BYYY-eng/deepseek-harness-file-upload-ocr-plugin

DeepSeek Harness File upload and local OCR plugin for PDF, Word

A file upload and local OCR plugin for DeepSeek Harness: add PDF, Word, Excel, PowerPoint, image, and text attachments as chat cards in the Web UI (drag anywhere, colored accent cards per type); scanned PDFs and images are recognized locally with OCR. PDF native-text extraction with automatic OCR for scanned or low-text pages; DOCX/XLSX/XLSM/PPTX/images and common text/code formats supported.

Files & Data ★ 4 updated 2026-08-19 ⚠️ needs adapt
View on GitHub ↗

Install

⚠️ Upstream documents a local-checkout install — the command it gives is a path on your own machine, so there is nothing pasteable here. See the README for its exact steps.

Compatibility

DeepSeek Harness Web profile; prerequisites: working dsh CLI, Python 3.9+, Git. The installer creates the web profile when it does not exist. Local OCR runs on-device.

Details

Recent updates

Attachment cards + drag-anywhere upload; local OCR for scanned PDFs/images; installer script for web profile; Python env auto-setup.

FAQ

What does the installer do?
It creates the local Python environment first, then registers the package through Harness's official dsh plugin --profile ... add flow — no manual cordis.yml or cordis.patch.yml edits are needed.
Which file types are supported?
PDF, Word (DOCX), Excel (XLSX/XLSM), PowerPoint (PPTX), images, and common text/code formats — as attachment cards with per-type accent colors.
Is OCR local?
Yes — scanned PDFs and images are recognized locally with OCR; no external OCR service is called.

Alternatives

HongMing-Huang/dsh-file-upload · joejojoking-cloud/dsh-file-explorer · slywalker2006/dsh-passwords

More plugins in Files & Data

Browse more in Files & Data

Guides for Files & Data plugins