GraphRAG for Supply Chain Resilience: Building an AI Supplier Discovery Engine

Session Track: AI Engineering

Session Time: 04:00 pm - 04:15 pm November 6

Session description

European public procurement data is a goldmine for supply chain intelligence but is often trapped in unstructured, multilingual silos. This lightning talk presents the architecture of a cross-border knowledge graph built in Neo4j that transforms fragmented public data into an engine for regional resilience. We will provide an overview of our GraphRAG architecture, which combines vector search with rich graph context to ground LLMs for nuanced, real-time queries. We will also demonstrate how graph data science algorithms move beyond simple keyword search to enable advanced capability mapping and agentic workflows. Attendees will get insights into how to build a production-ready, multilingual GraphRAG system and the key lessons learned from deploying it in a real-world GovTech environment.