dsh-zpdf
Run the following command in DeepSeek Harness:
dsh plugin install komoai2026/dsh-zpdf
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install komoai2026/dsh-zpdf in the DeepSeek Harness terminal to pull and activate the plugin from https://github.com/komoai2026/dsh-zpdf into your current profile.
About this plugin
Handling PDFs inside a model-inference loop is often the most tedious part — juggling parsers, translators, and format converters one by one. dsh-zpdf folds the full ZPDF toolkit directly into DeepSeek Harness, so document processing becomes a single conversational step.
Core capabilities include high-fidelity PDF-to-Markdown parsing that preserves formulas, tables, and images; layout-preserving PDF translation in translated-only or side-by-side mode; and multi-format export from Markdown or ZIP to DOCX, HTML, PDF, and LaTeX. On top of that, the plugin offers local page-count and credit estimates, balance checks, and task-status tracking — every network call honours an abort signal to prevent wasted resources.
Built for developers who hold a ZPDF Plus or Pro account and want seamless document parsing and translation inside their inference workflow. A dedicated settings page auto-refreshes credit balance and task status every 30 seconds and 10 seconds respectively. The API key is stored securely through the DSH credential store, with environment variables taking precedence over GUI settings for both safety and flexibility.
Use Cases
- Parse academic PDFs with formulas and tables into structured Markdown for model inference
- Translate English PDFs to Chinese with layout preservation and side-by-side output
- Export Markdown drafts to DOCX, PDF, or LaTeX in one step
Best For
- Developers with ZPDF Plus/Pro accounts who process PDF documents at scale
- Teams embedding document parsing and translation pipelines in DeepSeek Harness workflows
- Document engineers who need multi-format interconversion between PDF and Markdown
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.