{"id":21149,"date":"2025-02-15T13:10:16","date_gmt":"2025-02-15T05:10:16","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=21149"},"modified":"2025-08-25T00:25:15","modified_gmt":"2025-08-24T16:25:15","slug":"kreuzberg","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/ja\/kreuzberg\/","title":{"rendered":"Kreuzberg\uff1a\u4ece\u4efb\u4f55\u6587\u6863\u4e2d\u63d0\u53d6\u6587\u672c\u7684\u5f00\u6e90\u5de5\u5177"},"content":{"rendered":"<p>Kreuzberg\u662f\u4e00\u4e2a\u7528\u4e8e\u7b80\u5316PDF\u6587\u4ef6\u6587\u672c\u63d0\u53d6\u7684\u5e93\uff0c\u65e8\u5728\u63d0\u4f9b\u7b80\u5355\u3001\u65e0\u5fe7\u7684\u6587\u672c\u63d0\u53d6\u89e3\u51b3\u65b9\u6848\u3002\u8be5\u5e93\u7279\u522b\u9002\u5408\u9700\u8981\u8fdb\u884c\u6587\u672c\u63d0\u53d6\u7684RAG\uff08Retrieval-Augmented Generation\uff09\u670d\u52a1\u3002Kreuzberg\u652f\u6301\u672c\u5730\u8fd0\u884c\uff0c\u6613\u4e8e\u63a7\u5236\u4e14\u6210\u672c\u4f4e\u5ec9\u3002\u5b83\u7ed3\u5408\u4e86\u591a\u79cd\u5f00\u6e90\u548c\u5546\u4e1a\u9009\u9879\uff0c\u63d0\u4f9b\u4e86\u7075\u6d3b\u7684\u6587\u672c\u63d0\u53d6\u529f\u80fd\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-21151\" title=\"Kreuzberg\uff1a\u4ece\u4efb\u4f55\u6587\u6863\u4e2d\u63d0\u53d6\u6587\u672c\u7684\u5f00\u6e90\u5de5\u5177-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/06e32921eeeb126.png\" alt=\"Kreuzberg\uff1a\u4ece\u4efb\u4f55\u6587\u6863\u4e2d\u63d0\u53d6\u6587\u672c\u7684\u5f00\u6e90\u5de5\u5177-1\" width=\"831\" height=\"586\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/06e32921eeeb126.png 831w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/06e32921eeeb126-768x542.png 768w\" sizes=\"auto, (max-width: 831px) 100vw, 831px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>PDF\u6587\u672c\u63d0\u53d6<\/strong>\uff1a\u4ecePDF\u6587\u4ef6\u4e2d\u63d0\u53d6\u6587\u672c\u5185\u5bb9\u3002<\/li>\n<li><strong>\u56fe\u50cf\/PDF OCR<\/strong>\uff1a\u4f7f\u7528Tesseract-OCR\u8fdb\u884c\u56fe\u50cf\u548cPDF\u7684\u5149\u5b66\u5b57\u7b26\u8bc6\u522b\u3002<\/li>\n<li><strong>\u975ePDF\u6587\u672c\u63d0\u53d6<\/strong>\uff1a\u901a\u8fc7Pandoc\u8fdb\u884c\u5176\u4ed6\u683c\u5f0f\u6587\u672c\u7684\u63d0\u53d6\u3002<\/li>\n<li><strong>\u672c\u5730\u8fd0\u884c<\/strong>\uff1a\u652f\u6301\u672c\u5730\u5b89\u88c5\u548c\u8fd0\u884c\uff0c\u6613\u4e8e\u63a7\u5236\u548c\u7ba1\u7406\u3002<\/li>\n<li><strong>\u5f00\u6e90\u514d\u8d39<\/strong>\uff1a\u57fa\u4e8eMIT\u8bb8\u53ef\u8bc1\u5f00\u6e90\uff0c\u514d\u8d39\u4f7f\u7528\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<ol>\n<li><strong>\u5b89\u88c5Python\u5305<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   pip install kreuzberg\r\n<\/code><\/pre>\n<ol start=\"2\">\n<li><strong>\u5b89\u88c5\u7cfb\u7edf\u4f9d\u8d56<\/strong>\uff1a\n<ul>\n<li><strong>Pandoc<\/strong>\uff1a\u7528\u4e8e\u975ePDF\u6587\u672c\u63d0\u53d6\uff08GPL v2.0\u8bb8\u53ef\u8bc1\uff0c\u4ec5\u4f5c\u4e3aCLI\u4f7f\u7528\uff09\u3002<\/li>\n<li><strong>Tesseract-OCR<\/strong>\uff1a\u7528\u4e8e\u56fe\u50cf\u548cPDF\u7684OCR\uff08Apache\u8bb8\u53ef\u8bc1\uff09\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u4f7f\u7528\u6307\u5357<\/h3>\n<ol>\n<li><strong>\u57fa\u672c\u4f7f\u7528<\/strong>\uff1a\n<ul>\n<li>\u5bfc\u5165\u5e93\u5e76\u521d\u59cb\u5316\uff1a <code>python<br \/>\nfrom kreuzberg import Kreuzberg<br \/>\nextractor = Kreuzberg()<br \/>\n<\/code><\/li>\n<li>\u63d0\u53d6PDF\u6587\u672c\uff1a <code>python<br \/>\ntext = extractor.extract_text('path\/to\/pdf\/file.pdf')<br \/>\nprint(text)<br \/>\n<\/code><\/li>\n<\/ul>\n<\/li>\n<li><strong>OCR\u529f\u80fd<\/strong>\uff1a\n<ul>\n<li>\u5bf9\u56fe\u50cf\u6216PDF\u8fdb\u884cOCR\uff1a <code>python<br \/>\nocr_text = extractor.ocr('path\/to\/image_or_pdf')<br \/>\nprint(ocr_text)<br \/>\n<\/code><\/li>\n<\/ul>\n<\/li>\n<li><strong>\u975ePDF\u6587\u672c\u63d0\u53d6<\/strong>\uff1a\n<ul>\n<li>\u4f7f\u7528Pandoc\u63d0\u53d6\u5176\u4ed6\u683c\u5f0f\u6587\u672c\uff1a <code>python<br \/>\nother_text = extractor.extract_text('path\/to\/other\/file')<br \/>\nprint(other_text)<br \/>\n<\/code><\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u8be6\u7ec6\u529f\u80fd\u64cd\u4f5c\u6d41\u7a0b<\/h3>\n<ol>\n<li><strong>PDF\u6587\u672c\u63d0\u53d6<\/strong>\uff1a\n<ul>\n<li>\u786e\u4fddPDF\u6587\u4ef6\u8def\u5f84\u6b63\u786e\u3002<\/li>\n<li>\u4f7f\u7528<code>extract_text<\/code>\u65b9\u6cd5\u63d0\u53d6\u6587\u672c\u3002<\/li>\n<li>\u5904\u7406\u63d0\u53d6\u7684\u6587\u672c\u6570\u636e\uff0c\u8fdb\u884c\u540e\u7eed\u64cd\u4f5c\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>OCR\u529f\u80fd<\/strong>\uff1a\n<ul>\n<li>\u5b89\u88c5\u5e76\u914d\u7f6eTesseract-OCR\u3002<\/li>\n<li>\u4f7f\u7528<code>ocr<\/code>\u65b9\u6cd5\u5bf9\u56fe\u50cf\u6216PDF\u8fdb\u884cOCR\u5904\u7406\u3002<\/li>\n<li>\u83b7\u53d6\u5e76\u5904\u7406OCR\u7ed3\u679c\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u975ePDF\u6587\u672c\u63d0\u53d6<\/strong>\uff1a\n<ul>\n<li>\u5b89\u88c5\u5e76\u914d\u7f6ePandoc\u3002<\/li>\n<li>\u4f7f\u7528<code>extract_text<\/code>\u65b9\u6cd5\u63d0\u53d6\u5176\u4ed6\u683c\u5f0f\u6587\u672c\u3002<\/li>\n<li>\u5904\u7406\u63d0\u53d6\u7684\u6587\u672c\u6570\u636e\uff0c\u8fdb\u884c\u540e\u7eed\u64cd\u4f5c\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u7528\u6237\u53ef\u4ee5\u8f7b\u677e\u4e0a\u624b\u4f7f\u7528Kreuzberg\u8fdb\u884c\u6587\u672c\u63d0\u53d6\u64cd\u4f5c\uff0c\u6ee1\u8db3\u5404\u79cd\u6587\u672c\u5904\u7406\u9700\u6c42\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Kreuzberg\u662f\u4e00\u4e2a\u7528\u4e8e\u7b80\u5316PDF\u6587\u4ef6\u6587\u672c\u63d0\u53d6\u7684\u5e93\uff0c\u65e8\u5728\u63d0\u4f9b\u7b80\u5355\u3001\u65e0\u5fe7\u7684\u6587\u672c\u63d0\u53d6\u89e3\u51b3\u65b9\u6848\u3002\u8be5\u5e93\u7279\u522b\u9002\u5408\u9700\u8981\u8fdb\u884c\u6587\u672c\u63d0\u53d6\u7684RAG\uff08Retrieval-Augmented Generation\uff09\u670d\u52a1\u3002Kreuzberg\u652f\u6301\u672c\u5730\u8fd0\u884c\uff0c\u6613\u4e8e\u63a7\u5236&#8230;<\/p>\n","protected":false},"author":1,"featured_media":32782,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20,499],"tags":[230,252],"class_list":["post-21149","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","category-document-extraction","tag-aikaiyuanxiangmu","tag-markdown"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts\/21149","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/comments?post=21149"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts\/21149\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/media\/32782"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/media?parent=21149"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/categories?post=21149"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/tags?post=21149"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}