1 Knowledge graphs and LLMs: a killing combination
This chapter covers
- Introduction to Generative AI and, in particular, Large Language Models (LLMs)
- The four pillars of knowledge graphs (KGs)
- How KGs and LLMs can be combined
- The application of knowledge graphs in multiple domains
In recent years, artificial intelligence (AI) has contributed to reaching unprecedented advances in many areas, helping to develop a new generation of systems to support decision-making and several other complex applications. New Generative AI [1] technologies – with their capability to “generate” text, images, and videos – are making new waves in diverse business areas. For example, ChatGPT, a chatbot that interacts with users through a web interface, was made publicly accessible on November 30, 2022, by the San Francisco company called OpenAI [2] . Users can have a conversation with it, ask it to write code, summarize a long piece of text, and do many other similar tasks. In a few days, it reached 1 million users, and in a few months more than 100 million. It was the beginning of a new era. On the wave of this success, other companies made similar generative AI tools accessible and easy to use to a broader public – outside of the small circle of Machine Learning practitioners and Data Scientists – extending enormously the user base and the type of applications.