[PR #1536] [MERGED] feat: Add md-text-chunker - intelligent markdown chunker for RAG systems #1677

New Issue

2026-02-22T18:04:50-05:00

yindo commented

2026-02-22 18:04:50 -05:00

📋 Pull Request Information

Original PR: https://github.com/langgenius/dify-plugins/pull/1536
Author: @Biaoo
Created: 11/12/2025
Status: ✅ Merged
Merged: 11/21/2025
Merged by: @crazywoola

Base: main ← Head: main

📝 Commits (2)

be4f46d feat: Add md-text-chunker plugin - intelligent markdown chunker with heading hierarchy
3c57ebd Update md-text-chunker plugin to v0.0.1 with custom icons

📊 Changes

1 file changed (+0 additions, -0 deletions)

View changed files

➕ biaoo/md-text-chunker-0.0.1.difypkg (+0 -0)

📄 Description

Plugin Submission Form

1. Metadata

Plugin Author: biaoo
Plugin Name: md-text-chunker
Repository URL: https://github.com/Biaoo/md-text-chunker

2. Submission Type

New plugin submission
Version update for existing plugin

3. Description

md-text-chunker is an intelligent Markdown text chunking tool designed specifically for RAG
(Retrieval-Augmented Generation) systems.

Key Features:

Intelligent Heading Hierarchy Preservation: Automatically extracts and maintains complete heading paths (e.g., H1 > H2 > H3), ensuring each chunk includes full contextual information
Hybrid Chunking Strategy: Combines semantic chunking (heading-based) with fixed-size chunking to respect document structure while maintaining optimal chunk sizes
Optional LLM-Based Heading Enhancement: Uses LLM to analyze and correct heading hierarchy levels, particularly useful for documents with inconsistent structures (e.g., converted PDFs)
Configurable Heading Levels: Supports H1-H6 heading levels with default at H3, allowing flexible control over chunking granularity
Metadata Injection: Optional XML metadata with file title and heading paths for downstream RAG systems (toggleable)
Atomic Unit Protection: Preserves tables, mathematical formulas, and other atomic content units to prevent breaking critical content across chunks
Text Preprocessing: Converts literal \n to actual newlines, with optional removal of extra whitespace and URLs/emails

Use Cases:

RAG knowledge base construction with contextual metadata
Technical documentation processing with table/formula preservation
Scientific paper processing with LLM-enhanced heading correction
Enterprise document management with consistent chunking

4. Checklist

I have read and followed the Publish to Dify Marketplace guidelines
I have read and comply with the Plugin Developer Agreement
I confirm my plugin works properly on both Dify Community Edition and Cloud Version
I confirm my plugin has been thoroughly tested for completeness and functionality
My plugin brings new value to Dify

5. Documentation Checklist

Please confirm that your plugin README includes all necessary information:

Step-by-step setup instructions
Detailed usage instructions
All required APIs and credentials are clearly listed
Connection requirements and configuration details
Link to the repository for the plugin source code

6. Privacy Protection Information

Based on Dify Plugin Privacy Protection Guidelines:

Data Collection

This plugin does NOT collect any user personal data by default. All processing is done locally within the Dify instance.

Optional LLM Enhancement Feature: If users enable the optional LLM-based heading enhancement feature, markdown text will be sent to the user-configured LLM API endpoint. This feature is:

Opt-in and disabled by default
Fully controlled by the user (they configure their own API endpoint, key, and model)
Subject to the privacy policy of the LLM service provider they choose

Privacy Policy

I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/langgenius/dify-plugins/pull/1536 **Author:** [@Biaoo](https://github.com/Biaoo) **Created:** 11/12/2025 **Status:** ✅ Merged **Merged:** 11/21/2025 **Merged by:** [@crazywoola](https://github.com/crazywoola) **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (2) - [`be4f46d`](https://github.com/langgenius/dify-plugins/commit/be4f46d3ff5ea6c6a9f0ca6ae4c849a8217f5b30) feat: Add md-text-chunker plugin - intelligent markdown chunker with heading hierarchy - [`3c57ebd`](https://github.com/langgenius/dify-plugins/commit/3c57ebd5f6148bbbc92abbb895ec563d1fcaeff5) Update md-text-chunker plugin to v0.0.1 with custom icons ### 📊 Changes **1 file changed** (+0 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `biaoo/md-text-chunker-0.0.1.difypkg` (+0 -0) </details> ### 📄 Description # Plugin Submission Form ## 1. Metadata - **Plugin Author**: biaoo - **Plugin Name**: md-text-chunker - **Repository URL**: [https://github.com/Biaoo/md-text-chunker](https://github.com/Biaoo/md-text-chunker) ## 2. Submission Type - [x] New plugin submission - [ ] Version update for existing plugin ## 3. Description **md-text-chunker** is an intelligent Markdown text chunking tool designed specifically for RAG (Retrieval-Augmented Generation) systems. ### Key Features: - **Intelligent Heading Hierarchy Preservation**: Automatically extracts and maintains complete heading paths (e.g., `H1 > H2 > H3`), ensuring each chunk includes full contextual information - **Hybrid Chunking Strategy**: Combines semantic chunking (heading-based) with fixed-size chunking to respect document structure while maintaining optimal chunk sizes - **Optional LLM-Based Heading Enhancement**: Uses LLM to analyze and correct heading hierarchy levels, particularly useful for documents with inconsistent structures (e.g., converted PDFs) - **Configurable Heading Levels**: Supports H1-H6 heading levels with default at H3, allowing flexible control over chunking granularity - **Metadata Injection**: Optional XML metadata with file title and heading paths for downstream RAG systems (toggleable) - **Atomic Unit Protection**: Preserves tables, mathematical formulas, and other atomic content units to prevent breaking critical content across chunks - **Text Preprocessing**: Converts literal `\n` to actual newlines, with optional removal of extra whitespace and URLs/emails ### Use Cases: - RAG knowledge base construction with contextual metadata - Technical documentation processing with table/formula preservation - Scientific paper processing with LLM-enhanced heading correction - Enterprise document management with consistent chunking ## 4. Checklist - [x] I have read and followed the Publish to Dify Marketplace guidelines - [x] I have read and comply with the Plugin Developer Agreement - [x] I confirm my plugin works properly on both Dify Community Edition and Cloud Version - [x] I confirm my plugin has been thoroughly tested for completeness and functionality - [x] My plugin brings new value to Dify ## 5. Documentation Checklist Please confirm that your plugin README includes all necessary information: - [x] Step-by-step setup instructions - [x] Detailed usage instructions - [x] All required APIs and credentials are clearly listed - [x] Connection requirements and configuration details - [x] Link to the repository for the plugin source code ## 6. Privacy Protection Information Based on Dify Plugin Privacy Protection [Guidelines](https://docs.dify.ai/plugins/publish-plugins/publish-to-dify-marketplace/plugin-privacy-protection-guidelines): ### Data Collection This plugin does **NOT** collect any user personal data by default. All processing is done locally within the Dify instance. **Optional LLM Enhancement Feature**: If users enable the optional LLM-based heading enhancement feature, markdown text will be sent to the user-configured LLM API endpoint. This feature is: - **Opt-in** and disabled by default - Fully controlled by the user (they configure their own API endpoint, key, and model) - Subject to the privacy policy of the LLM service provider they choose ### Privacy Policy - [x] I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

yindo added the pull-request label 2026-02-22 18:04:50 -05:00

yindo closed this issue

2026-02-22 18:04:52 -05:00

yindo referenced this issue

2026-02-22 18:07:33 -05:00

[PR #1677] [MERGED] bump openai_trigger plugin to version 0.2.0 #1771

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: langgenius/dify-plugins#1677