Tagged vector databases · show all articles
Retrieval is sold as a cheap fix for a model that does not know your data. Embedding compute, vector storage, ANN queries, reranking, and index freshness are five separate meters running underneath it, and none of them appear in the price of the model call.
Two axes decide what retrieval-augmented generation becomes by 2035: whether evidence-gathering stays a separate, inspectable step, and whether what it returns can be verified. Crossing them gives four futures, and current evidence does not yet pick one.
A production retrieval system is not one architecture but six coupled engineering decisions — chunking, hybrid weighting, reranking, access control, index freshness, and what gets watched once it is live.