GITHUB TOPIC
15个项目包含此标签
15 个项目
GitHub Topic 精确匹配
Sqhao-O
Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness 全本地文档智能插件，支持 PDF、Office、图片与离线 OCR
xiehuan123
Evidence-first deep reading for AI agents — trace claims, evidence, confidence and knowledge maps across articles, books and PDFs.
sunshine-lang
PDF toolbox for DeepSeek Harness: extract text, metadata, and page ranges via pdfjs-dist (local, no API key)
linkingoscar
Codex-style attachment formats for the DeepSeek Harness Web GUI: PDF text-layer extraction, Office text extraction, scanned-PDF OCR, long-document spill + index cards, image-to-PNG.
beijingwahw
dsh-conv-export（对话导出）— export the current DeepSeek Harness conversation as Markdown, PDF, or a long PNG image
AATINF
让 AI Agent 直接处理 PDF：提取/拆分/合并/旋转，100% 纯本地执行。DeepSeek Harness 插件，三种接入方式：DSH Skill / MCP Server / 原生 Cordis 插件。| PDF tools for AI agents - extract, split, merge, rotate, fully local. 3 integration paths for DeepSeek Harness: Skill, MCP Server, native Cordis plugin.
dawsondx
DSH 对话报告化分享插件：生成带封面、摘要统计与章节排版的精美报告，导出为 PNG 图片 / 单 HTML 文件 / PDF。
Jeffine322
DeepSeek Harness (dsh) plugin - read_pdf tool for PDF text extraction. Read and extract text from PDF files with AI agents / LLM tools, built on PDF.js (unpdf).
zhtx2024
PDF parsing toolkit for DeepSeek Harness: pdf_info, pdf_extract_text, pdf_render_page with hybrid pdfjs/built-in engines and system-font rendering for non-embedded CJK PDFs.
zjsthmjialin
Codex skill for removing gray backgrounds from scanned PDFs without changing resolution or anti-aliased text.
ASAKAFENG
该仓库暂未提供项目说明。
genusamblyrhynchusbrunooftoul602
Extend DeepSeek Harness composer to accept PDFs and more attachment formats Codex-style, with zero core changes and native pipeline reuse.
henryxiao709
DSH-PDF插件，让 AI 助手读取任意大小的 PDF 文件： 通过 pdfjs-dist 提取完整 Unicode 文本层（中文、英文及其它文字系统），并对扫描件/图片页自动 OCR， 手写笔记也能变成可读文本。DSH-PDF plugin — read any-size PDFs in DeepSeek Harness: full Unicode text (Chinese/English) via pdfjs-dist + automatic OCR (Windows WinRT / tesseract.js) for scanned pages. MIT.
jiaoqsh
DeepSeek Harness plugin: read_document tool — Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF as Markdown for the model
louwenbo580
Paper review panel for the DeepSeek Harness: PDF to selectable text with figures, equations, and an ask-the-paper dialog