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.
Speculative RAG: draft several, verify, pick
From: RAG That Thinks →A small model drafts several candidate answers in parallel, each from a different retrieved subset; a larger verifier model scores them and picks the best. Parallel drafting plus one verify beats a long serial loop.
A small model drafts several candidate answers in parallel, each from a different retrieved subset of the documents.
Agentic RAG: retrieval as a decision
From: RAG That Thinks →Retrieval becomes one tool among several. An agent routes a question to a source, grades what comes back, and loops to try another when a result is weak: vector index, web search, SQL, or a knowledge graph.
The agent routes the question to the vector index and grades the result: weak, the answer is not in the indexed documents. So it does not plough ahead.
GraphRAG local search
From: Beyond the Vector →Local search starts at the entity your question names and walks its neighbourhood in the knowledge graph, one hop at a time, gathering connected facts. Ideal for pointed questions about a specific thing.
Local search starts at the entity your question names, here “Ada”.