Graph RAG: Knowledge-Graph-Based Retrieval

A linear, one-concept-per-lesson path through Graph RAG, the knowledge-graph-based retrieval architecture, from extracting entities and relationships by hand to a complete FastAPI service combining networkx graph traversal with ChromaDB hybrid retrieval. 26 lessons · 3 tiers.

Prerequisites: Comfortable writing basic Python. Assumes you've done this site's Naive RAG and Hybrid RAG courses (or otherwise know what dense retrieval, embeddings, and cosine similarity are) - this course builds on that foundation by extracting entities and relationships into a graph instead of retrieving chunks. Distinct from this site's pggraph course, which teaches the Postgres AGE extension and Cypher, not the Graph RAG architecture itself.

Lessons use Google's Gemini free tier (gemini-embedding-001 for embeddings, gemini-3.5-flash-lite for chat), the same models as this site's other RAG courses. No Docker, no database, no extra account - GOOGLE_API_KEY in a .env file is the only setup.

Built on networkx, the graph library this course graduates to in the Advanced tier.