Retrieval & RAG

Vector stores, hybrid retrieval and reranking, and when to retrieve instead of fine-tune.

14concepts
161flashcards
115minutes of reading
  1. 01 Choosing and Adapting an Embedding Model Why the top of the MTEB leaderboard is a bad way to pick an embedding model, what dimension, context length, and asymmetry actually cost you in production, and when fine-tuning on your own hard negatives beats buying a bigger model. intermediate 8m 15 cards
  2. 02 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. intermediate 8m 15 cards
  3. 03 Contextual Retrieval and Chunk Augmentation Chunks lose the context that made them meaningful; prepending a short LLM-written situating sentence to each chunk before embedding cuts retrieval failures by roughly a third, and the technique only became affordable because of prompt caching. intermediate 7m 15 cards
  4. 04 Fine-tuning vs RAG When to teach the model new behaviour vs when to retrieve fresh context at runtime. intermediate 8m 4 cards
  5. 05 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. intermediate 8m 5 cards
  6. 06 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. intermediate 8m 12 cards
  7. 07 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. intermediate 9m 15 cards
  8. 08 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. intermediate 8m 12 cards
  9. 09 Retrieval Augmented Generation The end-to-end RAG pipeline from chunking through retrieval, reranking, and grounded generation. intermediate 9m 5 cards
  10. 10 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. intermediate 9m 6 cards
  11. 11 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. advanced 9m 15 cards
  12. 12 Agentic and Iterative Retrieval Why a single retrieve-then-read pass cannot answer questions whose second search depends on the first result, and how retrieve-reason interleaving, self-reflection tokens, and search agents trade latency and cost for multi-hop accuracy. advanced 8m 15 cards
  13. 13 GraphRAG and Community Summarisation Why top-k retrieval cannot answer "what are the main themes in this corpus", how building an entity graph and pre-summarising its communities turns a global question into a map-reduce over summaries, and what that indexing bill buys you. advanced 8m 15 cards
  14. 14 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. advanced 8m 12 cards