https://abhishekmurthy.com/tags/search/Recent content in search on Abhishek MurthyHugo -- gohugo.ioen-usMon, 24 Nov 2025 16:05:24 -0500https://abhishekmurthy.com/posts/search-engine-fits-in-l3-cache/Mon, 24 Nov 2025 16:05:24 -0500https://abhishekmurthy.com/posts/search-engine-fits-in-l3-cache/The first version of my search engine was slower after I added an index. That sounds backwards, but it is a real failure mode. A bad index can turn a simple sequential scan into a pile of cache misses, hash lookups, tiny heap allocations, branchy score calculations, and random memory walks. The CPU stops doing search and starts waiting for memory. The target I wanted was intentionally unreasonable: a local search engine for a few hundred thousand short technical records that could answer ranked queries inside an interactive UI budget, while keeping the hot path small enough to stay friendly to an L3 cache.https://abhishekmurthy.com/posts/rag-is-not-provenance/Fri, 20 Jun 2025 16:05:24 -0400https://abhishekmurthy.com/posts/rag-is-not-provenance/The easiest way to make a document extraction system look good in a demo is to hide the evidence. Ask a model to read a few PDFs, retrieve the top chunks, and fill a spreadsheet. If the answer looks plausible, ship the JSON. The failure usually arrives later, when somebody asks a very simple question: Where did this number come from? That question breaks a surprising number of systems. The value might be correct, but the cited source points at a row label.