dsh-evidence
Enables multi-file upload, private local retrieval, and coordinate-exact reads for PDF, DOCX, XLSX, and PPTX in DeepSeek Harness.
Install
$ dsh plugin --profile web add . # link this checkout into the web profilePlugin 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
- Upload files and folders via the Web composer with byte-level format validation and per-session quotas
- Private local indexing and text retrieval with SQLite FTS5 or fallback in-memory JS search
- Coordinate-exact reading of PDF (page ranges), DOCX (line/char ranges), XLSX (sheets and A1 cell ranges), and PPTX (slides)
- Handoff of raster images (JPEG/PNG/WebP/GIF) to DeepSeek Harness native vision workflows
- Deterministic version verification ensuring coordinates match file hashes before reading
Useful For
- Grounding AI responses with exact citations to specific pages, lines, or spreadsheet cells
- Analyzing large collections of PDFs, Word documents, Excel workbooks, and slide decks without blowing up context limits
- Querying local business documents and meeting notes privately without external parsing APIs
Who It Fits
- DeepSeek Harness web users needing precise document Q&A
- Researchers and knowledge workers analyzing multi-format office files
- Developers building RAG-like local evidence retrieval workflows in DSH
Documented Limitations
- No OCR support for scanned PDFs, image-only pages, or embedded images in office files
- Does not calculate XLSX formulas, run macros, or interpret PPTX charts/SmartArt/animations
- Requires Node.js >= 22.13.0 for runtime PDF parsing and SQLite FTS5
- Session isolation depends on host loopback/reverse proxy configurations and is not a multi-tenant auth layer
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 4 runtime, 15 development, 9 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
- Cooberped/dsh-evidence
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 2ef0f50 · 2026-09-14
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
- 0GitHub stars
- Forks
- 0
- Open issues
- 2
- Last commit
- 2026-08-29
- Last release
- No release detected
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 →Vision routing and pixel-level visual tool suite for DeepSeek Harness agents with built-in free fallbacks.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Composable three-tier memory control plane for DeepSeek Harness with runtime context, searchable documents, and pluggable long-term memory.
View plugin →