Interactive · no API key, no install

Take it apart.

The five playgrounds from the lesson, on one page. Everything runs in your browser. Playgrounds 02 and 05 use real precomputed OpenAI vectors; the rest is exact browser code.

Playground 01

When do you actually need RAG?

Corpus scale explorer drag the slider
0
tokens
0
chunks @800
$0
to embed once
0
of a 2M window

Embedding cost assumes text-embedding-3-small at $0.02 per million tokens. One-off, not per question.

Playground 02

The neighbourhood map

Real embeddings · text-embedding-3-small click any word to make it the probe
cat
probe word
closest
furthest

These are genuine 1,536-dimension OpenAI vectors, precomputed by tools/export_slide_data.py. The map is a 2-D projection of all 1,536.

Playground 03

Watch the chunks re-cut

Chunking playground overlap is highlighted in each chunk
0
chunks
0
avg chars
0%
duplicated
0
est. tokens
Playground 04

Ask, and watch the prompt build

Retrieval playground highlighted chunks are the ones sent
annual leave laptop budget when is payday what is the capital of France
0
prompt tokens
0
document tokens
0%
sent to model
0.00
top score

Scoring here uses character-trigram vectors so the page runs with no API key. The mechanism is identical; demo 07 does the same thing with real embeddings.

Playground 05

Flip the model, break the system

Same store · same question · different query model real precomputed scores
0.00
top score
model used for the question
0
errors raised

Now take the lesson →