Documentation
¶
Overview ¶
Package sqlite provides a SQLite-based vector store for memoryrails.
Uses sqlite-vec extension for vector similarity search. Suitable for edge deployments, CLI tools, and single-machine applications.
Index ¶
- type Store
- func (s *Store) Close() error
- func (s *Store) Delete(ctx context.Context, id string) error
- func (s *Store) Get(ctx context.Context, id string) (*memoryrails.Memory, error)
- func (s *Store) List(ctx context.Context, opts memoryrails.ListOptions) ([]*memoryrails.Memory, error)
- func (s *Store) Put(ctx context.Context, mem *memoryrails.Memory) error
- func (s *Store) Search(ctx context.Context, embedding []float64, opts memoryrails.SearchOptions) ([]memoryrails.SearchResult, error)
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Store ¶
type Store struct {
// contains filtered or unexported fields
}
Store implements memoryrails.Store using SQLite with in-process cosine similarity computation. Works without sqlite-vec extension by storing embeddings as JSON arrays and computing similarity in Go.
func (*Store) List ¶
func (s *Store) List(ctx context.Context, opts memoryrails.ListOptions) ([]*memoryrails.Memory, error)
func (*Store) Search ¶
func (s *Store) Search(ctx context.Context, embedding []float64, opts memoryrails.SearchOptions) ([]memoryrails.SearchResult, error)
Source Files
Click to show internal directories.
Click to hide internal directories.