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

InMemoryDocumentEmbeddingStorage

open class InMemoryDocumentEmbeddingStorage<Document>(embedder: DocumentEmbedder<Document>) : EmbeddingStorage<Document> (source)

An in-memory VectorStorage implementation.

This class facilitates the storage and retrieval of documents and their corresponding vector embeddings entirely in memory. It utilizes an InMemoryVectorStorageBackend for managing the document embeddings and extends EmbeddingStorage, inheriting capabilities such as ranking, storing, and deleting documents based on their embeddings.

Parameters

embedder

A mechanism responsible for embedding the documents into vector representations.

Type Parameters

Document

The type of the documents being stored.

Inheritors

InMemoryTextDocumentEmbeddingStorage

Constructors

InMemoryDocumentEmbeddingStorage

constructor(embedder: DocumentEmbedder<Document>)

Properties

capabilities

open override val capabilities: Set<StorageCapability>

Functions

add

open suspend override fun add(documents: List<Document>, namespace: String?): List<String>

allDocuments

open fun allDocuments(): Flow<Document>

Retrieves a flow of all documents stored in the system.

delete

open suspend override fun delete(ids: List<String>, namespace: String?): List<String>

get

open suspend override fun get(ids: List<String>, namespace: String?): List<Document>

rankDocuments

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

open suspend override fun search(request: SimilaritySearchRequest, namespace: String?): List<SearchResult<Document>>

supports

open fun supports(capability: StorageCapability): Boolean

update

open suspend override fun update(documents: Map<String, Document>, namespace: String?): List<String>