langchain ui

This repository is unmaintained

Note that this repository is unmaintained. We've started working on another approach which gives more granular access to LLM-powered Agents. Please check out out https://github.com/homanp/superagent. We appreciate all the feedback and contributions

? LangChain UI

The no-code open source chat-ai toolkit built on top of LangChain.

About the project

LangChain UI enables anyone to create and host chatbots using a no-code type of inteface.

Features:

Create custom chatGPT like Chatbot.

Give context to the chatbot using external datasources, chatGPT plugins and prompts.

Dedicated API endpoint for each Chatbot.

Bring your own DB

Bring your own Auth provider (defaults to Github)

Usage quoutas

Embed Chatbots to any site or application

Chatbot themes

... and more

Roadmap

• Bring your own db
• Bring your own Auth provider
• Chatbots
• Prompt templates
• API endpoints to chatbot
• External datasources
• chatGPT plugins
• Chatbots themes
• Chatbot embedding

Stack

• Next.js
• Chakra UI
• Prisma
• NextAuth

LangChain UI utilizes NextJS 13 appDir. Read more about it here

Getting started

Langchain UI API

We have migrated all agent functionality from LangChain Typescript to LangChain Python. Thus you will need to run the Langchain UI API in order to interact with the chatbot. In the future when the TS package is on par with the Python package we will migrate to only using Javascript.

Installation

1. Setup the Langchain UI API

2. Clone the repo into a public GitHub repository (or fork https://github.com/homanp/langchain-ui/fork). If you plan to distribute the code, keep the source code public.

   git clone https://github.com/homanp/langchain-ui.git

3. Go to the project folder

   cd langchain-ui

4. Install packages with npm

   npm install

5. Set up your .env file

   • Duplicate .env.example to .env

6. Run the project

   npm run dev

7. Run the linter

   npm run lint

8. Build the project

   npm run build

Contributions

Our mission is to make it easy for anyone to create and run LLM apps in the cloud. We are super happy for any contributions you would like to make. Create new features, fix bugs or improve on infra.

You can read more on how to contribute here.