Vector Search & RAG

AI/ML Engineering Track | Phase 3

Best for: learners building retrieval-backed LLM systems who need both the fundamentals and the local-first version of the stack.

This phase starts with core vector and RAG concepts, then extends into evaluation, long-context tradeoffs, and home-scale deployment choices.

Modules

#	Module
1.1	Vector Databases Deep Dive
1.2	Building RAG Systems
1.3	Advanced RAG Patterns
1.4	RAG Evaluation & Optimization
1.5	Long-Context LLMs and Prompt Caching
1.6	Home-Scale RAG Systems

Suggested Route

• start with 1.1 and 1.2 if you are new to RAG
• do 1.4 before you trust any production claims about retrieval quality
• use 1.6 if your real starting point is a laptop, workstation, or small private document corpus

After This Phase

• go to Frameworks & Agents if you want orchestration patterns
• go to MLOps & LLMOps if you need to move from experiments to repeatable systems