Tag: vector-search

Parquet was built for scans; ML needs random access, fat embedding columns, cheap column backfills, and versioned datasets. A practitioner's look at the Lance format and LanceDB: what the peer-reviewable numbers actually show, where the hype outruns the evidence, and how it changes the dataloader and RAG designs from my earlier posts.

From naive vector search to industry-standard multimodal RAG. Master hybrid search, query rewriting, cross-encoder reranking, and the architecture of high-precision retrieval systems.