Visualizers
Learn by moving things
Interactive explainers for the ideas behind retrieval, embeddings, and agents. A formula tells you what is true; dragging a vector shows you why. Each one also appears inside the article it belongs to, and runs entirely in your browser, so drag, poke, and break it.
Query rewriting
From: A Field Guide to RAG →A messy, context-dependent question ('and how much does it cost?') is unsearchable on its own. Query rewriting resolves the context and produces a clear, standalone query the index can match.
On its own the follow-up is unsearchable: the index has no idea what “it” refers to.
Query expansion / multi-query
From: A Field Guide to RAG →One wording can miss documents that use different words. Multi-query fans the question into several phrasings, searches all of them in parallel, and pools the results, catching passages a single phrasing would have missed.
You start with a single wording, which may not match documents that use different words.
HyDE: search from a made-up answer
From: A Field Guide to RAG →A question sits far from the passages that answer it on the embedding map. HyDE drafts a rough made-up answer, which lands beside the real answer passages because it is shaped like one, and searches from there. The guess is discarded; the real passages it found are read.
The question is worded nothing like the passages that answer it, so it sits far away on the map and pulls back weak matches.