TextFileDocumentEmbeddingStorage

A file-based VectorStorage implementation for text documents.

This class specializes in storing and ranking text documents in a file system using embeddings derived from their textual content.

embedder

Converts text into vector embeddings and calculates similarity between embeddings.

documentProvider

Provider for reading/writing documents.

Platform-specific file system provider for path manipulations.

root

Root directory where all vector storage will be located.

Document

The type of document to be stored and processed.

Constructors

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

Retrieves a flow of all documents stored in the system.

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

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

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