An open-source AI conceptual engineer built with SvelteKit, the Vercel AI SDK, OpenAI, LangChain and Vercel KV. It should help you analyze, understand, and engineer concepts, mainly using LLM prompting.
Features · Model Providers · Deploy Your Own · Running locally · Authors
- SvelteKit
- Vercel AI SDK for streaming chat UI
- Support for OpenAI (default), Anthropic, HuggingFace, or custom AI chat models and/or LangChain
- Edge runtime-ready
- shadcn/ui and shadcn-svelte
- Styling with Tailwind CSS
- Radix Svelte and Svelte Headless UI for headless component primitives
- Icons from Phosphor Icons
- Chat History, rate limiting, and session storage with Vercel KV (🚧 Under construction)
- Auth.js for authentication
This template ships with OpenAI gpt-3.5-turbo
as the default. However, thanks to the Vercel AI SDK, you can switch LLM providers to Anthropic, HuggingFace, or using LangChain with just a few lines of code.
You can deploy your own version of the AI Chatbot to Vercel with one click (but it will not have the AI conceptual engineering tooling):
Follow the steps outlined in the quick start guide provided by Vercel. This guide will assist you in creating and configuring your KV database instance on Vercel, enabling your application to interact with it.
Remember to update your environment variables (KV_URL
, KV_REST_API_URL
, KV_REST_API_TOKEN
, KV_REST_API_READ_ONLY_TOKEN
) in the .env
file with the appropriate credentials provided during the KV database setup.
You will need to use the environment variables defined in .env.example
to run Next.js AI Chatbot. It's recommended you use Vercel Environment Variables for this, but a .env
file is all that is necessary.
Note: You should not commit your
.env
file or it will expose secrets that will allow others to control access to your various OpenAI and authentication provider accounts.
- Install Vercel CLI:
npm i -g vercel
- Link local instance with Vercel and GitHub accounts (creates
.vercel
directory):vercel link
- Download your environment variables:
vercel env pull
npm install
npm run dev
# or start the server and open the app in a new browser tab
npm run dev -- --open
Your app template should now be running on localhost:5173.
- Jeremy Hadfield (AI tooling, major infrastructure changes), switch to LangChain & Svelte, prompt engineering
This template is similar to the Next.js version, with contributions from:
- Jian Yuan Lee (@jyuan)