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.
Summary indexing
From: How RAG Reads a Corpus →Index a short summary of each document so matching is fast and topical, but when a summary matches, retrieve the full source document behind it and read from that.
Only a short summary of each document is indexed, so matching is fast and topical: the IT policy summary wins.
RAPTOR: retrieve at the right altitude
From: How RAG Reads a Corpus →RAPTOR builds a tree of summaries over the raw chunks. Retrieval lands at the right level: a detailed question matches a leaf chunk, a broad question matches a high-level summary node that already condensed the span.
The same index holds the corpus at every level of abstraction, so a broad, whole-section question matches a summary node that already condensed the relevant span.
A CDN serves you from the nearest edge
From: CDNs: The Cache Nearest Your Users →Instead of a round trip to one far origin, a CDN keeps copies of your content in edge locations near users. A request is served from the nearest edge in a few milliseconds, not the far origin hundreds away.
A user in Tokyo is served from the Tokyo edge in about 9 ms, instead of the round trip to the far origin at roughly 160 ms. The copy is kept close, so the trip is short.