Agentic GraphRAG: Simplifying Retrieval Across Structured & Unstructured Data
summary
Builds a pipeline that extracts entities from PDFs, loads embeddings and structured ETL into Neo4j graph, uses LangChain decomposition and Pydantic to produce JSON, an ADK agent plus an MCP tool generating Cypher runs graph queries. On a resume corpus for “Cyberdine Systems” aggregation returns 28 Python developers and similarity search identifies Sarah as the closest match to Lucas using overlap scoring. Adding HR project data creates collaborator edges so queries return exact collaborator lists and explainable answers; end-to-end notebooks and code are provided.
AI-written summary · about
chapters (10)
- 0:00Introduction to graph rag
- 0:40Knowledge graph architecture
- 1:54Use case and data overview
- 2:37Vector search limitations
- 4:46Need for analytics
- 5:51Constructing the graph
- 7:48Graph RAG implementation
- 9:47Enhancing query precision
- 12:19Expanding data models
- 14:00Collaboration analytics
related talks
29mAgentic GraphRAG: Multi-Agent Knowledge Graph Construction for Research Teams
36mGraphRAG Explained 🔥 Building Smarter LLMs
01h 17mGraph Database and Retrieval Augmented Generation
24mAgentic GraphRAG: AI’s Logical Edge
12mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
15mGraphRAG-Powered AI Agents: Transforming Corporate Metadata into Intelligent Knowledge
21mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
25mEnhancing Job Matching With Knowledge Graphs and RAG