# AI Chat App

A Next.js chat app with streaming responses, authentication, and saved conversations

The [Supabase Community AI chatbot template](https://github.com/supabase-community/vercel-ai-chatbot) includes a chat interface, streaming responses, Supabase Auth, and conversation history in Postgres. Creating the app installs those features together.

## Installation

### Create the app

Scaffold the template with the [Next.js CLI](https://nextjs.org/docs/app/api-reference/cli/create-next-app):

```bash
npx create-next-app@latest my-chat --example https://github.com/supabase-community/vercel-ai-chatbot --use-pnpm
cd my-chat
cp .env.example .env
```

This community template uses Next.js 13, AI SDK 2, and Supabase Auth Helpers. Review its [dependency versions](https://github.com/supabase-community/vercel-ai-chatbot/blob/main/package.json) and plan upgrades before deployment. For a new authentication foundation using `@supabase/ssr`, start with the [Next.js starter](https://supabase.com/library/docs/starters/nextjs-starter.md).

## Start Supabase

Install [Docker](https://docs.docker.com/get-started/get-docker/) and the [Supabase CLI](https://supabase.com/docs/guides/local-development/cli/getting-started), then run the local stack from the template directory:

```bash
supabase start
```

The template includes database migrations for chat history. Use the project URL and `anon` key printed by the CLI in `.env`:

```env
NEXT_PUBLIC_SUPABASE_URL=your-local-api-url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your-local-anon-key
OPENAI_API_KEY=your-model-provider-api-key
NEXT_PUBLIC_AUTH_GITHUB=false
```

The variable names match the template's [environment example](https://github.com/supabase-community/vercel-ai-chatbot/blob/main/.env.example). Keep `OPENAI_API_KEY` on the server. To add GitHub sign-in, follow the template's [OAuth setup](https://github.com/supabase-community/vercel-ai-chatbot#set-up-github-oauth) and fill in its provider settings.

## Choose a model

The template selects its model in [`app/api/chat/route.ts`](https://github.com/supabase-community/vercel-ai-chatbot/blob/main/app/api/chat/route.ts). Replace the example model with one available to your provider account that supports the template's Chat Completions streaming API. Keep the model selection and API key in the server route.

## Run the app

```bash
pnpm dev
```

Open [the app](http://localhost:3000), sign up, and send a message. Use the local email inbox URL printed by the Supabase CLI to confirm your account. Confirm that the response streams and that the conversation appears in your history after refreshing.

## Deploy the app

Follow the template's [deployment guide](https://github.com/supabase-community/vercel-ai-chatbot#deploy-your-own) to connect a hosted Supabase project, apply its migrations, and set the production Auth Site URL and server environment variables.