Graph Database - DACH (Germany, Austria, Switzerland )

Register: https://www.meetup.com/de-DE/hamburg-data-science-meetup/events/310344244/

Welcome to the August version of our Data Science + Machine Learning Meetup Hamburg!

Neo4j Session:

Martin Preusse, Partner & Founder, Kaiser & Preusse 🔗 LinkedIn
Neurosymbolic AI with LLMs and Knowledge Graphs

This talk outlines a neurosymbolic approach—combining neural LLMs with symbolic knowledge graphs and ontologies—for practical data-science workflows. We’ll introduce GraphRAG: building a graph from your corpus and using graph structure and summaries to retrieve context, contrasted with text-only RAG. We’ll then use ontologies and SHACL constraints as machine-checkable contracts to scope prompts and validate model outputs. Finally, we’ll discuss using LLMs for entity harmonization and for bootstrapping vocabularies/ontologies, with notes on accuracy, cost, and human oversight. For context, we’ll situate these patterns in recent work on neurosymbolic AI.

Register: https://www.meetup.com/de-DE/cologne-ai-and-machine-learning-meetup/events/305829303/

We will have two talks with additional time for networking.
Talk 1: Tomaz Bratanic (Graph ML and GenAI research at Neo4j): Agentic GraphRAG with MCP servers
Talk 2: Pablo Iyu Guerrero (AI Inference Engineer at Aleph Alpha) and Lukas Blübaum (AI Engineer at Aleph Alpha): Tokenizer-free language model inference