npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

pageindex-vectorless

v1.0.2

Published

PageIndex - Vectorless RAG using LLM-based tree search

Readme

pageindex-vectorless

Vectorless RAG: documents are parsed into section trees and an LLM walks the tree to answer queries (no embeddings). Ships as a library (PageIndex), an Express app factory (createServer), and a CLI that runs the HTTP API.

npm package: pageindex-vectorless · repo: pageindex-ts


Use the package (consumers)

Install

npm install pageindex-vectorless

Environment

| Variable | Required | Default | |----------|----------|---------| | OPENAI_API_KEY | Yes (for server / LLM features) | — | | OPENAI_MODEL | No | gpt-4o-mini | | PORT | No | 3000 | | HOST | No | 0.0.0.0 | | DATA_DIR | No | ./data (relative to process cwd for the CLI) |

Run the REST server (CLI)

export OPENAI_API_KEY=sk-...
npx pageindex-vectorless

Or from your own package.json script after installing the dependency: pageindex-vectorless (same binary name as the package).

Use as a library

import { PageIndex } from 'pageindex-vectorless';

const pageIndex = new PageIndex({
  openaiApiKey: process.env.OPENAI_API_KEY!,
  openaiModel: 'gpt-4o-mini',
  dataDir: './data'
});

await pageIndex.indexFromFile('./doc.pdf', { name: 'my-doc', useLLMTreeBuilder: true });
const results = await pageIndex.query('Your question?', ['my-doc']);

Mount the API in your own Express app

import { createServer } from 'pageindex-vectorless';

const app = createServer({
  port: 3000,
  host: '0.0.0.0',
  openaiApiKey: process.env.OPENAI_API_KEY!,
  openaiModel: 'gpt-4o-mini',
  dataDir: './data'
});

app.listen(3000);

API smoke test (server running on port 3000)

curl -s http://localhost:3000/api/health
curl -s -X POST http://localhost:3000/api/documents/index-content \
  -H "Content-Type: application/json" \
  -d '{"name":"demo","content":"# Hello\n\nSection body.","contentType":"text/markdown"}'

Develop and test changes (this repo)

Setup

git clone https://github.com/sparrowwelcomehr-jpg/pageindex-ts.git
cd pageindex-ts
npm install
cp .env.example .env   # add OPENAI_API_KEY

Run from source (no build)

npm run dev

Same behavior as the published CLI, but executes src/cli.ts via ts-node.

Build and run compiled output

npm run build
npm start

Use this to confirm what users get from dist/ after tsc.

Try the bundled demo script

Requires OPENAI_API_KEY and uses the library-style flow (see comments at top of the file):

npx ts-node test/demo.ts

Lint

npm run lint

Test the npm package locally before publishing

From the repo root:

npm run build
npm pack

Inspect the tarball or install it into another folder:

cd /path/to/another-project
npm install /path/to/pageindex-ts/pageindex-vectorless-1.0.1.tgz

Or link the package:

cd /path/to/pageindex-ts
npm run build
npm link
cd /path/to/consumer
npm link pageindex-vectorless

Publish checklist

npm run build
npm publish --dry-run
npm publish

License

MIT