Retrieval & RAG
Vector stores, hybrid retrieval and reranking, and when to retrieve instead of fine-tune.
10concepts
74flashcards
84minutes of reading
- 01 Chunking Strategies for Retrieval Why the unit you index decides the ceiling on retrieval quality, how fixed, recursive, semantic and contextual chunking differ, and what each one loses.
- 02 Fine-tuning vs RAG When to teach the model new behaviour vs when to retrieve fresh context at runtime.
- 03 Hybrid Retrieval - BM25 + Vector + Reranking Why pure vector search misses exact-match queries, how RRF combines lexical and semantic results, and where a cross-encoder reranker buys back the precision you lost.
- 04 Query Transformation for Retrieval Why the user's question is often a bad search query, and how rewriting, decomposition, multi-query fan-out and HyDE close the gap between how people ask and how documents are written.
- 05 RAG Evaluation and Groundedness How to separate retrieval failures from generation failures, which metrics actually diagnose each stage, and why groundedness is measurable while helpfulness mostly is not.
- 06 Reranking and Cross-Encoders Why a second-stage model that reads the query and document together fixes most retrieval failures, what it costs in latency, and how to size the candidate set.
- 07 Retrieval Augmented Generation The end-to-end RAG pipeline from chunking through retrieval, reranking, and grounded generation.
- 08 Vector Databases Compared - pgvector, Qdrant, Milvus, Weaviate, LanceDB A practitioner's guide to picking a vector store, weighing index trade-offs against the operational cost of running yet another database alongside your primary store.
- 09 ANN Indexes: HNSW, IVF and PQ How approximate nearest neighbour indexes trade recall for latency and memory, what HNSW, IVF-PQ, ScaNN and DiskANN each optimise for, and why recall is a knob rather than a property.
- 10 Late Interaction and Multi-Vector Retrieval How ColBERT-style models keep one vector per token instead of one per document, why MaxSim recovers most cross-encoder quality at index-time cost, and what the storage bill looks like.