Harmonizing AI and Graphs: Building Intelligent Music Apps with Neo4j and AI
summary
Graph of ~200 nodes uses Neo4j for artists, albums, producers and text summaries with embeddings and a Spring Boot app uses Spring AI to inject a chat client and callable repository methods as tools; three live queries show: first returns three correct artists (Coldplay, Radiohead, Tame Impala), second matches flamenco/Latin roots semantically but drifts, third hallucinates plausible but incorrect collaborations — tool chaining is brittle; adding the JVM agent framework Embable produces reproducible goal‑oriented playlists by planning paths, selecting albums via embedding math, and summarizing the journey.
AI-written summary · about
chapters (6)
- 0:00Introduction to graph AI
- 3:54Setting up the graph tools
- 10:49Chatting with the graph
- 16:57Limitations of LLM tool chains
- 20:42Agentic flows with Embabel
- 27:43Playlist generation demo
related talks
29mAgentic AI with Knowledge Graphs on the JVM: A Music Graph in Practice
12mLeveraging Neo4j Graph Data and AI Across the App Development and Deployment Lifecycle
30mBuilding Smarter Mobile Apps with On-device AI Agents & GraphRAG
45mConcerto for Java & AI - Building Production-Ready LLM Applications
21mUI in The Age of AI
53mAgents, Tools, and Mcp, Oh My! Next Level AI Concepts for Developers
08mHarness Graph Power With Agentic AI: An Insights Discovery Use Case
29mNext-Gen Travel Agents: Merging AI Agentic and Neo4j for Personalized Experiences