dsh-pdf-mineru
MinerU-powered PDF reading and background parsing plugin for DeepSeek Harness with local verification.
Install
$ dsh plugin --profile web add dsh-pdf-mineruPlugin 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
- Evidence-based reading with table of contents, literal search, stable block IDs, and page numbers
- Support for official MinerU cloud (v4) and self-hosted 4.x / 3.x backends
- Background parsing jobs integrated with DSH task tracking for long documents
- Content-addressable caching based on document content and parsing configuration
- Local original page rendering and verification via Poppler or PDF.js + @napi-rs/canvas fallback
- Dedicated Web settings UI for provider configuration, connection tests, and cache management
Useful For
- Reading academic papers or technical documentation with precise extraction of tables, formulas, and figures
- Asynchronous background parsing of lengthy reports without blocking ongoing agent conversations
- Cross-referencing OCR readings against local rendered page images to verify questionable numbers or text
- Keeping document parsing entirely on-premises using self-hosted MinerU instances
Who It Fits
- DeepSeek Harness users working extensively with complex or long PDF documents
- Researchers and analysts needing formula and table extraction with page verification
- Enterprises and developers requiring local or private document parsing workflows
Documented Limitations
- Settings and maintenance UI only accepts loopback address access (localhost/127.x.x.x/::1)
- Local page rendering is not an OS-level sandbox and relies on host isolation for untrusted PDFs
- Requires Node.js ^22.19.0 or >=24.0.0 and DSH >=0.2.1-rc.2 <0.3.0-0
- Installing with --no-optional will omit Canvas platform binaries, requiring Poppler for page rendering
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 3 runtime, 61 development, 13 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.
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
- Yurzi/dsh-pdf-mineru
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 4166ed1 · 2026-10-24
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
- 19GitHub stars
- Forks
- 2
- Open issues
- 0
- Last commit
- 2026-10-19
- Last release
- 2026-10-19
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →DeepSeek Harness-native vision toolkit enabling image Q&A, OCR, UI restoration, grounding, and pixel diff for text-only models.
View plugin →Automates invoice retrieval from IMAP mailboxes, OCR extraction, categorization, and Excel summary report generation.
View plugin →A DeepSeek Harness vision plugin that turns pasted images into structured OCR, layout, and semantic evidence for supported text-only models.
View plugin →