Power Users/Automators 折腾/讨论/分享各种开源工具/脚本/自动化工作流👥 @zhetengsha_group📌 合集 https://t.me/zhetengsha/2🎁 恰饭 https://t.me/zhetengsha/957📢 广告投放 @xream @xream_botBuy ads: https://telega.io/c/zhetengshafeedId:55438372655431680+userId:62307599601855488http://telegram.zhetengsha.eu.orghttp://telegram.zhetengsha.eu.org/posts/5235http://telegram.zhetengsha.eu.org/posts/5235Mon, 30 Mar 2026 02:03:26 GMT<u>Kreuzberg: 面向多语言生态的高性能文档解析与 OCR 引擎</u><br /><br />• 支持 88+ 文件格式解析，覆盖 PDF、Office、图片、HTML、XML、邮件、压缩包与学术文档，适合构建统一的数据提取管线<br /><br />• 基于 Rust 内核与原生绑定，提供 Python、Node.js、Go、Java、C#、PHP 等多语言支持，并可作为库、CLI、REST API 或 MCP Server 部署<br /><br />• 内置可扩展插件架构，支持 Tesseract、PaddleOCR、EasyOCR 等 OCR 后端，同时可选生成 Embeddings，无需 GPU 也能获得原生级处理速度<br /><br /><a href="https://github.com/kreuzberg-dev/kreuzberg" target="_blank" rel="noopener" title="https://github.com/kreuzberg-dev/kreuzberg">https://github.com/kreuzberg-dev/kreuzberg</a><br /><br /><a href="/search/result?q=%23%E6%96%87%E6%A1%A3%E8%A7%A3%E6%9E%90" title="#文档解析">#文档解析</a> <a href="/search/result?q=%23OCR" title="#OCR">#OCR</a> <a href="/search/result?q=%23Rust" title="#Rust">#Rust</a> <a href="/search/result?q=%23Embeddings" title="#Embeddings">#Embeddings</a> <a href="/search/result?q=%23%E5%A4%9A%E8%AF%AD%E8%A8%80%E5%BC%80%E5%8F%91" title="#多语言开发">#多语言开发</a> <a href="/search/result?q=%23%E6%96%87%E4%BB%B6%E5%A4%84%E7%90%86" title="#文件处理">#文件处理</a> <a href="/search/result?q=%23%E5%BC%80%E5%8F%91%E5%B7%A5%E5%85%B7" title="#开发工具">#开发工具</a> <a href="/search/result?q=%23GitHub" title="#GitHub">#GitHub</a> <a href="/search/result?q=%23MCP" title="#MCP">#MCP</a> <a href="/search/result?q=%23API" title="#API">#API</a><a class="tgme_widget_message_link_preview" href="https://github.com/kreuzberg-dev/kreuzberg" target="_blank" rel="noopener" title="A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Pyt..."> <div class="link_preview_site_name accent_color">GitHub</div> <img class="link_preview_image" alt="GitHub - xberg-io/xberg: A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured…" src="/static/https://cdn4.telesco.pe/file/MJSzB-GPh9ctAeYRTR9rxqL1zaqljsqAJyQrqM66S2tXa_r1JJ25N8n-_Kx_PEQ5FqSFEivldTHkW_kynLUsb2FG-o52SlGOofxrxhrJtnzaSjl7KHmVRCZEnCwbLBXH2yMxSeSANicf6ocKGjFnYj2-gdwwVjrM5OX9tsLYQKSPd_E0Mpg3F-qaxjEhCZvfXT8ZjDNzd44pqhuxXUFDfRO-E9jC8hJxnPxMOxL1NXjbq-7j3CndzIMBHeLMXtNMmnamCb8fxpZbwiQ9VBL7F3kalJ2llh3VxRkknx7qMOj-yy2v6r0ikqTmeKsScQWbY4dvV2OAwOkwsnKbju8M1g.jpg" width="1200" height="630" loading="eager" /> <div class="link_preview_title">GitHub - xberg-io/xberg: A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured…</div> <div class="link_preview_description">A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Pyt...</div> </a>