DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Handwritten Ocr — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
H

dsh-handwritten-ocr

Handwritten Ocr

Local OCR for DSH: handwritten Chinese and math formulas to Markdown with LaTeX. GPU (DirectML) / CPU / NPU backends, settings-driven, one-click install.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:KL3jd/handwritten-ocr#429fdc8950264c87a5c08a05d8e81fb21a33905e
READMECompatibilityVersions

Compatibility and provenance

Handwritten Ocr is published as dsh-handwritten-ocr and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
8/27/2026

Versions

0.1.0stable
8/27/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
8/28/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in vision-media.

Tool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — Modlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIVision Toolkit@anionex/dsh-vision-toolkitDeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.Deepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.

README

OCR 本地插件 — 手写中文 + 数学公式 → Markdown

本地 OCR 插件:识别手写中文笔记与数学公式图片,输出 Markdown(中文纯文本 + 公式 LaTeX)。 全程本地推理、不联网,图片与数据不出本机。可作为 DSH(或其他 LLM 工具框架)的插件调用。

功能

  • 整页手写笔记识别:中文 → 纯文本、公式 → LaTeX
  • 三模式后端:GPU(DirectML,推荐)/ CPU / NPU(实验性,见下)
  • 可调参数集中在 settings.json,无需改代码
  • FastAPI 服务(ocr_server.py,POST /ocr)+ CLI(ocr_cli.py)
  • DSH 工具预设(dsh-assets/):LLM 可直接调用 ocr_image 识别图片

组件

组件用途许可
Pix2Text MFD 1.5公式区检测(YOLO)MIT
RapidOCR中文文本行识别Apache-2.0
UniMERNet公式 → LaTeX(手写优先)MIT
Pix2Text MFR 1.5公式 → LaTeX(兜底)MIT

安装

一键安装(Windows,推荐)

powershell -ExecutionPolicy Bypass -File install.ps1

自动完成:建 .venv + 装依赖(清华源优先、失败退官方源)→ 下载模型(hf-mirror)→ 装 DSH 预设。 模型已有可加 -SkipModels。

手动安装

# 1. Python 3.10 环境
python -m venv .venv
# Windows: .venv\Scripts\activate

# 2. 依赖
pip install -r requirements-gpu.txt

# 3. 下载模型(自动走 hf-mirror 国内镜像,落 models/ocr/)
python scripts/download_models.py

使用

# CLI
python ocr_cli.py 笔记照片.jpg --mode gpu

# HTTP 服务(默认 8765 端口)
python -m uvicorn ocr_server:app --port 8765
# POST /ocr  (multipart: file=图片, mode=gpu)

设置(settings.json)

键默认说明
modeautogpu / npu / cpu / auto
formula_backendautounimernet / mfr / auto
formula_iou0.3文本与公式框去重 IoU
mfd_conf0.25公式检测置信度
mfd_resized_shape768检测输入尺寸
merge_x_iou / merge_y_gap0.3 / 24公式碎片合并
crop_pad_ratio0.08公式裁剪外扩
crop_min_width / height24 / 18裁剪最小尺寸
crop_upscale256小图放大阈值

环境变量:OCR_PY / OCR_CLI / OCR_MODEL_DIR / OCR_SETTINGS 可覆盖默认路径。

DSH 集成

install.ps1 会自动安装预设;手动安装:

Copy-Item dsh-assets\preset-ocr-assistant "C:\Users\$env:USERNAME\.dsh\.agent-presets\ocr-assistant" -Recurse -Force

刷新后出现「OCR 助手」预设,LLM 拥有 ocr_image 工具(识别本地图片 → Markdown)。 若报 python 找不到,设 OCR_PY / OCR_CLI 环境变量后重启 DSH。

已知限制

  • NPU 模式(AMD XDNA1)受 amd/RyzenAI-SW#389 阻塞: Windows + RAI 1.8.0 下 DPU 分派报 ERT_CMD_STATE_ERROR(AMD open bug),建议用 GPU 或 CPU 模式。
  • 手写矩阵的完整 bmatrix 输出仍在打磨(当前 MFD 会拆成多个公式框)。