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.
Navigate vs grab: vectorless retrieval
From: Vectorless RAG →The same question against the same structured document, two ways. Navigate the table-of-contents tree root to leaf by reasoning, or grab the top chunks by similarity and watch them arrive scattered and out of context. Similarity is not relevance.
- 1. Getting Started
- 2. Compensation and Benefits
- 2.1 Salary
- 2.2 Health Insurance
- 2.3 Paid Time Off
- 3. Workplace Policies
- 4. Equipment and Returns
- 4.1 Company Laptops
- 4.2 Returning Equipment
- 4.3 Defective Devices
- 5. Leaving the Company
Start at the top. Read the section titles and pick the branch that fits the question.
How a vectorless index is built
From: Vectorless RAG →The full index-building algorithm, step by step, the way tree-index systems like PageIndex do it: parse pages, detect or generate the table of contents, split into overlapping page-groups, extract and number the hierarchy, locate and verify every section, then summarize each node. Each step is labelled as an LLM call or deterministic code. No embeddings, no chunking anywhere.
The PDF is read into a list of pages. Each page is tagged with its number, like <physical_index_7>, so every later step can point back to exact pages. Nothing is embedded or chunked.
The text-analysis pipeline
From: Text Analysis →Type a sentence and watch raw text become the terms an index stores: tokenize, lowercase, drop stopwords, then stem to a root. The same pipeline runs on your query too.