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

InMemoryTextDocumentEmbeddingStorage

class InMemoryTextDocumentEmbeddingStorage<Document, Path>(embedder: Embedder, documentReader: DocumentProvider<Path, Document>) : InMemoryDocumentEmbeddingStorage<Document> (source)

Implementation of an in-memory storage solution for text document embeddings.

This class leverages the functionality of an embedder and a document provider to compute embeddings for text documents and store them in memory for efficient retrieval.

Parameters

embedder

The embedder used for generating vectorized representations of text.

documentReader

The document provider facilitating access to document contents.

Type Parameters

Document

The type representing the document being managed.

Path

The type representing the path or identifier for locating documents.

Constructors

InMemoryTextDocumentEmbeddingStorage

constructor(embedder: Embedder, documentReader: DocumentProvider<Path, 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>