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

Web Vector Storage

Web Vector Storage is a TypeScript library that stores document vectors in browser IndexedDB and provides cosine-similarity search over text. It offers embedding integrations for OpenAI, Ollama and Hugging Face Transformers, and includes metadata or text-content filtering and storage-size management.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Web 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 WVS when a web application needs browser-native vector storage and semantic retrieval over text, including as a retrieval component in an in-browser or other RAG workflow.

Who it is for

  • Web developers adding semantic search to text collections.
  • Developers building browser-based knowledge stores or retrieval components for RAG applications.

Documented uses

  • Store text documents as vectors in browser IndexedDB.
  • Retrieve documents similar in meaning to a query.
  • Filter search results using metadata or text content.
  • Manage a configured storage-size limit by removing least-recently-used documents.
Before you choose

Requirements & limits

  • Choose an embedding integration based on infrastructure: OpenAI needs an API key and costs money; Ollama needs a local instance and embedding model; Hugging Face Transformers are also supported.
  • Vectors are stored in browser IndexedDB, and the library documents an adjustable maximum size with least-recently-used removal when the limit is exceeded.
  • The repository identifies the project as TypeScript and 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 text and search with OpenAI embeddings

Use the documented VectorStorage API to add a text document with metadata and run a semantic similarity search.

Before you start

  • Install the package with npm.
  • An OpenAI API key; the README notes that OpenAI embeddings cost money.

Steps

  1. Import VectorStorage and OpenAIEmbedder from web-vector-storage.

  2. Create VectorStorage with an OpenAIEmbedder configured with the API key.

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

  4. Call similaritySearch with a query and receive the results.

Expected outcome

A similarity-search result list for the query, based on vectors stored in browser IndexedDB.

Guide limitations

  • The documented example uses OpenAI embeddings, which require an API key and incur cost.
  • The guide covers adding one text and searching; it does not describe a complete RAG application.
Documentation 1 ↗
Evidence and transparency

Sources & review

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