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

@l7mp/tivadar-ai-chat-widget

v1.0.4

Published

AI-powered chat widget for websites. Works with React, Angular, Vue, Next.js, and vanilla HTML. Integrates with Tivadar.ai from L7mp.io.

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

rg0nowrg0nowbalazsharkaibalazsharkailevaitlevait

Keywords

chatchatbotaiazureopenaiwidgetweb-componentreactangularvuenextjsragl7mp

Readme

@l7mp/tivadar-ai-chat-widget

AI-powered chat widget for websites. Works with React, Angular, Vue, Next.js, and vanilla HTML.

Integrates with Azure OpenAI and Retrieval-Augmented Generation (RAG) for context-aware responses.

Installation

npm install @l7mp/tivadar-ai-chat-widget

Or with yarn:

yarn add @l7mp/tivadar-ai-chat-widget

Or via CDN:

<script src="https://unpkg.com/@l7mp/tivadar-ai-chat-widget@latest/widget-webcomponent.js"></script>

Quick Start

Vanilla HTML

<!DOCTYPE html>
<html>
<head>
  <script src="https://unpkg.com/@l7mp/tivadar-ai-chat-widget@latest/widget-webcomponent.js"></script>
</head>
<body>
  <h1>My Website</h1>

  <tivadar-ai-chat-widget
    api-key="your-api-key"
    api-endpoint="https://api.yourdomain.com/v1/chat"
    position="bottom-right"
    title="Chat with AI"
  ></tivadar-ai-chat-widget>
</body>
</html>

React / Next.js

// Import once in your app (e.g., _app.tsx or layout.tsx)
import '@l7mp/tivadar-ai-chat-widget'

export default function Page() {
  return (
    <div>
      <h1>My Website</h1>

      <tivadar-ai-chat-widget
        api-key="your-api-key"
        api-endpoint="https://api.yourdomain.com/v1/chat"
        position="bottom-right"
        title="Chat with AI"
      />
    </div>
  )
}

React wrapper component (with TypeScript support)

import AIChatWidget from '@l7mp/tivadar-ai-chat-widget/react'

export default function Page() {
  return (
    <div>
      <h1>My Website</h1>

      <AIChatWidget
        apiKey="your-api-key"
        apiEndpoint="https://api.yourdomain.com/v1/chat"
        position="bottom-right"
        title="Chat with AI"
      />
    </div>
  )
}

Angular

// app.module.ts
import { CUSTOM_ELEMENTS_SCHEMA } from '@angular/core';
import '@l7mp/tivadar-ai-chat-widget'

@NgModule({
  schemas: [CUSTOM_ELEMENTS_SCHEMA]
})
export class AppModule { }
<!-- app.component.html -->
<h1>My Website</h1>

<tivadar-ai-chat-widget
  api-key="your-api-key"
  api-endpoint="https://api.yourdomain.com/v1/chat"
  position="bottom-right"
  title="Chat with AI"
></tivadar-ai-chat-widget>

Vue

<script setup>
import '@l7mp/tivadar-ai-chat-widget'
</script>

<template>
  <div>
    <h1>My Website</h1>

    <tivadar-ai-chat-widget
      api-key="your-api-key"
      api-endpoint="https://api.yourdomain.com/v1/chat"
      position="bottom-right"
      title="Chat with AI"
    />
  </div>
</template>

Svelte

<script>
  import '@l7mp/tivadar-ai-chat-widget'
</script>

<h1>My Website</h1>

<tivadar-ai-chat-widget
  api-key="your-api-key"
  api-endpoint="https://api.yourdomain.com/v1/chat"
  position="bottom-right"
  title="Chat with AI"
/>

Configuration

The widget accepts the following HTML attributes:

| Attribute | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | api-key | string | Yes | - | Chat API key (sent as query param) | | api-endpoint | string | Yes | - | Chat API endpoint URL | | position | string | No | "bottom-right" | Widget position: "bottom-right", "bottom-left", "top-right", "top-left" | | title | string | No | "Chat with AI" | Widget header title | | theme | string | No | "light" | Theme (currently only "light" supported) | | placeholder | string | No | "Type your message..." | Input field placeholder | | welcome-message | string | No | "Hello! How can I help you today?" | Initial greeting message |

Example with All Options

<tivadar-ai-chat-widget
  api-key="your-api-key"
  api-endpoint="https://api.yourdomain.com/chat"
  position="bottom-left"
  theme="light"
  title="Support Chat"
  placeholder="Ask me anything..."
  welcome-message="Hi! How can I assist you today?"
></tivadar-ai-chat-widget>

Classic Version (Legacy)

For compatibility with older browsers or if you prefer the imperative API, you can use the classic version:

<script src="https://unpkg.com/@l7mp/tivadar-ai-chat-widget@latest/widget.js"></script>
<script>
  AIChatWidget.init({
    apiKey: 'your-api-key',
    apiEndpoint: 'https://api.yourdomain.com/v1/chat',
    position: 'bottom-right',
    title: 'Chat with AI'
  });
</script>

Browser Support

  • Chrome/Edge 88+
  • Firefox 85+
  • Safari 14.1+
  • Opera 74+

(Supports all modern browsers with Web Components API)

TypeScript

TypeScript definitions are included via index.d.ts.

Development

Files

| File | Description | |------|-------------| | widget-webcomponent.js | Web Component version (recommended) | | widget.js | Classic vanilla JS version (legacy) |

Publish to npm

cd packages/tivadar-chat-widget

# Bump version
npm version patch   # or minor/major

# Publish (requires npm login)
npm publish --access public

License

Copyright (c) 2025 L7mp.io

See LICENSE file for details.