dsh-markdownize
将文档（PDF、Word、PowerPoint、Excel、HTML、CSV、JSON、ZIP……）转换为 Markdown，供 LLM 读取。内置 JavaScript 引擎；如果已安装 Microsoft MarkItDown，则使用 Microsoft MarkItDown。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:Gorkaseto/dsh-markdownize#efccbcc4b158c6a4f96c6727c3384dc32ee073a3Markdownize 以 dsh-markdownize 发布，当前版本为 0.2.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
A DeepSeek Harness (dsh) plugin that converts documents to Markdown so an LLM can read them.
Models work best with plain text. A PDF, a Word file or a spreadsheet read as
raw bytes is noise to them. Markdown keeps the structure (headings, lists,
tables, slides, pages) while staying compact and easy to read. This plugin
gives the agent a convert_to_markdown tool that does that conversion
locally. You can also preview a conversion yourself before anything is sent
to the model.
convert_to_markdown tool. The model calls it with a local file path
and gets the document back as Markdown, truncated to max_chars
(100,000 by default).[Image N: alt text]
markers. When the current model accepts images, each image is sent right
after its marker.| Format | Own engine (JS) | Microsoft MarkItDown |
|---|---|---|
| yes (text per page) | yes | |
Word .docx | yes | yes |
PowerPoint .pptx | yes (text and notes per slide) | yes |
Excel .xlsx | yes (one table per sheet) | yes |
| HTML / HTM | yes | yes |
| CSV / TSV | yes (as a table) | yes |
| JSON / XML | yes (fenced code block) | yes |
| TXT / MD | yes (as is) | yes |
| ZIP | yes (each supported file inside) | yes |
Excel 97 .xls, EPUB, Jupyter .ipynb, Outlook .msg | no | yes |
convert.js mirrors MarkItDown's offline converters with Node libraries:
mammoth for DOCX;exceljs for XLSX;unpdf (pdf.js) for PDF;turndown with GFM tables for HTML;jszip and fast-xml-parser for PPTX and ZIP.It needs no Python, no network and no child processes. The libraries ship
pre-bundled in vendor/, so the plugin has no runtime npm dependencies. This
matters because dsh installs local plugins as link: dependencies, and pnpm
never installs a linked package's dependencies.
MarkItDown is Microsoft's Python tool for the same job. It gives the reference output and reads a few more formats. Install it with:
pip install "markitdown[all]"
The plugin looks for it on PATH as markitdown, py -m markitdown,
python -m markitdown or python3 -m markitdown. If it lives somewhere else,
such as a virtualenv's markitdown.exe, set its command on the plugin's page.
Use double quotes around paths with spaces.
Open Plugins → dsh-markdownize. The page shows which engines were found. When both are available, choose:
The choice and the custom command are saved in
<dshHome>/storages/dsh-markdownize/settings.json, together with the image
settings. They apply to both the tool and debug mode. MarkItDown is detected once per Host start; press
Search again after installing it.
The JavaScript engine extracts the images embedded in DOCX and PPTX files (including those inside a ZIP). Each one leaves a marker where it sat: in the text for DOCX, after the slide's text for PPTX.
[Image 1: Sales by quarter]
[Image 2]
[Image 3: Company logo — same as image 1]
[Image 4: Vector logo — format not supported]
The plugin's page sets what happens next:
read_image does. With an image-capable model, each image is stored as an
attachment and sent right after its marker. With a text-only model, such as
DeepSeek's, only the markers are sent, followed by a note saying why.Most images per conversion (1–50, 10 by default) caps what one call sends,
and never exceeds the harness's own per-message image limit. Images past the
cap keep their marker with a note. The model can also pass
include_images: false to get the markers only; it cannot override the
settings.
Repeated images (a logo on every slide) are sent once. Icons smaller than 32 px on both sides are skipped when they have no alt text. PNG, JPEG, GIF and WebP are sent; EMF, WMF and TIFF keep a marker only. Debug mode always shows markers.
MarkItDown does not extract images, so these settings have no effect while it is the engine in use.
The plugin needs no build step and no Python. For a web profile:
dsh plugin --profile web add ./dsh-markdownize
dsh --profile web --dump-config
The dump should show a # == dsh-markdownize layer. Then start the client:
dsh web
On the desktop profile, add it from the app's plugin manager as a local
folder.
@.Each compatible attachment and @file reference is converted on the Host.
@file paths are resolved against the Session's workspace. The full output,
with no truncation, is written to <os tmpdir>/dsh-markdownize-debug/ and
opened in the right Sidebar preview. A composer notice reports its size, path
and the engine used.
Nothing is sent to the model, and the draft is left as it was. Images and unsupported formats are skipped.
Not covered: OCR of scanned documents, images in PDFs, image captioning
for text-only models, audio transcription, YouTube, Azure Document
Intelligence, and the legacy .doc and .ppt formats.
index.js — the Host half. It registers the convert_to_markdown tool and
the markdownize service (convert, convertPath, status, configure,
configureImages, redetect), served through the Gateway's SRC fallback.engine.js — engine selection, MarkItDown detection and invocation, and
the saved settings.convert.js — the JavaScript engine.images.js — embedded images: markers, model hand-off, and the tool's
output schema.client.js — the Client half: the engine page under Plugins, the
debug-mode shortcut, and the en / es / zh UI strings.locale/ — the plugin's localized title and description.cordis.patch.yml — inserts the dsh-markdownize plugin row.vendor/ — the bundled converter libraries (generated; committed).build-vendor.mjs — rebuilds vendor/.After changing a converter's version in devDependencies:
npm install && npm run build
Commit the regenerated vendor/ files: the plugin loads them at runtime.
Copyright 2026 gorkaseto. Licensed under the Apache License, Version 2.0; see NOTICE for the bundled third-party libraries and their licenses.