Skip to main content

meta_embed_search

nodedb_vector::multivec::meta_embed

Function meta_embed_search 

Source 
pub fn meta_embed_search(
    store: &MultiVectorStore,
    plaid: Option<&PlaidPruner>,
    query: &[Vec<f32>],
    budget: u8,
    k: usize,
    metric: DistanceMetric,
) -> Vec<(u32, f32)>
Expand description

Search a MultiVectorStore using budgeted MaxSim with optional PLAID candidate pruning.

§Parameters

  • store — the document collection.
  • plaid — optional PLAID pruner (pass None to scan all docs).
  • query — query Meta Token vectors (Matryoshka ordering).
  • budget — number of leading query tokens to use; 0 falls back to all.
  • k — number of top documents to return.
  • metric — distance metric (Cosine recommended for MetaEmbed).

§Returns

A Vec<(doc_id, score)> sorted descending by score, length ≤ k.