You're reading from Power BI Machine Learning and OpenAI

Product type Book

Published in May 2023

Publisher Packt

ISBN-13 9781837636150

Pages 308 pages

Edition 1st Edition

Languages

Python

Concepts

GPT/LLMs

Author (1):

Greg Beaumont

Table of Contents (21) Chapters

Preface

Part 1: Data Exploration and Preparation

Chapter 1: Requirements, Data Modeling, and Planning

Chapter 2: Preparing and Ingesting Data with Power Query

Chapter 3: Exploring Data Using Power BI and Creating a Semantic Model

Chapter 4: Model Data for Machine Learning in Power BI

Part 2: Artificial Intelligence and Machine Learning Visuals and Publishing to the Power BI Service

Chapter 5: Discovering Features Using Analytics and AI Visuals

Chapter 6: Discovering New Features Using R and Python Visuals

Chapter 7: Deploying Data Ingestion and Transformation Components to the Power BI Cloud Service

Part 3: Machine Learning in Power BI

Chapter 8: Building Machine Learning Models with Power BI

Chapter 9: Evaluating Trained and Tested ML Models

Chapter 10: Iterating Power BI ML models

Chapter 11: Applying Power BI ML Models

Part 4: Integrating OpenAI with Power BI

Chapter 12: Use Cases for OpenAI

Chapter 13: Using OpenAI and Azure OpenAI in Power BI Dataflows

Chapter 14: Project Review and Looking Forward

Index

Why subscribe?

Other Books You May Enjoy

Use Cases for OpenAI

In the previous chapter, you scored fresh data via the Power BI ML models and assessed the output in comparison to the automated testing performed by Power BI during the training phase. The FAA Wildlife Strike database provided fresh data that was generated in the real world beyond the scope of the training and testing datasets. This data could potentially serve as a framework for scheduling the scoring of new data utilizing a Power BI ML model in collaboration with dataflows. The recently evaluated data produced outcomes that were relatively consistent with the expected results derived from the testing data.

In this chapter, you are tasked by your stakeholders to incorporate OpenAI functionalities into the solution. OpenAI is garnering a lot of attention in the IT sector, and this project is being implemented during this trend. Although this entails a change in scope, the project’s beneficiaries are fully supportive of and optimistic about this initiative...

Technical requirements

The requirements are slightly different for this chapter:

An account with the original open source OpenAI: https://openai.com/.
Optional – Azure OpenAI in your Azure subscription: https://azure.microsoft.com/en-us/products/cognitive-services/openai-service. The book is written so that this is optional since it is not available to everyone at the time of publication.
FAA Wildlife Strike data files from either the FAA website or the Packt GitHub site.
A Power BI Pro license.
One of the following Power BI licensing options for access to Power BI dataflows:
- Power BI Premium
- Power BI Premium Per User
One of the following options for getting data into the Power BI cloud service:
- Microsoft OneDrive (with connectivity to the Power BI cloud service)
- Microsoft Access + Power BI Gateway
- Azure Data Lake (with connectivity to the Power BI cloud service)

Brief overview and reference links for OpenAI and Azure OpenAI

In the latter part of 2022, the global media and information technology enthusiasts were captivated by the potential of ChatGPT. ChatGPT is a vast large language model (LLM) chatbot that facilitates natural language communication, code generation, and other functionalities, and was developed by OpenAI.

OpenAI

OpenAI is an AI research organization, and interested readers may find more information about it at this link: https://openai.com/about.

The renowned ChatGPT is constructed utilizing generative pre-training (GPT) models, and OpenAI also produces other types of AI models such as DALL-E for image generation. This book abstains from delving into OpenAI’s intricate details, as there is already a plethora of information available on the internet.

The OpenAI platform is constructed upon Microsoft’s Azure cloud infrastructure, which provides a powerful and reliable foundation for the platform’...

Generating descriptions with OpenAI

Our first step will be to identify a suitable use case for leveraging the power of GPT models to generate descriptions of elements of FAA Wildlife Strike data. Our objective is to unlock the potential of external data by creating prompts for GPT models that can provide detailed information and insights about the data we are working with. Through this use case, we will explore the value that GPT models can bring to the table when it comes to data analysis and interpretation.

For example, a description of the FAA Wildlife Strike database by ChatGPT might look like this:

Figure 12.2 – OpenAI ChatGPT description of FAA Wildlife Strike database

Within your solution using the FAA Wildlife Strike database, you have data that could be tied to external data using the GPT models. A few examples include additional information about the following:

Airports
FAA regions
Flight operators
Aircraft
Aircraft...

Summarizing data with OpenAI

You can also use OpenAI GPT models to summarize data. Numerous databases feature free text fields that comprise entries from a diverse array of sources, including survey results, physician notes, feedback forms, and comments regarding incident reports for the FAA Wildlife Strike database that we have used in this book. These text entry fields represent a wide range of content, from structured data to unstructured data, making it challenging to extract meaning from them without the assistance of sophisticated natural language processing tools.

The Remarks field of the FAA Wildlife Strike database contains text that was presumably entered by people involved in filling out incident forms about aircraft striking wildlife. A few examples of the remarks for recent entries are shown in Power BI in the following screenshot:

Figure 12.6 – Examples of remarks from the FAA Wildlife Strike database

You will notice that the remarks...

Choosing GPT models for your use cases

OpenAI and Azure OpenAI offer several different GPT models that can be called iteratively using an API. At the time of writing this book, there is limited availability of the new GPT-4 models, which are the latest and greatest releases. The GPT-3.5 models are available in both OpenAI and Azure OpenAI, with a few different options. The following information was referenced on March 26, 2023, from the OpenAI website at this link: https://platform.openai.com/docs/models/gpt-4.

...

Summary

In this chapter, you have delved into the fundamental concepts associated with OpenAI and Microsoft Azure OpenAI, and how these platforms can be employed to generate and summarize text. Moreover, you have explored several options for integrating GPT models from both OpenAI and Azure OpenAI into your Power BI solution using FAA Wildlife Strike data. Following a careful evaluation process, it has been determined that the text-davinci-003 GPT model will be utilized for the summarization of remarks present in FAA Wildlife Strike data reports, and for generating novel descriptive information about airplanes within the reports.

Chapter 13 will be dedicated to the implementation of functions within Power BI dataflows, enabling the seamless calling of OpenAI and Azure OpenAI REST APIs for data. These APIs will facilitate the successful implementation of your summarization and descriptive generation use cases, thereby providing new capabilities for your solution to address the challenges...

The rest of the chapter is locked

You have been reading a chapter from

Power BI Machine Learning and OpenAI

Published in: May 2023 Publisher: Packt ISBN-13: 9781837636150

A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.

Unlock this book and the full library FREE for 7 days

Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of

Start free trial

Renews at $15.99/month. Cancel anytime}

Authors (1)

Greg Beaumont

Greg Beaumont is a data architect at Microsoft, where he enjoys identifying and solving complex problems backed by his experience in data architecture and a passion for innovation. Focusing on the healthcare industry, Greg works closely with customers to plan enterprise analytics strategies, evaluate new tools and products, conduct training sessions and hackathons, and architect solutions that improve the quality of care and reduce costs. He strives to be a trusted advisor to his customers and is always seeking new ways to drive progress and help organizations thrive. He is a veteran of the Microsoft data speaker network and has worked with hundreds of customers on their data management and analytics strategies.

See other products by Greg Beaumont

Personalised recommendations for you

Based on your interests and search pattern

Et al.

Ever wonder why speech recognition systems don't understand the Scottish accent, or what would happen if an astronaut only ate mac 'n' cheese, or other spurious reflections you'd have at a bar? We did, then collated those deliberations into absurd research articles with fake figures and methodologies inspired by even more fictionally absurd studies.

Aug 2023 7 hours 40 minutes

Generative AI with LangChain

This book is a comprehensive introduction to LLMs and LangChain, demystifying the basic mechanics of LangChain, its functionalities, and the myriad of applications it can be integrated into.

Dec 2023 12 hours 0 minutes

Generative AI with LangChain

This book is a comprehensive introduction to LLMs and LangChain, demystifying the basic mechanics of LangChain, its functionalities, and the myriad of applications it can be integrated into.

Dec 2023 12 hours 0 minutes

Generative AI with LangChain

This book is a comprehensive introduction to LLMs and LangChain, demystifying the basic mechanics of LangChain, its functionalities, and the myriad of applications it can be integrated into.

Dec 2023 12 hours 0 minutes

Generative AI with LangChain

This book is a comprehensive introduction to LLMs and LangChain, demystifying the basic mechanics of LangChain, its functionalities, and the myriad of applications it can be integrated into.

Dec 2023 12 hours 0 minutes

Mastering Tableau 2023

This book is a comprehensive resource to mastering your Tableau skills and becoming a BI expert. As you progress, you will learn how to build advanced dashboards and improve your storytelling to derive key business insight, as well as make you well-versed with advanced functionalities of Tableau in the business intelligence domain.

Aug 2023 22 hours 48 minutes

Building AI Applications with ChatGPT APIs

This guide covers all ChatGPT API features for effortless creation of robust AI powered apps. With its help, you’ll be able to leverage ChatGPT’s cutting-edge NLP models to take your app development skills to the next level. You’ll also work on ten exciting projects that will give you the practical know-how that you can apply to your existing applications.

Sep 2023 8 hours 36 minutes

Building AI Applications with ChatGPT APIs

Sep 2023 8 hours 36 minutes

Data Engineering with AWS

Embark on a journey to master data engineering pipelines on AWS! Our book offers a hands-on experience of AWS services for ingesting, transforming, and consuming data. Whether you're an absolute beginner or someone with basic data engineering experience, this guide is an indispensable resource.

Oct 2023 21 hours 12 minutes

Modern Data Architecture on AWS

Every organization wants an agile, performant, and cost-effective data platform that meets all their current and future business needs. Purpose-built AWS analytics services and their features play a big part in building such a modern data platform. This book brings to you all the design and architectural patterns that’ll help you achieve this goal.

Aug 2023 14 hours 0 minutes

Practical Guide to Applied Conformal Prediction in Python

Discover the power of Conformal Prediction with the "Practical Guide to Applied Conformal Prediction in Python." Master the latest techniques to quantify uncertainty in machine learning and computer vision models, and seamlessly apply them to your industry applications.

Dec 2023 8 hours 0 minutes

TinyML Cookbook

With over 70 project-based recipes, the TinyML Cookbook is a practical guide that will help you to get the most out of your microcontrollers. It provides a comprehensive understanding of the theoretical foundations while giving you hands-on experience training ML models for deployment on Arduino Nano 33 BLE Sense, Raspberry Pi Pico, and SparkFun RedBoard Artemis Nano microcontrollers.

Nov 2023 22 hours 8 minutes

Latest model	Description	Max tokens	Training data
gpt-3.5-turbo	Most capable GPT-3.5 model and optimized for chat at one-tenth the cost of text-davinci-003. Will be updated with our latest model iteration.	4,096 tokens	Up to September 2021