GraphRAG: Building a Smarter AI System (full walkthrough)

From the creator

πŸ“ˆ Get started with SerpApi for free πŸ‘‰ https://serpapi.link/thu-vu πŸ’» Git repo for this tutorial πŸ‘‰ https://github.com/thu-vu92/graphRAG πŸ“ Original Microsoft's GraphRAG paper πŸ‘‰ https://arxiv.org/pdf/2404.16130 🌟 Master Python and Build Awesome AI Projects πŸ‘‰ https://python-course-earlybird.framer.website/?&utm_source=lessonsdegree πŸ“© Get FREE weekly AI & data insights πŸ‘‰ https://thu-vu.ck.page/49c5ee08f6 πŸ”‘ TIMESTAMPS β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€β–€ 0:00 - Today's project 1:10 - SerpApi 1:35 - The problem with standard RAG 4:01 - What is GraphRAG 4:50 - When to use GraphRAG vs. standard RAG 5:54 - How GraphRAG works 6:41 - Scraping article data with SerpApi 15:01 - GraphRAG pipeline 15:27 - 1. Importing libraries 16:04 - 2. Configuration 17:14 - 3. Defining ontology 18:37 - 4. Graph extraction prompt 20:40 - 5. Pydantic data model 22:21 - 6. Extracting entities & relationships (and descriptions) 23:45 - 7. GraphRAGStore 24:46 - 8. Querying engine 26:10 - 9+10. Load article data 27:03 - 11. Build knowledge graph 29:44 - 12. Build communities & Generate summaries 30:24 - 13. Visualize graph with d3.js 32:01 - 14. Query the GraphRAG system 35:24 - Conclusions #graphrag #ai #ThuVu

Stop watching Β· start building
Matched to AI Agents

Makers residency 4th edition

Your idea can be anything. At our last workshops, people built plant-based nutrition businesses, a way to measure planetary resilience, crochet headwear and a way to connect lonely people living in the same building. An asset manager went on to raise an additional Β£25M on their fund within nine months. The fourth workshop is a full day at KOKO with Nick Sarafa, learning to build with Claude Code. Bring the thing you keep meaning to start. We’ll bring the pizza.

β—† Fri 13 Nov 2026 β—† KOKO, London
Makers residency 4th edition
Live event
Makers residency 4th edition
Fri 13 Nov 2026

More like this

Running one yourself?

List your AI event,
wherever it is.

A meetup, a workshop, a hackathon, a conference. Any city, or online. Tell us about it and it lands in front of people already learning this stuff.