GraphRAG for Supply Chain Resilience: Building an AI Supplier Discovery Engine
summary
Architecture converts fragmented multilingual EU procurement CSVs into a Neo4j cross-border knowledge graph that powers a GraphRAG stack combining vector search and graph context to ground LLMs. A Danish SAS pilot cleans messy tables to extract suppliers and capabilities; later scaling consolidates 40,000+ validated suppliers across the Nordics. Uses graph data science (centrality, community detection, pathfinding) plus an agentic pipeline to auto-identify, validate and outreach to suppliers for rapid crisis sourcing.
AI-written summary · about
chapters (7)
- 0:00Introduction to GraphRAG
- 1:27Why tackle procurement challenges
- 4:35GraphRAG approach explained
- 8:13Knowledge graph core concepts
- 9:37Demo of supplier discovery tool
- 11:44Nordic-level supplier analysis
- 13:29Q&A and collaboration
related talks
01h 40mKnowledge Graphs & GraphRAG: Techniques for Building Effective GenAI Applications
39mEnhancing RAG with Neo4j Knowledge Graph
24mEmpowering Lifelong Learning: Transforming Data into Insights With GraphRAG
23mGraphRAG for Increased Trust and Confidence in GenAI for Manufacturing Processes
31mBuilding a Customer-Intelligence Brain: How GraphRAG Turns Data into Decisions
15mAgentic GraphRAG: Simplifying Retrieval Across Structured & Unstructured Data
36mAgentic GraphRAG: AI’s Logical Edge
17mEnhancing Chat-Based Customer Recommendations With GraphRAG and Hybrid Search