1 Introduction to the use of generative AI in data analytics

As the dust over the generative AI hype begins to settle and the notes of disappointment mix in with the chorus of praises, it may be a good time to ask yourself a question: “If LLMs aren’t the silver bullet to all world problems, what are they really good for?” Our experience using these amazing tools to improve various processes gave us the answer. They are really good, and we mean really good in supporting improvements for different processes. Throughout this book, we will guide you through our methods for utilizing the enormous potential hidden in the matrices of generative AI to improve your analytics skills without falling victim to the risks inherent in this technology.

1.1 Inherent limitations of generative AI models

1.2 The role of generative AIs in data analytics

1.2.1 Generative AI in the data analytics flow

1.2.2 The complementarity of language models and other data analytics tools

1.2.3 Limits of generative AIs’ ability to automate and streamline data analytics processes

1.3 Getting started with generative AIs for data analytics

1.3.1 Web interface

1.3.2 Beware of tokens

1.3.3 Accessing and using the API

1.3.4 Third-party integrations of generative AI models

1.3.5 Running LLMs locally

1.3.6 Best practices and tips for successful generative AI implementation

Summary