Generative Artificial Intelligence with the OpenAI API for Developers
Published by Pearson
Easily deploy ChatGPT, DALL-E, and CODEX in your own applications
- Learn about the OpenAI API structure and how you can use it
- Develop practical applications that leverage the power of each model
- See how to combine different models to increase their functionality
OpenAI is the current leader in publicly available AI models, with state-of-the-art tools like ChatGPT, Codex, and Dall-E being accessible to everyone online. OpenAI also provides powerful and modular APIs that allow programmers to leverage the functionality of these models directly into their applications.
In this workshop, we will introduce the main concepts behind this class of models and how their functionality is published through the API. We will combine the tools provided by OpenAI to answer questions on a topic with ChatGPT, generate image variations from a text prompt with DALL-E, create a textual description of an image, and generate code from a prompt.
What you’ll learn and how you can apply it
By the end of the live online course, you’ll understand:
- The structure of the OpenAI API
- Large language models
- How to combine different models in a single application
And you’ll be able to:
- Apply GPT-3 and GPT-4 models to your own content
- Leverage Codex to generate and understand code automatically
- Use Dall-E to programmatically generate images from text
This live event is for you because...
The typical audience member will be a software engineer or programmer who is interested in getting up to speed with the latest state-of-the-art generative models provided by OpenAI and learning how to leverage them in their own applications. The primary audience member will be someone who is proficient with the Python programming language and interacting with APIs but has no experience with the OpenAPI functionality. The course is designed around practical applications to best get attendees up and running as quickly as possible.
Prerequisites
- Basic Python
- NumPy
- Matplotlib
- Jupyter
Course Set-up
- Python
- Pandas
- Matplotlib
- Jupyter
- OpenAI
- The GitHub link provides all the notebooks and any data files required to run the code: https://github.com/DataForScience/OpenAI
Recommended Preparation
- Attend: LLMs, GPT and Prompt Engineering for Developers by Sinan Ozdemir
- Attend: Using Open- and Closed-Source LLMs in Real World Applications by Sinan Ozdemir
- Watch: Introduction to Transformer Models for NLP by Sinan Ozdemir
Recommended Follow-up
- Read: Quick Start Guide to Large Language Models: Strategies and Best Practices for using ChatGPT and Other LLMs by Sinan Ozdemir
- Attend: LLMs from Prototypes to Production while Optimizing for Real-World Applications by Sinan Ozdemir
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Segment 1: Generative AI and OpenAI (50 min)
- Basic Principles
- Transformers
- Large Language Models
- Temperature
- Hallucinations
- Image Models
- API Structure
Break (10 min)
Q&A (5 min)
Segment 2: GPT Models (50 min)
- Basic Usage
- Input Formatting
- Multi-step Prompts
- Document summarization
Break (10 min)
Q&A (5 min)
Segment 3: Embeddings (30 min)
- Understanding Embeddings
- Question Answering
- Recommendations
- Long Texts
Segment 4: Image Generation (30 min)
- DALL-E Model
- DALL-E vs GPT-4
- Generating Images from a Prompt
- Image Variations
- Prompt Expansion with GPT
Break (5 min)
Segment 5: Code Generation and Explanation (30 min)
- CODEX Model
- Generating Code from a Prompt
- Explaining Existing Code
- Generating Comments
Course wrap-up, Q&A, and Next Steps (15 min)
Your Instructor
Bruno Gonçalves
Bruno Gonçalves is currently a Head of Data Science working at the intersection of AI, Blockchain Technologies, and Finance. Previously, he was a Data Science Fellow at NYU's Center for Data Science while on leave from a tenured faculty position at Aix-Marseille Université. Since the completion of his PhD in the Physics of Complex Systems in 2008, he has pursued the use of Data Science and Machine Learning to the large-scale study of human behavior. In 2015, he was awarded the Complex Systems Society's Junior Scientific Award for "outstanding contributions in Complex Systems Science," and in 2018 he was named a Science Fellow of the Institute for Scientific Interchange in Turin, Italy.