Adaptive RAG: Routing Between the Series' Five Strategies

A linear, one-concept-per-lesson path through Adaptive RAG, classifying each question and routing it to whichever of naive, hybrid, graph, corrective, or agentic retrieval actually fits, from a single-tier router to a complete FastAPI service wiring in the real implementations from courses 1-5. 26 lessons · 3 tiers.

Prerequisites: You should complete naive_rag, hybrid_rag, graph_rag, corrective_rag, and agentic_rag before starting this course - Lesson 2 recaps what each is good and bad at, but assumes you've already built and watched each one fail firsthand.

Lessons use Google's Gemini free tier (gemini-3.5-flash-lite) via direct google-genai calls, no LangChain, no LlamaIndex. No Docker, no database, no extra account - GOOGLE_API_KEY in a .env file is the only setup, and no new dependency beyond what courses 1-5 already installed.

Built directly on google-genai, Gemini's native SDK, routing to real implementations from five prior courses rather than a new retrieval mechanic of its own.