Leveraging Neo4j Graph Data and AI Across the App Development and Deployment Lifecycle
summary
Using the Neo4j movies dataset, AI generates Cypher queries, explains existing Cypher, runs vector searches and applies retrieval-augmented generation so templates produce publication-quality interactive analytics that actually return complex JSON graph results and drilldowns. The demo wires an assistant to OpenAI (also supports Vertex and Bedrock), auto-inserts embeddings (1536-dim plot embeddings and 512-dim poster embeddings), executes queries like find Sean Connory movies, and produces a GraphRAG commentary that summarizes similarities and revenues in real time.
AI-written summary · about
chapters (9)
- 0:00Introduction to AI in deployment
- 3:20AI for Cypher query authoring
- 5:08Context and data source design
- 6:14Vector similarity indices in queries
- 8:03User prompting and dynamic queries
- 9:05Formatting results with AI
- 9:25Retrieval augmented generation
- 10:10Embedding AI in applications
- 10:51Summary and prompt engineering
related talks
32mHarmonizing AI and Graphs: Building Intelligent Music Apps with Neo4j and AI
30mBuilding GenAI Apps with the LangChain Neo4j Package
30mLive-Coding Graph-Native Agents: Neo4j AuraDB + Microsoft Agent Framework in Action
28mData-Empowered AI Assistants
21mUI in The Age of AI
53mAgents, Tools, and Mcp, Oh My! Next Level AI Concepts for Developers
32mAgentic AI Governance: Data Foundations & Real-Time Policy Enforcement
15mAgentic GraphRAG: Simplifying Retrieval Across Structured & Unstructured Data