xParse Document Parsing Tool

Author: intsig-textin
Version: 0.0.1
Type: tool

Description

xParse Document Parsing Tool extracts structured content from various file formats (PDF, WORD, EXCEL, PPT, images, etc.) and converts them into queryable and analyzable structured elements.

Provider Credentials

When configuring the plugin in Dify, you need to provide the following credentials:

Get your credentials: Please log in to Textin and go to Workspace → Account Settings → Developer Information to view your and .

Parameter	Type	Required	Description
	secret-input	Yes	Textin application ID. Please log in to Textin and go to "Workspace → Account Settings → Developer Information" to view x-ti-app-id. See API Documentation for details.
	secret-input	Yes	Textin secret code. Please log in to Textin and go to "Workspace → Account Settings → Developer Information" to view x-ti-secret-code. See API Documentation for details.

Parse Input Parameters

The xParse Parse tool provides parameters to customize the processing of documents.

The only required parameter is – the file you wish to process.

Main Parameters

Type	Required	Default	Description
file	Yes	-	The file to be parsed (supports PDF, WORD, EXCEL, PPT, images, etc.)
select	No		The document parsing provider/engine to use. Options: (Recommended), , ,
string	No	-	Password for encrypted PDF files
string	No	-	Specify page ranges to parse. Format: for page 15, for pages 20-25, for pages 1, 3, 5, 6, 7
select	No		Whether to perform crop and dewarp preprocessing. Options: (No), (Yes)
select	No		Whether to remove watermark preprocessing. Options: (No), (Yes)
boolean	No		Whether to return page images (for PDF and other formats that need to be converted to images)
boolean	No		Whether to return sub-images within pages

TextIn Engine Specific Parameters

The following parameters only apply when is set to :

Type	Required	Description
select	No	PDF parsing mode. Options: (extract text directly from PDF), (treat PDF as images). Note: Images always use scan mode
select	No	Control underline recognition range (only for scan mode). Options: (No recognition), (Only recognize underlines without text)
select	No	Whether to enable chart recognition. Recognized charts will be output as tables. Options: (No), (Yes)

Advanced Parameters

Parameter	Type	Required	Default	Description
	string	No	-	JSON format S3 storage configuration for storing page images. Includes: , , , , , ,

Notes

For more details on each parameter, refer to the xParse Parse Documentation.
Some parameters are only available for specific providers or file types.
Default values are shown where applicable.

API Response Structure

Top-Level Fields

The tool returns structured data with the following fields:

Field	Type	Description
	string	The full parsed content in Markdown format, including images, sections, etc.
	array of object	List of structured content blocks (sections, paragraphs, images, tables, etc.)
	array of object	List of image objects extracted from the content (if or is enabled)

Field Details

text

Type: string
Description:
The entire content, formatted in Markdown. This includes images (as markdown image syntax), headings, paragraphs, and other formatting for direct rendering.

elements

Type: array of objects
Description:
List of structured content blocks. Each object represents a section, paragraph, image, table, or other content element extracted from the document.

Each element object contains:

Field	Type	Description
	string	Unique identifier for the element (SHA-256 hash of text + coordinates + page number + filename)
	string	The type of element (e.g., , , , , )
	string	The text content of the element
	object	Metadata for the element (see below for details)

metadata (object)

The field provides detailed information about the element's origin, layout, and context.

Common fields include:

Field	Type	Description
	string	Name of the source file (e.g., )
	string	MIME type or file type (e.g., )
	string	Timestamp of last file modification
	integer	Page number in the source file (if applicable)
	integer	Width of the page in pixels
	integer	Height of the page in pixels
	array	8-element array representing quadrilateral coordinates (normalized, range [0, 1])
	string	ID of the parent element
	integer	Depth in the document hierarchy
	string	Base64 encoded image data (if is enabled)
	string	MIME type for images (e.g., )
	string	URL for page image (if is enabled)
	string	URL for original page image (if preprocessing is enabled)
	string	Preview URL for images (after uploading to Dify)
	string	Unique file ID for images in Dify
	string	HTML representation for tables or rich text elements
	object	Data source information including record locator, URLs, version, dates

images

Type: array of objects
Description:
List of images found in the content (only returned if or is enabled). Each image object contains:

Field	Type	Description
	string	Unique image ID (Dify file ID)
	string	Image file name
	string	MIME type of the image
	string	URL for image preview
	integer	Image file size in bytes
	string	Always

Example Response

JSON Structure

Usage

Install this plugin in Dify
Configure Provider credentials ( and )
Use the Parse tool in Workflow or Agent applications
Upload a file and configure parsing parameters
Get parsed structured content and images

API Reference

Notes

The field is suitable for direct display in web or app frontends.
The field is useful for structured processing, highlighting, or further analysis.
The field provides all image resources for preview or download.
The object in each element may contain additional fields depending on the extraction process and file type.
Image processing:
- When is enabled, images () are automatically decoded and uploaded to Dify's file system. Their and are included in the response , and images are added to the list.
- When is enabled, page image URLs () are directly included in the response and are not uploaded to Dify's file system.