KNOWLEDGE, EMBEDDINGS & RAG • 119 / 397
Teach models to look up relevant information before answering.
HNSW
HNSW is a graph-based approximate nearest-neighbor indexing method widely used for vector search.
Think of it like
Think of HNSW like a library system: instead of memorizing every book, find the right shelf and bring only the useful pages to the desk.
Real life
Search engines and recommendation systems use ideas related to HNSW.
SRE lens
An SRE may tune HNSW index settings when retrieval latency or memory becomes an issue.
Remember thisHNSW is a graph-based approximate nearest-neighbor indexing method widely used for vector search.