Retrieval (RAG) — Course Notes
These notes follow the Ultimate RAG Bootcamp section-by-section, so each note maps to exactly what's taught in the course. I'm writing them up in my own words as I go, with the key ideas, the code I understand, and the gotchas.
Progress: Sections 1–14 studied — foundations through vector stores, advanced chunking, hybrid search, query enhancement, multi-modal RAG, the updated LangChain v1 essentials, and LangGraph basics. Sections 15–29 are coming soon; I publish each as I finish it.
Course progress~48% · 14 / 29 sections
Course progress tracker
| # | Section | Status |
|---|---|---|
| 1 | Introduction | ✅ Done |
| 2 | Introduction to RAG | ✅ Done |
| 3 | Core Components in RAG | ✅ Done |
| 4 | VS Code & Anaconda Installation | ✅ Done |
| 5 | Data Ingestion & Data Parsing Techniques | ✅ Done (10/10) |
| 6 | Vector Embedding & Vector Databases | ✅ Done (5/5) |
| 7 | Vector Stores & Vector Databases | ✅ Done (13/13) |
| 8 | Advanced Chunking & Preprocessing | ✅ Done (4/4) |
| 9 | Hybrid Search Strategies | ✅ Done (8/8) |
| 10 | Query Enhancement | ✅ Done (4/4) |
| 11 | Multi-Modal RAG | ✅ Done (2/2) |
| 12 | Getting Started with AI Agents & Agentic AI | ⏳ Notes pending |
| 13 | Updated LangChain Hands-On (v1) | ✅ Done |
| 14 | LangGraph Basics | ✅ Done (16/16) |
| 15 | Agents Architecture | 🔲 Soon |
| 16 | Agentic RAG | 🔲 Soon |
| 17 | Autonomous RAG | 🔲 Soon |
| 18 | Multi-Agent RAGs | 🔲 Soon |
| 19 | Corrective RAG | 🔲 Soon |
| 20 | Adaptive RAG | 🔲 Soon |
| 21 | RAG with Persistent Memory | 🔲 Soon |
| 22 | Cache RAG with LangGraph | 🔲 Soon |
| 23 | VectorLess RAG with PageIndex | 🔲 Soon |
| 24 | Guardrails | 🔲 Soon |
| 25 | LLM Gateways | 🔲 Soon |
| 26 | Chatbot & RAG Evaluation | 🔲 Soon |
| 27 | Graph Databases & Cypher with LangChain | 🔲 Soon |
| 28 | Practical GraphDB with LangChain | 🔲 Soon |
| 29 | End-to-End RAG Document Search Project | 🔲 Soon |
What's live now
- Section 1 · Introduction
- Section 2 · Introduction to RAG
- Section 3 · Core Components in RAG
- Section 4 · VS Code & Anaconda Setup
- Section 5 · Data Ingestion & Parsing
- Section 6 · Vector Embedding & Vector Databases
- Section 7 · Vector Stores & Vector Databases
- Section 8 · Advanced Chunking & Preprocessing
- Section 9 · Hybrid Search Strategies
- Section 10 · Query Enhancement
- Section 11 · Multi-Modal RAG
- Section 13 · Updated LangChain (v1) Hands-On
- Section 14 · LangGraph Basics
- LangChain vs LangGraph vs LangSmith vs Langflow