Knowledge Graphs

Knowledge graphs are powerful data structures that represent information as a network of interconnected entities and relationships. Unlike traditional databases, knowledge graphs store data in a way that mimics human-like understanding of concepts and their associations. At their core, knowledge graphs consist of nodes (representing entities) and edges (representing relationships between entities), forming a flexible and intuitive representation of complex information.

In the context of LLMs and artificial intelligence, knowledge graphs serve as a bridge between unstructured data and machine-readable formats. They excel at capturing the nuanced connections within large datasets, making them particularly valuable for tasks that require reasoning across multiple pieces of information.

Required Reading and Listening

Listen to the podcast:

(Click here for transcript)

Read the following:

1. Summary Blog: Knowledge Graphs in LLM Development

2. Textbooks:

   • Chapter 6. Knowledge and Memory in Michael Albada, Building Applications with AI Agents, 1st ed., Published by O’Reilly Media, Inc., ISBN-13 978-1098176495. This book is available in print and digital on O’Reilly Media.

   • Chapter 2. Building Knowledge Graphs in Jesus Barrasa, Amy E. Hodler, Jim Webber, “Knowledge Graphs”, O’Reilly Media Inc. This book is available in print and digital on O’Reilly Media.

   • Chapter 7. Building Scalable Knowledge-Graph-Based RAG with Wikipedia API and LlamaIndex in Denis Rothman, “RAG-Driven Generative AI”, O’Reilly Media Inc. This book is available in print and digital on O’Reilly Media.

3. Paper: Shirui Pan, Senior Member, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu, Unifying Large Language Models and Knowledge Graphs: A Roadmap[PDF]

More resources can be found on the resource page Knowledge Graphs