RAG Core Study Series (26 parts)

RAG Core Study Series (26 parts)

Retrieval, chunking, embedding, hybrid, reranking, routing — 26 parts to build and run RAG

---

Prerequisites	LLM Core Study Series (recommended)
Next series	Agent / Evaluation / Tooling Series (upcoming)

All parts

1	RAG Core Study (1/26) — What RAG Is and Why You Need It
2	RAG Core Study (2/26) — Document Preprocessing & PDF→Markdown Pipeline
3	RAG Core Study (3/26) — Ingestion Design: Document Boundary, Model-aware Schema, Filter-first Retrieval
4	RAG Core Study (4/26) — OCR & Layout Analysis
5	RAG Core Study (5/26) — Five Paths of Chunking
6	RAG Core Study (6/26) — Contextual Chunking: Parent-Child & Contextual Retrieval
7	RAG Core Study (7/26) — Metadata Design: Filters, Permissions, Provenance
8	RAG Core Study (8/26) — Embedding Models: BGE-M3 / OpenAI / Upstage / E5 / Jina / Voyage
9	RAG Core Study (9/26) — Vector DB Showdown: FAISS / Chroma / Qdrant / Milvus / Weaviate / Pinecone / pgvector
10	RAG Core Study (10/26) — Dense Retrieval Deep Dive
11	RAG Core Study (11/26) — Sparse Retrieval & BM25 Deep Dive
12	RAG Core Study (12/26) — Hybrid Search & Score Fusion
13	RAG Core Study (13/26) — Reranker: The Role of Cross-encoders
14	RAG Core Study (14/26) — Evaluation Sets with RAGAS & DeepEval
15	RAG Core Study (15/26) — Search Quality Metrics: Recall@K, MRR, NDCG, Hit Rate
16	RAG Core Study (16/26) — Experiment Automation with LangSmith, Phoenix, and MLflow
17	RAG Core Study (17/26) — Query Classification: Typing the User Question
18	RAG Core Study (18/26) — Query Rewrite & Expansion: HyDE, Step-back, Multi-query
19	RAG Core Study (19/26) — Query Routing: Multi-Retriever and Collection Routing
20	RAG Core Study (20/26) — Dynamic Sparse-Dense Weighting
21	RAG Core Study (21/26) — Adaptive Top-K and Conditional Reranking
22	RAG Core Study (22/26) — Search Confidence and Corrective RAG
23	RAG Core Study (23/26) — Graph RAG: Knowledge Graphs Meet Vectors
24	RAG Core Study (24/26) — Agentic RAG: Planning, Tool Use, Verification
25	RAG Core Study (25/26) — Security, Permissions, and Re-indexing Operations
26	RAG Core Study (26/26) — Personal-Documents RAG Capstone and Roadmap

Recommended pace

Each part takes 25–40 minutes on average. One to three parts per week is the sweet spot for retention.