OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Vector Storage

Vector Storage is a TypeScript library for storing text-document embeddings in browser IndexedDB and retrieving similar documents through cosine-similarity search. It uses OpenAI embeddings and supports metadata or text-content filters.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vector Storage — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a browser application needs local vector storage and semantic search over text documents, with OpenAI generating the embeddings.

Who it is for

  • Developers building browser-based notes or document applications.
  • Developers adding semantic retrieval to a small personal document collection.

Documented uses

  • Store vectors for text documents in IndexedDB.
  • Find documents similar to a text query or supplied vector.
  • Filter retrieval results using metadata or text content.
Before you choose

Requirements & limits

  • The documented storage backend is browser IndexedDB, not a hosted database.
  • An OpenAI API key is required for embedding generation.
  • The README describes LRU removal when the storage limit is reached, prioritizing documents with fewer hits and older timestamps.
  • The repository identifies the package as MIT-licensed.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add and search a text document

Install the package, store a text document, then retrieve similar content using a text query.

Before you start

  • npm
  • A browser environment with IndexedDB
  • An OpenAI API key for generating embeddings

Steps

  1. Install the package with the command below.

    Documented command
    npm i vector-storage

  2. Import VectorStorage from vector-storage and create an instance with an openAIApiKey.

  3. Call addText with the document text and a metadata object.

  4. Call similaritySearch with a text query; optionally provide a result count or filter options.

Expected outcome

The documented methods return the stored document and an array of similar documents for the query.

Guide limitations

  • The guide follows the README example and does not establish execution or compatibility testing.
  • Vector storage is in browser IndexedDB; OpenAI is used to generate embeddings.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
nitaiaharoni1/vector-storage · Official homepage title · retained in its source language
How we review sourcesSuggest a correction