Lakehouse + Graph: Delta Lake, Unity Catalog and Neo4j for Governed AI Pipelines
summary
Demonstrates a practical pipeline pairing Delta Lake bronze/silver/gold with Neo4j to power GraphRAG and feature extraction, using the Neo4j Spark Connector for production reads/writes and the new Neo4j Connector for Unity Catalog (beta) to sync Unity Catalog metadata, RBAC, audit logs and data contracts. Describes text‑to‑Cypher LLM flow, Graph Data Science with ~60–65 algorithms, Delta time‑travel rollbacks, and a reference architecture plus code samples and a governance dashboard.
AI-written summary · about
chapters (7)
- 0:00Introduction and architecture
- 3:39Delta lake storage features
- 4:50Governance and integration
- 17:30GraphRAG implementations
- 18:20Fraud detection use case
- 18:33Use cases and best practices
- 23:36Summary and conclusion
related talks
28mLakehouse Architecture with Delta Lake and Databricks
45mBuilding a Lakehouse on the Microsoft Intelligent Data Platform
42mBuilding a Lakehouse data platform using Delta Lake, PySpark, and Trino
05mUnity Catalog Demo of New Features
38mGetting Started with Delta Lake
01h 28mBuilding Reliable, Open Lakehouses with Delta Lake
29mBuild simple & scalable data pipelines with Polars & DeltaLake
49mDelta Live Tables: Building Reliable ETL Pipelines with Azure Databricks