Struct VectorMemory 

pub struct VectorMemory<E> { /* private fields */ }

A semantic Memory backend: embeds payloads on remember and ranks recall by cosine similarity to query.semantic. The index is in-memory. A durable vector store is a future drop-in behind the same trait.

Implementations

impl<E> VectorMemory<E>

pub fn new(embedder: E) -> Self

An in-memory semantic memory using embedder.

pub fn governed(laser: Laser, embedder: E) -> Self

An in-memory semantic memory whose writes run through the governor enrolled on laser. Directly constructed vector memories remain standalone. Laser::memory_with(.., MemoryBackend::Vector) uses this governed form.

Trait Implementations

impl<E: Embedder + Sync> Memory for VectorMemory<E>

async fn remember( &self, scope: &MemoryScope, payload: Vec<u8>, ) -> Result<MemoryId, LaserError>

Append payload to the memory under scope. The body is opaque bytes, so encode it with whatever codec you like before calling.

async fn append( &self, scope: &MemoryScope, id: MemoryId, kind: MemoryKind, payload: Vec<u8>, ) -> Result<MemoryId, LaserError>

Append a typed item. Custom backends can keep their remember fallback.

async fn recall( &self, scope: &MemoryScope, query: &MemoryQuery, ) -> Result<Vec<MemoryItem>, LaserError>

async fn improve( &self, scope: &MemoryScope, feedback: Feedback, ) -> Result<MemoryId, LaserError>

Record feedback on a recalled item, the log-native signal a ranking backend folds into future recall. Returns the feedback record’s id.

async fn forget( &self, scope: &MemoryScope, id: MemoryId, ) -> Result<(), LaserError>