The human brain is divided into two hemispheres and each specializes in different types of tasks. Your right brain is great at imagination, intuition, art, rhythm, feelings, and dreams. While the left brain is more analytical and focused on logic, sequencing, linear thinking, and mathematics. Just like a human brain, generative AI excels at certain tasks, especially those to do with right-brain creative activities. However, in the absence of relevant and up-to-date information this produces confusing hallucinations that are not grounded in reality. In this presentation we will explore how knowledge graphs built with factual and updated information can be used to complement LLMs via graph retrieval augment generation (GraphRAG) in order to produce more reliable results.
Stephen Chin
Neo4j
Stephen Chin is VP of Developer Relations at Neo4j and author of The Definitive Guide to Modern Client Development, Raspberry Pi with Java, Pro JavaFX Platform, and the DevOps Tools for Java Developers title from O'Reilly. He has keynoted numerous conferences around the world including Devoxx, DevNexus, JNation, JavaOne, Joker, swampUP, and Open Source India. Stephen is an avid motorcyclist who has done evangelism tours in Europe, Japan, and Brazil, interviewing hackers in their natural habitat. When he is not traveling, he enjoys teaching kids how to do AI, embedded, and robot programming together with his daughters.