@nlux/core

NLUX JS 🌲✨💬

The Conversational AI UI Library For Any LLM

NLUX (for Natural Language User Experience) is an open-source JavaScript library that makes it super simple to integrate powerful large language models (LLMs) like ChatGPT into your web app or website. With just a few lines of code, you can add conversational AI capabilities and interact with your favourite LLM.

Key Features 🌟

• Build AI Chat Interfaces In Minutes ― High quality conversational AI interfaces with just a few lines of code.
• LLM Adapters ― For ChatGPT / LangChain 🦜 LangServe / HuggingFace 🤗 Inference.
• A flexible interface to Create Your Own Adapter for any LLM or API.
• Bot and User Personas ― Customize the bot and user personas with names, images, and more.
• Streaming LLM Output ― Stream the chat response to the UI as it's being generated.
• Customizable Theme - Easily customize the look and feel of the chat interface using CSS variables.
• Event Listeners - Listen to messages, errors, and other events to customize the UI and behaviour.
• Zero Dependencies ― Lightweight codebase, with zero-dep except for LLM front-end libraries.

Docs & Examples 📖

• Developer portal ― nlux.dev
• Examples and live code playgrounds ― nlux.dev/examples
• Standard LLM adapters available
• How to create your own adapter for nlux

Vanilla JS 🟨 vs React JS ⚛️

This package @nlux/core is the vanilla JS version of the library. If you're looking for the React JS version, please check the @nlux/react package.

Get Started With NLUX JS 🚀

The example below demonstrates how to create an AI chat interface using NLUX JS and LangChain, the open source framework for building LLM backends. But you can use NLUX with any LLM ― either via the standard adapters provided, or by creating your own adapter.

To get started with NLUX JS and LangChain, install the @nlux/core and @nlux/langchain packages:

npm install @nlux/core @nlux/langchain

Configure the LangChain LangServe adapter to connect to your API endpoint:

import {createAiChat} from '@nlux/core';
import {createChatAdapter} from '@nlux/langchain';

const langChainAdapter = createChatAdapter().withUrl('https://<Your LangServe Runnable URL>');

Then render the AiChat component into your web page:

const aiChat = createAiChat()
    .withAdapter(langChainAdapter)
    .withConversationOptions({
        historyPayloadSize: 'max'
    })
    .withComposerOptions({
        placeholder: 'How can I help you today?'
    })

aiChat.mount(document.getElementById('root'));

You should also include the NLUX theme CSS file in your HTML page.

And The Result Is ✨

An AI chatbot, powered by LangChain, that can understand and respond to user messages:

Theme File and CSS 🎨

You should include a theme CSS file into your HTML page.
You can download and host the Luna Theme CSS file from @nlux/themes package.