Documentation
¶
Overview ¶
Package vector provides interfaces and implementations for vector storage and embedding.
Index ¶
Constants ¶
This section is empty.
Variables ¶
View Source
var ( // ErrNotFound is returned when a document is not found in the vector store. ErrNotFound = errors.New("document not found") // ErrEmbedding is returned when embedding generation fails. ErrEmbedding = errors.New("embedding failed") // ErrConnection is returned when the vector store connection fails. ErrConnection = errors.New("vector store connection failed") )
Functions ¶
This section is empty.
Types ¶
type Document ¶
type Document struct {
// ID is a unique identifier for the document (typically the node hash).
ID string
// Hash is the merkle node hash this document corresponds to.
Hash string
// Embedding is the vector representation of the document content.
Embedding []float32
}
Document represents a stored item with its embedding and metadata.
type Driver ¶
type Driver interface {
// Add stores documents with their embeddings.
// If a document with the same ID already exists, implementers should update
// the document.
Add(ctx context.Context, docs []Document) error
// Query finds the topK most similar documents to the given embedding.
Query(ctx context.Context, embedding []float32, topK int) ([]QueryResult, error)
// Get retrieves documents by their IDs.
Get(ctx context.Context, ids []string) ([]Document, error)
// Delete removes documents by their IDs.
Delete(ctx context.Context, ids []string) error
// Close releases any resources held by the driver.
Close() error
}
Driver handles storage and retrieval of vector embeddings.
type QueryResult ¶
type QueryResult struct {
Document
// Score represents the similarity score (higher = more similar).
Score float32
}
QueryResult represents a search result with similarity score.
Source Files
Directories
Click to show internal directories.
Click to hide internal directories.