0.3.0

vector-storage/ai.koog.rag.vector/EmbeddingBasedDocumentStorage

EmbeddingBasedDocumentStorage

open class EmbeddingBasedDocumentStorage<Document>(embedder: DocumentEmbedder<Document>, storage: VectorStorage<Document>) : RankedDocumentStorage<Document> (source)

A document storage implementation that utilizes embeddings for document ranking and retrieval. This class combines a document embedder for generating vector representations and a storage mechanism capable of associating documents with their respective embeddings. It provides ranking capabilities by measuring similarity between query embeddings and stored document embeddings.

Parameters

Document

The type of the document being stored and ranked.

Inheritors

FileDocumentEmbeddingStorage

InMemoryDocumentEmbeddingStorage

Constructors

EmbeddingBasedDocumentStorage

constructor(embedder: DocumentEmbedder<Document>, storage: VectorStorage<Document>)

Functions

open override fun allDocuments(): Flow<Document>

Retrieves a flow of all documents stored in the system.

allDocumentsWithPayload

open override fun allDocumentsWithPayload(): Flow<DocumentWithPayload<Document, Unit>>

open suspend override fun delete(documentId: String): Boolean

Deletes the document with the specified ID from the storage.

open suspend override fun getPayload(documentId: String)

open override fun rankDocuments(query: String): Flow<RankedDocument<Document>>

Ranks documents based on their similarity to a given query string.

open suspend override fun read(documentId: String): Document?

Reads a document by its unique identifier.

readWithPayload

open suspend override fun readWithPayload(documentId: String): DocumentWithPayload<Document, Unit>?

open suspend fun store(document: Document): String

open suspend override fun store(document: Document, data: Unit): String

Stores the given document after embedding it into a vector representation.