ragkit

type Document struct {
	ID       string         // Unique ID
	Text     string         // Original text
	Metadata map[string]any // Optional: Additional metadata
	Vector   []float32      // Optional: Embedding vector (generated by Embeder if not provided)
}

type Embedder interface {
	// Embed: Convert texts to embedding vectors
	Embed(ctx context.Context, texts ...string) ([][]float32, error)
}

type Indexer interface {
	// Index: Index multiple documents
	// Returns: IDs of indexed documents
	Index(ctx context.Context, docs ...Document) ([]string, error)

	// Delete: Delete a document by ID
	Delete(ctx context.Context, id string) error

	// Exists: Check if a document with the given ID exists
	Exists(ctx context.Context, id string) (bool, error)
}

type RetrievedDoc struct {
	// ID       string         // Document ID
	// Score    float32        // Similarity score
	Vector   []float32      // Retrieved vector
	Text     string         // Retrieved text
	Metadata map[string]any // Optional metadata
}

type Retriever interface {
	// Retrieve: Return top-K documents based on query vector
	Retrieve(ctx context.Context, query []float32, topK int) ([]RetrievedDoc, error)

	// RetrieveText: Return top-K documents based on text query
	RetrieveText(ctx context.Context, text string, topK int) ([]RetrievedDoc, error)
}

type Vectorizer interface {
	Indexer
	Retriever
}