dsh-docchain
DSH 知识库和文档转换插件：支持按文件名/内容/元数据搜索、主题列表、批量上传文档、文档转 Markdown，以及深度研究工作流
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:wct-lab/dsh-docchain#ba356b8b4c0ef1ee3ae01c0b65848c3676734a79Docchain 以 dsh-docchain 发布，当前版本为 1.3.0。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。
English | 中文
A DSH knowledge base and document conversion plugin bundling filename/content/metadata search, topic listing, bulk document upload, document-to-Markdown conversion, plus a multi-subagent deep-research workflow: install once with plugin_manager install_bundle and it works on any machine — no manual copying into ~/.agents/skills required. Built on docchain.
| Skill | Kind | Description |
|---|---|---|
docchain-filename-search | SKILL.md + Node.js script | Find documents whose filename matches keywords, across topics |
docchain-content-search | SKILL.md + Node.js script | Search document content by keyword; returns line numbers and content; or/and operators |
docchain-meta-search | SKILL.md + Node.js script | Query documents by custom metadata fields (string/number/time, exact and range) |
docchain-topic-info | SKILL.md + Node.js script | List docchain topics with pagination and name keyword filter |
docchain-upload | SKILL.md + Node.js script | Upload a local file or a whole folder to a given docchain topic in bulk |
doc2markdown | SKILL.md + Node.js script | Convert docx/doc/pdf/pptx/xlsx/images and many more formats to Markdown via the docchain parsing service; results land next to the source file |
deep-research-advanced | SKILL.md only | Orchestrator-style multi-subagent deep research workflow (pure instructions, no scripts) |
From the GitHub repository (recommended; pure-JS package, no build step needed):
dsh plugin --profile web add github:wct-lab/dsh-docchain
Or from a local checkout:
plugin_manager install_bundle target=<absolute path to this directory>
No credentials ship in this package. Every script except doc2markdown (Node.js) needs a docchain service endpoint and an API key before it can run; doc2markdown (Node.js) works with neither — it defaults to the public parsing service and uploads anonymously, while the same config chain can point it at a custom endpoint/key.
| Field | Meaning | Required |
|---|---|---|
docchain_url | docchain service address, e.g. http://<host>:7100/llmdoc | Yes |
docchain_api_key | API authentication key | Yes |
Four ways to provide them, in priority order (higher wins):
DOCCHAIN_URL and DOCCHAIN_API_KEY;<skill>/scripts/config.json;~/.dsh/storages/docchain-config.json (written by the plugin config — see below);skills/docchain_config.json (file-drop distribution fallback; the package ships only docchain_config.example.json as a template).Config file format (all JSON-based):
{
"docchain_url": "http://<host>:7100/llmdoc",
"docchain_api_key": "your-api-key-here"
}
All scripts need only Node.js. Invoke them from the skill's base directory as node scripts/<script>.js … (see each SKILL.md for parameters).
The plugin ships a configuration page in the web client: in dsh web, open Plugins in the sidebar, find the dsh-docchain plugin, and use the configure control on its row. The page edits the service URL (saved to the row config and hot-reloaded through the host settings service) and writes the API key to the credential store. The key is write-only: the page never echoes a stored value, only whether one is set.
The plugin follows the official credential pattern. Its Config schema declares:
| Field | Meaning |
|---|---|
docchain_url | Service endpoint; volatile, editable on the configuration page |
docchain_api_key_ref | Credential reference name for the key; default DOCCHAIN_API_KEY |
docchain_api_key | Fallback literal key (not recommended; the store wins over it) |
The key's value lives in the credential store ~/.dsh/.credentials.yaml (refs: section, owner-only permissions) — save it through the configuration page or edit the file directly; changes hot-reload. It can also come from the launch environment under the same variable name. On activation, whenever a stored credential changes, and whenever this row's settings are saved, the resolved values are mirrored into ~/.dsh/storages/docchain-config.json (permissions 0600): the file is a pure projection of the current resolution, so a cleared config entry disappears from it; the scripts read it on every run.
Key resolution order: credential store (launch env > stored file) > docchain_api_key row literal.
To change values, either:
DOCCHAIN_API_KEY in the credential store — takes effect without touching this plugin, or~/.dsh/storages/docchain-config.json directly (takes effect on the next script run; the plugin rewrites it from the resolved config on activation and config changes — for durable overrides use env vars or a per-skill config.json), ordocchain_url / docchain_api_key_ref / docchain_api_key in the plugin's config row (patch config / preset override) and re-activate the plugin.The bundle inserts one Host plugin (dsh-docchain). At activation it registers a skill provider on ctx.skills that serves every <skills>/<name>/SKILL.md directory in this package:
name, description); bodies are re-read on every load..dsh/skills = 100, project .agents/skills = 200), runtime registrations (250) and customSkillDirs (300) keep precedence, as does ~/.dsh/skills (400); the bundle outranks ~/.agents/skills (500) and the bundled root (600). In practice: same-name copies in ~/.agents/skills are shadowed by this bundle; delete them there if you want a single source.Locate documents quickly by filename keywords across topics.
How to use it — describe the filename keywords you are looking for. You must specify the topic ID(s) when asking.
Examples:
Search keywords inside document content; returns the matching line numbers and content. Supports or and and operators.
How to use it — specify the search scope and keywords. You must provide at least one of doc_ids or topic_ids.
Examples:
Filter documents by custom metadata field conditions — string, number, and time types with exact and range operators.
How to use it — describe the filter conditions. You must specify topic ID(s) or document ID(s).
Examples:
Lists the topics in a docchain system with pagination, optionally filtered by a name keyword. Often a first step before other skills: get the topic IDs, then search or upload within a topic.
How to use it — just ask what topics exist; optionally give a page number, page size, or a name keyword.
Examples:
Uploads a single local file or a whole folder to a given docchain topic, one file at a time, with progress and success/failure counts. Folder scans cover top-level files only (non-recursive).
How to use it — provide the file/folder path and the target topic ID (--topic_id is required).
Examples:
Uploads a document (docx, doc, pdf, ppt, xlsx, images, epub, mobi and many more) to the docchain parsing service and downloads the converted Markdown next to the source file — either a single .md file (--md) or a package with images and tables.
How to use it — point it at a file path, e.g. "read the content of ./report.pdf" or "convert 合同.docx to Markdown".
Examples:
The service URL and API key follow the same config chain as the search scripts, but both are optional: without configuration the public service (https://lab.hjcloud.com/llmdoc) is used with anonymous upload.
A ReAct orchestrator-style deep-research workflow (pure instructions, no scripts): the main agent probes the topic, splits independent sub-tasks and dispatches them to parallel subagents; each subagent iterates on retrieval, close reading and deduction and returns a sub-report with its reasoning chain; the main agent cross-validates, reviews and enforces at least two global loops before deciding to stop. The final report is logic-closed, traceable and low-hallucination.
When to use — complex, open-ended questions that need external evidence and logical deduction: industry analysis, market research, competitive analysis, policy interpretation, technology research, trend forecasting. Do not use it for simple Q&A or basic computation.
Removing the bundle unregisters the provider and its skills:
dsh plugin remove dsh-docchain
(or plugin_manager remove_bundle).