Vector Retrieval Infrastructure

The chapters in this module, in reading order.

#	Chapter
00	Vector retrieval infrastructure — First-principles overview
01	Why traditional SQL indexes fail here — exact rows are not meaning neighborhoods
02	Vector similarity metrics — the ruler decides the answer
03	Brute force baseline — perfectly correct, painfully expensive
04	IVF clustering — search only nearby buckets, not the whole warehouse
05	HNSW graph — shortcut roads over the warehouse floor
06	Product quantization — smaller tags, cheaper memory, fuzzier geometry
07	Metadata filtering — the aisle sticker can rescue or ruin search
08	Hybrid search — exact words and semantic meaning, both together
09	Index lifecycle — build, update, and rebuild without downtime
10	Scaling and sharding — one warehouse becomes many buildings
11	Managed services and database choices — pick your pain carefully
12	Embedding management — the scanner changes, so the tags change too
13	Monitoring and debugging — if recall falls quietly, users notice loudly
14	Honest admission — what vector databases still do not solve cleanly