0.3.0

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

JVMTextFileDocumentEmbeddingStorage

class JVMTextFileDocumentEmbeddingStorage(embedder: Embedder, root: Path) : TextFileDocumentEmbeddingStorage<Path, Path> (source)

A JVM-specific implementation of TextFileDocumentEmbeddingStorage tailored for text document embedding and storage within a file system. This class utilizes a JVMDocumentProvider to handle document reading and manages embeddings using a provided Embedder.

This storage solution is designed for efficient document querying and retrieval based on embeddings derived from textual content.

Parameters

embedder

The embedding implementation used to generate and compare vector embeddings.

root

The root directory where the document storage system is initialized.

Constructors

JVMTextFileDocumentEmbeddingStorage

constructor(embedder: Embedder, root: Path)

Creates an instance of JVMTextFileDocumentEmbeddingStorage.

Functions

open override fun allDocuments(): Flow<Path>

Retrieves a flow of all documents stored in the system.

allDocumentsWithPayload

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

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

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

Reads a document by its unique identifier.

readWithPayload

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

open suspend fun store(document: Path): String

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

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