Markdown Cleaner for RAG · emploidai Marketplace
emploidai Marketplace
Add-onsAppletsPlugins
Search tools, teams, and capabilitiesPublish
MarketplacePluginsMarkdown Cleaner for RAG
Plugin
Limited listing

Markdown Cleaner for RAG

by fangyong20062006 · v0.0.4

Clean Markdown documents to boost retrieval quality in Dify knowledge bases (parent-child chunking). Supports both file upload (.md) and direct text input from previous workflow nodes. A 12-step pipeline removes header/footer noise, fixes cross-page sentence breaks, protects clause numbers, repairs garbled symbols, normalizes terminology, and deduplicates chunks by MD5.

299 installsUpdated Jul 14, 2026
Publisher information is incomplete

This community listing does not yet include every recommended support, privacy, pricing, and permission disclosure. Review the available package permissions before installing.

Capabilities

Tools

Available inside your emploidai workspace after installation.

Data sources

Available inside your emploidai workspace after installation.

Category

tool

Version

0.0.4fangyong20062006

Requirements

Maximum memory 256MB

Pricing

Not disclosed by publisher

Security & access

Review before installing

CompatibleRequires emploidai 1.0.0+

Permissions

  • Uses tool capability

Dependencies

No additional dependencies

Resources

Privacy policy
emploidai Marketplace

Discover capabilities. Review access. Install inside your workspace.

DocumentationSecuritySupportPrivacyTerms

Markdown Cleaner for RAG

Clean Markdown documents to boost retrieval quality in Dify parent-child knowledge bases.

Features

A 12-step pipeline that handles:

  • Header/footer noise removal
  • Cross-page sentence repair
  • Clause number protection
  • Garbled symbol fixing
  • Terminology normalization
  • MD5-based chunk deduplication

Supports both input modes:

  • File upload: Upload a .md file directly
  • Text input: Paste Markdown text directly or pipe from a previous workflow node (e.g. PyMuPDF PDF-to-Markdown, Web Crawler, LLM output). At least one of markdown_text or file must be provided.

It returns cleaned Markdown text plus a downloadable .md file.

Usage

Add the Clean Markdown tool to your Dify workflow:

  • To clean an uploaded file: connect a file input and leave markdown_text empty.
  • To clean text from a previous node: pipe the text into markdown_text (e.g. {{#NODE_PDF.markdown_text#}}) and leave file empty.

Privacy

This plugin processes all text locally within the Dify runtime and does not collect or transmit any user data. See PRIVACY.md for details.