{"id":15389,"date":"2024-12-13T11:25:28","date_gmt":"2024-12-13T03:25:28","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=15389"},"modified":"2025-08-25T00:56:31","modified_gmt":"2025-08-24T16:56:31","slug":"chunkr","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/de\/chunkr\/","title":{"rendered":"Chunkr\uff1a\u4f7f\u7528\u89c6\u89c9\u6a21\u578b\u8fdb\u884c\u6587\u6863\u6444\u53d6\u4ee5\u53ca\u6839\u636e\u6587\u672c\u6bb5\u843d\u5c42\u7ea7\u667a\u80fd\u5206\u5757\u7684\u4e00\u4f53\u5316\u670d\u52a1"},"content":{"rendered":"<p>Chunkr \u662f\u4e00\u4e2a\u81ea\u6258\u7ba1\u7684 API\uff0c\u4e13\u95e8\u7528\u4e8e\u5c06 PDF\u3001PPTX\u3001DOCX \u548c Excel \u6587\u4ef6\u8f6c\u6362\u4e3a\u9002\u5408 RAG\uff08\u68c0\u7d22\u589e\u5f3a\u751f\u6210\uff09\u548c LLM\uff08\u5927\u8bed\u8a00\u6a21\u578b\uff09\u4f7f\u7528\u7684\u6570\u636e\u3002\u8be5\u9879\u76ee\u7531 Lumina AI Inc. \u5f00\u53d1\uff0c\u5229\u7528\u5148\u8fdb\u7684\u89c6\u89c9\u6a21\u578b\u8fdb\u884c\u6587\u6863\u6444\u53d6\uff0c\u652f\u6301 OCR\uff08\u5149\u5b66\u5b57\u7b26\u8bc6\u522b\uff09\u548c\u8fb9\u754c\u6846\u68c0\u6d4b\uff0c\u751f\u6210\u7ed3\u6784\u5316\u7684 HTML \u548c Markdown \u683c\u5f0f\u6570\u636e\u3002Chunkr \u63d0\u4f9b\u4e86\u9ad8\u6548\u7684\u6587\u6863\u5904\u7406\u89e3\u51b3\u65b9\u6848\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u4f01\u4e1a\u548c\u5f00\u53d1\u8005\u9700\u6c42\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-15390\" title=\"Chunkr\uff1a\u4f7f\u7528\u89c6\u89c9\u6a21\u578b\u8fdb\u884c\u6587\u6863\u6444\u53d6\u4ee5\u53ca\u6839\u636e\u6587\u672c\u6bb5\u843d\u5c42\u7ea7\u667a\u80fd\u5206\u5757\u7684\u4e00\u4f53\u5316\u670d\u52a1-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/a5c82396b104f3b.png\" alt=\"Chunkr\uff1a\u4f7f\u7528\u89c6\u89c9\u6a21\u578b\u8fdb\u884c\u6587\u6863\u6444\u53d6\u4ee5\u53ca\u6839\u636e\u6587\u672c\u6bb5\u843d\u5c42\u7ea7\u667a\u80fd\u5206\u5757\u7684\u4e00\u4f53\u5316\u670d\u52a1-1\" width=\"1172\" height=\"816\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/a5c82396b104f3b.png 1172w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/a5c82396b104f3b-300x209.png 300w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/a5c82396b104f3b-1024x713.png 1024w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/a5c82396b104f3b-768x535.png 768w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/12\/a5c82396b104f3b-18x12.png 18w\" sizes=\"auto, (max-width: 1172px) 100vw, 1172px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>\u6587\u6863\u8f6c\u6362<\/strong>\uff1a\u652f\u6301\u5c06 PDF\u3001PPTX\u3001DOCX \u548c Excel \u6587\u4ef6\u8f6c\u6362\u4e3a RAG\/LLM \u6570\u636e\u3002<\/li>\n<li><strong>OCR \u652f\u6301<\/strong>\uff1a\u96c6\u6210\u5149\u5b66\u5b57\u7b26\u8bc6\u522b\u6280\u672f\uff0c\u81ea\u52a8\u8bc6\u522b\u6587\u6863\u4e2d\u7684\u6587\u672c\u5185\u5bb9\u3002<\/li>\n<li><strong>\u8fb9\u754c\u6846\u68c0\u6d4b<\/strong>\uff1a\u901a\u8fc7\u89c6\u89c9\u6a21\u578b\u68c0\u6d4b\u6587\u6863\u5e03\u5c40\uff0c\u751f\u6210\u7cbe\u786e\u7684\u8fb9\u754c\u6846\u3002<\/li>\n<li><strong>\u7ed3\u6784\u5316\u8f93\u51fa<\/strong>\uff1a\u751f\u6210\u7ed3\u6784\u5316\u7684 HTML \u548c Markdown \u683c\u5f0f\uff0c\u4fbf\u4e8e\u540e\u7eed\u5904\u7406\u548c\u4f7f\u7528\u3002<\/li>\n<li><strong>\u81ea\u6258\u7ba1<\/strong>\uff1a\u652f\u6301 Docker \u548c Kubernetes \u90e8\u7f72\uff0c\u7528\u6237\u53ef\u4ee5\u5728\u672c\u5730\u6216\u4e91\u7aef\u81ea\u6258\u7ba1\u670d\u52a1\u3002<\/li>\n<li><strong>\u9ad8\u53ef\u7528\u6027\u548c\u6269\u5c55\u6027<\/strong>\uff1a\u63d0\u4f9b\u9ad8\u53ef\u7528\u6027\u914d\u7f6e\u548c\u6269\u5c55\u6307\u5357\uff0c\u9002\u5e94\u4f01\u4e1a\u7ea7\u5e94\u7528\u9700\u6c42\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<h4>Docker Compose \u5feb\u901f\u542f\u52a8<\/h4>\n<ol>\n<li><strong>\u5b89\u88c5\u524d\u63d0<\/strong>\uff1a\u786e\u4fdd\u5df2\u5b89\u88c5 Docker \u548c Docker Compose\u3002<\/li>\n<li><strong>\u514b\u9686\u4ed3\u5e93<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   git clone https:\/\/github.com\/lumina-ai-inc\/chunkr\r\ncd chunkr\r\n<\/code><\/pre>\n<ol start=\"3\">\n<li><strong>\u590d\u5236\u73af\u5883\u914d\u7f6e\u6587\u4ef6<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   cp .env.example .env\r\n<\/code><\/pre>\n<ol start=\"4\">\n<li><strong>\u542f\u52a8\u670d\u52a1<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   docker compose up -d\r\n<\/code><\/pre>\n<ol start=\"5\">\n<li><strong>\u8bbf\u95ee\u670d\u52a1<\/strong>\uff1a\n<ul>\n<li>Web UI: http:\/\/localhost:5173<\/li>\n<li>API: http:\/\/localhost:8000<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h4>Kubernetes \u751f\u4ea7\u73af\u5883\u90e8\u7f72<\/h4>\n<ol>\n<li><strong>\u51c6\u5907\u5de5\u4f5c<\/strong>\uff1a\u786e\u4fdd\u5df2\u5b89\u88c5 Kubernetes \u96c6\u7fa4\u548c kubectl\u3002<\/li>\n<li><strong>\u90e8\u7f72\u670d\u52a1<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   kubectl apply -f kubernetes-manifests\/\r\n<\/code><\/pre>\n<ol start=\"3\">\n<li><strong>\u914d\u7f6e\u9ad8\u53ef\u7528\u6027\u548c\u6269\u5c55<\/strong>\uff1a\u53c2\u8003 <code>self-deployment.md<\/code> \u6587\u6863\uff0c\u8fdb\u884c\u9ad8\u53ef\u7528\u6027\u914d\u7f6e\u548c\u6269\u5c55\u3002<\/li>\n<\/ol>\n<h3>\u4f7f\u7528\u6307\u5357<\/h3>\n<ol>\n<li><strong>\u521b\u5efa\u8d26\u6237\u5e76\u83b7\u53d6 API \u5bc6\u94a5<\/strong>\uff1a\n<ul>\n<li>\u8bbf\u95ee chunkr.ai \u6ce8\u518c\u8d26\u6237\u3002<\/li>\n<li>\u767b\u5f55\u540e\u83b7\u53d6 API \u5bc6\u94a5\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u521b\u5efa\u4efb\u52a1<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   curl -X POST https:\/\/api.chunkr.ai\/api\/v1\/task \\\r\n-H \"Content-Type: multipart\/form-data\" \\\r\n-H \"Authorization: ${YOUR_API_KEY}\" \\\r\n-F \"file=@\/path\/to\/your\/file\" \\\r\n-F \"model=HighQuality\" \\\r\n-F \"target_chunk_length=512\" \\\r\n-F \"ocr_strategy=Auto\"\r\n<\/code><\/pre>\n<ol start=\"3\">\n<li><strong>\u8f6e\u8be2\u4efb\u52a1\u72b6\u6001<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   curl -X GET https:\/\/api.chunkr.ai\/api\/v1\/task\/${TASK_ID} \\\r\n-H \"Authorization: ${YOUR_API_KEY}\"\r\n<\/code><\/pre>\n<h3>\u4e3b\u8981\u529f\u80fd\u64cd\u4f5c\u6d41\u7a0b<\/h3>\n<ul>\n<li><strong>\u6587\u6863\u8f6c\u6362<\/strong>\uff1a\u4e0a\u4f20\u6587\u4ef6\u540e\uff0c\u9009\u62e9\u8f6c\u6362\u6a21\u578b\u548c\u76ee\u6807\u5757\u957f\u5ea6\uff0c\u7cfb\u7edf\u4f1a\u81ea\u52a8\u5904\u7406\u5e76\u8fd4\u56de\u7ed3\u6784\u5316\u6570\u636e\u3002<\/li>\n<li><strong>OCR \u8bc6\u522b<\/strong>\uff1a\u5728\u4e0a\u4f20\u6587\u4ef6\u65f6\u9009\u62e9 OCR \u7b56\u7565\uff0c\u7cfb\u7edf\u4f1a\u81ea\u52a8\u8bc6\u522b\u6587\u6863\u4e2d\u7684\u6587\u672c\u5185\u5bb9\u5e76\u751f\u6210\u8fb9\u754c\u6846\u3002<\/li>\n<li><strong>\u7ed3\u679c\u67e5\u770b<\/strong>\uff1a\u901a\u8fc7 API \u6216 Web UI \u67e5\u770b\u8f6c\u6362\u540e\u7684\u7ed3\u6784\u5316\u6570\u636e\uff0c\u652f\u6301 HTML \u548c Markdown \u683c\u5f0f\u3002<\/li>\n<\/ul>\n<p>Chunkr \u63d0\u4f9b\u4e86\u8be6\u7ec6\u7684\u6587\u6863\u548c\u793a\u4f8b\u4ee3\u7801\uff0c\u5e2e\u52a9\u7528\u6237\u5feb\u901f\u4e0a\u624b\u5e76\u96c6\u6210\u5230\u73b0\u6709\u7cfb\u7edf\u4e2d\u3002\u65e0\u8bba\u662f\u5f00\u53d1\u8005\u8fd8\u662f\u4f01\u4e1a\u7528\u6237\uff0c\u90fd\u53ef\u4ee5\u5229\u7528 Chunkr \u9ad8\u6548\u5904\u7406\u548c\u8f6c\u6362\u6587\u6863\uff0c\u63d0\u5347\u5de5\u4f5c\u6548\u7387\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Chunkr \u662f\u4e00\u4e2a\u81ea\u6258\u7ba1\u7684 API\uff0c\u4e13\u95e8\u7528\u4e8e\u5c06 PDF\u3001PPTX\u3001DOCX \u548c Excel \u6587\u4ef6\u8f6c\u6362\u4e3a\u9002\u5408 RAG\uff08\u68c0\u7d22\u589e\u5f3a\u751f\u6210\uff09\u548c LLM\uff08\u5927\u8bed\u8a00\u6a21\u578b\uff09\u4f7f\u7528\u7684\u6570\u636e\u3002\u8be5\u9879\u76ee\u7531 Lumina AI Inc. \u5f00\u53d1\uff0c\u5229\u7528\u5148\u8fdb\u7684\u89c6\u89c9\u6a21\u578b\u8fdb\u884c\u6587\u6863&#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":[230,248,252],"class_list":["post-15389","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","category-document-extraction","tag-aikaiyuanxiangmu","tag-ocr","tag-markdown"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts\/15389","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/comments?post=15389"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts\/15389\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/media\/32782"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/media?parent=15389"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/categories?post=15389"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/tags?post=15389"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}