Book Image

Power Platform and the AI Revolution

By : Aaron Guilmette
Book Image

Power Platform and the AI Revolution

By: Aaron Guilmette

Overview of this book

In this AI era, employing leading machine learning and AI models such as ChatGPT for responding to customer feedback and prototyping applications is crucial to drive business success in the competitive market. This book is an indispensable guide to integrating cutting-edge technology into business operations and leveraging AI to analyze sentiment at scale, helping free up valuable time to enhance customer relationships. Immerse yourself in the future of AI-enabled application development by working with Power Automate, Power Apps, and the new Copilot Studio. With this book, you’ll learn foundational AI concepts as you explore the extensive capabilities of the low-code Power Platform. You’ll see how Microsoft's advanced machine learning technologies can streamline common business tasks such as extracting key data elements from customer documents, reviewing customer emails, and validating passports and drivers’ licenses. The book also guides you in harnessing the power of generative AI to expedite tasks like creating executive summaries, building presentations, and analyzing resumes. You’ll build apps using natural language prompting and see how ChatGPT can be used to power chatbots in your organization. By the end of this book, you’ll have charted your path to developing your own reusable AI automation patterns to propel your business operations into the future.
Table of Contents (16 chapters)

So, what’s a token?

I’m glad you asked! This will come up when you’re interacting with ChatGPT (or other language models and services). In the context of ChatGPT, a token is the smallest unit of text that the model processes. It could be as small as a single character, commonly used groups of letters, prefixes, and suffixes, or even whole words, depending on how the model is configured.

From a cost and billing perspective, models typically charge you based on how many tokens you’re submitting and how many tokens you’re getting back as a response. Let’s use the example prompt featured in Figure 3.2 – What are three side dishes I can serve with pizza?

Using a tool such as OpenAI’s Tokenizer, you can figure out how much this request is going to cost to send:

Figure 3.3 – Viewing the Tokenizer’s result

Figure 3.3 – Viewing the Tokenizer’s result

As you can see, this request costs 11 tokens. The area at the bottom shows how OpenAI...