dsh-docs
Local document parsing and offline OCR tools for DeepSeek Harness.
Install
$ dsh plugin --profile web add dsh-docPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Installs into a DSH profile as the published `dsh-doc` package.
- Parses PDF, DOCX, XLSX, PPTX, Markdown, HTML, CSV, and text files.
- Processes PNG, JPEG, TIFF, WebP, and scanned PDFs with local OCR when configured.
- Returns Markdown, plain text, or JSON-shaped tool results.
- Provides `dshdoc_health`, `dshdoc_convert_file`, `dshdoc_extract`, and a URL-rejecting compatibility tool.
- Restricts file access to the session workspace and configured allowed local roots.
- Offers a Windows x64 embedded Python runtime with pinned local Tesseract English and Simplified Chinese language data.
Useful For
- Extracting text and tables from local reports and spreadsheets.
- Reading scanned invoices or image-based documents with offline OCR.
- Making approved local document folders available to a DSH agent.
- Converting supported local files into Markdown or structured output for analysis.
Who It Fits
- DeepSeek Harness users working with local documents.
- Teams requiring offline document conversion and OCR workflows.
- Windows x64 users who need the supplied local Python/OCR runtime.
Documented Limitations
- Complete bundled offline OCR coverage is described for Windows x64; other platforms use the Node engine unless separately configured.
- The Node-only fallback defaults OCR to disabled and requires reviewed local Tesseract language data to enable OCR.
- Only files under the session workspace or configured `allowedLocalRoots` are readable.
- Remote URLs are not converted; `dshdoc_convert_url` returns `UNSUPPORTED_URL`.
- The documented maximum default input size is 52,428,800 bytes and default output limit is 32,000 characters.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 1 runtime, 12 development, 4 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- Sqhao-O/dsh-docs
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 67d3ae9 · 2026-09-21
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 14GitHub stars
- Forks
- 0
- Open issues
- 9
- Last commit
- 2026-08-15
- Last release
- 2026-08-15
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Preview, create, and edit spreadsheets, docs, slides, and canvases in DeepSeek Harness powered by Univer.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Compatibility bridge and host ABI enabling unmodified Pi plugins to run natively on DeepSeek Harness.
View plugin →Vision routing and pixel-level visual tool suite for DeepSeek Harness agents with built-in free fallbacks.
View plugin →