Struct EmbeddingRetriever 

pub struct EmbeddingRetriever<E, V> { /* private fields */ }

Adapter that combines an Embedder and a VectorStore (scoped to one Namespace) into a Retriever.

Cloning is cheap — both the embedder and the store sit behind Arc, so multiple retrievers can share one connection pool / embedding client.

Implementations

impl<E, V> EmbeddingRetriever<E, V>

where E: Embedder, V: VectorStore,

pub const fn new(embedder: Arc<E>, store: Arc<V>, namespace: Namespace) -> Self

Build a retriever that runs every query against store scoped to namespace, using embedder to turn query text into the search vector.

pub const fn embedder(&self) -> &Arc<E>

Borrow the wired embedder.

pub const fn store(&self) -> &Arc<V>

Borrow the wired vector store.

pub const fn namespace(&self) -> &Namespace

Borrow the configured namespace.

Trait Implementations

impl<E, V> Clone for EmbeddingRetriever<E, V>

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<E, V> Debug for EmbeddingRetriever<E, V>

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

Formats the value using the given formatter.

impl<E, V> Retriever for EmbeddingRetriever<E, V>

where E: Embedder + 'static, V: VectorStore + 'static,

fn retrieve<'life0, 'life1, 'async_trait>( &'life0 self, query: RetrievalQuery, ctx: &'life1 ExecutionContext, ) -> Pin<Box<dyn Future<Output = Result<Vec<Document>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Look up matches for query.