Skip to main content
HomeBlogArtificial Intelligence (AI)

OpenAI Announces GPTs and ChatGPT Store

Discover the future of AI customization as OpenAI unveils GPTs and the GPT Store. Explore how you can create tailored AI models for specific tasks and learn about the innovative GPT marketplace.
Updated Nov 2023  · 7 min read

At OpenAI’s recent Dev Day, we were treated to an array of exciting announcements. Alongside the unveiling of GPT-4 Turbo and the Assistants API, we also saw announcements for GPTs, user-created, tailored versions of ChatGPT, and the GPT store, a place to publicly share your GPT creations. We explore the details and everything you need to know about these announcements.

Learn more about ChatGPT today with our Introduction to ChatGPT course.

What are GPTs?

GPTs are tailored versions of ChatGPT that you can customize for a specific purpose. The technology gives anyone the ability to create a custom version of ChatGPT to help with tasks and productivity. The best part is that no coding is required to create custom GPTs—you can use the same conversational interface that’s currently available with ChatGPT. All you need to do is give it the relevant instructions and knowledge.

In many ways, this is an extension of the custom instructions that OpenAI launched in July 2023; GPTs allow users to combine all of their carefully crafted prompts and instruction sets into one handy version of ChatGPT.

An example of GPTs from the OpenAI page

An example of GPTs from the OpenAI page - source

Benefits of Building GPTs

GPTs have three enhancements over standard ChatGPT: instructions, expanded knowledge, and actions.

Instructions

While ChatGPT can generate text on a very wide variety of content and in a wide variety of styles, sometimes this isn't desirable. For example, if you are generating marketing content, then you only want ChatGPT to talk about topics related to your business, and respond in a professional tone that is appropriate to your organization.

Similarly, many uses of ChatGPT require it to roleplay as a specific character. You could be using the AI to pretend to be a customer for your sales training, or as a character to generate dialog for your novel, or as a personal tutor. In each case, having a custom GPT can help it stay "in character" and be consistent about the content and tone of its responses.

GPTs lets you describe how ChatGPT should respond by giving it additional instructions, sometimes known as "prompt augmentation".

In this way, GPTs is OpenAI's answer to character.ai.

Expanded knowledge

GPTs can be given additional knowledge, beyond that which GPT-4 Turbo was trained on, by uploading text documents, similar to how data files can be uploaded for the Advanced Data Analysis tool, or images can be uploaded for the GPT-4 Turbo with vision model.

The text documents can be used to increase the accuracy of answers given on specific topics. For example, if you want to create a chatbot that answers questions on a particular product, then you can add documents containing details about that product.

The OpenAI Dev Day presentation gave no details about how this feature works, though it is likely that this is a no-code implementation of retrieval augmented generation—a technique where factual information is stored in a vector database and fed to the LLM to improve the accuracy of responses.

Actions

One of the big promises of generative AI has been the idea that we can create AI Agents—tools that can perform actions as well as merely generating text. Earlier in 2023, three prototype AI Agents—Auto-GPT, AgentGPT, and BabyAGI—quickly shot to GitHub fame, revealing huge developer interest in the idea.

GPTs is OpenAI's first attempt at an AI Agent. The OpenAI Dev Day presentation included a demo of a Zapier AI Actions" agent, which uses the ChatGPT natural language interface to read a calendar and send text messages.

Again, details were provided about how you create actions for your custom GPT. Since Zapier is a tool to connect different pieces of software (like calendars and texting services and large language models), the demo may have been stitched together using the GPT function calling feature to let Zapier do the heavy lifting.

The promise of useful AI agents looks a little closer, but there are many unanswered questions about how easy this feature will be to use, and what range of actions can be performed.

What is the GPT Store?

Once you’ve built your GPT, you can share it publicly. So, you could create a helpful version of ChatGPT to share among your friends and family for leisure purposes or build a time-saving tool that you can share across your entire organization.

OpenAI hopes that builders in the community, be they teachers, coaches, or innovators, will create helpful tools. The fact that you don’t need to know how to code means that anyone with a grasp of ChatGPT foundations and some creative thinking can create useful GPTs. Furthermore, those same creators will soon be able to monetize their creations on the GPT Store.

While access to custom GPTs is already being rolled out, OpenAI announced that the GPT Store will launch later in November 2023. The store gives verified GPT builders the chance to showcase their creations in a searchable storefront.

OpenAI promises that, along with a variety of categories and chances to spotlight creations, in the coming months, users will be able to earn money based on how many other users use your GPTs.

GPTs for Developers and Enterprise Customers

For more advanced users of ChatGPT, there will be options to connect your GPTs to external sources and vice versa. Developers can define custom actions by using APIs to integrate data, connect to databases, and have greater control over how APIs are called, building on what we’ve so far seen with ChatGPT plugins.

Similarly, Enterprise customers will have the option of creating and deploying internal-only GPTs. Potential use cases highlighted by OpenAI include creating marketing materials and aiding support staff. Of course, as you’d expect from an enterprise tool, security is paramount, particularly when dealing with proprietary data sets.

GPTs and Privacy

Naturally, some users may be concerned about what data will be shared when creating GPTs. OpenAI gives assurances that chats are not shared with builders, and that you can choose whether data can be shared with APIs. Those building GPTs can also decide whether user chats can be used to train and improve GPT models

Along with other usage policy updates, you’ll soon be able to verify your identity, giving greater transparency as to who is creating GPTs.

Final Thoughts

OpenAI’s Dev Day marked an important moment in the evolution of AI customization and accessibility. With the introduction of GPTs and the upcoming GPT Store, the possibilities for tailored AI experiences are expanding like never before.

To get started with ChatGPT, check out our Introduction to ChatGPT course and our ChatGPT cheat sheet. For more advanced users, you’ll find our tutorial on using GPT-3.5 and GPT-4 via the OpenAI API in Python a useful resource to get up to speed.


Photo of Richie Cotton
Author
Richie Cotton

Richie helps individuals and organizations get better at using data and AI. He's been a data scientist since before it was called data science, and has written two books and created many DataCamp courses on the subject. He is a host of the DataFramed podcast, and runs DataCamp's webinar program.

Topics

Start Your OpenAI Journey Today!

Course

Working with the OpenAI API

3 hr
11.6K
Start your journey developing AI-powered applications with the OpenAI API. Learn about the functionality that underpins popular AI applications like ChatGPT.
See DetailsRight Arrow
Start Course
See MoreRight Arrow
Related

You’re invited! Join us for Radar: AI Edition

Join us for two days of events sharing best practices from thought leaders in the AI space
DataCamp Team's photo

DataCamp Team

2 min

The Art of Prompt Engineering with Alex Banks, Founder and Educator, Sunday Signal

Alex and Adel cover Alex’s journey into AI and what led him to create Sunday Signal, the potential of AI, prompt engineering at its most basic level, chain of thought prompting, the future of LLMs and much more.
Adel Nehme's photo

Adel Nehme

44 min

The Future of Programming with Kyle Daigle, COO at GitHub

Adel and Kyle explore Kyle’s journey into development and AI, how he became the COO at GitHub, GitHub’s approach to AI, the impact of CoPilot on software development and much more.
Adel Nehme's photo

Adel Nehme

48 min

A Comprehensive Guide to Working with the Mistral Large Model

A detailed tutorial on the functionalities, comparisons, and practical applications of the Mistral Large Model.
Josep Ferrer's photo

Josep Ferrer

12 min

Serving an LLM Application as an API Endpoint using FastAPI in Python

Unlock the power of Large Language Models (LLMs) in your applications with our latest blog on "Serving LLM Application as an API Endpoint Using FastAPI in Python." LLMs like GPT, Claude, and LLaMA are revolutionizing chatbots, content creation, and many more use-cases. Discover how APIs act as crucial bridges, enabling seamless integration of sophisticated language understanding and generation features into your projects.
Moez Ali's photo

Moez Ali

How to Improve RAG Performance: 5 Key Techniques with Examples

Explore different approaches to enhance RAG systems: Chunking, Reranking, and Query Transformations.
Eugenia Anello's photo

Eugenia Anello

See MoreSee More