ChatGPT plugins provide a new medium for developers to take advantage of OpenAI’s powerful GPT-4 model. plugins give ChatGPT access to tools via a REST API. When a plugin is installed in a user’s ChatGPT session, the model may decide to use the plugin as a part of it’s response.
You can develop plugins that enable ChatGPT to plan travel, go shopping, or do complex mathematics. In this tutorial, you’ll learn the basics of developing a ChatGPT plugin using Ruby and Rails.
This tutorial assumes you have Ruby and Rails installed. For information about how to create a plugin in other languages, see:
Create a new Rails project by running:
rails new ruby_chatgpt_plugin --api
This example is API-only because ChatGPT plugins are API-only. You can omit the API flags from the generation if you plan to have a frontend for your application. This will create a new Rails project.
You can confirm your Rails application is setup properly by running rails server
from the project directory and navigating to the localhost:3000
:
Now you’re ready to create the plugin API!
ChatGPT interacts with plugins via a defined REST API. To start defining your REST API, create a new route in config/routes.rb
inside an api
scope:
scope path: '/api' do
get 'hello', to: 'chat_gpt#hello'
end
This will create a new route at /api/hello
which dispatches to the hello
method in the ChatGPT controller. Next, create app/controllers/chat_gpt_controller.rb
and define a new controller:
class ChatGptController < ApplicationController
end
Next, define the hello
method:
def hello
message = { message: "Hello from the plugin!" }
render json: message
end
This will return a JSON response from the server with the message Hello from the plugin!
. Your entire controller will look like this:
class ChatGptController < ApplicationController
def hello
message = { message: "Hello from the plugin" }
render json: message
end
end
With your API defined, you need to define an OpenAPI Spec. Rails doesn’t automatically generate OpenAPI specs, so you need to generate them yourself.
The OpenAPI Spec is how your ChatGPT plugin knows which endpoints are available to interact with. ChatGPT will use your OpenAPI spec to structure its requests and parse the responses from your plugin. For your Ruby plugin, create a new file public/openapi.yaml
. Next, open up openapi.yaml
and add the following:
openapi: 3.0.0
info:
title: Ruby ChatGPT Plugin
version: 1.0.0
servers:
- url: http://localhost:3000/api
paths:
/hello:
get:
summary: Say hello
description: Says hello from the plugin
responses:
"200":
description: OK
content:
application/json:
schema:
type: object
properties:
message:
type: string
operationId: sayHello
This spec defines your single /hello
endpoint which is available from the url http://localhost:3000/api/hello
. Now you’re ready to define the ai-plugin.json
for your Ruby plugin.
Every ChatGPT plugin must ship with a plugin manifest hosted on the same domain as the API. ChatGPT looks for the plugin specifically at the path /.well-known/ai-plugin.json
. You can read more about the specifics of the plugin manifest in our What is the ChatGPT plugin manifest? post.
For your plugin, start by creating a new directory public/.well-known
. Next, create a new file in that directory called ai-plugin.json
. Then, add the following to ai-plugin.json
:
{
"schema_version": "v1",
"name_for_human": "My First plugin",
"name_for_model": "ruby_plugin",
"description_for_human": "My first ChatGPT plugin",
"description_for_model": "plugin which says hello.",
"auth": {
"type": "none"
},
"api": {
"type": "openapi",
"url": "http://localhost:3000/openapi.yaml",
"is_user_authenticated": false
},
"logo_url": "http://localhost:3000/logo.png",
"contact_email": "support@example.com",
"legal_info_url": "http://www.example.com/legal"
}
In this example, the “auth” field is set to “none” because this plugin doesn’t require authentication. However, depending on your use case, you might need your plugin to handle authentication. For more information about how to implement authentication in a ChatGPT plugin, you can refer to our ChatGPT Plugin Authentication Guide.
Both openapi.yaml
and .well-known/ai-plugin.json
should be served from your application. You can verify it worked by starting your server and accessing both files from the browser.
In order to test your plugin locally before deploying to production, you need to configure your application to allow Cross-Origin Resource Sharing (CORS) from the ChatGPT website. CORS enables ChatGPT to request access to resources from your locally running webserver. To setup CORS with Ruby and Rails, you can use the rack-cors
gem. First, install the rack-cors
gem by adding it to your application’s Gemfile:
gem 'rack-cors'
Then run bundle install
to install your new dependencies. Finally, add the following code to config/application.rb
:
# Configure CORS
config.middleware.insert_before 0, Rack::Cors do
allow do
origins ['https://chat.openai.com']
resource '*',
headers: :any,
methods: [:get, :post]
end
end
This will configure CORS correctly in your application for local development. Now you’re all set for testing!
First, start your plugin server locally by running:
rails server
You can verify it worked by navigating to http://localhost:3000
in your browser:
Next, navigate to the ChatGPT UI and select the plugin model:
Then, you’ll want to select the plugins dropdown, navigate to the plugin store, and click “Develop your own plugin” in the bottom right:
Finally, type your localhost URL into the plugin form:
After awhile, you’ll see the following:
Click “Install localhost plugin” to continue. With your plugin enabled, you can start to interact with it using ChatGPT. For example, try typing in “Say hello from my plugin” into the chat window:
Congratulations! You’ve successfully made your first ChatGPT plugin with Ruby and Rails and confirmed it works locally. Next, check out our deployment and hosting guide to learn about deploying your plugin to production.
Get updates on new content, exclusive offers, and exclusive materials by subscribing to our newsletter.