{"id":119350,"date":"2026-10-29T12:48:52","date_gmt":"2026-10-29T04:48:52","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/119350.html"},"modified":"2026-10-29T12:48:52","modified_gmt":"2026-10-29T04:48:52","slug":"agent%e8%ae%b0%e5%bf%86%e4%b8%8e%e6%a3%80%e7%b4%a204%ef%bc%9arag%e6%96%87%e6%a1%a3%e5%a4%84%e7%90%86%e7%ae%a1%e9%81%93","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/119350.html","title":{"rendered":"Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053"},"content":{"rendered":"<h2>RAG \u6587\u6863\u5904\u7406\u7ba1\u9053&#xff1a;MarkItDown\u3001\u667a\u80fd\u5206\u5757\u4e0e\u5411\u91cf\u5316<\/h2>\n<p>\u6458\u8981&#xff1a;\u672c\u6587\u8fdb\u5165 HelloAgents \u7684 RAG \u7cfb\u7edf&#xff0c;\u5305\u62ec RAG \u4f53\u9a8c\u3001RAGTool \u521d\u59cb\u5316\u3001\u591a\u683c\u5f0f\u8f6c\u6362\u3001Markdown \u5206\u5757\u3001Token \u4f30\u7b97\u548c\u5411\u91cf\u7d22\u5f15\u4ee3\u7801\u3002<\/p>\n<hr \/>\n<h3>\u4e00\u3001RAG \u8981\u89e3\u51b3\u4ec0\u4e48\u95ee\u9898<\/h3>\n<p>\u68c0\u7d22\u589e\u5f3a\u751f\u6210&#xff08;Retrieval-Augmented Generation&#xff0c;RAG&#xff09;\u7684\u6838\u5fc3\u662f\u628a\u201c\u4ece\u6a21\u578b\u53c2\u6570\u91cc\u56de\u5fc6\u77e5\u8bc6\u201d\u6539\u6210\u201c\u4ece\u5916\u90e8\u77e5\u8bc6\u5e93\u68c0\u7d22\u77e5\u8bc6&#xff0c;\u518d\u4ea4\u7ed9\u6a21\u578b\u751f\u6210\u201d\u3002\u4e09\u4e2a\u8bcd\u5206\u522b\u5bf9\u5e94\u4e09\u4e2a\u9636\u6bb5&#xff1a;<\/p>\n<ul>\n<li>\u68c0\u7d22&#xff1a;\u4ece\u77e5\u8bc6\u5e93\u4e2d\u67e5\u8be2\u76f8\u5173\u5185\u5bb9\u3002<\/li>\n<li>\u589e\u5f3a&#xff1a;\u628a\u68c0\u7d22\u7ed3\u679c\u878d\u5165\u63d0\u793a\u8bcd&#xff0c;\u8f85\u52a9\u6a21\u578b\u751f\u6210\u3002<\/li>\n<li>\u751f\u6210&#xff1a;\u8f93\u51fa\u517c\u5177\u51c6\u786e\u6027\u4e0e\u900f\u660e\u5ea6\u7684\u7b54\u6848\u3002<\/li>\n<\/ul>\n<p>RAG \u7684\u6f14\u8fdb\u53ef\u4ee5\u770b\u6210\u68c0\u7d22\u80fd\u529b\u548c\u6a21\u5757\u5316\u7a0b\u5ea6\u4e0d\u65ad\u63d0\u5347\u7684\u8fc7\u7a0b\u3002<\/p>\n<p>#mermaid-svg-wJzoyx5Xf5QpTmXM{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-wJzoyx5Xf5QpTmXM .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-wJzoyx5Xf5QpTmXM .error-icon{fill:#552222;}#mermaid-svg-wJzoyx5Xf5QpTmXM .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-wJzoyx5Xf5QpTmXM .marker{fill:#333333;stroke:#333333;}#mermaid-svg-wJzoyx5Xf5QpTmXM .marker.cross{stroke:#333333;}#mermaid-svg-wJzoyx5Xf5QpTmXM svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-wJzoyx5Xf5QpTmXM p{margin:0;}#mermaid-svg-wJzoyx5Xf5QpTmXM .label{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;color:#333;}#mermaid-svg-wJzoyx5Xf5QpTmXM .cluster-label text{fill:#333;}#mermaid-svg-wJzoyx5Xf5QpTmXM .cluster-label span{color:#333;}#mermaid-svg-wJzoyx5Xf5QpTmXM .cluster-label span p{background-color:transparent;}#mermaid-svg-wJzoyx5Xf5QpTmXM .label text,#mermaid-svg-wJzoyx5Xf5QpTmXM span{fill:#333;color:#333;}#mermaid-svg-wJzoyx5Xf5QpTmXM .node rect,#mermaid-svg-wJzoyx5Xf5QpTmXM .node circle,#mermaid-svg-wJzoyx5Xf5QpTmXM .node ellipse,#mermaid-svg-wJzoyx5Xf5QpTmXM .node polygon,#mermaid-svg-wJzoyx5Xf5QpTmXM .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#mermaid-svg-wJzoyx5Xf5QpTmXM .rough-node .label text,#mermaid-svg-wJzoyx5Xf5QpTmXM .node .label text,#mermaid-svg-wJzoyx5Xf5QpTmXM .image-shape .label,#mermaid-svg-wJzoyx5Xf5QpTmXM .icon-shape .label{text-anchor:middle;}#mermaid-svg-wJzoyx5Xf5QpTmXM .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-svg-wJzoyx5Xf5QpTmXM .rough-node .label,#mermaid-svg-wJzoyx5Xf5QpTmXM .node .label,#mermaid-svg-wJzoyx5Xf5QpTmXM .image-shape .label,#mermaid-svg-wJzoyx5Xf5QpTmXM .icon-shape .label{text-align:center;}#mermaid-svg-wJzoyx5Xf5QpTmXM .node.clickable{cursor:pointer;}#mermaid-svg-wJzoyx5Xf5QpTmXM .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#mermaid-svg-wJzoyx5Xf5QpTmXM .arrowheadPath{fill:#333333;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edgePath .path{stroke:#333333;stroke-width:2.0px;}#mermaid-svg-wJzoyx5Xf5QpTmXM .flowchart-link{stroke:#333333;fill:none;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-wJzoyx5Xf5QpTmXM .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#mermaid-svg-wJzoyx5Xf5QpTmXM .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-wJzoyx5Xf5QpTmXM .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#mermaid-svg-wJzoyx5Xf5QpTmXM .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#mermaid-svg-wJzoyx5Xf5QpTmXM .cluster text{fill:#333;}#mermaid-svg-wJzoyx5Xf5QpTmXM .cluster span{color:#333;}#mermaid-svg-wJzoyx5Xf5QpTmXM div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-svg-wJzoyx5Xf5QpTmXM .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#mermaid-svg-wJzoyx5Xf5QpTmXM rect.text{fill:none;stroke-width:0;}#mermaid-svg-wJzoyx5Xf5QpTmXM .icon-shape,#mermaid-svg-wJzoyx5Xf5QpTmXM .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-wJzoyx5Xf5QpTmXM .icon-shape p,#mermaid-svg-wJzoyx5Xf5QpTmXM .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#mermaid-svg-wJzoyx5Xf5QpTmXM .icon-shape .label rect,#mermaid-svg-wJzoyx5Xf5QpTmXM .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-wJzoyx5Xf5QpTmXM .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#mermaid-svg-wJzoyx5Xf5QpTmXM .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#mermaid-svg-wJzoyx5Xf5QpTmXM :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6734\u7d20 RAGTF-IDF \/ BM25 &#043; \u76f4\u63a5\u62fc\u63a5<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u9ad8\u7ea7 RAG\u7a20\u5bc6\u5d4c\u5165 &#043; \u91cd\u6392\u5e8f<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6a21\u5757\u5316 RAG\u6df7\u5408\u68c0\u7d22\u3001MQE\u3001HyDE<\/p>\n<p><\/span><\/p>\n<p>\u4e00\u4e2a\u5b8c\u6574 RAG \u5e94\u7528\u901a\u5e38\u5305\u542b\u79bb\u7ebf\u51c6\u5907\u548c\u5728\u7ebf\u95ee\u7b54\u4e24\u4e2a\u73af\u8282&#xff1a;<\/p>\n<p>#mermaid-svg-o2ydqzEik6CVD8N3{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-o2ydqzEik6CVD8N3 .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-o2ydqzEik6CVD8N3 .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-o2ydqzEik6CVD8N3 .error-icon{fill:#552222;}#mermaid-svg-o2ydqzEik6CVD8N3 .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-o2ydqzEik6CVD8N3 .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-o2ydqzEik6CVD8N3 .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-o2ydqzEik6CVD8N3 .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-o2ydqzEik6CVD8N3 .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-o2ydqzEik6CVD8N3 .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-o2ydqzEik6CVD8N3 .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-o2ydqzEik6CVD8N3 .marker{fill:#333333;stroke:#333333;}#mermaid-svg-o2ydqzEik6CVD8N3 .marker.cross{stroke:#333333;}#mermaid-svg-o2ydqzEik6CVD8N3 svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-o2ydqzEik6CVD8N3 p{margin:0;}#mermaid-svg-o2ydqzEik6CVD8N3 .label{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;color:#333;}#mermaid-svg-o2ydqzEik6CVD8N3 .cluster-label text{fill:#333;}#mermaid-svg-o2ydqzEik6CVD8N3 .cluster-label span{color:#333;}#mermaid-svg-o2ydqzEik6CVD8N3 .cluster-label span p{background-color:transparent;}#mermaid-svg-o2ydqzEik6CVD8N3 .label text,#mermaid-svg-o2ydqzEik6CVD8N3 span{fill:#333;color:#333;}#mermaid-svg-o2ydqzEik6CVD8N3 .node rect,#mermaid-svg-o2ydqzEik6CVD8N3 .node circle,#mermaid-svg-o2ydqzEik6CVD8N3 .node ellipse,#mermaid-svg-o2ydqzEik6CVD8N3 .node polygon,#mermaid-svg-o2ydqzEik6CVD8N3 .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#mermaid-svg-o2ydqzEik6CVD8N3 .rough-node .label text,#mermaid-svg-o2ydqzEik6CVD8N3 .node .label text,#mermaid-svg-o2ydqzEik6CVD8N3 .image-shape .label,#mermaid-svg-o2ydqzEik6CVD8N3 .icon-shape .label{text-anchor:middle;}#mermaid-svg-o2ydqzEik6CVD8N3 .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-svg-o2ydqzEik6CVD8N3 .rough-node .label,#mermaid-svg-o2ydqzEik6CVD8N3 .node .label,#mermaid-svg-o2ydqzEik6CVD8N3 .image-shape .label,#mermaid-svg-o2ydqzEik6CVD8N3 .icon-shape .label{text-align:center;}#mermaid-svg-o2ydqzEik6CVD8N3 .node.clickable{cursor:pointer;}#mermaid-svg-o2ydqzEik6CVD8N3 .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#mermaid-svg-o2ydqzEik6CVD8N3 .arrowheadPath{fill:#333333;}#mermaid-svg-o2ydqzEik6CVD8N3 .edgePath .path{stroke:#333333;stroke-width:2.0px;}#mermaid-svg-o2ydqzEik6CVD8N3 .flowchart-link{stroke:#333333;fill:none;}#mermaid-svg-o2ydqzEik6CVD8N3 .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-o2ydqzEik6CVD8N3 .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#mermaid-svg-o2ydqzEik6CVD8N3 .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-o2ydqzEik6CVD8N3 .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#mermaid-svg-o2ydqzEik6CVD8N3 .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#mermaid-svg-o2ydqzEik6CVD8N3 .cluster text{fill:#333;}#mermaid-svg-o2ydqzEik6CVD8N3 .cluster span{color:#333;}#mermaid-svg-o2ydqzEik6CVD8N3 div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-svg-o2ydqzEik6CVD8N3 .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#mermaid-svg-o2ydqzEik6CVD8N3 rect.text{fill:none;stroke-width:0;}#mermaid-svg-o2ydqzEik6CVD8N3 .icon-shape,#mermaid-svg-o2ydqzEik6CVD8N3 .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-o2ydqzEik6CVD8N3 .icon-shape p,#mermaid-svg-o2ydqzEik6CVD8N3 .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#mermaid-svg-o2ydqzEik6CVD8N3 .icon-shape .label rect,#mermaid-svg-o2ydqzEik6CVD8N3 .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-o2ydqzEik6CVD8N3 .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#mermaid-svg-o2ydqzEik6CVD8N3 .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#mermaid-svg-o2ydqzEik6CVD8N3 :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<span class=\"nodeLabel\"><\/p>\n<p>\u5e94\u7528\u9636\u6bb5<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6570\u636e\u51c6\u5907\u9636\u6bb5<\/p>\n<p><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6570\u636e\u63d0\u53d6<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6587\u672c\u5206\u5272<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u5411\u91cf\u5316<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u5199\u5165\u5411\u91cf\u6570\u636e\u5e93<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u7528\u6237\u63d0\u95ee<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u68c0\u7d22\u76f8\u5173\u4fe1\u606f<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6ce8\u5165 Prompt<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>LLM \u751f\u6210\u7b54\u6848<\/p>\n<p><\/span><\/p>\n<h3>\u4e8c\u3001\u5feb\u901f\u4f53\u9a8c<\/h3>\n<p>\u5148\u7528 RAGTool \u6dfb\u52a0\u4e09\u6bb5\u6587\u672c\u77e5\u8bc6&#xff0c;\u518d\u505a\u4e00\u6b21\u8bed\u4e49\u641c\u7d22\u3002<\/p>\n<p><span class=\"token keyword\">from<\/span> hello_agents <span class=\"token keyword\">import<\/span> SimpleAgent<span class=\"token punctuation\">,<\/span> HelloAgentsLLM<span class=\"token punctuation\">,<\/span> ToolRegistry<br \/>\n<span class=\"token keyword\">from<\/span> hello_agents<span class=\"token punctuation\">.<\/span>tools <span class=\"token keyword\">import<\/span> RAGTool<\/p>\n<p><span class=\"token comment\"># \u521b\u5efaLLM\u5b9e\u4f8b<\/span><br \/>\nllm <span class=\"token operator\">&#061;<\/span> HelloAgentsLLM<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u521b\u5efaRAG\u5de5\u5177<\/span><br \/>\nrag_tool <span class=\"token operator\">&#061;<\/span> RAGTool<span class=\"token punctuation\">(<\/span><br \/>\n    knowledge_base_path<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;.\/knowledge_base&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    collection_name<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;test_collection&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    rag_namespace<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;test&#034;<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<p>tool_registry <span class=\"token operator\">&#061;<\/span> ToolRegistry<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\ntool_registry<span class=\"token punctuation\">.<\/span>register_tool<span class=\"token punctuation\">(<\/span>rag_tool<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u521b\u5efa\u5177\u6709RAG\u80fd\u529b\u7684Agent<\/span><br \/>\nagent <span class=\"token operator\">&#061;<\/span> SimpleAgent<span class=\"token punctuation\">(<\/span>name<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;\u77e5\u8bc6\u52a9\u624b&#034;<\/span><span class=\"token punctuation\">,<\/span> llm<span class=\"token operator\">&#061;<\/span>llm<span class=\"token punctuation\">,<\/span> tool_registry<span class=\"token operator\">&#061;<\/span>tool_registry<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u4f53\u9a8cRAG\u529f\u80fd<\/span><br \/>\n<span class=\"token comment\"># \u6dfb\u52a0\u7b2c\u4e00\u4e2a\u77e5\u8bc6<\/span><br \/>\nresult1 <span class=\"token operator\">&#061;<\/span> rag_tool<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;add_text&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    text<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;Python\u662f\u4e00\u79cd\u9ad8\u7ea7\u7f16\u7a0b\u8bed\u8a00&#xff0c;\u7531Guido van Rossum\u4e8e1991\u5e74\u9996\u6b21\u53d1\u5e03\u3002Python\u7684\u8bbe\u8ba1\u54f2\u5b66\u5f3a\u8c03\u4ee3\u7801\u7684\u53ef\u8bfb\u6027\u548c\u7b80\u6d01\u7684\u8bed\u6cd5\u3002&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    document_id<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;python_intro&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u77e5\u8bc61: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>result1<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u6dfb\u52a0\u7b2c\u4e8c\u4e2a\u77e5\u8bc6  <\/span><br \/>\nresult2 <span class=\"token operator\">&#061;<\/span> rag_tool<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;add_text&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    text<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;\u673a\u5668\u5b66\u4e60\u662f\u4eba\u5de5\u667a\u80fd\u7684\u4e00\u4e2a\u5206\u652f&#xff0c;\u901a\u8fc7\u7b97\u6cd5\u8ba9\u8ba1\u7b97\u673a\u4ece\u6570\u636e\u4e2d\u5b66\u4e60\u6a21\u5f0f\u3002\u4e3b\u8981\u5305\u62ec\u76d1\u7763\u5b66\u4e60\u3001\u65e0\u76d1\u7763\u5b66\u4e60\u548c\u5f3a\u5316\u5b66\u4e60\u4e09\u79cd\u7c7b\u578b\u3002&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    document_id<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;ml_basics&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u77e5\u8bc62: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>result2<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u6dfb\u52a0\u7b2c\u4e09\u4e2a\u77e5\u8bc6<\/span><br \/>\nresult3 <span class=\"token operator\">&#061;<\/span> rag_tool<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;add_text&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    text<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;RAG&#xff08;\u68c0\u7d22\u589e\u5f3a\u751f\u6210&#xff09;\u662f\u4e00\u79cd\u7ed3\u5408\u4fe1\u606f\u68c0\u7d22\u548c\u6587\u672c\u751f\u6210\u7684AI\u6280\u672f\u3002\u5b83\u901a\u8fc7\u68c0\u7d22\u76f8\u5173\u77e5\u8bc6\u6765\u589e\u5f3a\u5927\u8bed\u8a00\u6a21\u578b\u7684\u751f\u6210\u80fd\u529b\u3002&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    document_id<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;rag_concept&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;\u77e5\u8bc63: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>result3<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\\\\n&#061;&#061;&#061; \u641c\u7d22\u77e5\u8bc6 &#061;&#061;&#061;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nresult <span class=\"token operator\">&#061;<\/span> rag_tool<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;search&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    query<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;Python\u7f16\u7a0b\u8bed\u8a00\u7684\u5386\u53f2&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    limit<span class=\"token operator\">&#061;<\/span><span class=\"token number\">3<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    min_score<span class=\"token operator\">&#061;<\/span><span class=\"token number\">0.1<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>result<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\\\\n&#061;&#061;&#061; \u77e5\u8bc6\u5e93\u7edf\u8ba1 &#061;&#061;&#061;&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nresult <span class=\"token operator\">&#061;<\/span> rag_tool<span class=\"token punctuation\">.<\/span>execute<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;stats&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>result<span class=\"token punctuation\">)<\/span><\/p>\n<h3>\u4e09\u3001\u4e94\u5c42\u4e03\u6b65\u67b6\u6784<\/h3>\n<p>\u4e0e\u8bb0\u5fc6\u7cfb\u7edf\u4e0d\u540c&#xff0c;RAG \u88ab\u8bbe\u8ba1\u6210\u4e00\u6761\u6e05\u6670\u7684 pipeline\u3002\u6574\u4f53\u53ef\u4ee5\u6982\u62ec\u4e3a\u201c\u4e94\u5c42\u4e03\u6b65\u201d\u3002<\/p>\n<p>#mermaid-svg-SEpiQRo9hHPIL2ok{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-SEpiQRo9hHPIL2ok .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-SEpiQRo9hHPIL2ok .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-SEpiQRo9hHPIL2ok .error-icon{fill:#552222;}#mermaid-svg-SEpiQRo9hHPIL2ok .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-SEpiQRo9hHPIL2ok .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-SEpiQRo9hHPIL2ok .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-SEpiQRo9hHPIL2ok .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-SEpiQRo9hHPIL2ok .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-SEpiQRo9hHPIL2ok .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-SEpiQRo9hHPIL2ok .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-SEpiQRo9hHPIL2ok .marker{fill:#333333;stroke:#333333;}#mermaid-svg-SEpiQRo9hHPIL2ok .marker.cross{stroke:#333333;}#mermaid-svg-SEpiQRo9hHPIL2ok svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-SEpiQRo9hHPIL2ok p{margin:0;}#mermaid-svg-SEpiQRo9hHPIL2ok .label{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;color:#333;}#mermaid-svg-SEpiQRo9hHPIL2ok .cluster-label text{fill:#333;}#mermaid-svg-SEpiQRo9hHPIL2ok .cluster-label span{color:#333;}#mermaid-svg-SEpiQRo9hHPIL2ok .cluster-label span p{background-color:transparent;}#mermaid-svg-SEpiQRo9hHPIL2ok .label text,#mermaid-svg-SEpiQRo9hHPIL2ok span{fill:#333;color:#333;}#mermaid-svg-SEpiQRo9hHPIL2ok .node rect,#mermaid-svg-SEpiQRo9hHPIL2ok .node circle,#mermaid-svg-SEpiQRo9hHPIL2ok .node ellipse,#mermaid-svg-SEpiQRo9hHPIL2ok .node polygon,#mermaid-svg-SEpiQRo9hHPIL2ok .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#mermaid-svg-SEpiQRo9hHPIL2ok .rough-node .label text,#mermaid-svg-SEpiQRo9hHPIL2ok .node .label text,#mermaid-svg-SEpiQRo9hHPIL2ok .image-shape .label,#mermaid-svg-SEpiQRo9hHPIL2ok .icon-shape .label{text-anchor:middle;}#mermaid-svg-SEpiQRo9hHPIL2ok .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-svg-SEpiQRo9hHPIL2ok .rough-node .label,#mermaid-svg-SEpiQRo9hHPIL2ok .node .label,#mermaid-svg-SEpiQRo9hHPIL2ok .image-shape .label,#mermaid-svg-SEpiQRo9hHPIL2ok .icon-shape .label{text-align:center;}#mermaid-svg-SEpiQRo9hHPIL2ok .node.clickable{cursor:pointer;}#mermaid-svg-SEpiQRo9hHPIL2ok .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#mermaid-svg-SEpiQRo9hHPIL2ok .arrowheadPath{fill:#333333;}#mermaid-svg-SEpiQRo9hHPIL2ok .edgePath .path{stroke:#333333;stroke-width:2.0px;}#mermaid-svg-SEpiQRo9hHPIL2ok .flowchart-link{stroke:#333333;fill:none;}#mermaid-svg-SEpiQRo9hHPIL2ok .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-SEpiQRo9hHPIL2ok .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#mermaid-svg-SEpiQRo9hHPIL2ok .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-SEpiQRo9hHPIL2ok .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#mermaid-svg-SEpiQRo9hHPIL2ok .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#mermaid-svg-SEpiQRo9hHPIL2ok .cluster text{fill:#333;}#mermaid-svg-SEpiQRo9hHPIL2ok .cluster span{color:#333;}#mermaid-svg-SEpiQRo9hHPIL2ok div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-svg-SEpiQRo9hHPIL2ok .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#mermaid-svg-SEpiQRo9hHPIL2ok rect.text{fill:none;stroke-width:0;}#mermaid-svg-SEpiQRo9hHPIL2ok .icon-shape,#mermaid-svg-SEpiQRo9hHPIL2ok .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-SEpiQRo9hHPIL2ok .icon-shape p,#mermaid-svg-SEpiQRo9hHPIL2ok .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#mermaid-svg-SEpiQRo9hHPIL2ok .icon-shape .label rect,#mermaid-svg-SEpiQRo9hHPIL2ok .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-SEpiQRo9hHPIL2ok .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#mermaid-svg-SEpiQRo9hHPIL2ok .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#mermaid-svg-SEpiQRo9hHPIL2ok :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u7528\u6237\u5c42&#xff1a;RAGTool \u7edf\u4e00\u63a5\u53e3<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u5e94\u7528\u5c42&#xff1a;\u667a\u80fd\u95ee\u7b54\u3001\u641c\u7d22\u3001\u7ba1\u7406<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u5904\u7406\u5c42&#xff1a;\u6587\u6863\u89e3\u6790\u3001\u5206\u5757\u3001\u5411\u91cf\u5316<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u5b58\u50a8\u5c42&#xff1a;\u5411\u91cf\u6570\u636e\u5e93\u3001\u6587\u6863\u5b58\u50a8<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u57fa\u7840\u5c42&#xff1a;\u5d4c\u5165\u6a21\u578b\u3001LLM\u3001\u6570\u636e\u5e93<\/p>\n<p><\/span><\/p>\n<p>RAGTool \u4f5c\u4e3a\u7edf\u4e00\u5165\u53e3&#xff0c;\u521b\u5efa\u547d\u540d\u7a7a\u95f4\u9694\u79bb\u7684 RAG \u7ba1\u9053&#xff1a;<\/p>\n<p><span class=\"token keyword\">class<\/span> <span class=\"token class-name\">RAGTool<\/span><span class=\"token punctuation\">(<\/span>Tool<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;RAG\u5de5\u5177<\/p>\n<p>    \u63d0\u4f9b\u5b8c\u6574\u7684 RAG \u80fd\u529b&#xff1a;<br \/>\n    &#8211; \u6dfb\u52a0\u591a\u683c\u5f0f\u6587\u6863&#xff08;PDF\u3001Office\u3001\u56fe\u7247\u3001\u97f3\u9891\u7b49&#xff09;<br \/>\n    &#8211; \u667a\u80fd\u68c0\u7d22\u4e0e\u53ec\u56de<br \/>\n    &#8211; LLM \u589e\u5f3a\u95ee\u7b54<br \/>\n    &#8211; \u77e5\u8bc6\u5e93\u7ba1\u7406<br \/>\n    &#034;&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">__init__<\/span><span class=\"token punctuation\">(<\/span><br \/>\n        self<span class=\"token punctuation\">,<\/span><br \/>\n        knowledge_base_path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;.\/knowledge_base&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        qdrant_url<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        qdrant_api_key<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        collection_name<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;rag_knowledge_base&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        rag_namespace<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;default&#034;<\/span><br \/>\n    <span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token comment\"># \u521d\u59cb\u5316RAG\u7ba1\u9053<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>_pipelines<span class=\"token punctuation\">:<\/span> Dict<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Dict<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">,<\/span> Any<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token punctuation\">}<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>llm <span class=\"token operator\">&#061;<\/span> HelloAgentsLLM<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token comment\"># \u521b\u5efa\u9ed8\u8ba4\u7ba1\u9053<\/span><br \/>\n        default_pipeline <span class=\"token operator\">&#061;<\/span> create_rag_pipeline<span class=\"token punctuation\">(<\/span><br \/>\n            qdrant_url<span class=\"token operator\">&#061;<\/span>self<span class=\"token punctuation\">.<\/span>qdrant_url<span class=\"token punctuation\">,<\/span><br \/>\n            qdrant_api_key<span class=\"token operator\">&#061;<\/span>self<span class=\"token punctuation\">.<\/span>qdrant_api_key<span class=\"token punctuation\">,<\/span><br \/>\n            collection_name<span class=\"token operator\">&#061;<\/span>self<span class=\"token punctuation\">.<\/span>collection_name<span class=\"token punctuation\">,<\/span><br \/>\n            rag_namespace<span class=\"token operator\">&#061;<\/span>self<span class=\"token punctuation\">.<\/span>rag_namespace<br \/>\n        <span class=\"token punctuation\">)<\/span><br \/>\n        self<span class=\"token punctuation\">.<\/span>_pipelines<span class=\"token punctuation\">[<\/span>self<span class=\"token punctuation\">.<\/span>rag_namespace<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> default_pipeline<\/p>\n<p>\u6574\u6761\u5904\u7406\u6d41\u7a0b\u53ef\u4ee5\u538b\u7f29\u4e3a&#xff1a;<\/p>\n<p>\u4efb\u610f\u683c\u5f0f\u6587\u6863 \u2192 MarkItDown\u8f6c\u6362 \u2192 Markdown\u6587\u672c \u2192 \u667a\u80fd\u5206\u5757 \u2192 \u5411\u91cf\u5316 \u2192 \u5b58\u50a8\u68c0\u7d22<\/p>\n<h3>\u56db\u3001\u591a\u6a21\u6001\u6587\u6863\u8f7d\u5165<\/h3>\n<p>RAG \u7684\u5165\u53e3\u7edf\u4e00\u4f7f\u7528 MarkItDown&#xff0c;\u5c06 PDF\u3001Word\u3001Excel\u3001\u56fe\u7247\u3001\u97f3\u9891\u7b49\u683c\u5f0f\u8f6c\u6362\u4e3a Markdown\u3002\u8fd9\u6837\u540e\u7eed\u5206\u5757\u548c\u5411\u91cf\u5316\u53ea\u9700\u5904\u7406\u4e00\u79cd\u7ed3\u6784\u5316\u683c\u5f0f\u3002<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">_convert_to_markdown<\/span><span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    Universal document reader using MarkItDown with enhanced PDF processing.<br \/>\n    \u6838\u5fc3\u529f\u80fd&#xff1a;\u5c06\u4efb\u610f\u683c\u5f0f\u6587\u6863\u8f6c\u6362\u4e3aMarkdown\u6587\u672c<\/p>\n<p>    \u652f\u6301\u683c\u5f0f&#xff1a;<br \/>\n    &#8211; \u6587\u6863&#xff1a;PDF\u3001Word\u3001Excel\u3001PowerPoint<br \/>\n    &#8211; \u56fe\u50cf&#xff1a;JPG\u3001PNG\u3001GIF&#xff08;\u901a\u8fc7OCR&#xff09;<br \/>\n    &#8211; \u97f3\u9891&#xff1a;MP3\u3001WAV\u3001M4A&#xff08;\u901a\u8fc7\u8f6c\u5f55&#xff09;<br \/>\n    &#8211; \u6587\u672c&#xff1a;TXT\u3001CSV\u3001JSON\u3001XML\u3001HTML<br \/>\n    &#8211; \u4ee3\u7801&#xff1a;Python\u3001JavaScript\u3001Java\u7b49<br \/>\n    &#034;&#034;&#034;<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> os<span class=\"token punctuation\">.<\/span>path<span class=\"token punctuation\">.<\/span>exists<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><\/p>\n<p>    <span class=\"token comment\"># \u5bf9PDF\u6587\u4ef6\u4f7f\u7528\u589e\u5f3a\u5904\u7406<\/span><br \/>\n    ext <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span>os<span class=\"token punctuation\">.<\/span>path<span class=\"token punctuation\">.<\/span>splitext<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token string\">&#039;&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>lower<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> ext <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#039;.pdf&#039;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> _enhanced_pdf_processing<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token comment\"># \u5176\u4ed6\u683c\u5f0f\u4f7f\u7528MarkItDown\u7edf\u4e00\u8f6c\u6362<\/span><br \/>\n    md_instance <span class=\"token operator\">&#061;<\/span> _get_markitdown_instance<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> md_instance <span class=\"token keyword\">is<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> _fallback_text_reader<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        result <span class=\"token operator\">&#061;<\/span> md_instance<span class=\"token punctuation\">.<\/span>convert<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><br \/>\n        markdown_text <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">getattr<\/span><span class=\"token punctuation\">(<\/span>result<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;text_content&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>markdown_text<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">and<\/span> markdown_text<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;[RAG] MarkItDown\u8f6c\u6362\u6210\u529f: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>path<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> -&gt; <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>markdown_text<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> chars Markdown&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token keyword\">return<\/span> markdown_text<br \/>\n        <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;&#034;<\/span><br \/>\n    <span class=\"token keyword\">except<\/span> Exception <span class=\"token keyword\">as<\/span> e<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;[WARNING] MarkItDown\u8f6c\u6362\u5931\u8d25 <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>path<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>e<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> _fallback_text_reader<span class=\"token punctuation\">(<\/span>path<span class=\"token punctuation\">)<\/span><\/p>\n<p>#mermaid-svg-bFRbz3TPq5oxz8kb{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-bFRbz3TPq5oxz8kb .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-bFRbz3TPq5oxz8kb .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-bFRbz3TPq5oxz8kb .error-icon{fill:#552222;}#mermaid-svg-bFRbz3TPq5oxz8kb .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-bFRbz3TPq5oxz8kb .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-bFRbz3TPq5oxz8kb .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-bFRbz3TPq5oxz8kb .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-bFRbz3TPq5oxz8kb .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-bFRbz3TPq5oxz8kb .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-bFRbz3TPq5oxz8kb .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-bFRbz3TPq5oxz8kb .marker{fill:#333333;stroke:#333333;}#mermaid-svg-bFRbz3TPq5oxz8kb .marker.cross{stroke:#333333;}#mermaid-svg-bFRbz3TPq5oxz8kb svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-bFRbz3TPq5oxz8kb p{margin:0;}#mermaid-svg-bFRbz3TPq5oxz8kb .label{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;color:#333;}#mermaid-svg-bFRbz3TPq5oxz8kb .cluster-label text{fill:#333;}#mermaid-svg-bFRbz3TPq5oxz8kb .cluster-label span{color:#333;}#mermaid-svg-bFRbz3TPq5oxz8kb .cluster-label span p{background-color:transparent;}#mermaid-svg-bFRbz3TPq5oxz8kb .label text,#mermaid-svg-bFRbz3TPq5oxz8kb span{fill:#333;color:#333;}#mermaid-svg-bFRbz3TPq5oxz8kb .node rect,#mermaid-svg-bFRbz3TPq5oxz8kb .node circle,#mermaid-svg-bFRbz3TPq5oxz8kb .node ellipse,#mermaid-svg-bFRbz3TPq5oxz8kb .node polygon,#mermaid-svg-bFRbz3TPq5oxz8kb .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#mermaid-svg-bFRbz3TPq5oxz8kb .rough-node .label text,#mermaid-svg-bFRbz3TPq5oxz8kb .node .label text,#mermaid-svg-bFRbz3TPq5oxz8kb .image-shape .label,#mermaid-svg-bFRbz3TPq5oxz8kb .icon-shape .label{text-anchor:middle;}#mermaid-svg-bFRbz3TPq5oxz8kb .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-svg-bFRbz3TPq5oxz8kb .rough-node .label,#mermaid-svg-bFRbz3TPq5oxz8kb .node .label,#mermaid-svg-bFRbz3TPq5oxz8kb .image-shape .label,#mermaid-svg-bFRbz3TPq5oxz8kb .icon-shape .label{text-align:center;}#mermaid-svg-bFRbz3TPq5oxz8kb .node.clickable{cursor:pointer;}#mermaid-svg-bFRbz3TPq5oxz8kb .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#mermaid-svg-bFRbz3TPq5oxz8kb .arrowheadPath{fill:#333333;}#mermaid-svg-bFRbz3TPq5oxz8kb .edgePath .path{stroke:#333333;stroke-width:2.0px;}#mermaid-svg-bFRbz3TPq5oxz8kb .flowchart-link{stroke:#333333;fill:none;}#mermaid-svg-bFRbz3TPq5oxz8kb .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-bFRbz3TPq5oxz8kb .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#mermaid-svg-bFRbz3TPq5oxz8kb .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-bFRbz3TPq5oxz8kb .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#mermaid-svg-bFRbz3TPq5oxz8kb .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#mermaid-svg-bFRbz3TPq5oxz8kb .cluster text{fill:#333;}#mermaid-svg-bFRbz3TPq5oxz8kb .cluster span{color:#333;}#mermaid-svg-bFRbz3TPq5oxz8kb div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-svg-bFRbz3TPq5oxz8kb .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#mermaid-svg-bFRbz3TPq5oxz8kb rect.text{fill:none;stroke-width:0;}#mermaid-svg-bFRbz3TPq5oxz8kb .icon-shape,#mermaid-svg-bFRbz3TPq5oxz8kb .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-bFRbz3TPq5oxz8kb .icon-shape p,#mermaid-svg-bFRbz3TPq5oxz8kb .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#mermaid-svg-bFRbz3TPq5oxz8kb .icon-shape .label rect,#mermaid-svg-bFRbz3TPq5oxz8kb .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-bFRbz3TPq5oxz8kb .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#mermaid-svg-bFRbz3TPq5oxz8kb .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#mermaid-svg-bFRbz3TPq5oxz8kb :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"nodeLabel\"><\/p>\n<p>PDF<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>MarkItDown<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>Word \/ Excel \/ PPT<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>JPG \/ PNG \/ GIF<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>MP3 \/ WAV \/ M4A<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u7edf\u4e00 Markdown \u6587\u672c<\/p>\n<p><\/span><\/p>\n<h3>\u4e94\u3001Markdown \u667a\u80fd\u5206\u5757<\/h3>\n<p>\u7531\u4e8e\u6240\u6709\u6587\u6863\u90fd\u5148\u8f6c\u6362\u4e3a Markdown&#xff0c;\u5206\u5757\u5668\u53ef\u4ee5\u5229\u7528\u6807\u9898\u5c42\u7ea7\u4fdd\u6301\u8bed\u4e49\u5b8c\u6574\u3002<\/p>\n<p>#mermaid-svg-Ligh977Subqo7peM{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-Ligh977Subqo7peM .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-Ligh977Subqo7peM .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-Ligh977Subqo7peM .error-icon{fill:#552222;}#mermaid-svg-Ligh977Subqo7peM .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-Ligh977Subqo7peM .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-Ligh977Subqo7peM .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-Ligh977Subqo7peM .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-Ligh977Subqo7peM .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-Ligh977Subqo7peM .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-Ligh977Subqo7peM .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-Ligh977Subqo7peM .marker{fill:#333333;stroke:#333333;}#mermaid-svg-Ligh977Subqo7peM .marker.cross{stroke:#333333;}#mermaid-svg-Ligh977Subqo7peM svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-Ligh977Subqo7peM p{margin:0;}#mermaid-svg-Ligh977Subqo7peM .label{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;color:#333;}#mermaid-svg-Ligh977Subqo7peM .cluster-label text{fill:#333;}#mermaid-svg-Ligh977Subqo7peM .cluster-label span{color:#333;}#mermaid-svg-Ligh977Subqo7peM .cluster-label span p{background-color:transparent;}#mermaid-svg-Ligh977Subqo7peM .label text,#mermaid-svg-Ligh977Subqo7peM span{fill:#333;color:#333;}#mermaid-svg-Ligh977Subqo7peM .node rect,#mermaid-svg-Ligh977Subqo7peM .node circle,#mermaid-svg-Ligh977Subqo7peM .node ellipse,#mermaid-svg-Ligh977Subqo7peM .node polygon,#mermaid-svg-Ligh977Subqo7peM .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#mermaid-svg-Ligh977Subqo7peM .rough-node .label text,#mermaid-svg-Ligh977Subqo7peM .node .label text,#mermaid-svg-Ligh977Subqo7peM .image-shape .label,#mermaid-svg-Ligh977Subqo7peM .icon-shape .label{text-anchor:middle;}#mermaid-svg-Ligh977Subqo7peM .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-svg-Ligh977Subqo7peM .rough-node .label,#mermaid-svg-Ligh977Subqo7peM .node .label,#mermaid-svg-Ligh977Subqo7peM .image-shape .label,#mermaid-svg-Ligh977Subqo7peM .icon-shape .label{text-align:center;}#mermaid-svg-Ligh977Subqo7peM .node.clickable{cursor:pointer;}#mermaid-svg-Ligh977Subqo7peM .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#mermaid-svg-Ligh977Subqo7peM .arrowheadPath{fill:#333333;}#mermaid-svg-Ligh977Subqo7peM .edgePath .path{stroke:#333333;stroke-width:2.0px;}#mermaid-svg-Ligh977Subqo7peM .flowchart-link{stroke:#333333;fill:none;}#mermaid-svg-Ligh977Subqo7peM .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-Ligh977Subqo7peM .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#mermaid-svg-Ligh977Subqo7peM .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-Ligh977Subqo7peM .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#mermaid-svg-Ligh977Subqo7peM .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#mermaid-svg-Ligh977Subqo7peM .cluster text{fill:#333;}#mermaid-svg-Ligh977Subqo7peM .cluster span{color:#333;}#mermaid-svg-Ligh977Subqo7peM div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-svg-Ligh977Subqo7peM .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#mermaid-svg-Ligh977Subqo7peM rect.text{fill:none;stroke-width:0;}#mermaid-svg-Ligh977Subqo7peM .icon-shape,#mermaid-svg-Ligh977Subqo7peM .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-Ligh977Subqo7peM .icon-shape p,#mermaid-svg-Ligh977Subqo7peM .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#mermaid-svg-Ligh977Subqo7peM .icon-shape .label rect,#mermaid-svg-Ligh977Subqo7peM .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-Ligh977Subqo7peM .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#mermaid-svg-Ligh977Subqo7peM .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#mermaid-svg-Ligh977Subqo7peM :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6807\u51c6 Markdown \u6587\u672c<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6807\u9898\u5c42\u6b21\u89e3\u6790# \/ ## \/ ###<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6bb5\u843d\u8bed\u4e49\u5206\u5272<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>Token \u8ba1\u7b97\u5206\u5757<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u91cd\u53e0\u7b56\u7565\u4f18\u5316<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u5411\u91cf\u5316\u51c6\u5907<\/p>\n<p><\/span><\/p>\n<p>\u7b2c\u4e00\u6b65\u6309\u6807\u9898\u548c\u7a7a\u884c\u628a\u6587\u6863\u62c6\u6210\u6bb5\u843d&#xff0c;\u5e76\u8bb0\u5f55\u6bcf\u4e2a\u6bb5\u843d\u6240\u5c5e\u7684\u6807\u9898\u8def\u5f84&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">_split_paragraphs_with_headings<\/span><span class=\"token punctuation\">(<\/span>text<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span>Dict<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u6839\u636e\u6807\u9898\u5c42\u6b21\u5206\u5272\u6bb5\u843d&#xff0c;\u4fdd\u6301\u8bed\u4e49\u5b8c\u6574\u6027&#034;&#034;&#034;<\/span><br \/>\n    lines <span class=\"token operator\">&#061;<\/span> text<span class=\"token punctuation\">.<\/span>splitlines<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    heading_stack<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    paragraphs<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span>Dict<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    buf<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    char_pos <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><\/p>\n<p>    <span class=\"token keyword\">def<\/span> <span class=\"token function\">flush_buf<\/span><span class=\"token punctuation\">(<\/span>end_pos<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> buf<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span><br \/>\n        content <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;\\\\n&#034;<\/span><span class=\"token punctuation\">.<\/span>join<span class=\"token punctuation\">(<\/span>buf<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> content<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">return<\/span><br \/>\n        paragraphs<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">:<\/span> content<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;heading_path&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034; &gt; &#034;<\/span><span class=\"token punctuation\">.<\/span>join<span class=\"token punctuation\">(<\/span>heading_stack<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> heading_stack <span class=\"token keyword\">else<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;start&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">max<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> end_pos <span class=\"token operator\">&#8211;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>content<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;end&#034;<\/span><span class=\"token punctuation\">:<\/span> end_pos<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">for<\/span> ln <span class=\"token keyword\">in<\/span> lines<span class=\"token punctuation\">:<\/span><br \/>\n        raw <span class=\"token operator\">&#061;<\/span> ln<br \/>\n        <span class=\"token keyword\">if<\/span> raw<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>startswith<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;#&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token comment\"># \u5904\u7406\u6807\u9898\u884c<\/span><br \/>\n            flush_buf<span class=\"token punctuation\">(<\/span>char_pos<span class=\"token punctuation\">)<\/span><br \/>\n            level <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>raw<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>raw<span class=\"token punctuation\">.<\/span>lstrip<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;#&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n            title <span class=\"token operator\">&#061;<\/span> raw<span class=\"token punctuation\">.<\/span>lstrip<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#039;#&#039;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token keyword\">if<\/span> level <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                level <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> level <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>heading_stack<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                heading_stack <span class=\"token operator\">&#061;<\/span> heading_stack<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span>level<span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><br \/>\n            heading_stack<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>title<span class=\"token punctuation\">)<\/span><\/p>\n<p>            char_pos <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>raw<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#043;<\/span> <span class=\"token number\">1<\/span><br \/>\n            <span class=\"token keyword\">continue<\/span><\/p>\n<p>        <span class=\"token comment\"># \u6bb5\u843d\u5185\u5bb9\u7d2f\u79ef<\/span><br \/>\n        <span class=\"token keyword\">if<\/span> raw<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            flush_buf<span class=\"token punctuation\">(<\/span>char_pos<span class=\"token punctuation\">)<\/span><br \/>\n            buf <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            buf<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>raw<span class=\"token punctuation\">)<\/span><br \/>\n        char_pos <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>raw<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#043;<\/span> <span class=\"token number\">1<\/span><\/p>\n<p>    flush_buf<span class=\"token punctuation\">(<\/span>char_pos<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> paragraphs<span class=\"token punctuation\">:<\/span><br \/>\n        paragraphs <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">:<\/span> text<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;heading_path&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;start&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;end&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>text<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> paragraphs<\/p>\n<p>\u7b2c\u4e8c\u6b65\u6309\u7167 Token \u6570\u91cf\u7ec4\u5408\u6bb5\u843d&#xff0c;\u5e76\u901a\u8fc7\u91cd\u53e0\u5757\u4fdd\u7559\u4e0a\u4e0b\u6587\u8fde\u7eed\u6027&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">_chunk_paragraphs<\/span><span class=\"token punctuation\">(<\/span>paragraphs<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span>Dict<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> chunk_tokens<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">,<\/span> overlap_tokens<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> List<span class=\"token punctuation\">[<\/span>Dict<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u57fa\u4e8eToken\u6570\u91cf\u7684\u667a\u80fd\u5206\u5757&#034;&#034;&#034;<\/span><br \/>\n    chunks<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span>Dict<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    cur<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span>Dict<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    cur_tokens <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><br \/>\n    i <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><\/p>\n<p>    <span class=\"token keyword\">while<\/span> i <span class=\"token operator\">&lt;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>paragraphs<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        p <span class=\"token operator\">&#061;<\/span> paragraphs<span class=\"token punctuation\">[<\/span>i<span class=\"token punctuation\">]<\/span><br \/>\n        p_tokens <span class=\"token operator\">&#061;<\/span> _approx_token_len<span class=\"token punctuation\">(<\/span>p<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token number\">1<\/span><\/p>\n<p>        <span class=\"token keyword\">if<\/span> cur_tokens <span class=\"token operator\">&#043;<\/span> p_tokens <span class=\"token operator\">&lt;&#061;<\/span> chunk_tokens <span class=\"token keyword\">or<\/span> <span class=\"token keyword\">not<\/span> cur<span class=\"token punctuation\">:<\/span><br \/>\n            cur<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>p<span class=\"token punctuation\">)<\/span><br \/>\n            cur_tokens <span class=\"token operator\">&#043;&#061;<\/span> p_tokens<br \/>\n            i <span class=\"token operator\">&#043;&#061;<\/span> <span class=\"token number\">1<\/span><br \/>\n        <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token comment\"># \u751f\u6210\u5f53\u524d\u5206\u5757<\/span><br \/>\n            content <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;\\\\n\\\\n&#034;<\/span><span class=\"token punctuation\">.<\/span>join<span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token keyword\">for<\/span> x <span class=\"token keyword\">in<\/span> cur<span class=\"token punctuation\">)<\/span><br \/>\n            start <span class=\"token operator\">&#061;<\/span> cur<span class=\"token punctuation\">[<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;start&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n            end <span class=\"token operator\">&#061;<\/span> cur<span class=\"token punctuation\">[<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;end&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n            heading_path <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">next<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;heading_path&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token keyword\">for<\/span> x <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">reversed<\/span><span class=\"token punctuation\">(<\/span>cur<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> x<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;heading_path&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            chunks<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n                <span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">:<\/span> content<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;start&#034;<\/span><span class=\"token punctuation\">:<\/span> start<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;end&#034;<\/span><span class=\"token punctuation\">:<\/span> end<span class=\"token punctuation\">,<\/span><br \/>\n                <span class=\"token string\">&#034;heading_path&#034;<\/span><span class=\"token punctuation\">:<\/span> heading_path<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token comment\"># \u6784\u5efa\u91cd\u53e0\u90e8\u5206<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> overlap_tokens <span class=\"token operator\">&gt;<\/span> <span class=\"token number\">0<\/span> <span class=\"token keyword\">and<\/span> cur<span class=\"token punctuation\">:<\/span><br \/>\n                kept<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span>Dict<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n                kept_tokens <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><br \/>\n                <span class=\"token keyword\">for<\/span> x <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">reversed<\/span><span class=\"token punctuation\">(<\/span>cur<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    t <span class=\"token operator\">&#061;<\/span> _approx_token_len<span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token number\">1<\/span><br \/>\n                    <span class=\"token keyword\">if<\/span> kept_tokens <span class=\"token operator\">&#043;<\/span> t <span class=\"token operator\">&gt;<\/span> overlap_tokens<span class=\"token punctuation\">:<\/span><br \/>\n                        <span class=\"token keyword\">break<\/span><br \/>\n                    kept<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">)<\/span><br \/>\n                    kept_tokens <span class=\"token operator\">&#043;&#061;<\/span> t<br \/>\n                cur <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">reversed<\/span><span class=\"token punctuation\">(<\/span>kept<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                cur_tokens <span class=\"token operator\">&#061;<\/span> kept_tokens<br \/>\n            <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                cur <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n                cur_tokens <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><\/p>\n<p>    <span class=\"token comment\"># \u5904\u7406\u6700\u540e\u4e00\u4e2a\u5206\u5757<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> cur<span class=\"token punctuation\">:<\/span><br \/>\n        content <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;\\\\n\\\\n&#034;<\/span><span class=\"token punctuation\">.<\/span>join<span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token keyword\">for<\/span> x <span class=\"token keyword\">in<\/span> cur<span class=\"token punctuation\">)<\/span><br \/>\n        start <span class=\"token operator\">&#061;<\/span> cur<span class=\"token punctuation\">[<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;start&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        end <span class=\"token operator\">&#061;<\/span> cur<span class=\"token punctuation\">[<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;end&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        heading_path <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">next<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;heading_path&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token keyword\">for<\/span> x <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">reversed<\/span><span class=\"token punctuation\">(<\/span>cur<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> x<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;heading_path&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        chunks<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">:<\/span> content<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;start&#034;<\/span><span class=\"token punctuation\">:<\/span> start<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;end&#034;<\/span><span class=\"token punctuation\">:<\/span> end<span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;heading_path&#034;<\/span><span class=\"token punctuation\">:<\/span> heading_path<span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">return<\/span> chunks<\/p>\n<p>\u4e3a\u4e86\u517c\u5bb9\u4e2d\u82f1\u6587\u6df7\u5408\u6587\u672c&#xff0c;Token \u957f\u5ea6\u91c7\u7528\u8fd1\u4f3c\u4f30\u7b97&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">_approx_token_len<\/span><span class=\"token punctuation\">(<\/span>text<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">int<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u8fd1\u4f3c\u4f30\u8ba1Token\u957f\u5ea6&#xff0c;\u652f\u6301\u4e2d\u82f1\u6587\u6df7\u5408&#034;&#034;&#034;<\/span><br \/>\n    <span class=\"token comment\"># CJK\u5b57\u7b26\u63091 token\u8ba1\u7b97<\/span><br \/>\n    cjk <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">sum<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">1<\/span> <span class=\"token keyword\">for<\/span> ch <span class=\"token keyword\">in<\/span> text <span class=\"token keyword\">if<\/span> _is_cjk<span class=\"token punctuation\">(<\/span>ch<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token comment\"># \u5176\u4ed6\u5b57\u7b26\u6309\u7a7a\u767d\u5206\u8bcd\u8ba1\u7b97<\/span><br \/>\n    non_cjk_tokens <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span>t <span class=\"token keyword\">for<\/span> t <span class=\"token keyword\">in<\/span> text<span class=\"token punctuation\">.<\/span>split<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">if<\/span> t<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> cjk <span class=\"token operator\">&#043;<\/span> non_cjk_tokens<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">_is_cjk<\/span><span class=\"token punctuation\">(<\/span>ch<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token builtin\">bool<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u5224\u65ad\u662f\u5426\u4e3aCJK\u5b57\u7b26&#034;&#034;&#034;<\/span><br \/>\n    code <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">ord<\/span><span class=\"token punctuation\">(<\/span>ch<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token punctuation\">(<\/span><br \/>\n        <span class=\"token number\">0x4E00<\/span> <span class=\"token operator\">&lt;&#061;<\/span> code <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0x9FFF<\/span> <span class=\"token keyword\">or<\/span>  <span class=\"token comment\"># CJK\u7edf\u4e00\u6c49\u5b57<\/span><br \/>\n        <span class=\"token number\">0x3400<\/span> <span class=\"token operator\">&lt;&#061;<\/span> code <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0x4DBF<\/span> <span class=\"token keyword\">or<\/span>  <span class=\"token comment\"># CJK\u6269\u5c55A<\/span><br \/>\n        <span class=\"token number\">0x20000<\/span> <span class=\"token operator\">&lt;&#061;<\/span> code <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0x2A6DF<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token comment\"># CJK\u6269\u5c55B<\/span><br \/>\n        <span class=\"token number\">0x2A700<\/span> <span class=\"token operator\">&lt;&#061;<\/span> code <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0x2B73F<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token comment\"># CJK\u6269\u5c55C<\/span><br \/>\n        <span class=\"token number\">0x2B740<\/span> <span class=\"token operator\">&lt;&#061;<\/span> code <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0x2B81F<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token comment\"># CJK\u6269\u5c55D<\/span><br \/>\n        <span class=\"token number\">0x2B820<\/span> <span class=\"token operator\">&lt;&#061;<\/span> code <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0x2CEAF<\/span> <span class=\"token keyword\">or<\/span> <span class=\"token comment\"># CJK\u6269\u5c55E<\/span><br \/>\n        <span class=\"token number\">0xF900<\/span> <span class=\"token operator\">&lt;&#061;<\/span> code <span class=\"token operator\">&lt;&#061;<\/span> <span class=\"token number\">0xFAFF<\/span>      <span class=\"token comment\"># CJK\u517c\u5bb9\u6c49\u5b57<\/span><br \/>\n    <span class=\"token punctuation\">)<\/span><\/p>\n<h3>\u516d\u3001\u7edf\u4e00\u5d4c\u5165\u4e0e\u5411\u91cf\u5b58\u50a8<\/h3>\n<p>\u5d4c\u5165\u6a21\u578b\u8d1f\u8d23\u628a\u5206\u5757\u6587\u672c\u8f6c\u6362\u4e3a\u5411\u91cf\u3002HelloAgents \u4f18\u5148\u4f7f\u7528\u767e\u70bc API&#xff0c;\u56de\u9000\u5230\u672c\u5730 all-MiniLM-L6-v2&#xff0c;\u6700\u540e\u7528 TF-IDF \u515c\u5e95\u3002<\/p>\n<p>#mermaid-svg-Eafq5pSnnqM6Foo2{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-Eafq5pSnnqM6Foo2 .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-Eafq5pSnnqM6Foo2 .error-icon{fill:#552222;}#mermaid-svg-Eafq5pSnnqM6Foo2 .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-Eafq5pSnnqM6Foo2 .marker{fill:#333333;stroke:#333333;}#mermaid-svg-Eafq5pSnnqM6Foo2 .marker.cross{stroke:#333333;}#mermaid-svg-Eafq5pSnnqM6Foo2 svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-Eafq5pSnnqM6Foo2 p{margin:0;}#mermaid-svg-Eafq5pSnnqM6Foo2 .label{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;color:#333;}#mermaid-svg-Eafq5pSnnqM6Foo2 .cluster-label text{fill:#333;}#mermaid-svg-Eafq5pSnnqM6Foo2 .cluster-label span{color:#333;}#mermaid-svg-Eafq5pSnnqM6Foo2 .cluster-label span p{background-color:transparent;}#mermaid-svg-Eafq5pSnnqM6Foo2 .label text,#mermaid-svg-Eafq5pSnnqM6Foo2 span{fill:#333;color:#333;}#mermaid-svg-Eafq5pSnnqM6Foo2 .node rect,#mermaid-svg-Eafq5pSnnqM6Foo2 .node circle,#mermaid-svg-Eafq5pSnnqM6Foo2 .node ellipse,#mermaid-svg-Eafq5pSnnqM6Foo2 .node polygon,#mermaid-svg-Eafq5pSnnqM6Foo2 .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#mermaid-svg-Eafq5pSnnqM6Foo2 .rough-node .label text,#mermaid-svg-Eafq5pSnnqM6Foo2 .node .label text,#mermaid-svg-Eafq5pSnnqM6Foo2 .image-shape .label,#mermaid-svg-Eafq5pSnnqM6Foo2 .icon-shape .label{text-anchor:middle;}#mermaid-svg-Eafq5pSnnqM6Foo2 .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-svg-Eafq5pSnnqM6Foo2 .rough-node .label,#mermaid-svg-Eafq5pSnnqM6Foo2 .node .label,#mermaid-svg-Eafq5pSnnqM6Foo2 .image-shape .label,#mermaid-svg-Eafq5pSnnqM6Foo2 .icon-shape .label{text-align:center;}#mermaid-svg-Eafq5pSnnqM6Foo2 .node.clickable{cursor:pointer;}#mermaid-svg-Eafq5pSnnqM6Foo2 .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#mermaid-svg-Eafq5pSnnqM6Foo2 .arrowheadPath{fill:#333333;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edgePath .path{stroke:#333333;stroke-width:2.0px;}#mermaid-svg-Eafq5pSnnqM6Foo2 .flowchart-link{stroke:#333333;fill:none;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-Eafq5pSnnqM6Foo2 .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#mermaid-svg-Eafq5pSnnqM6Foo2 .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-Eafq5pSnnqM6Foo2 .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#mermaid-svg-Eafq5pSnnqM6Foo2 .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#mermaid-svg-Eafq5pSnnqM6Foo2 .cluster text{fill:#333;}#mermaid-svg-Eafq5pSnnqM6Foo2 .cluster span{color:#333;}#mermaid-svg-Eafq5pSnnqM6Foo2 div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-svg-Eafq5pSnnqM6Foo2 .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#mermaid-svg-Eafq5pSnnqM6Foo2 rect.text{fill:none;stroke-width:0;}#mermaid-svg-Eafq5pSnnqM6Foo2 .icon-shape,#mermaid-svg-Eafq5pSnnqM6Foo2 .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-Eafq5pSnnqM6Foo2 .icon-shape p,#mermaid-svg-Eafq5pSnnqM6Foo2 .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#mermaid-svg-Eafq5pSnnqM6Foo2 .icon-shape .label rect,#mermaid-svg-Eafq5pSnnqM6Foo2 .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-Eafq5pSnnqM6Foo2 .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#mermaid-svg-Eafq5pSnnqM6Foo2 .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#mermaid-svg-Eafq5pSnnqM6Foo2 :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/p>\n<p>\u5df2\u914d\u7f6e\u767e\u70bc API<\/p>\n<p><\/span><span class=\"edgeLabel\"><\/p>\n<p>\u65e0\u4e91\u7aef API<\/p>\n<p><\/span><span class=\"edgeLabel\"><\/p>\n<p>\u5747\u4e0d\u53ef\u7528<\/p>\n<p><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"edgeLabel\"><\/span><span class=\"nodeLabel\"><\/p>\n<p>Markdown chunks<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u7edf\u4e00\u5d4c\u5165\u5668<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>DashScope<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>all-MiniLM-L6-v2<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>TF-IDF<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>\u6279\u91cf\u5411\u91cf<\/p>\n<p><\/span><span class=\"nodeLabel\"><\/p>\n<p>Qdrant \u5411\u91cf\u5b58\u50a8<\/p>\n<p><\/span><\/p>\n<p>\u6279\u91cf\u7d22\u5f15\u51fd\u6570\u5904\u7406\u5206\u5757\u3001\u7f16\u7801\u3001\u7ef4\u5ea6\u68c0\u67e5\u548c\u5f02\u5e38\u515c\u5e95&#xff1a;<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">index_chunks<\/span><span class=\"token punctuation\">(<\/span><br \/>\n    store <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    chunks<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span>Dict<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    cache_db<span class=\"token punctuation\">:<\/span> Optional<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    batch_size<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">int<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">64<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    rag_namespace<span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;default&#034;<\/span><br \/>\n<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;<br \/>\n    Index markdown chunks with unified embedding and Qdrant storage.<br \/>\n    Uses\u767e\u70bc API with fallback to sentence-transformers.<br \/>\n    &#034;&#034;&#034;<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> chunks<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;[RAG] No chunks to index&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">return<\/span><\/p>\n<p>    <span class=\"token comment\"># \u4f7f\u7528\u7edf\u4e00\u5d4c\u5165\u6a21\u578b<\/span><br \/>\n    embedder <span class=\"token operator\">&#061;<\/span> get_text_embedder<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    dimension <span class=\"token operator\">&#061;<\/span> get_dimension<span class=\"token punctuation\">(<\/span><span class=\"token number\">384<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token comment\"># \u521b\u5efa\u9ed8\u8ba4Qdrant\u5b58\u50a8<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> store <span class=\"token keyword\">is<\/span> <span class=\"token boolean\">None<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        store <span class=\"token operator\">&#061;<\/span> _create_default_vector_store<span class=\"token punctuation\">(<\/span>dimension<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;[RAG] Created default Qdrant store with dimension <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>dimension<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token comment\"># \u9884\u5904\u7406Markdown\u6587\u672c\u4ee5\u83b7\u5f97\u66f4\u597d\u7684\u5d4c\u5165\u8d28\u91cf<\/span><br \/>\n    processed_texts <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> c <span class=\"token keyword\">in<\/span> chunks<span class=\"token punctuation\">:<\/span><br \/>\n        raw_content <span class=\"token operator\">&#061;<\/span> c<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;content&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n        processed_content <span class=\"token operator\">&#061;<\/span> _preprocess_markdown_for_embedding<span class=\"token punctuation\">(<\/span>raw_content<span class=\"token punctuation\">)<\/span><br \/>\n        processed_texts<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>processed_content<span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;[RAG] Embedding start: total_texts&#061;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>processed_texts<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> batch_size&#061;<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>batch_size<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token comment\"># \u6279\u91cf\u7f16\u7801<\/span><br \/>\n    vecs<span class=\"token punctuation\">:<\/span> List<span class=\"token punctuation\">[<\/span>List<span class=\"token punctuation\">[<\/span><span class=\"token builtin\">float<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> i <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>processed_texts<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> batch_size<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        part <span class=\"token operator\">&#061;<\/span> processed_texts<span class=\"token punctuation\">[<\/span>i<span class=\"token punctuation\">:<\/span>i<span class=\"token operator\">&#043;<\/span>batch_size<span class=\"token punctuation\">]<\/span><br \/>\n        <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token comment\"># \u4f7f\u7528\u7edf\u4e00\u5d4c\u5165\u5668&#xff08;\u5185\u90e8\u5904\u7406\u7f13\u5b58&#xff09;<\/span><br \/>\n            part_vecs <span class=\"token operator\">&#061;<\/span> embedder<span class=\"token punctuation\">.<\/span>encode<span class=\"token punctuation\">(<\/span>part<span class=\"token punctuation\">)<\/span><\/p>\n<p>            <span class=\"token comment\"># \u6807\u51c6\u5316\u4e3aList[List[float]]\u683c\u5f0f<\/span><br \/>\n            <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token builtin\">isinstance<\/span><span class=\"token punctuation\">(<\/span>part_vecs<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">list<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">hasattr<\/span><span class=\"token punctuation\">(<\/span>part_vecs<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;tolist&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    part_vecs <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span>part_vecs<span class=\"token punctuation\">.<\/span>tolist<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">]<\/span><br \/>\n                <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    part_vecs <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token builtin\">list<\/span><span class=\"token punctuation\">(<\/span>part_vecs<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">]<\/span><\/p>\n<p>            <span class=\"token comment\"># \u5904\u7406\u5411\u91cf\u683c\u5f0f\u548c\u7ef4\u5ea6<\/span><br \/>\n            <span class=\"token keyword\">for<\/span> v <span class=\"token keyword\">in<\/span> part_vecs<span class=\"token punctuation\">:<\/span><br \/>\n                <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                    <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">hasattr<\/span><span class=\"token punctuation\">(<\/span>v<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;tolist&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                        v <span class=\"token operator\">&#061;<\/span> v<span class=\"token punctuation\">.<\/span>tolist<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                    v_norm <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token builtin\">float<\/span><span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">for<\/span> x <span class=\"token keyword\">in<\/span> v<span class=\"token punctuation\">]<\/span><\/p>\n<p>                    <span class=\"token comment\"># \u7ef4\u5ea6\u68c0\u67e5\u548c\u8c03\u6574<\/span><br \/>\n                    <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>v_norm<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">!&#061;<\/span> dimension<span class=\"token punctuation\">:<\/span><br \/>\n                        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;[WARNING] \u5411\u91cf\u7ef4\u5ea6\u5f02\u5e38: \u671f\u671b<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>dimension<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">, \u5b9e\u9645<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>v_norm<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n                        <span class=\"token keyword\">if<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>v_norm<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">&lt;<\/span> dimension<span class=\"token punctuation\">:<\/span><br \/>\n                            v_norm<span class=\"token punctuation\">.<\/span>extend<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">0.0<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">*<\/span> <span class=\"token punctuation\">(<\/span>dimension <span class=\"token operator\">&#8211;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>v_norm<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n                        <span class=\"token keyword\">else<\/span><span class=\"token punctuation\">:<\/span><br \/>\n                            v_norm <span class=\"token operator\">&#061;<\/span> v_norm<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span>dimension<span class=\"token punctuation\">]<\/span><\/p>\n<p>                    vecs<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>v_norm<span class=\"token punctuation\">)<\/span><br \/>\n                <span class=\"token keyword\">except<\/span> Exception <span class=\"token keyword\">as<\/span> e<span class=\"token punctuation\">:<\/span><br \/>\n                    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;[WARNING] \u5411\u91cf\u8f6c\u6362\u5931\u8d25: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>e<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">, \u4f7f\u7528\u96f6\u5411\u91cf&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n                    vecs<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">0.0<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">*<\/span> dimension<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token keyword\">except<\/span> Exception <span class=\"token keyword\">as<\/span> e<span class=\"token punctuation\">:<\/span><br \/>\n            <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;[WARNING] Batch <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>i<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\"> encoding failed: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span>e<span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><br \/>\n            <span class=\"token comment\"># \u5b9e\u73b0\u91cd\u8bd5\u673a\u5236<\/span><br \/>\n            <span class=\"token comment\"># &#8230; \u91cd\u8bd5\u903b\u8f91 &#8230;<\/span><\/p>\n<p>        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string-interpolation\"><span class=\"token string\">f&#034;[RAG] Embedding progress: <\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span><span class=\"token builtin\">min<\/span><span class=\"token punctuation\">(<\/span>i<span class=\"token operator\">&#043;<\/span>batch_size<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>processed_texts<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">\/<\/span><span class=\"token interpolation\"><span class=\"token punctuation\">{<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>processed_texts<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><\/span><span class=\"token string\">&#034;<\/span><\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>\u4e0b\u4e00\u7bc7\u7ee7\u7eed\u770b\u67e5\u8be2\u4fa7\u7684\u9ad8\u7ea7\u68c0\u7d22\u7b56\u7565&#xff1a;MQE \u4e0e HyDE \u5982\u4f55\u6539\u5584\u53ec\u56de\u7387\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>RAG \u6587\u6863\u5904\u7406\u7ba1\u9053&#xff1a;MarkItDown\u3001\u667a\u80fd\u5206\u5757\u4e0e\u5411\u91cf\u5316\u6458\u8981&#xff1a;\u672c\u6587\u8fdb\u5165 HelloAgents \u7684 RAG \u7cfb\u7edf&#xff0c;\u5305\u62ec RAG \u4f53\u9a8c\u3001RAGTool \u521d\u59cb\u5316\u3001\u591a\u683c\u5f0f\u8f6c\u6362\u3001Markdown \u5206\u5757\u3001Token \u4f30\u7b97\u548c\u5411\u91cf\u7d22\u5f15\u4ee3\u7801\u3002\u4e00\u3001RAG \u8981\u89e3\u51b3\u4ec0\u4e48\u95ee\u9898<br \/>\n\u68c0\u7d22\u589e\u5f3a\u751f\u6210&#xff08;Retrieval-Augmented Generation&#xff0c;RAG&#xff09;\u7684\u6838\u5fc3\u662f\u628a\u201c\u4ece\u6a21\u578b\u53c2\u6570\u91cc\u56de\u5fc6\u77e5\u8bc6\u201d\u6539\u6210\u201c\u4ece\u5916\u90e8\u77e5\u8bc6\u5e93\u68c0<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[13592,74,4119,188,4988],"topic":[],"class_list":["post-119350","post","type-post","status-publish","format-standard","hentry","category-server","tag-13592","tag-agent","tag-rag","tag-188","tag-4988"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/119350.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"RAG \u6587\u6863\u5904\u7406\u7ba1\u9053&#xff1a;MarkItDown\u3001\u667a\u80fd\u5206\u5757\u4e0e\u5411\u91cf\u5316\u6458\u8981&#xff1a;\u672c\u6587\u8fdb\u5165 HelloAgents \u7684 RAG \u7cfb\u7edf&#xff0c;\u5305\u62ec RAG \u4f53\u9a8c\u3001RAGTool \u521d\u59cb\u5316\u3001\u591a\u683c\u5f0f\u8f6c\u6362\u3001Markdown \u5206\u5757\u3001Token \u4f30\u7b97\u548c\u5411\u91cf\u7d22\u5f15\u4ee3\u7801\u3002\u4e00\u3001RAG \u8981\u89e3\u51b3\u4ec0\u4e48\u95ee\u9898 \u68c0\u7d22\u589e\u5f3a\u751f\u6210&#xff08;Retrieval-Augmented Generation&#xff0c;RAG&#xff09;\u7684\u6838\u5fc3\u662f\u628a\u201c\u4ece\u6a21\u578b\u53c2\u6570\u91cc\u56de\u5fc6\u77e5\u8bc6\u201d\u6539\u6210\u201c\u4ece\u5916\u90e8\u77e5\u8bc6\u5e93\u68c0\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/119350.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-10-29T04:48:52+00:00\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"21 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/119350.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/119350.html\",\"name\":\"Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-10-29T04:48:52+00:00\",\"dateModified\":\"2026-10-29T04:48:52+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/119350.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/119350.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/119350.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/119350.html","og_locale":"zh_CN","og_type":"article","og_title":"Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"RAG \u6587\u6863\u5904\u7406\u7ba1\u9053&#xff1a;MarkItDown\u3001\u667a\u80fd\u5206\u5757\u4e0e\u5411\u91cf\u5316\u6458\u8981&#xff1a;\u672c\u6587\u8fdb\u5165 HelloAgents \u7684 RAG \u7cfb\u7edf&#xff0c;\u5305\u62ec RAG \u4f53\u9a8c\u3001RAGTool \u521d\u59cb\u5316\u3001\u591a\u683c\u5f0f\u8f6c\u6362\u3001Markdown \u5206\u5757\u3001Token \u4f30\u7b97\u548c\u5411\u91cf\u7d22\u5f15\u4ee3\u7801\u3002\u4e00\u3001RAG \u8981\u89e3\u51b3\u4ec0\u4e48\u95ee\u9898 \u68c0\u7d22\u589e\u5f3a\u751f\u6210&#xff08;Retrieval-Augmented Generation&#xff0c;RAG&#xff09;\u7684\u6838\u5fc3\u662f\u628a\u201c\u4ece\u6a21\u578b\u53c2\u6570\u91cc\u56de\u5fc6\u77e5\u8bc6\u201d\u6539\u6210\u201c\u4ece\u5916\u90e8\u77e5\u8bc6\u5e93\u68c0","og_url":"https:\/\/www.wsisp.com\/helps\/119350.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-10-29T04:48:52+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"21 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/119350.html","url":"https:\/\/www.wsisp.com\/helps\/119350.html","name":"Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-10-29T04:48:52+00:00","dateModified":"2026-10-29T04:48:52+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/119350.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/119350.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/119350.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"Agent\u8bb0\u5fc6\u4e0e\u68c0\u7d2204\uff1aRAG\u6587\u6863\u5904\u7406\u7ba1\u9053"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/119350","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=119350"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/119350\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=119350"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=119350"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=119350"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=119350"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}