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
- Sign in to track this item
Why RAG; embeddings; vector DB; cosine KEY
RAG from First Principles - Ankit BansalvideoDEEP38m
- Sign in to track this item
Build a real RAG app
Ed Donner - LLM Engineering, Wk5 (knowledge-worker) ↗repoDEEPUdemy
3b · Advanced retrieval (the gap)
- Sign in to track this item
Hybrid search: BM25 + dense + RRF
Production RAG w/ LangChain & Vector DBs - freeCodeCamp ↗videoDEEP7h38m
- Sign in to track this item
Reranking (cross-encoders/ColBERT)
Advanced RAG techniques - Field Guide to AI ↗articleDEEP9m read
- Sign in to track this item
Query transforms (HyDE, multi-query)
Advanced RAG: hybrid, reranking, query expansion ↗articleDEEPread
- Sign in to track this item
Chunking: parent-child, sentence-window
12 Advanced RAG Techniques (2026) - Atlan ↗articleDEEPread
- Sign in to track this item
GraphRAG / RAPTOR / Contextual Retrieval
Same Atlan guide (techniques 8-12) ↗articleDEEPread
3c · RAG evaluation (RAGAS) [KEY]
- Sign in to track this item
Metrics: faithfulness, context precision/recall
RAG Evaluation, RAGAS explained - Logical Lenses ↗videoDEEP12m
- Sign in to track this item
RAGAS hands-on in Python
RAG Evaluation Metrics Tutorial - Analytics Vidhya ↗videoDEEP6m