OpenViSTAI · Agents · Blockchain · Crypto
Menu
RAG & Knowledge Systems

Vortex

Vortex is a self-hosted web application that ingests PDFs, text files and URL content into knowledge bases and uses retrieval-augmented generation to answer questions grounded in that material.

Independent OpenViST project profile, based on linked sources.

Vortex — 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 Vortex when you want a self-hosted document-chat workflow with hybrid keyword and vector retrieval, reranking and citations tied to the ingested sources.

Who it is for

  • People who want to ask questions across their own PDFs, text files or web pages.
  • Developers or teams able to configure and operate a Node.js application with Supabase.

Documented uses

  • Build separate knowledge bases from uploaded files and ingested URLs.
  • Ask questions over a knowledge base and receive streaming answers with source citations.
  • Choose among supported LLM and embedding providers, including local embeddings.
Before you choose

Requirements & limits

Vortex is open source under the MIT license. The documented self-hosting setup requires Node.js 18+ and a Supabase project. An OpenRouter API key is optional when using free models.

  • Hybrid retrieval combines pgvector similarity and BM25 keyword matching using Reciprocal Rank Fusion.
  • Responses provide citation notation linked to source documents.
  • Embedding choices include local Xenova/Transformers.js as well as OpenAI, Google and OpenRouter.
  • Each knowledge base uses a fixed embedding model.
  • The setup requires configuring Supabase and an encryption key.

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

Set up Vortex for local development

Configure the documented prerequisites and start the Vortex development server.

Before you start

  • Node.js 18 or newer
  • A Supabase account and project
  • Supabase project URL, anon key and service role key
  • A 32-byte hexadecimal encryption key
  • An OpenRouter API key is optional; the README says free models can be used without one

Steps

  1. Clone the repository and install dependencies with npm.

  2. Copy .env.example to .env.local and enter the Supabase credentials.

  3. Create a Supabase project, then run migrations 001 through 005 in order in its SQL Editor.

  4. Generate a 32-byte hexadecimal key and set it as ENCRYPTION_KEY in .env.local.

  5. Run npm run dev and open http://localhost:3000.

Expected outcome

The documented local setup opens Vortex at localhost:3000, where an account can be created to begin building knowledge bases.

Guide limitations

  • This guide covers local setup and startup only; it does not verify a successful installation.
  • The setup requires a Supabase project and its credentials.
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
VortexBuild separate knowledge bases from uploaded files and ingested URLs.Self-hosted, WebVortex is open source under the MIT license. The documented self-hosting setup requires Node.js 18+ and a Supabase project. An OpenRouter API key is optional when using free models.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
ankushchhabra02/vortex · Official homepage title · retained in its source language