Document Cutter

Document Cutter is a Dify tool plugin for extracting selected page ranges from PDF, Word, and Excel files. It can return either structured text chunks or a same-format binary file through Dify's native file output.

Features

Supports PDF (), Word (), Excel (), and legacy Excel () inputs.
Extracts pages as text chunks for downstream LLM processing.
Returns same-format files for selected ranges, such as PDF to PDF, DOCX to DOCX, and XLSX to XLSX.
Supports flexible page range syntax: , , , , or empty for all pages.
Processes files locally inside the Dify plugin runtime.

Tools

Split Document

Parameters:

Type	Required	Description
file	Yes	Source document file.
select	Yes	returns text chunks. returns a selected-range file.
string	No	1-based inclusive page range. Empty means all pages.
number	No	Text mode only. Groups every N pages into one chunk.
string	No	Optional output file base name without extension.

Page Range Examples

Input	Meaning
	Pages 1 through 2
	Page 5 through the end
	First 3 pages
	Page 7 only
empty	All pages

For Word documents, page boundaries are based on manual page breaks stored in the DOCX file. For Excel documents, pages refer to sheet indexes.

Output Modes

returns JSON containing extracted chunks and metadata.

returns JSON metadata, workflow variables, and a Dify blob message containing the generated file.

Privacy

All processing is performed in the Dify plugin runtime. No document content is sent to third-party services.

License

MIT