Learn LLM Path / pillar 3 of 10
Deeper track: heavier resources for job-ready depth. Concepts you already checked stay checked.
build RAG that works in production. Biggest hidden gap - basic tutorials stop at "embed + top-k," real systems need hybrid search, reranking, evaluation
3a · Foundations
Why RAG; embeddings; vector DB; cosine KEY
RAG from First Principles - Ankit BansalvideoDEEP38m
Build a real RAG app
Ed Donner - LLM Engineering, Wk5 (knowledge-worker)repoDEEPUdemy
3b · Advanced retrieval (the gap)
Hybrid search: BM25 + dense + RRF
Production RAG w/ LangChain & Vector DBs - freeCodeCampvideoDEEP7h38m
Reranking (cross-encoders/ColBERT)
Advanced RAG techniques - Field Guide to AIarticleDEEP9m read
Query transforms (HyDE, multi-query)
Advanced RAG: hybrid, reranking, query expansionarticleDEEPread
Chunking: parent-child, sentence-window
12 Advanced RAG Techniques (2026) - AtlanarticleDEEPread
GraphRAG / RAPTOR / Contextual Retrieval
Same Atlan guide (techniques 8-12)articleDEEPread
3c · RAG evaluation (RAGAS) [KEY]
Metrics: faithfulness, context precision/recall
RAG Evaluation, RAGAS explained - Logical LensesvideoDEEP12m
RAGAS hands-on in Python
RAG Evaluation Metrics Tutorial - Analytics VidhyavideoDEEP6m