Using ChatGPT Plugins: Enable Internet Access, Find Valuable data and Plugin Chaining

ChatGPT plugins are a powerful feature that allows developers to extend the capabilities of the base ChatGPT model. They can be used to add new functionalities, improve the quality of responses, or even interact with external services.

Photo by Markus Winkler on Unsplash

How Plugins Work

Plugin developers expose one or more API endpoints, accompanied by a standardized manifest file and an OpenAPI specification. These define the plugin's functionality, allowing ChatGPT to consume the files and call the developer-defined APIs.

The AI model acts as an intelligent API caller. Given an API spec and a natural-language description of when to use the API, the model proactively calls the API to perform actions. For instance, if a user asks, "Where should I stay in Paris for a couple of nights?" the model may call a hotel reservation plugin API, receive the API response, and generate a user-facing answer combining the API data and its natural language capabilities.

Pre-Requisites

At the time of this writing, ChatGPT plugin access is not publicly available but is available for ChatGPT plus subscribers. For regular users, you can join the waitlist for plugin access here.

Using ChatGPT Plugins Effectively

In this blog post, we will look at some experiments with ChatGPT plugins and provide tips and tricks for practical usage of the ChatGPT Plugin ecosystem

Let's get started

Setup

Step 1: Log in to ChatGPT plus

and you should be greeted with a screen like the one below with two options:
[a] Default ChatGPT-3.5 model version (Default)
[b] Updated ChatGPT-4 model with Plugin Support

GPT-4 with plugins

Select the ChatGPT-4 model

Step 2: Browse the Plugin Store