Retrieval-Augmented Generation (RAG)
Not Started0 / 10 complete
Open a video or resource link, watch it, then check its box to track your progress and unlock what comes next.
10 lessons3 levels1 capstone project
Build grounded LLM applications that retrieve relevant external knowledge before generation; master chunking, embeddings, indexing, retrieval, reranking, generation and RAG evaluation.
BASIC
- What Is Retrieval-Augmented Generation (RAG)? — IBM Technology (8 min)
Clear first-principles explanation of why RAG exists and how retrieval improves freshness, grounding and trust. - RAG From Scratch: Part 1 (Overview) — LangChain (15 min)
Excellent architecture-level walkthrough of indexing, retrieval and generation from a leading RAG framework team. - Learn RAG From Scratch — freeCodeCamp / LangChain (30 min selected)
Adds query translation, routing, advanced indexing and adaptive RAG patterns.
INTERMEDIATE
- Production RAG Agent — Google Cloud Tech
A deeper treatment of the same skill; use it to move from concept to working patterns. - Fine- tuning Open LLMs on GKE — Google Cloud Tech
Apply Retrieval-Augmented Generation (RAG) through the adjacent capability: Fine-Tuning & Model Adaptation. - Vector Databases Explained: Complete Guide — Aishwarya Srinivasan
Apply Retrieval-Augmented Generation (RAG) through the adjacent capability: Vector Databases.
ADVANCED
- Build an MCP Server in 20 Minutes — pixegami
Extend Retrieval-Augmented Generation (RAG) into senior/production practice through Tool Use & Function Calling. - Semantic Search with Pinecone — DataCamp
Extend Retrieval-Augmented Generation (RAG) into senior/production practice through Embeddings. - What Is a Vector Database? Beyond Coding - Search Is In Everything You Build — IBM Technology
Extend Retrieval-Augmented Generation (RAG) into senior/production practice through Search & AI Search.