NODES 2025 - Crafting a Neo4j Knowledge Graph Semantic Reasoner for LPG-Based Ontologies with Python and CDC

5.0 (1)

9 learners

What you'll learn

This course includes

51.3 hours of video
Certificate of completion
Access on mobile and TV

Summary

Keywords

neo4j graph databases graphs LLM retrieval augmented generation RAG vector database vector search GenAI AI Artificial intelligence nodes25

Full Transcript

Knowledge graphs offer robust solutions for modeling complex relationships, yet developing dynamic, reasoning-driven applications with ontology-like semantics remains a significant challenge. In this session, Pierre Halftermeyer will guide you through constructing a Neo4j-based semantic reasoner using Python, utilizing Change Data Capture (CDC) for real-time updates, and will propose a labeled property graph (LPG) equivalent to RDF ontologies. You will explore key concepts such as semantic reasoning, graph modeling, CDC integration, and ontology mapping while leveraging Cypher and Python. By the end, you will learn to design and implement a scalable knowledge graph reasoner, process dynamic data changes, map LPG to ontological structures, and apply semantic inference to address real-world problems effectively. Speaker: Pierre Halftermeyer Resources: Get Started with Aura - https://bit.ly/3LOLrjh Deployment Center - https://bit.ly/4jOelM3 Ground AI Systems and Agents with Neo4j - https://bit.ly/4oVsnyb #nodes2025 #neo4j #graphdatabase #graphrag #knowledgegraph