Why retrieval — not the model — caps your whole system, how embeddings and ANN actually work, the embedding choices that move the needle, and the three production shapes of RAG you must pick between before you write a line.

• →Embeddings and Vector Search
• →Production RAG Architecture

The unglamorous decision that silently caps every RAG system — chunking failure modes, sizing by metric, parsing as the real bottleneck, late chunking, Anthropic’s contextual retrieval, small-to-big, and how systems like Cursor chunk at scale.

• →Chunking and Context
• →Production RAG Architecture

Dense misses exact tokens; BM25 misses paraphrase. How BM25 actually scores, why you fuse with RRF, the multi-stage pipeline Perplexity and Uber run in production, sparse-neural retrievers, and when hybrid isn’t worth it.

• →Hybrid Retrieval and Reranking

The precision stage: how cross-encoders differ from bi-encoders, reranking (the highest-ROI upgrade), ColBERT late interaction, query transforms, and when GraphRAG, agentic retrieval, and long-context are worth it vs hype.

• →Hybrid Retrieval and Reranking
• →Production RAG Architecture

What breaks only at scale — HNSW/IVF/IVFPQ memory economics, the build-vs-buy decision, the silent freshness graveyard, multi-tenant permission leaks, and caching/cost — with case studies from Perplexity, Harvey, Notion and LinkedIn.

• →Production RAG Architecture
• →Embeddings and Vector Search

Prove it works without fooling yourself: the IR retrieval metrics, split retrieval vs generation eval, where RAGAS metrics lie, LLM-as-judge biases & calibration, golden sets, observability, drift, and prompt-injection in the retrieval path.

• →RAG Evaluation
• →Production RAG Architecture

Assemble the whole pipeline into a permission-aware, cited, evaluated assistant over private docs — the full ingest-to-answer architecture, the numbers to defend, and a rehearsal of the decisions an interviewer (or an incident) will push on.

• →Production RAG Architecture
• →RAG Evaluation