Vibing with Data -- Multi-Agent Data Modeling and Constructi...
summary
Describes a concrete multi-agent pipeline that takes files to a runnable knowledge graph by iterating: clarify intent, discover relevant CSV/markdown, propose a schema, verify mappings, then execute a batched import and entity/fact extraction; includes a structured-data agent, unstructured-data agent and a graph RAG agent that ties vectors to nodes. Implements with Neo4j and Google ADK, published as DeepLearning.AI notebooks plus an MIT‑licensed GitHub repo, and the system produces actionable plans before execution.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:04Knowledge graphs inevitable
- 3:51Relational joins to graph
- 8:27Graph modeling best practices
- 9:49LLMs to multi-agent systems
- 14:00Multi-agent knowledge graph builder
- 17:30Agents for structured/unstructured data
- 23:09Extracting text knowledge
- 28:01Executing graph plan
- 33:20Benefits of agentic construction
- 34:24Resources and next steps
related talks
15mGraphRAG-Powered AI Agents: Transforming Corporate Metadata into Intelligent Knowledge
01h 29mBuild Your Own Data Science AI Agents
52mSerg Masís | AI Track | Compass AI & Data Summit 2025
14mEmpowering Voice AI Agents with Real-Time Knowledge from Neo4j
01h 04mGraph Theory for Multi-Agent Integration: Clinical Use Cases
15mAgentic GraphRAG: Simplifying Retrieval Across Structured & Unstructured Data
01h 17mGraph Database and Retrieval Augmented Generation
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI