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

@kozmoai/rag-ai

v0.2.1

Published

This plugin is the frontend for RAG AI Backstage plugin. You can see the corresponding backend plugin in [here](/plugins/backend/rag-ai-backend/README.md).

Readme

Glint RAG AI Frontend plugin for Backstage

This plugin is the frontend for RAG AI Backstage plugin. You can see the corresponding backend plugin in here.

docs/petstore-rag-openapi-example.gif

Getting started

The plugin exposes a single Modal React component which can be triggered on the application UI by pressing ctrl+, (control + comma). docs/empty-modal.png

You can ask the plugin information about your catalog and request assistance on how to better interact with the catalog entities that have been configured to your system. The plugin provides functionality to call the RAG AI backend, which enhances your queries with additional context and requests responses from configured LLMs to provide answers based on that context.

docs/simple-q-a.png

Depending on how you implement your Embeddings providers and retrieval functionality, you can use the LLM, for example, to construct specific code samples from your Catalog Entity API endpoints, while using the wider knowledge of specific best practices from various programming languages and frameworks.

docs/api-spec-query.png

Configuration

To configure the frontend plugin, you need to do two things:

  • Create an API client for the frontend plugin
  • Add the exposed UI element into the application

Creating an API client

The RAG AI plugin exposes an API client which needs to be configured for your Backstage application frontend to be able to use the RAG AI functionality. You can do that by adding a new API factory into your apis.ts file. See configuration example below:

// packages/app/src/apis.ts

import {
  AnyApiFactory,
  configApiRef,
  createApiFactory,
  discoveryApiRef,
  fetchApiRef,
  identityApiRef,
} from '@backstage/core-plugin-api';
import fetch from 'cross-fetch';
import { ragAiApiRef, GlintRagAiClient } from '@kozmoai/rag-ai';

export const apis: AnyApiFactory[] = [
  // ... Other APIs
  createApiFactory({
    api: ragAiApiRef,
    deps: {
      configApi: configApiRef,
      discoveryApi: discoveryApiRef,
      fetchApi: fetchApiRef,
      identityApi: identityApiRef,
    },
    factory: ({ discoveryApi, fetchApi, configApi, identityApi }) => {
      return new GlintRagAiClient({
        discoveryApi,
        fetchApi,
        configApi,
        identityApi,
      });
    },
  }),
];

Adding the UI components into the application

The plugin exposes a single UI component which is used to communicate with the application Backend. You can register this

App.tsx


// packages/app/src/App.tsx
import { RagModal } from '@kozmoai/rag-ai';

...
const App = () => (
  <AppProvider>
    <AlertDisplay />
    <OAuthRequestDialog />
    <AppRouter>
      <RagModal />
      <Root>{routes}</Root>
    </AppRouter>
  </AppProvider>
);