rag-vector/ai.koog.rag.vector.backend/InMemoryVectorStorageBackend

InMemoryVectorStorageBackend

class InMemoryVectorStorageBackend<Document> : VectorStorageBackend<Document> (source)

A concrete implementation of VectorStorageBackend that stores documents and their associated vector embeddings in memory.

Use this class to manage the storage and retrieval of documents and their vector-based data without relying on any external persistent storage. This is suitable for in-memory operations and testing environments where persistent storage is not required.

Type Parameters

Document

The type of document managed by this storage.

Constructors

InMemoryVectorStorageBackend

constructor()

Functions

open override fun allDocuments(): Flow<Document>

Retrieves a flow of all documents.

allDocumentsWithPayload

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

Retrieves a flow of all documents with their vector embeddings.

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

Deletes the document with the specified ID.

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, Vector>?

Reads a document along with its vector embedding by document ID.

open suspend override fun store(document: Document, vector: Vector): String

Stores a document along with its pre-computed vector embedding.

open suspend override fun store(id: String, document: Document, vector: Vector): Boolean

Updates a document along with its pre-computed vector embedding under the specified ID. Only updates if a document with the given ID already exists.