Jakob Leander Müller
Hey, Im Jakob. I have studied Data Science in my Bachelors and Masters and currently work at a fin-tech where Im involved in all kinds of projects. My main goal is creating things that are actually useful and not just full of buzz-words. Im a big fan of visualizing things and always make sure that anyone who is interested in the topics Im working on can follow the reasoning of the chosen approach.
Session
Traditional RAG systems struggle to understand holistic connections in distributed, constantly changing knowledge sources that characterize real-world organizations. While document-based approaches using vector embeddings provide basic retrieval, they fail to capture relationships and answer complex questions about interconnected information. Graph-based RAG offers a solution, but existing implementations like Microsoft's GraphRAG explicitly avoid dynamic operations due to complexity, requiring costly rebuilds when knowledge changes.
This talk introduces a production-ready dynamic knowledge graph system that supports real-time insertion, querying, and deletion of information. Through practical implementation details you will learn to build maintainable knowledge graphs that evolve with data, handle ambiguous entities and preserve information lineage.