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

Embedjs

EmbedJs is an open-source TypeScript framework for building Node.js applications that ground LLM responses in a developer’s own data. It chunks source data, generates embeddings, stores them in a vector database, and retrieves context for answers or chat.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Embedjs — 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 EmbedJs when developing a Node.js LLM application that needs to retrieve information from a developer-provided data collection before responding.

Who it is for

  • Node.js developers building retrieval-augmented generation applications.
  • Teams creating question-answering or chat experiences based on organizational documents or private knowledge bases.

Documented uses

  • Prepare source data as chunks and embeddings for vector-database storage.
  • Retrieve contextual information to support LLM answers or chat.
  • Build a data ingestion and indexing layer for a knowledge-grounded application.
Before you choose

Requirements & limits

  • EmbedJs is a framework for building applications, not a finished chat or knowledge-base product.
  • Its described retrieval pipeline uses data chunking, embeddings, and a vector database.
  • The repository identifies TypeScript as its primary language and Apache-2.0 as its license.

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

Build a local Ollama RAG application with EmbedJs

Install EmbedJs and assemble a local-model RAG application that indexes web pages and queries them.

Before you start

  • Node.js package installation using npm.
  • Ollama with the Llama 3.2 model and nomic-embed-text embedding model available locally.
  • The quickstart uses the Ollama service at http://localhost:11434.

Steps

  1. Install the package with the command below.

    Documented command
    npm i @llm-tools/embedjs

  2. In a TypeScript application, import RAGApplicationBuilder, OllamaEmbeddings and Ollama, and the HNSW vector database package as shown in the quickstart.

  3. Build the application with the Ollama model, Ollama embeddings, and HNSWDb.

  4. Add the Forbes and Wikipedia URLs using addLoader, then call query with a question about the indexed material.

Expected outcome

A configured RAG application can load the two web sources and submit a query; the quickstart shows an example answer to a question about Elon Musk’s net worth.

Guide limitations

  • The Ollama example requires locally run models; the quickstart identifies Llama 3.2 and nomic-embed-text.
  • The example’s displayed answer is illustrative and does not establish current factual accuracy.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
llm-tools/embedJs · Official homepage title · retained in its source language
How we review sourcesSuggest a correction