This one teaches you to build RAG systems that understand relationships between entities, not just semantic similarity. You'll extract entities and connections from documents, store them in Neo4j, then retrieve context by traversing the graph. It covers three retrieval patterns: entity-centric (expand from query entities to neighbors), path-based (find connections between entities), and community-based (the Microsoft GraphRAG approach with hierarchical clustering). The integration examples with LangChain are solid, including natural language to Cypher queries. Use this when your data has meaningful connections and you need multi-hop reasoning, like "How is X related to Y through Z?" Standard vector search can't do that.
npx skills add https://github.com/latestaiagents/agent-skills --skill graphrag-patterns