dsh-pdf-mineru
Provider-independent DeepSeek Harness PDF and document parsing tool powered by MinerU with background jobs and content caching.
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
- Structured extraction of text, tables, LaTeX formulas, and inline multimodal images from PDFs
- Dual provider support for MinerU Official Cloud API (v4) and private self-hosted services (v2)
- Non-blocking asynchronous parsing integrated into DSH native background jobs
- Content-addressed local caching based on file SHA-256 and parse semantics to eliminate duplicate processing
- Targeted sliced reading with page range, block ID, focus filtering, query matching, and cursor pagination
- Local original page rendering fallback via Poppler or bundled PDF.js with @napi-rs/canvas
- Integrated DSH Web GUI settings panel with provider connectivity testing and cache maintenance
Useful For
- Parsing complex academic papers and technical research reports containing formulas and multi-column layouts
- Offloading multi-page PDF processing to background asynchronous jobs during conversational sessions
- Extracting specific tables or sections on demand using focused sliced reading
- Verifying extracted OCR and formula data against rendered original page snapshots
Who It Fits
- DeepSeek Harness users requiring advanced PDF and document understanding capabilities
- Researchers, data analysts, and knowledge workers processing structured PDF literature
- Enterprises running self-hosted MinerU clusters for private document parsing
Documented Limitations
- Requires DeepSeek Harness >= 0.1.7-rc.2 (RC and stable releases only; alpha builds unsupported)
- MinerU Official Cloud v4 requires an active API token and limits single files to 200MB and 200 pages
- Local page rendering requires Poppler in PATH or compatible @napi-rs/canvas platform binaries
- Fixed safety limits and storage root paths cannot be modified at runtime without restarting the host
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, 50 development, 10 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
- 710af2a · 2026-09-30
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
- 11GitHub stars
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-09-30
- Last release
- 2026-09-30
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Multimodal vision router and deep pixel tools for text-only DeepSeek Harness agents with free fallback chains.
View plugin →Native DeepSeek Harness vision toolkit providing image Q&A, long-screenshot OCR, UI restoration, vector tracing, grounding, and pixel diff.
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 →