Sqhao-O/dsh-docs ↗★ 14

dsh-doc

本地文档智能与OCR处理服务 适合需要离线处理PDF、Office及图片OCR等文档智能任务的用户。

套件
dsh-doc
相容性
待驗證
Harness 依賴範圍
^0.1.0-rc.6
Cordis 依賴範圍
^4.0.1
版本
0.1.1
授權
MIT
最近更新
2026年9月11日

同名套件的其他儲存庫

安裝

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Sqhao-O/dsh-docs

Configuration

FieldDefaultMeaning
engineautonode, python, or auto; auto selects configured embedded Python, otherwise Node Xberg.
runtimeDirunsetAbsolute embedded-runtime directory.
pythonCommandunsetTrusted Python executable for a managed runtime.
pythonWorkerPathshipped workerAbsolute Python worker override.
tessdataPathruntime ocr/tessdataAbsolute bundled Tesseract language-data directory.
ocrBackendautoauto or tesseract; both select the pinned local Tesseract backend.
ocrLanguagesevery bundled packOrdered local OCR language packs. Unset uses every .traineddata pack in the configured runtime.
timeoutMs120000Per-conversion deadline.
maxFileBytes52428800Authorized input-size cap.
allowedLocalRoots[]Extra absolute non-root directories the model may read, beyond the session workspace.
allowWorkspaceFilestrueImplicitly authorize the session workspace (session cwd) as a readable root; set false for allowlist-only lockdown.
defaultOcrfalseOCR default for images and scans; enable it only with a configured local tessdata runtime.
defaultTableModeaccuratefast or accurate PDF table behavior.
defaultOutputFormatmdmd, text, or json.
maxOutputChars32000Maximum result returned to the model.
debugfalseLogs safe engine metadata only.

Older baseUrl, apiKey, enableRemoteUrls, and allowPrivateUrls profile fields are accepted only for migration; they do not enable a remote engine.