Retrieval & RAG
Vector stores, hybrid retrieval and reranking, and when to retrieve instead of fine-tune.
14concepts
161flashcards
115minutes of reading
- 01 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.
- 02 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.
- 03 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.
- 04 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.