GraphRAG Hands-On Knowledge Graphs for RAG

What you'll learn

---

Recognise the three question types that make vector RAG fail and explain why
Build and walk a knowledge graph by hand, then extract entities and relations with an LLM
Configure and run Microsoft GraphRAG indexing and read its outputs
Use local and global search and answer multi-hop questions
Estimate the token cost of GraphRAG and decide when it is worth it
Requirements

---

A computer with Python 3.10+ (a free Google Colab account is enough for most sessions)
Comfort reading Python code; you do not need to be an expert
An OpenAI API key or a local Ollama installation
Basic familiarity with LLM APIs and embeddings
Description

---

This course contains the use of artificial intelligence.
The voice-over in this course is synthesized with a text-to-speech model from scripts written and reviewed by the instructor, and the on-screen material (notebooks, code, slides) is the instructor's own work.
Vector RAG works until the question needs more than one chunk. Multi-hop questions, global summary questions and questions about relations all fail the same way: the right chunk is never retrieved, because the answer lives in the connections between documents. GraphRAG fixes that with a knowledge graph - and this course shows exactly how, on a small fictional corpus with planted facts so you can verify every answer by hand.
Session 1 builds a naive RAG pipeline from scratch and breaks it on purpose on three question types. Session 2 covers knowledge-graph fundamentals: nodes, edges, building a graph by hand with NetworkX, walking it, and LLM-based entity and relation extraction with a prompt you can read. Session 3 is Microsoft GraphRAG hands-on: installation, the settings file line by line, the indexing pipeline, and the entities, relationships and communities it produces. Session 4 covers querying: local versus global search and what each is for, multi-hop reasoning, community visualisation, token cost, and - importantly - when not to use GraphRAG.
Every session is a notebook shown on screen while the narration explains each cell; the notebooks work with OpenAI or with a local Ollama model. Cost is measured, not assumed.
The follow-up course, *GraphRAG in Production*, takes this to real public documents with evaluation, provenance and agents.
Who this course is for

---

Developers who have built a RAG chatbot and hit its limits
Data and knowledge engineers evaluating knowledge-graph retrieval
Teams considering Microsoft GraphRAG and needing a realistic cost picture
Anyone who wants to understand retrieval beyond similarity search
Homepage

---