AI Agents in Action cover
welcome to this free extract from
an online version of the Manning book.
to read more
or

3 Engaging GPT assistants

 

This chapter covers

  • Introducing the OpenAI GPT Assistants platform and the ChatGPT UI
  • Building a GPT that can use the code interpretation capabilities
  • Extending an assistant via custom actions
  • Adding knowledge to a GPT via file uploads
  • Commercializing your GPT and publishing it to the GPT Store

As we explore the OpenAI crusade into assistants and what has been hinted at, ultimately, an agent platform called GPT Assistants, we’ll introduce GPT assistants through the ChatGPT interface. Then, we’ll add in several fully developed assistants that can suggest recipes from ingredients, fully analyze data as a data scientist, guide readers through books, and be extended with custom actions. By the end of the chapter, we’ll be ready to build a fully functional agent that can be published to the OpenAI GPT Store.

3.1 Exploring GPT assistants through ChatGPT

3.2 Building a GPT that can do data science

3.3 Customizing a GPT and adding custom actions

3.3.1 Creating an assistant to build an assistant

3.3.2 Connecting the custom action to an assistant

3.4 Extending an assistant’s knowledge using file uploads

3.4.1 Building the Calculus Made Easy GPT

3.4.2 Knowledge search and more with file uploads

3.5 Publishing your GPT

3.5.1 Expensive GPT assistants

3.5.2 Understanding the economics of GPTs

3.5.3 Releasing the GPT

3.6 Exercises

Summary