Build AI Agents Using OpenAI REST APIs
Published by O'Reilly Media, Inc.
Create and leverage AI Agents using HTTP REST calls
What you’ll learn and how you can apply it
- Understand how AI agents can unlock the next generation of experiences for AI-based applications for your customers, users, and employees
- Learn about the types of problems agents can solve compared to traditional uses of ChatGPT and other large Language models Quickly create AI agents with OpenAI APIs
- Get familiar with multi-agent architectures and learn about the best practices for working with confidential, sensitive, and personal data sources
- Discover the new types of applications and services that can be created with efficient use of AI agents
Course description
State-of-the-art AI models used by ChatGPT are able to solve complex problems and provide users with answers in natural language, but they can only answer within the context of content they’ve been trained on. AI models lack the capability to answer even the most basic questions regarding your professional or your personal lives. These types of questions can only be answered using an AI agent. Join Bruce Hopkins to learn how to create and leverage AI agents using HTTP REST calls, which can be implemented in any language.
This live event is for you because...
- You’re a software developer who needs to create AI-based applications and services to connect to corporate, confidential, or personal data sources.
- You’re familiar with ChatGPT, but you want to learn the best practices for creating intelligent applications that leverage ChatGPT and OpenAI APIs.
- You’re a technical manager who wants to understand the capabilities and benefits of AI agents.
Prerequisites
- A basic understanding of programming in any major programming language, such as how to interact with HTTP REST APIs and make HTTP calls
- Experience with HTTP tools like Postman or cURL (helpful, but not mandatory)
- Some experience using ChatGPT or LLMs
- (Optional) Postman installed on your machine (to participate in exercises)
- (Optional) An API key for OpenAI (to participate in exercises)
- (Optional) An IDE configured with your preferred programming language to execute HTTP REST calls
Recommended preparation:
- Read ChatGPT for Java (book)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Understanding the problems that AI agents can solve (30 minutes)
- Presentation: Problems that ChatGPT can solve with and without agents
Creating your first app using the ChatGPT APIs (35 minutes)
- Presentation: First steps with OpenAI APIs
- Hands-on exercise: Use OpenAI APIs to invoke ChatGPT programmatically
- Q&A
- Break
The benefits of enhancing your application with the Resourses API (30 minutes)
- Presentation: Improving the user experience—best practices for remembering previous interactions
- Hands-on exercise: Get started with the Assistants API
- Q&A
Getting familiar with multi-agent architectures (35 minutes)
- Presentation: Configuring tool calls for multi-agent architectures
- Hands-on exercise: Configure your agent with tool calls
- Q&A
- Break
Creating an AI agent for file searching (30 minutes)
- Presentation: Loading and searching within external files
- Hands-on exercise: Load and search within files
- Q&A
Utilizing multiple AI agents for a single problem (35 minutes)
- Presentation: Why is it so hot in here?
- Hands-on exercise: Leveraging multiple AI agents
- Q&A
- Break
Protecting sensitive data in your AI agent (35 minutes)
- Presentation: Keeping private and sensitive information secure when using ChatGPT
- Demonstration: Securing your data
- Q&A
Wrap-up (10 minutes)
- Presentation: New business opportunities and next steps
Your Instructor
Bruce Hopkins
Bruce Hopkins is a technical writer, an AI expert, an Intel Software Innovator for AI, and an Oracle Java Champion. He’s also the author of ChatGPT for Java and the coauthor of Beginning ChatGPT for Python.
Skills covered
- OpenAI
- Web APIs
- GPT