bolt

Documentation

Index

• Constants
• type Options
• type VectorStore
  • func NewVectorStore(embeddings flowllm.Embeddings, opts Options) (*VectorStore, func(), error)
  • func (s *VectorStore) AddDocuments(ctx context.Context, documents ...flowllm.Document) error
  • func (s *VectorStore) SimilaritySearch(ctx context.Context, query string, k int) ([]flowllm.Document, error)
  • func (s *VectorStore) SimilaritySearchVectorWithScore(_ context.Context, query []float32, k int) ([]flowllm.ScoredDocument, error)

Constants

const (
	DefaultPath       = "vector_store.db"
	DefaultBucket     = "embeddings"
	DefaultPermission = 0600
)

Types

type Options

type Options struct {
	Path       string
	Bucket     string
	Permission fs.FileMode
	Timeout    time.Duration
}

Options for the Bolt vector store.

type VectorStore

type VectorStore struct {
	// contains filtered or unexported fields
}

VectorStore is a vector store backed by BoltDB. It implements the flowllm.VectorStore interface, and it is ideal for small to medium-sized collections of vectors.

func NewVectorStore

func NewVectorStore(embeddings flowllm.Embeddings, opts Options) (*VectorStore, func(), error)

NewVectorStore creates a new Bolt vector store.

func (*VectorStore) AddDocuments

func (s *VectorStore) AddDocuments(ctx context.Context, documents ...flowllm.Document) error

func (*VectorStore) SimilaritySearch

func (s *VectorStore) SimilaritySearch(ctx context.Context, query string, k int) ([]flowllm.Document, error)

func (*VectorStore) SimilaritySearchVectorWithScore

func (s *VectorStore) SimilaritySearchVectorWithScore(_ context.Context, query []float32, k int) ([]flowllm.ScoredDocument, error)