Name		Name	Last commit message	Last commit date
parent directory ..
app		app
cache		cache
.env.local.example		.env.local.example
.eslintrc.json		.eslintrc.json
.gitignore		.gitignore
README.md		README.md
environment.d.ts		environment.d.ts
next.config.js		next.config.js
package-lock.json		package-lock.json
package.json		package.json
postcss.config.js		postcss.config.js
tailwind.config.ts		tailwind.config.ts
tsconfig.json		tsconfig.json

README.md

Arcjet rate limit OpenAI chat route with Next.js

This example shows how to implement a rate limit on a Next.js API route which uses the OpenAI chat API. It uses the openai-chat-tokens library to track the number of tokens used by a gpt-3.5-turbo AI chatbot.

There are 2 example routes:

/api/chat is the default route that tracks the user by IP address. It applies a limit of 2,000 tokens per hour with a maximum of 5,000 tokens in the bucket. This allows for a reasonable conversation length without consuming too many tokens.
/api/chat_userid is a route that tracks the user by a unique identifier. You could use this to track a quota per authenticated user.

How to use

From the root of the project, install the SDK dependencies.
```
npm ci
```
Enter this directory and install the example's dependencies.
```
cd examples/nextjs-openai
npm ci
```
Rename .env.local.example to .env.local and add your Arcjet & OpenAI keys.
Start the dev server.
```
npm run dev
```
Visit http://localhost:3000.
Refresh the page to trigger the rate limit.