vectorstores

Documentation

Index

• func CosineSimilarity(a, b []float32) float32
• func SimilaritySearch(ctx context.Context, store llmcomposer.VectorStore, ...) ([]llmcomposer.Document, error)
• type Memory
  • func NewMemoryVectorStore(embeddings llmcomposer.Embeddings) *Memory
  • func (m *Memory) AddDocuments(ctx context.Context, documents ...llmcomposer.Document) error
  • func (m *Memory) SimilaritySearch(ctx context.Context, query string, k int) ([]llmcomposer.Document, error)
  • func (m *Memory) SimilaritySearchVectorWithScore(_ context.Context, query []float32, k int) ([]llmcomposer.ScoredDocument, error)

Functions

func CosineSimilarity

func CosineSimilarity(a, b []float32) float32

func SimilaritySearch

func SimilaritySearch(ctx context.Context, store llmcomposer.VectorStore, embeddings llmcomposer.Embeddings, query string, k int) ([]llmcomposer.Document, error)

SimilaritySearch returns the k most similar documents to the given query. It uses the given vector store's SimilaritySearchVectorWithScore method to perform the search.

Types

type Memory

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

func NewMemoryVectorStore

func NewMemoryVectorStore(embeddings llmcomposer.Embeddings) *Memory

func (*Memory) AddDocuments

func (m *Memory) AddDocuments(ctx context.Context, documents ...llmcomposer.Document) error

func (*Memory) SimilaritySearch

func (m *Memory) SimilaritySearch(ctx context.Context, query string, k int) ([]llmcomposer.Document, error)

func (*Memory) SimilaritySearchVectorWithScore

func (m *Memory) SimilaritySearchVectorWithScore(_ context.Context, query []float32, k int) ([]llmcomposer.ScoredDocument, error)