Tutorial: AI Powered Textarea
Step 2: Setup CopilotKit
Now that we have our todo list app running, we're ready to integrate CopilotKit. For this tutorial, we will install the following dependencies:
@copilotkit/react-core
: The core library for CopilotKit, which contains the CopilotKit provider and useful hooks.@copilotkit/react-textarea
: The textarea component for CopilotKit, which enables you to get instant context-aware autocompletions in your app.
Install Dependencies
To install the CopilotKit dependencies, run the following:
Setup CopilotKit
Set up Copilot Runtime Endpoint
Add your OpenAI API key to your .env
file in the root of your project:
Please note that the code below uses GPT-4o, which requires a paid OpenAI API key. If you are using a free OpenAI API key, change the model to a different option such as gpt-3.5-turbo
.
Endpoint Setup
Create a new route to handle the /api/copilotkit
endpoint.
Your Copilot Runtime endpoint should be available at http://localhost:3000/api/copilotkit
.
Let's break this down:
- First, we imported the
CopilotKit
provider from@copilotkit/react-core
. - Then, we wrapped the page with the
<CopilotKit>
provider. - We imported the built-in styles from
@copilotkit/react-textarea
. This is optional.
In the next step, we'll implement the AI-powered textarea as a replacement for our existing input component.