✞ disciplr is a faith focused ai product built on the bones of vercel/ai-chat!
Read Docs · Features · Model Providers · Deploy Your Own · Running locally
- Next.js App Router
- Advanced routing for seamless navigation and performance
- React Server Components (RSCs) and Server Actions for server-side rendering and increased performance
- AI SDK
- Unified API for generating text, structured objects, and tool calls with LLMs
- Hooks for building dynamic chat and generative user interfaces
- Supports Gemini (default), OpenAI, Fireworks, and other model providers
- shadcn/ui
- Styling with Tailwind CSS
- Component primitives from Radix UI for accessibility and flexibility
- Data Persistence
- Neon Serverless Postgres for saving chat history and user data
- Vercel Blob for efficient file storage
- Auth.js
- Simple and secure authentication
This template ships with Gemini as the default chat model. However, with the AI SDK, you can switch LLM providers to OpenAI, Anthropic, Cohere, and many more with just a few lines of code.
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.
- Docker and Docker Compose installed
- Node.js and npm
Note: You should not commit your
.envfile or it will expose secrets that will allow others to control access to your various AI and authentication provider accounts.
We will be getting our own environement variables so we can run this separate from Vercel upon launch
-
Create a .env file
-
Copy over .env.example to your .env (which won't be committed to github)
-
go to get auth secret key, and google ai key from the links
Once we have .env variables sorted these steps will successfully run our app locally
If this doesn't work try to npm install before running docker
docker-compose build
docker-compose upYour app template should now be running on localhost:3000.