query - search query
§Returns

Vector of SearchResults sorted by similarity (best first)

§Errors

Returns an error if:

  • Query dimensions don’t match collection dimensions
  • Storage read fails
Source

fn search_with_nprobe<'life0, 'life1, 'async_trait>( &'life0 self, query: &'life1 Query, nprobe: usize, ) -> Pin<Box<dyn Future<Output = Result<Vec<SearchResult>>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Source

fn get<'life0, 'life1, 'async_trait>( &'life0 self, id: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<Option<Vector>>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Retrieve a vector record by its external ID.

This is a point lookup operation that retrieves a single record with all its fields. Returns None if the record doesn’t exist or has been deleted.

§Arguments
  • id - External ID of the record to retrieve
§Returns

Some(VectorRecord) if found, None if not found or deleted.

Implementors§