Chunkbook.

Cut a long document into labelled parts that fit in a model's context — along its own chapter boundaries, or along ranges you set by hand.

runs in this browser
nothing is uploaded
pdf · txt · md
One — Source
WHY

A long book won't fit in one chat. Sending it in random slices breaks sentences and loses the thread.

WHAT THIS DOES

Cuts the book at its own chapter boundaries, and writes on each piece which part it is and which pages it covers.

WHAT YOU GET

A folder of numbered files. Hand them to a model one at a time — each one says where it sits in the book.

Drop a PDF, TXT or Markdown file

Or choose one. Large files are fine — the whole thing stays on your machine.

Reading…
—File
—Pages
—Words
—Est. tokens
—Outline entries
This book has no text layer. The pages are images, so there is nothing to read, label or cut into text.

Chunkbook does not do OCR and there is no plan to add it. Turning pictures of pages back into text is a separate job, and doing it badly is worse than not doing it at all. If you need the text, run the file through an OCR tool first and bring the result back here.

Compressing the file won't help either — a model would still have to look at every page as a picture. What you can do right now is use Manual ranges below to cut this PDF into smaller PDFs by page range.
The printed page numbers don't match the PDF.
Everything below — the ranges you type and the labels you get — uses whichever you pick.
look like a table of contents or an index — . These are lists of page numbers rather than prose, so they cost tokens and tell a model nothing.
Reading the bar below. It is the whole file, left to right. Red ticks are the chapter headings that were found. Blue is covered by a part, gold is covered twice, grey is not covered at all.
A token is roughly three quarters of an English word — a 6,000-token part is about 4,500 words.
part heading overlap not covered contents / index
Two — Cutting

Cut along the book's own structure

Headings come from the book's built-in outline when it has one, and are worked out from type size and numbering when it doesn't. Works in any language.

What this book is made of

Pick the unit to cut at. Anything still too big is broken down further using the headings inside it.

Fine tuning
Detected structure
This book has no outline and no headings could be worked out from the text, so it has been cut into even parts instead. Switch to manual ranges if you want to place the cuts yourself.

Cut at page ranges you choose

Name each part and give it a first and last page. Any language — nothing here depends on reading the text. Add as many ranges as you like; they may overlap, and they don't have to cover the whole file.

#Part nameFirst pageLast pageEst. tokens
No ranges yet. Add one, or fill the file evenly.
Three — Parts

Parts

Four — Something wrong?

Tell us what broke

This tool guesses a great deal: where chapters begin, which pages are contents, how the printed numbering lines up. When it guesses wrong on your book, that is worth knowing — the fix is usually small, once someone can see what happened.

What gets included

Nothing leaves this page until you press a button below, and nothing is gathered in the background. No page content, no file name, nothing personal — only numbers describing how the tool behaved. Edit or delete any of it.