zengli
/
coding-agent


			
							12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997
							
<!doctype html>
<html lang="zh" class="no-js">
  <head>
    
      <meta charset="utf-8">
      <meta name="viewport" content="width=device-width,initial-scale=1">
      
      
        <link rel="prev" href="4.9%20RAG%E4%B8%AD%E7%9A%84Query%E6%94%B9%E5%86%99%28%E6%89%A9%E5%B1%95%E8%B5%84%E6%96%99%29.html">
      
      
        <link rel="next" href="../%E2%91%A4%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0/5.1%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0%E5%B7%A5%E5%85%B7.html">
      
      
      <link rel="icon" href="../img/AI.jpg">
      <meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.21">
    
    
        <title>数据集生成与优化(扩展资料) - 企业知识库RAG智能问答项目V1.0</title>
      
    
      <link rel="stylesheet" href="../assets/stylesheets/main.2a3383ac.min.css">
      
      
        <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
        <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
        <style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
      
    
      <link rel="stylesheet" href="../stylesheets/extra.css">
    
    <script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
    
      
  </head>
  
  
    <body dir="ltr">
  
    
    <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
    <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
    <label class="md-overlay" for="__drawer"></label>
    <div data-md-component="skip">
      
        
        <a href="#_1" class="md-skip">
          跳转至
        </a>
      
    </div>
    <div data-md-component="announce">
      
    </div>
    
    
<header class="md-header md-header--shadow" data-md-component="header">
  <nav class="md-header__inner md-grid" aria-label="页眉">
    <a href="../index.html" title="企业知识库RAG智能问答项目V1.0" class="md-header__button md-logo" aria-label="企业知识库RAG智能问答项目V1.0" data-md-component="logo">
      
  <img src="../img/AI.jpg" alt="logo">

    </a>
    <label class="md-header__button md-icon" for="__drawer">
      
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
    </label>
    <div class="md-header__title" data-md-component="header-title">
      <div class="md-header__ellipsis">
        <div class="md-header__topic">
          <span class="md-ellipsis">
            企业知识库RAG智能问答项目V1.0
          </span>
        </div>
        <div class="md-header__topic" data-md-component="header-topic">
          <span class="md-ellipsis">
            
              数据集生成与优化(扩展资料)
            
          </span>
        </div>
      </div>
    </div>
    
    
      <script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
    
    
        <label class="md-header__button md-icon" for="__search">
          
          <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
        </label>
        <div class="md-search" data-md-component="search" role="dialog">
  <label class="md-search__overlay" for="__search"></label>
  <div class="md-search__inner" role="search">
    <form class="md-search__form" name="search">
      <input type="text" class="md-search__input" name="query" aria-label="搜索" placeholder="搜索" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
      <label class="md-search__icon md-icon" for="__search">
        
        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
        
        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
      </label>
      <nav class="md-search__options" aria-label="查找">
        
        <button type="reset" class="md-search__icon md-icon" title="清空当前内容" aria-label="清空当前内容" tabindex="-1">
          
          <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
        </button>
      </nav>
      
    </form>
    <div class="md-search__output">
      <div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
        <div class="md-search-result" data-md-component="search-result">
          <div class="md-search-result__meta">
            正在初始化搜索引擎
          </div>
          <ol class="md-search-result__list" role="presentation"></ol>
        </div>
      </div>
    </div>
  </div>
</div>
      
    
  </nav>
  
</header>
    
    <div class="md-container" data-md-component="container">
      
      
      <main class="md-main" data-md-component="main">
        <div class="md-main__inner md-grid">
          
            
              <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
                <div class="md-sidebar__scrollwrap">
                  <div class="md-sidebar__inner">
                    

<nav class="md-nav md-nav--primary" aria-label="导航栏" data-md-level="0">
  <label class="md-nav__title" for="__drawer">
    <a href="../index.html" title="企业知识库RAG智能问答项目V1.0" class="md-nav__button md-logo" aria-label="企业知识库RAG智能问答项目V1.0" data-md-component="logo">
      
  <img src="../img/AI.jpg" alt="logo">

    </a>
    企业知识库RAG智能问答项目V1.0
  </label>
  
  <ul class="md-nav__list" data-md-scrollfix>
    
      
    <li class="md-nav__item">
      <a href="../index.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    知识库内容
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item md-nav__item--nested">
      
        
        <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
        
          
          <label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
            
  
  <span class="md-ellipsis">
    ① 项目概述
    
  </span>
  

            <span class="md-nav__icon md-icon"></span>
          </label>
        
        <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
          <label class="md-nav__title" for="__nav_2">
            <span class="md-nav__icon md-icon"></span>
            ① 项目概述
          </label>
          <ul class="md-nav__list" data-md-scrollfix>
            
              
    <li class="md-nav__item">
      <a href="../%E2%91%A0%20%E9%A1%B9%E7%9B%AE%E6%A6%82%E8%BF%B0/1.1%20%E9%A1%B9%E7%9B%AE%E6%9E%B6%E6%9E%84.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    1.1 项目架构
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A0%20%E9%A1%B9%E7%9B%AE%E6%A6%82%E8%BF%B0/1.2%20%E9%A1%B9%E7%9B%AE%E7%8E%AF%E5%A2%83%28window%29.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    1.2 项目环境(window)
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A0%20%E9%A1%B9%E7%9B%AE%E6%A6%82%E8%BF%B0/1.3%20%E9%A1%B9%E7%9B%AE%E7%8E%AF%E5%A2%83%28mac%29.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    1.3 项目环境(mac)
    
  </span>
  

      </a>
    </li>
  

          </ul>
        </nav>
      
    </li>
  

    <li class="md-nav__item md-nav__item--nested">
      
        
        <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" >
        
          
          <label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
            
  
  <span class="md-ellipsis">
    ② 项目工具
    
  </span>
  

            <span class="md-nav__icon md-icon"></span>
          </label>
        
        <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
          <label class="md-nav__title" for="__nav_3">
            <span class="md-nav__icon md-icon"></span>
            ② 项目工具
          </label>
          <ul class="md-nav__list" data-md-scrollfix>
              
                
    <li class="md-nav__item">
      <a href="../%E2%91%A1%20%E9%A1%B9%E7%9B%AE%E5%B7%A5%E5%85%B7/2.1%20Ollama%E5%A4%A7%E6%A8%A1%E5%9E%8B%E9%AB%98%E6%95%88%E7%AE%A1%E7%90%86%E5%B7%A5%E5%85%B7.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    2.1 Ollama大模型高效管理工具
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A1%20%E9%A1%B9%E7%9B%AE%E5%B7%A5%E5%85%B7/2.2%20LangChain%E5%9F%BA%E7%A1%80%E7%9F%A5%E8%AF%86.md.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    2.2 LangChain基础知识.md
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A1%20%E9%A1%B9%E7%9B%AE%E5%B7%A5%E5%85%B7/2.3%20%E5%90%91%E9%87%8F%E7%B4%A2%E5%BC%95%EF%BC%9AHNSW%E3%80%81IVF%E4%B8%8EIVF_PQ.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    2.3 向量索引：HNSW、IVF与IVF_PQ
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A1%20%E9%A1%B9%E7%9B%AE%E5%B7%A5%E5%85%B7/2.4%20Milvus%E5%90%91%E9%87%8F%E6%95%B0%E6%8D%AE%E5%BA%93.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    2.4 Milvus向量数据库
    
  </span>
  

      </a>
    </li>
  

          </ul>
        </nav>
      
    </li>
  

    <li class="md-nav__item md-nav__item--nested">
      
        
        <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" >
        
          
          <label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
            
  
  <span class="md-ellipsis">
    ③ 基于Mysql库的问答系统
    
  </span>
  

            <span class="md-nav__icon md-icon"></span>
          </label>
        
        <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
          <label class="md-nav__title" for="__nav_4">
            <span class="md-nav__icon md-icon"></span>
            ③ 基于Mysql库的问答系统
          </label>
          <ul class="md-nav__list" data-md-scrollfix>
            
              
    <li class="md-nav__item">
      <a href="../%E2%91%A2%20%E5%9F%BA%E4%BA%8EMysql%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/3.1%20Python%E6%97%A5%E5%BF%97%E4%BB%8B%E7%BB%8D%E4%B8%8E%E5%BA%94%E7%94%A8.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    3.1 Python日志介绍与应用
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A2%20%E5%9F%BA%E4%BA%8EMysql%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/3.2%20Redis%E6%95%B0%E6%8D%AE%E5%BA%93%E7%AE%80%E4%BB%8B%E4%B8%8E%E4%BD%BF%E7%94%A8.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    3.2 Redis数据库简介与使用
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A2%20%E5%9F%BA%E4%BA%8EMysql%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/3.3%20%E5%9F%BA%E4%BA%8EMysql%E6%95%B0%E6%8D%AE%E5%BA%93%E5%AE%9E%E7%8E%B0%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    3.3 基于Mysql数据库实现问答系统
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A2%20%E5%9F%BA%E4%BA%8EMysql%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/3.4%20BM25%E7%AE%97%E6%B3%95%E7%AE%80%E4%BB%8B%E4%B8%8E%E5%BA%94%E7%94%A8.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    3.4 BM25算法简介与应用
    
  </span>
  

      </a>
    </li>
  

          </ul>
        </nav>
      
    </li>
  

    <li class="md-nav__item md-nav__item--active md-nav__item--nested">
      
        
        <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" checked>
        
          
          <label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
            
  
  <span class="md-ellipsis">
    ④ 基于Milvus库的问答系统
    
  </span>
  

            <span class="md-nav__icon md-icon"></span>
          </label>
        
        <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="true">
          <label class="md-nav__title" for="__nav_5">
            <span class="md-nav__icon md-icon"></span>
            ④ 基于Milvus库的问答系统
          </label>
          <ul class="md-nav__list" data-md-scrollfix>
            
              
    <li class="md-nav__item">
      <a href="4.1%20%E6%95%B4%E4%BD%93%E6%9E%B6%E6%9E%84%E4%B8%8E%E5%B7%A5%E7%A8%8B%E6%B5%81%E7%A8%8B.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.1 整体架构与工程流程
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.2%20%E5%9F%BA%E7%A1%80%E6%A8%A1%E5%9D%97.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.2 基础模块
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.3%20%E6%96%87%E6%A1%A3%E5%A4%84%E7%90%86%E6%A8%A1%E5%9D%97.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.3 文档处理模块
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.4%20%E5%90%91%E9%87%8F%E5%AD%98%E5%82%A8.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.4 向量存储
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.5%20prompts%E8%AE%BE%E8%AE%A1%E4%B8%8Equery%E6%84%8F%E5%9B%BE%E8%AF%86%E5%88%AB.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.5 prompts设计与query意图识别
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.6%20%E6%A3%80%E7%B4%A2%E7%AD%96%E7%95%A5%E4%B8%8ERAG%E7%B3%BB%E7%BB%9F%E8%AE%BE%E8%AE%A1.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.6 检索策略与RAG系统设计
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.7%20RAG%E7%B3%BB%E7%BB%9F%E8%BF%90%E8%A1%8C.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.7 RAG系统运行
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.8%20%E6%96%87%E6%A1%A3%E8%A7%A3%E6%9E%90%E5%B7%A5%E5%85%B7%28%E6%89%A9%E5%B1%95%E8%B5%84%E6%96%99%29.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.8 文档解析工具(扩展资料)
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.9%20RAG%E4%B8%AD%E7%9A%84Query%E6%94%B9%E5%86%99%28%E6%89%A9%E5%B1%95%E8%B5%84%E6%96%99%29.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.9 RAG中的Query改写(扩展资料)
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item md-nav__item--active">
      
      <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
      
      
        <label class="md-nav__link md-nav__link--active" for="__toc">
          
  
  <span class="md-ellipsis">
    数据集生成与优化(扩展资料)
    
  </span>
  

          <span class="md-nav__icon md-icon"></span>
        </label>
      
      <a href="%E6%95%B0%E6%8D%AE%E9%9B%86%E7%94%9F%E6%88%90%E4%B8%8E%E4%BC%98%E5%8C%96%28%E6%89%A9%E5%B1%95%E8%B5%84%E6%96%99%29.html" class="md-nav__link md-nav__link--active">
        
  
  <span class="md-ellipsis">
    数据集生成与优化(扩展资料)
    
  </span>
  

      </a>
      
        
<nav class="md-nav md-nav--secondary" aria-label="目录">
  
  
    <label class="md-nav__title" for="__toc">
      <span class="md-nav__icon md-icon"></span>
      目录
    </label>
    <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
      
        <li class="md-nav__item">
  <a href="#_1" class="md-nav__link">
    <span class="md-ellipsis">
      学习目标
    </span>
  </a>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_2" class="md-nav__link">
    <span class="md-ellipsis">
      一、数据生成与优化
    </span>
  </a>
  
    <nav class="md-nav" aria-label="一、数据生成与优化">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能概述
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2" class="md-nav__link">
    <span class="md-ellipsis">
      2 完整代码
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现细节
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#5" class="md-nav__link">
    <span class="md-ellipsis">
      5 执行示例
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_3" class="md-nav__link">
    <span class="md-ellipsis">
      二、数据集生成流程
    </span>
  </a>
  
    <nav class="md-nav" aria-label="二、数据集生成流程">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_1" class="md-nav__link">
    <span class="md-ellipsis">
      1 生成流程
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_1" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例（使用数据集）
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_4" class="md-nav__link">
    <span class="md-ellipsis">
      三、数据集特点与优化
    </span>
  </a>
  
    <nav class="md-nav" aria-label="三、数据集特点与优化">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_2" class="md-nav__link">
    <span class="md-ellipsis">
      1 数据集特点
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_2" class="md-nav__link">
    <span class="md-ellipsis">
      2 优化效果
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_5" class="md-nav__link">
    <span class="md-ellipsis">
      章节小结
    </span>
  </a>
  
</li>
      
    </ul>
  
</nav>
      
    </li>
  

          </ul>
        </nav>
      
    </li>
  

    <li class="md-nav__item md-nav__item--nested">
      
        
        <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
        
          
          <label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
            
  
  <span class="md-ellipsis">
    ⑤ RAG系统评估
    
  </span>
  

            <span class="md-nav__icon md-icon"></span>
          </label>
        
        <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
          <label class="md-nav__title" for="__nav_6">
            <span class="md-nav__icon md-icon"></span>
            ⑤ RAG系统评估
          </label>
          <ul class="md-nav__list" data-md-scrollfix>
            
              
    <li class="md-nav__item">
      <a href="../%E2%91%A4%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0/5.1%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0%E5%B7%A5%E5%85%B7.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    5.1 RAG系统评估工具
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A4%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0/5.2%20%E5%AE%9E%E7%8E%B0EnterpriseKB-RAG%E7%B3%BB%E7%BB%9F%E7%9A%84%E8%AF%84%E4%BC%B0.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    5.2 实现企业知识库RAG系统的评估
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A4%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0/5.3%20RAG%E8%AF%84%E4%BC%B0%E6%95%B0%E6%8D%AE%E9%9B%86%E7%9A%84%E6%9E%84%E9%80%A0%28%E6%89%A9%E5%B1%95%29.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    5.3 RAG评估数据集的构造(扩展)
    
  </span>
  

      </a>
    </li>
  

          </ul>
        </nav>
      
    </li>
  

    <li class="md-nav__item md-nav__item--nested">
      
        
        <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
        
          
          <label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
            
  
  <span class="md-ellipsis">
    ⑥ 融合Mysql的RAG系统
    
  </span>
  

            <span class="md-nav__icon md-icon"></span>
          </label>
        
        <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
          <label class="md-nav__title" for="__nav_7">
            <span class="md-nav__icon md-icon"></span>
            ⑥ 融合Mysql的RAG系统
          </label>
          <ul class="md-nav__list" data-md-scrollfix>
            
              
    <li class="md-nav__item">
      <a href="../%E2%91%A5%20%E8%9E%8D%E5%90%88Mysql%E7%9A%84RAG%E7%B3%BB%E7%BB%9F/6.1%20%E8%9E%8D%E5%90%88FQA%E5%92%8C%E7%9F%A5%E8%AF%86%E5%BA%93%E6%9F%A5%E8%AF%A2.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    6.1 融合FQA和知识库查询
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A5%20%E8%9E%8D%E5%90%88Mysql%E7%9A%84RAG%E7%B3%BB%E7%BB%9F/6.2%20%E8%9E%8D%E5%90%88FAQ%20%E5%92%8C%E7%9F%A5%E8%AF%86%E5%BA%93%E6%9F%A5%E8%AF%A2%EF%BC%88%E4%BC%98%E5%8C%96%E7%89%88%EF%BC%89.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    6.2 融合FAQ 和知识库查询（优化版）
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A5%20%E8%9E%8D%E5%90%88Mysql%E7%9A%84RAG%E7%B3%BB%E7%BB%9F/6.3%20%E5%9F%BA%E4%BA%8E%20FastAPI%20%E7%9A%84%20FAQ%20%E4%B8%8E%E7%9F%A5%E8%AF%86%E5%BA%93%E6%9F%A5%E8%AF%A2%E6%8E%A5%E5%8F%A3.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    6.3 基于 FastAPI 的 FAQ 与知识库查询接口
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A5%20%E8%9E%8D%E5%90%88Mysql%E7%9A%84RAG%E7%B3%BB%E7%BB%9F/6.4%20FastAPI%E5%92%8CFlask%E7%9A%84%E5%8C%BA%E5%88%AB%E5%92%8C%E8%81%94%E7%B3%BB%28%E6%89%A9%E5%B1%95%E8%B5%84%E6%96%99%29.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    6.4 FastAPI和Flask的区别和联系(扩展资料)
    
  </span>
  

      </a>
    </li>
  

          </ul>
        </nav>
      
    </li>
  

    <li class="md-nav__item md-nav__item--nested">
      
        
        <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" >
        
          
          <label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
            
  
  <span class="md-ellipsis">
    ⑦ 企业级生产环境部署
    
  </span>
  

            <span class="md-nav__icon md-icon"></span>
          </label>
        
        <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
          <label class="md-nav__title" for="__nav_8">
            <span class="md-nav__icon md-icon"></span>
            ⑦ 企业级生产环境部署
          </label>
          <ul class="md-nav__list" data-md-scrollfix>
            
              
    <li class="md-nav__item">
      <a href="../%E2%91%A6%20%E4%BC%81%E4%B8%9A%E7%BA%A7%E7%94%9F%E4%BA%A7%E7%8E%AF%E5%A2%83%E9%83%A8%E7%BD%B2/7.1%20Docker%E7%9A%84%E5%8E%9F%E7%90%86%E5%92%8C%E5%9F%BA%E6%9C%AC%E4%BD%BF%E7%94%A8.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    7.1 Docker的原理和基本使用
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../%E2%91%A6%20%E4%BC%81%E4%B8%9A%E7%BA%A7%E7%94%9F%E4%BA%A7%E7%8E%AF%E5%A2%83%E9%83%A8%E7%BD%B2/7.2%20%E6%9C%8D%E5%8A%A1%E9%83%A8%E7%BD%B2.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    7.2 服务部署
    
  </span>
  

      </a>
    </li>
  

          </ul>
        </nav>
      
    </li>
  

  </ul>
</nav>
                  </div>
                </div>
              </div>
            
            
              <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
                <div class="md-sidebar__scrollwrap">
                  <div class="md-sidebar__inner">
                    

<nav class="md-nav md-nav--secondary" aria-label="目录">
  
  
    <label class="md-nav__title" for="__toc">
      <span class="md-nav__icon md-icon"></span>
      目录
    </label>
    <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
      
        <li class="md-nav__item">
  <a href="#_1" class="md-nav__link">
    <span class="md-ellipsis">
      学习目标
    </span>
  </a>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_2" class="md-nav__link">
    <span class="md-ellipsis">
      一、数据生成与优化
    </span>
  </a>
  
    <nav class="md-nav" aria-label="一、数据生成与优化">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能概述
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2" class="md-nav__link">
    <span class="md-ellipsis">
      2 完整代码
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现细节
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#5" class="md-nav__link">
    <span class="md-ellipsis">
      5 执行示例
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_3" class="md-nav__link">
    <span class="md-ellipsis">
      二、数据集生成流程
    </span>
  </a>
  
    <nav class="md-nav" aria-label="二、数据集生成流程">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_1" class="md-nav__link">
    <span class="md-ellipsis">
      1 生成流程
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_1" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例（使用数据集）
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_4" class="md-nav__link">
    <span class="md-ellipsis">
      三、数据集特点与优化
    </span>
  </a>
  
    <nav class="md-nav" aria-label="三、数据集特点与优化">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_2" class="md-nav__link">
    <span class="md-ellipsis">
      1 数据集特点
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_2" class="md-nav__link">
    <span class="md-ellipsis">
      2 优化效果
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_5" class="md-nav__link">
    <span class="md-ellipsis">
      章节小结
    </span>
  </a>
  
</li>
      
    </ul>
  
</nav>
                  </div>
                </div>
              </div>
            
          
            <div class="md-content" data-md-component="content">
              <article class="md-content__inner md-typeset">
                
                  
  <h1>数据集生成与优化(扩展资料)</h1>

<h2 id="_1">学习目标<a class="headerlink" href="#_1" title="Permanent link">&para;</a></h2>
<ul>
<li>1.掌握如何结合规则模板和 Qwen-Plus 模型生成高质量查询数据集。</li>
<li>2.通过 tqdm 进度条监控生成进度，并实现分阶段数据保存。</li>
</ul>
<hr />
<p><code>generate_query_dataset_hybrid.py</code> 是 EnterpriseKB-RAG 系统中用于生成训练数据集的核心脚本，旨在为 <code>QueryClassifier</code> 提供 6000 条高质量数据（“通用知识”和“企业知识”各 3000 条）。通过规则模板和 Qwen-Plus 模型的混合生成，结合进度条和分阶段保存，本脚本确保了生成效率和数据可靠性。本章节将详细讲解其功能、实现和应用。</p>
<h2 id="_2">一、数据生成与优化<a class="headerlink" href="#_2" title="Permanent link">&para;</a></h2>
<h3 id="1">1 功能概述<a class="headerlink" href="#1" title="Permanent link">&para;</a></h3>
<p><code>generate_query_dataset_hybrid.py</code> 提供以下功能：</p>
<ul>
<li><strong>规则生成</strong>：基于模板和同义词替换生成 3000 条数据（“通用知识”和“企业知识”各 1500 条）。</li>
<li><strong>大模型生成</strong>：利用 Qwen-Plus 生成 3000 条自然语言查询（各 1500 条）。</li>
<li><strong>进度监控</strong>：通过 <code>tqdm</code> 进度条可视化每个生成阶段。</li>
<li><strong>分阶段保存</strong>：每生成 1500 条数据保存一次，最终合并保存完整数据集。</li>
<li><strong>数据集输出</strong>：生成均衡的 6000 条数据，保存为 JSON 文件。</li>
</ul>
<h3 id="2">2 完整代码<a class="headerlink" href="#2" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><span class="c1"># generate_query_dataset_hybrid.py</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">random</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">re</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">openai</span><span class="w"> </span><span class="kn">import</span> <span class="n">OpenAI</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">dotenv</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_dotenv</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tqdm</span><span class="w"> </span><span class="kn">import</span> <span class="n">tqdm</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">time</span>

<span class="c1"># 加载环境变量</span>
<span class="n">load_dotenv</span><span class="p">()</span>

<span class="c1"># 初始化Qwen-Plus客户端</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">OpenAI</span><span class="p">(</span>
    <span class="n">api_key</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="s2">&quot;DASHSCOPE_API_KEY&quot;</span><span class="p">),</span>
    <span class="n">base_url</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="s2">&quot;DASHSCOPE_BASE_URL&quot;</span><span class="p">,</span> <span class="s2">&quot;https://dashscope.aliyuncs.com/compatible-mode/v1&quot;</span><span class="p">),</span>
<span class="p">)</span>

<span class="c1"># 同义词词典</span>
<span class="n">synonym_dict</span> <span class="o">=</span> <span class="p">{</span>
    <span class="s2">&quot;什么&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;什么&quot;</span><span class="p">,</span> <span class="s2">&quot;啥是&quot;</span><span class="p">,</span> <span class="s2">&quot;如何解释&quot;</span><span class="p">,</span> <span class="s2">&quot;具体是什么&quot;</span><span class="p">,</span> <span class="s2">&quot;请解释&quot;</span><span class="p">],</span>
    <span class="s2">&quot;知识文档&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;知识文档&quot;</span><span class="p">,</span> <span class="s2">&quot;内部赋能知识文档&quot;</span><span class="p">,</span> <span class="s2">&quot;制度安排&quot;</span><span class="p">,</span> <span class="s2">&quot;教学内容&quot;</span><span class="p">,</span> <span class="s2">&quot;课&quot;</span><span class="p">],</span>
    <span class="s2">&quot;报销标准&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;报销标准&quot;</span><span class="p">,</span> <span class="s2">&quot;费用&quot;</span><span class="p">,</span> <span class="s2">&quot;申请费&quot;</span><span class="p">,</span> <span class="s2">&quot;学习费用&quot;</span><span class="p">,</span> <span class="s2">&quot;价格&quot;</span><span class="p">,</span> <span class="s2">&quot;收费&quot;</span><span class="p">],</span>
    <span class="s2">&quot;大纲&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;大纲&quot;</span><span class="p">,</span> <span class="s2">&quot;知识库内容&quot;</span><span class="p">,</span> <span class="s2">&quot;教学计划&quot;</span><span class="p">,</span> <span class="s2">&quot;讲义&quot;</span><span class="p">],</span>
    <span class="s2">&quot;专家支持&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;专家支持&quot;</span><span class="p">,</span> <span class="s2">&quot;教师团队&quot;</span><span class="p">,</span> <span class="s2">&quot;讲师阵容&quot;</span><span class="p">,</span> <span class="s2">&quot;专家支持力量&quot;</span><span class="p">,</span> <span class="s2">&quot;支持人员&quot;</span><span class="p">,</span> <span class="s2">&quot;讲师&quot;</span><span class="p">],</span>
    <span class="s2">&quot;内部赋能&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;内部赋能&quot;</span><span class="p">,</span> <span class="s2">&quot;辅导&quot;</span><span class="p">,</span> <span class="s2">&quot;工作计划&quot;</span><span class="p">,</span> <span class="s2">&quot;知识库知识文档&quot;</span><span class="p">],</span>
    <span class="s2">&quot;在哪里&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;在哪里&quot;</span><span class="p">,</span> <span class="s2">&quot;位于何处&quot;</span><span class="p">,</span> <span class="s2">&quot;设在何地&quot;</span><span class="p">,</span> <span class="s2">&quot;在哪&quot;</span><span class="p">],</span>
    <span class="s2">&quot;介绍&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;介绍&quot;</span><span class="p">,</span> <span class="s2">&quot;说明&quot;</span><span class="p">,</span> <span class="s2">&quot;讲解&quot;</span><span class="p">,</span> <span class="s2">&quot;概述&quot;</span><span class="p">,</span> <span class="s2">&quot;讲讲&quot;</span><span class="p">,</span> <span class="s2">&quot;说说&quot;</span><span class="p">],</span>
    <span class="s2">&quot;请问&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;请问&quot;</span><span class="p">,</span> <span class="s2">&quot;能否告知&quot;</span><span class="p">,</span> <span class="s2">&quot;是否可以告诉我&quot;</span><span class="p">,</span> <span class="s2">&quot;麻烦说下&quot;</span><span class="p">],</span>
    <span class="s2">&quot;原理&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;原理&quot;</span><span class="p">,</span> <span class="s2">&quot;基本思想&quot;</span><span class="p">,</span> <span class="s2">&quot;工作机制&quot;</span><span class="p">],</span>
    <span class="s2">&quot;写一个&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;写一个&quot;</span><span class="p">,</span> <span class="s2">&quot;编写一个&quot;</span><span class="p">,</span> <span class="s2">&quot;生成一个&quot;</span><span class="p">,</span> <span class="s2">&quot;创建一个&quot;</span><span class="p">],</span>
    <span class="s2">&quot;等于多少&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;等于多少&quot;</span><span class="p">,</span> <span class="s2">&quot;是多少&quot;</span><span class="p">,</span> <span class="s2">&quot;结果是啥&quot;</span><span class="p">,</span> <span class="s2">&quot;得多少&quot;</span><span class="p">],</span>
    <span class="s2">&quot;如何&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;如何&quot;</span><span class="p">,</span> <span class="s2">&quot;怎样&quot;</span><span class="p">,</span> <span class="s2">&quot;咋样&quot;</span><span class="p">],</span>
    <span class="s2">&quot;需要&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;需要&quot;</span><span class="p">,</span> <span class="s2">&quot;要&quot;</span><span class="p">,</span> <span class="s2">&quot;得有&quot;</span><span class="p">,</span> <span class="s2">&quot;必须具备&quot;</span><span class="p">],</span>
    <span class="s2">&quot;基础&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;基础&quot;</span><span class="p">,</span> <span class="s2">&quot;前提&quot;</span><span class="p">,</span> <span class="s2">&quot;背景&quot;</span><span class="p">,</span> <span class="s2">&quot;基本知识&quot;</span><span class="p">]</span>
<span class="p">}</span>

<span class="k">def</span><span class="w"> </span><span class="nf">apply_synonym_variation</span><span class="p">(</span><span class="n">text</span><span class="p">,</span> <span class="n">replace_prob</span><span class="o">=</span><span class="mf">0.5</span><span class="p">):</span>
<span class="w">    </span><span class="sd">&quot;&quot;&quot;对文本进行同义词随机替换&quot;&quot;&quot;</span>
    <span class="k">for</span> <span class="n">word</span><span class="p">,</span> <span class="n">synonyms</span> <span class="ow">in</span> <span class="n">synonym_dict</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
        <span class="n">pattern</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">&quot;\b&quot;</span> <span class="o">+</span> <span class="n">re</span><span class="o">.</span><span class="n">escape</span><span class="p">(</span><span class="n">word</span><span class="p">)</span> <span class="o">+</span> <span class="sa">r</span><span class="s2">&quot;\b&quot;</span>
        <span class="k">def</span><span class="w"> </span><span class="nf">repl</span><span class="p">(</span><span class="n">match</span><span class="p">):</span>
            <span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span> <span class="o">&lt;</span> <span class="n">replace_prob</span><span class="p">:</span>
                <span class="k">return</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">synonyms</span><span class="p">)</span>
            <span class="k">return</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
        <span class="n">text</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="n">pattern</span><span class="p">,</span> <span class="n">repl</span><span class="p">,</span> <span class="n">text</span><span class="p">)</span>
    <span class="k">return</span> <span class="n">text</span>

<span class="c1"># 规则生成部分</span>
<span class="k">def</span><span class="w"> </span><span class="nf">generate_generic_query_rule</span><span class="p">():</span>
<span class="w">    </span><span class="sd">&quot;&quot;&quot;规则生成通用知识查询&quot;&quot;&quot;</span>
    <span class="n">templates</span> <span class="o">=</span> <span class="p">[</span>
        <span class="s2">&quot;什么</span><span class="si">{concept}</span><span class="s2">？&quot;</span><span class="p">,</span>
        <span class="s2">&quot;</span><span class="si">{concept}</span><span class="s2">的定义是什么？&quot;</span><span class="p">,</span>
        <span class="s2">&quot;请解释</span><span class="si">{concept}</span><span class="s2">的原理。&quot;</span><span class="p">,</span>
        <span class="s2">&quot;如何运用</span><span class="si">{concept}</span><span class="s2">？&quot;</span><span class="p">,</span>
        <span class="s2">&quot;计算</span><span class="si">{num1}</span><span class="s2">+</span><span class="si">{num2}</span><span class="s2">等于多少？&quot;</span><span class="p">,</span>
        <span class="s2">&quot;写一个</span><span class="si">{lang}</span><span class="s2">的</span><span class="si">{func}</span><span class="s2">函数&quot;</span><span class="p">,</span>
        <span class="s2">&quot;为什么</span><span class="si">{thing}</span><span class="s2">是</span><span class="si">{state}</span><span class="s2">？&quot;</span>
    <span class="p">]</span>
    <span class="n">concepts</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;AI&quot;</span><span class="p">,</span> <span class="s2">&quot;Transformer模型&quot;</span><span class="p">,</span> <span class="s2">&quot;Python&quot;</span><span class="p">,</span> <span class="s2">&quot;递归&quot;</span><span class="p">,</span> <span class="s2">&quot;算法复杂度&quot;</span><span class="p">,</span> <span class="s2">&quot;数据结构&quot;</span><span class="p">,</span> <span class="s2">&quot;机器学习&quot;</span><span class="p">]</span>
    <span class="n">langs</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;Python&quot;</span><span class="p">,</span> <span class="s2">&quot;Java&quot;</span><span class="p">,</span> <span class="s2">&quot;C++&quot;</span><span class="p">]</span>
    <span class="n">funcs</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;排序&quot;</span><span class="p">,</span> <span class="s2">&quot;计算&quot;</span><span class="p">,</span> <span class="s2">&quot;打印&quot;</span><span class="p">]</span>
    <span class="n">things</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;太阳&quot;</span><span class="p">,</span> <span class="s2">&quot;水&quot;</span><span class="p">,</span> <span class="s2">&quot;风&quot;</span><span class="p">]</span>
    <span class="n">states</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;热的&quot;</span><span class="p">,</span> <span class="s2">&quot;流动的&quot;</span><span class="p">,</span> <span class="s2">&quot;无形的&quot;</span><span class="p">]</span>
    <span class="n">nums</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">100</span><span class="p">))</span>

    <span class="n">t</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">templates</span><span class="p">)</span>
    <span class="k">if</span> <span class="s2">&quot;</span><span class="si">{concept}</span><span class="s2">&quot;</span> <span class="ow">in</span> <span class="n">t</span><span class="p">:</span>
        <span class="n">replacements</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;concept&quot;</span><span class="p">:</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">concepts</span><span class="p">)}</span>
    <span class="k">elif</span> <span class="s2">&quot;</span><span class="si">{num1}</span><span class="s2">&quot;</span> <span class="ow">in</span> <span class="n">t</span><span class="p">:</span>
        <span class="n">replacements</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;num1&quot;</span><span class="p">:</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">nums</span><span class="p">),</span> <span class="s2">&quot;num2&quot;</span><span class="p">:</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">nums</span><span class="p">)}</span>
    <span class="k">elif</span> <span class="s2">&quot;</span><span class="si">{lang}</span><span class="s2">&quot;</span> <span class="ow">in</span> <span class="n">t</span><span class="p">:</span>
        <span class="n">replacements</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;lang&quot;</span><span class="p">:</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">langs</span><span class="p">),</span> <span class="s2">&quot;func&quot;</span><span class="p">:</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">funcs</span><span class="p">)}</span>
    <span class="k">elif</span> <span class="s2">&quot;</span><span class="si">{thing}</span><span class="s2">&quot;</span> <span class="ow">in</span> <span class="n">t</span><span class="p">:</span>
        <span class="n">replacements</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;thing&quot;</span><span class="p">:</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">things</span><span class="p">),</span> <span class="s2">&quot;state&quot;</span><span class="p">:</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">states</span><span class="p">)}</span>
    <span class="k">else</span><span class="p">:</span>
        <span class="n">replacements</span> <span class="o">=</span> <span class="p">{}</span>

    <span class="n">query</span> <span class="o">=</span> <span class="n">t</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="n">replacements</span><span class="p">)</span>
    <span class="k">return</span> <span class="n">apply_synonym_variation</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>

<span class="k">def</span><span class="w"> </span><span class="nf">generate_professional_query_rule</span><span class="p">():</span>
<span class="w">    </span><span class="sd">&quot;&quot;&quot;规则生成企业知识查询&quot;&quot;&quot;</span>
    <span class="n">templates</span> <span class="o">=</span> <span class="p">[</span>
        <span class="s2">&quot;请问</span><span class="si">{subject}</span><span class="s2">知识文档的报销标准是多少？&quot;</span><span class="p">,</span>
        <span class="s2">&quot;</span><span class="si">{subject}</span><span class="s2">的知识文档目录是什么？&quot;</span><span class="p">,</span>
        <span class="s2">&quot;</span><span class="si">{subject}</span><span class="s2">内部赋能的学习周期有多长？&quot;</span><span class="p">,</span>
        <span class="s2">&quot;请介绍一下</span><span class="si">{subject}</span><span class="s2">内部赋能的主要项目内容。&quot;</span><span class="p">,</span>
        <span class="s2">&quot;请问</span><span class="si">{subject}</span><span class="s2">内部赋能地点在哪里？&quot;</span>
    <span class="p">]</span>
    <span class="n">subjects</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;JAVA&quot;</span><span class="p">,</span> <span class="s2">&quot;AI&quot;</span><span class="p">,</span> <span class="s2">&quot;测试&quot;</span><span class="p">,</span> <span class="s2">&quot;Web前端&quot;</span><span class="p">,</span> <span class="s2">&quot;Python&quot;</span><span class="p">,</span> <span class="s2">&quot;大数据&quot;</span><span class="p">,</span> <span class="s2">&quot;DevOps&quot;</span><span class="p">]</span>
    <span class="n">t</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">templates</span><span class="p">)</span>
    <span class="n">query</span> <span class="o">=</span> <span class="n">t</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">subject</span><span class="o">=</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">subjects</span><span class="p">))</span>
    <span class="k">return</span> <span class="n">apply_synonym_variation</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>

<span class="c1"># 大模型生成部分</span>
<span class="k">def</span><span class="w"> </span><span class="nf">generate_with_qwen</span><span class="p">(</span><span class="n">prompt</span><span class="p">):</span>
<span class="w">    </span><span class="sd">&quot;&quot;&quot;调用Qwen-Plus生成查询，添加超时控制&quot;&quot;&quot;</span>
    <span class="k">try</span><span class="p">:</span>
        <span class="n">completion</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">chat</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
            <span class="n">model</span><span class="o">=</span><span class="s2">&quot;qwen-plus&quot;</span><span class="p">,</span>
            <span class="n">messages</span><span class="o">=</span><span class="p">[{</span><span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span> <span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="n">prompt</span><span class="p">}],</span>
            <span class="n">temperature</span><span class="o">=</span><span class="mf">0.9</span><span class="p">,</span>
            <span class="n">timeout</span><span class="o">=</span><span class="mi">10</span>
        <span class="p">)</span>
        <span class="k">return</span> <span class="n">completion</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">message</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
    <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
        <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Qwen-Plus调用失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
        <span class="k">return</span> <span class="kc">None</span>

<span class="k">def</span><span class="w"> </span><span class="nf">generate_generic_query_qwen</span><span class="p">():</span>
<span class="w">    </span><span class="sd">&quot;&quot;&quot;使用Qwen-Plus生成通用知识查询&quot;&quot;&quot;</span>
    <span class="n">prompt</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;</span>
<span class="s2">    你是一个用户，生成一个“通用知识”类的查询，涉及数学计算、代码生成/纠错、概念与原理或常识性问题。</span>
<span class="s2">    示例：</span>
<span class="s2">    - “3+5等于多少？”</span>
<span class="s2">    - “写一个Python排序函数”</span>
<span class="s2">    - “什么是神经网络？”</span>
<span class="s2">    - “太阳为什么是热的？”</span>
<span class="s2">    请生成一个类似的查询，直接返回查询文本，不要多余说明。</span>
<span class="s2">    &quot;&quot;&quot;</span>
    <span class="k">return</span> <span class="n">generate_with_qwen</span><span class="p">(</span><span class="n">prompt</span><span class="p">)</span>

<span class="k">def</span><span class="w"> </span><span class="nf">generate_professional_query_qwen</span><span class="p">():</span>
<span class="w">    </span><span class="sd">&quot;&quot;&quot;使用Qwen-Plus生成企业知识查询&quot;&quot;&quot;</span>
    <span class="n">prompt</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;</span>
<span class="s2">    你是一个用户，生成一个“企业知识”类的查询，涉及IT知识库内部赋能（如知识文档详情、专家支持、费用、周期、地点等）。</span>
<span class="s2">    示例：</span>
<span class="s2">    - “JAVA知识文档费用多少？”</span>
<span class="s2">    - “AI内部赋能有哪些支持人员？”</span>
<span class="s2">    - “测试知识文档什么时候开课？”</span>
<span class="s2">    请生成一个类似的查询，直接返回查询文本，不要多余说明。</span>
<span class="s2">    &quot;&quot;&quot;</span>
    <span class="k">return</span> <span class="n">generate_with_qwen</span><span class="p">(</span><span class="n">prompt</span><span class="p">)</span>

<span class="c1"># 保存数据集</span>
<span class="k">def</span><span class="w"> </span><span class="nf">save_dataset</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">filename</span><span class="p">,</span> <span class="n">stage_name</span><span class="p">):</span>
<span class="w">    </span><span class="sd">&quot;&quot;&quot;保存数据集到指定文件&quot;&quot;&quot;</span>
    <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s2">&quot;w&quot;</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s2">&quot;utf-8&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
        <span class="n">json</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">ensure_ascii</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">indent</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
    <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">stage_name</span><span class="si">}</span><span class="s2">：已保存 </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span><span class="si">}</span><span class="s2"> 条数据到 </span><span class="si">{</span><span class="n">filename</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>

<span class="k">def</span><span class="w"> </span><span class="nf">generate_training_dataset</span><span class="p">(</span><span class="n">total_samples</span><span class="o">=</span><span class="mi">6000</span><span class="p">):</span>
<span class="w">    </span><span class="sd">&quot;&quot;&quot;生成6000条训练数据，规则和大模型各占一半，每1500条保存&quot;&quot;&quot;</span>
    <span class="n">num_per_category</span> <span class="o">=</span> <span class="n">total_samples</span> <span class="o">//</span> <span class="mi">2</span>  <span class="c1"># 3000</span>
    <span class="n">num_rule</span> <span class="o">=</span> <span class="n">num_per_category</span> <span class="o">//</span> <span class="mi">2</span>  <span class="c1"># 1500</span>
    <span class="n">num_qwen</span> <span class="o">=</span> <span class="n">num_per_category</span> <span class="o">-</span> <span class="n">num_rule</span>  <span class="c1"># 1500</span>

    <span class="n">generic_samples</span> <span class="o">=</span> <span class="p">[]</span>
    <span class="n">professional_samples</span> <span class="o">=</span> <span class="p">[]</span>
    <span class="n">generic_set</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
    <span class="n">professional_set</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>

    <span class="c1"># 规则生成 - 通用知识</span>
    <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;生成规则通用知识数据...&quot;</span><span class="p">)</span>
    <span class="k">with</span> <span class="n">tqdm</span><span class="p">(</span><span class="n">total</span><span class="o">=</span><span class="n">num_rule</span><span class="p">,</span> <span class="n">desc</span><span class="o">=</span><span class="s2">&quot;Rule-based Generic&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">pbar</span><span class="p">:</span>
        <span class="k">while</span> <span class="nb">len</span><span class="p">(</span><span class="n">generic_samples</span><span class="p">)</span> <span class="o">&lt;</span> <span class="n">num_rule</span><span class="p">:</span>
            <span class="n">q</span> <span class="o">=</span> <span class="n">generate_generic_query_rule</span><span class="p">()</span>
            <span class="k">if</span> <span class="n">q</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">generic_set</span><span class="p">:</span>
                <span class="n">generic_set</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">q</span><span class="p">)</span>
                <span class="n">generic_samples</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">&quot;query&quot;</span><span class="p">:</span> <span class="n">q</span><span class="p">,</span> <span class="s2">&quot;label&quot;</span><span class="p">:</span> <span class="s2">&quot;通用知识&quot;</span><span class="p">})</span>
                <span class="n">pbar</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
    <span class="n">save_dataset</span><span class="p">(</span><span class="n">generic_samples</span><span class="p">,</span> <span class="s2">&quot;rule_generic_1500.json&quot;</span><span class="p">,</span> <span class="s2">&quot;规则通用知识&quot;</span><span class="p">)</span>

    <span class="c1"># 规则生成 - 企业知识</span>
    <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;生成规则企业知识数据...&quot;</span><span class="p">)</span>
    <span class="k">with</span> <span class="n">tqdm</span><span class="p">(</span><span class="n">total</span><span class="o">=</span><span class="n">num_rule</span><span class="p">,</span> <span class="n">desc</span><span class="o">=</span><span class="s2">&quot;Rule-based Professional&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">pbar</span><span class="p">:</span>
        <span class="k">while</span> <span class="nb">len</span><span class="p">(</span><span class="n">professional_samples</span><span class="p">)</span> <span class="o">&lt;</span> <span class="n">num_rule</span><span class="p">:</span>
            <span class="n">q</span> <span class="o">=</span> <span class="n">generate_professional_query_rule</span><span class="p">()</span>
            <span class="k">if</span> <span class="n">q</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">professional_set</span><span class="p">:</span>
                <span class="n">professional_set</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">q</span><span class="p">)</span>
                <span class="n">professional_samples</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">&quot;query&quot;</span><span class="p">:</span> <span class="n">q</span><span class="p">,</span> <span class="s2">&quot;label&quot;</span><span class="p">:</span> <span class="s2">&quot;企业知识&quot;</span><span class="p">})</span>
                <span class="n">pbar</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
    <span class="n">save_dataset</span><span class="p">(</span><span class="n">professional_samples</span><span class="p">,</span> <span class="s2">&quot;rule_professional_1500.json&quot;</span><span class="p">,</span> <span class="s2">&quot;规则企业知识&quot;</span><span class="p">)</span>

    <span class="c1"># Qwen-Plus生成 - 通用知识</span>
    <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;生成Qwen-Plus通用知识数据...&quot;</span><span class="p">)</span>
    <span class="k">with</span> <span class="n">tqdm</span><span class="p">(</span><span class="n">total</span><span class="o">=</span><span class="n">num_qwen</span><span class="p">,</span> <span class="n">desc</span><span class="o">=</span><span class="s2">&quot;Qwen-based Generic&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">pbar</span><span class="p">:</span>
        <span class="k">while</span> <span class="nb">len</span><span class="p">(</span><span class="n">generic_samples</span><span class="p">)</span> <span class="o">&lt;</span> <span class="n">num_per_category</span><span class="p">:</span>
            <span class="n">q</span> <span class="o">=</span> <span class="n">generate_generic_query_qwen</span><span class="p">()</span>
            <span class="k">if</span> <span class="n">q</span> <span class="ow">and</span> <span class="n">q</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">generic_set</span><span class="p">:</span>
                <span class="n">generic_set</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">q</span><span class="p">)</span>
                <span class="n">generic_samples</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">&quot;query&quot;</span><span class="p">:</span> <span class="n">q</span><span class="p">,</span> <span class="s2">&quot;label&quot;</span><span class="p">:</span> <span class="s2">&quot;通用知识&quot;</span><span class="p">})</span>
                <span class="n">pbar</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
            <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mf">0.5</span><span class="p">)</span>  <span class="c1"># 避免 API 限流</span>
    <span class="n">save_dataset</span><span class="p">(</span><span class="n">generic_samples</span><span class="p">,</span> <span class="s2">&quot;generic_3000.json&quot;</span><span class="p">,</span> <span class="s2">&quot;通用知识（规则+Qwen）&quot;</span><span class="p">)</span>

    <span class="c1"># Qwen-Plus生成 - 企业知识</span>
    <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;生成Qwen-Plus企业知识数据...&quot;</span><span class="p">)</span>
    <span class="k">with</span> <span class="n">tqdm</span><span class="p">(</span><span class="n">total</span><span class="o">=</span><span class="n">num_qwen</span><span class="p">,</span> <span class="n">desc</span><span class="o">=</span><span class="s2">&quot;Qwen-based Professional&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">pbar</span><span class="p">:</span>
        <span class="k">while</span> <span class="nb">len</span><span class="p">(</span><span class="n">professional_samples</span><span class="p">)</span> <span class="o">&lt;</span> <span class="n">num_per_category</span><span class="p">:</span>
            <span class="n">q</span> <span class="o">=</span> <span class="n">generate_professional_query_qwen</span><span class="p">()</span>
            <span class="k">if</span> <span class="n">q</span> <span class="ow">and</span> <span class="n">q</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">professional_set</span><span class="p">:</span>
                <span class="n">professional_set</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">q</span><span class="p">)</span>
                <span class="n">professional_samples</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">&quot;query&quot;</span><span class="p">:</span> <span class="n">q</span><span class="p">,</span> <span class="s2">&quot;label&quot;</span><span class="p">:</span> <span class="s2">&quot;企业知识&quot;</span><span class="p">})</span>
                <span class="n">pbar</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
            <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mf">0.5</span><span class="p">)</span>  <span class="c1"># 避免 API 限流</span>
    <span class="n">save_dataset</span><span class="p">(</span><span class="n">professional_samples</span><span class="p">,</span> <span class="s2">&quot;professional_3000.json&quot;</span><span class="p">,</span> <span class="s2">&quot;企业知识（规则+Qwen）&quot;</span><span class="p">)</span>

    <span class="c1"># 合并并混洗</span>
    <span class="n">dataset</span> <span class="o">=</span> <span class="n">generic_samples</span> <span class="o">+</span> <span class="n">professional_samples</span>
    <span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span>
    <span class="n">final_filename</span> <span class="o">=</span> <span class="s2">&quot;training_dataset_hybrid_6000.json&quot;</span>
    <span class="n">save_dataset</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">final_filename</span><span class="p">,</span> <span class="s2">&quot;最终数据集&quot;</span><span class="p">)</span>
    <span class="k">return</span> <span class="n">dataset</span>

<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</span><span class="p">:</span>
    <span class="n">dataset</span> <span class="o">=</span> <span class="n">generate_training_dataset</span><span class="p">(</span><span class="n">total_samples</span><span class="o">=</span><span class="mi">6000</span><span class="p">)</span>
    <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;成功生成 </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span><span class="si">}</span><span class="s2"> 条训练数据，保存在 training_dataset_hybrid_6000.json 文件中。&quot;</span><span class="p">)</span>
    <span class="c1"># 输出前10条作为示例</span>
    <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">dataset</span><span class="p">[:</span><span class="mi">10</span><span class="p">]:</span>
        <span class="nb">print</span><span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">item</span><span class="p">,</span> <span class="n">ensure_ascii</span><span class="o">=</span><span class="kc">False</span><span class="p">))</span>
</code></pre></div>
<h3 id="3">3 实现细节<a class="headerlink" href="#3" title="Permanent link">&para;</a></h3>
<ol>
<li><strong><code>apply_synonym_variation</code></strong>：</li>
<li><strong>作用</strong>：为规则生成查询增加多样性，通过同义词替换（如“什么” -&gt; “啥是”）。</li>
<li><strong>逻辑</strong>：正则表达式匹配词边界，50% 概率替换。</li>
<li><strong><code>generate_generic_query_rule</code> 和 <code>generate_professional_query_rule</code></strong>：</li>
<li><strong>作用</strong>：基于模板生成初始数据。</li>
<li><strong>设计</strong>：覆盖数学计算、代码生成、概念问题和 IT 内部赋能场景。</li>
<li><strong><code>generate_with_qwen</code></strong>：</li>
<li><strong>作用</strong>：封装 Qwen-Plus API 调用，生成自然语言查询。</li>
<li><strong>参数</strong>：<code>temperature=0.9</code> 确保多样性，<code>timeout=10</code> 防止卡顿。</li>
<li><strong><code>generate_generic_query_qwen</code> 和 <code>generate_professional_query_qwen</code></strong>：</li>
<li><strong>作用</strong>：通过精心设计的 Prompt 指导 Qwen-Plus 生成符合类别的查询。</li>
<li><strong>逻辑</strong>：提供示例，输出简洁的查询文本。</li>
<li><strong><code>save_dataset</code></strong>：</li>
<li><strong>作用</strong>：统一保存数据集，显示阶段名称和数据量。</li>
<li><strong>实现</strong>：支持 JSON 格式，保存中间和最终结果。</li>
<li><strong><code>generate_training_dataset</code></strong>：</li>
<li><strong>作用</strong>：整合规则和大模型生成流程。</li>
<li><strong>流程</strong>：<ul>
<li>规则生成 1500 条“通用知识”，保存。</li>
<li>规则生成 1500 条“企业知识”，保存。</li>
<li>Qwen-Plus 生成 1500 条“通用知识”，累计 3000 条保存。</li>
<li>Qwen-Plus 生成 1500 条“企业知识”，累计 3000 条保存。</li>
<li>合并混洗 6000 条，保存最终数据集。</li>
</ul>
</li>
<li><strong>进度条</strong>：<code>tqdm</code> 实时显示每个阶段的生成进度。</li>
</ol>
<h3 id="4">4 说明<a class="headerlink" href="#4" title="Permanent link">&para;</a></h3>
<ul>
<li><strong>混合生成</strong>：规则生成高效可控，Qwen-Plus 生成自然真实。</li>
<li><strong>分阶段保存</strong>：每 1500 条保存一次，支持断点恢复。</li>
<li><strong>进度监控</strong>：<code>tqdm</code> 提供直观反馈，优化用户体验。</li>
</ul>
<h3 id="5">5 执行示例<a class="headerlink" href="#5" title="Permanent link">&para;</a></h3>
<p>运行脚本时，输出类似：
<div class="highlight"><pre><span></span><code>生成规则通用知识数据...
Rule-based Generic: 100%|██████████| 1500/1500 [00:02&lt;00:00, 750it/s]
规则通用知识：已保存 1500 条数据到 rule_generic_1500.json
生成规则企业知识数据...
Rule-based Professional: 100%|██████████| 1500/1500 [00:02&lt;00:00, 700it/s]
规则企业知识：已保存 1500 条数据到 rule_professional_1500.json
生成Qwen-Plus通用知识数据...
Qwen-based Generic: 100%|██████████| 1500/1500 [05:00&lt;00:00, 5it/s]
通用知识（规则+Qwen）：已保存 3000 条数据到 generic_3000.json
生成Qwen-Plus企业知识数据...
Qwen-based Professional: 100%|██████████| 1500/1500 [05:05&lt;00:00, 4.9it/s]
企业知识（规则+Qwen）：已保存 3000 条数据到 professional_3000.json
最终数据集：已保存 6000 条数据到 training_dataset_hybrid_6000.json
成功生成 6000 条训练数据，保存在 training_dataset_hybrid_6000.json 文件中。
</code></pre></div></p>
<hr />
<h2 id="_3">二、数据集生成流程<a class="headerlink" href="#_3" title="Permanent link">&para;</a></h2>
<h3 id="1_1">1 生成流程<a class="headerlink" href="#1_1" title="Permanent link">&para;</a></h3>
<ol>
<li><strong>规则生成（3000 条）</strong>：</li>
<li>生成 1500 条“通用知识”数据，保存为 <code>rule_generic_1500.json</code>。</li>
<li>生成 1500 条“企业知识”数据，保存为 <code>rule_professional_1500.json</code>.</li>
<li>使用模板和同义词替换，确保多样性。</li>
<li><strong>Qwen-Plus 生成（3000 条）</strong>：</li>
<li>生成 1500 条“通用知识”数据，累计 3000 条保存为 <code>generic_3000.json</code>。</li>
<li>生成 1500 条“企业知识”数据，累计 3000 条保存为 <code>professional_3000.json</code>.</li>
<li>通过 Prompt 控制生成质量。</li>
<li><strong>数据整合</strong>：</li>
<li>合并 6000 条数据，随机混洗。</li>
<li>保存为 <code>training_dataset_hybrid_6000.json</code>.</li>
</ol>
<h3 id="2_1">2 代码示例（使用数据集）<a class="headerlink" href="#2_1" title="Permanent link">&para;</a></h3>
<div class="highlight"><pre><span></span><code><span class="c1"># core/query_classifier.py</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">sklearn.feature_extraction.text</span><span class="w"> </span><span class="kn">import</span> <span class="n">TfidfVectorizer</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">sklearn.naive_bayes</span><span class="w"> </span><span class="kn">import</span> <span class="n">MultinomialNB</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">sklearn.pipeline</span><span class="w"> </span><span class="kn">import</span> <span class="n">Pipeline</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">joblib</span>

<span class="k">class</span><span class="w"> </span><span class="nc">QueryClassifier</span><span class="p">:</span>
    <span class="k">def</span><span class="w"> </span><span class="nf">train_model</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
        <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">&quot;training_dataset_hybrid_6000.json&quot;</span><span class="p">,</span> <span class="s2">&quot;r&quot;</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s2">&quot;utf-8&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
            <span class="n">data</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
        <span class="n">texts</span> <span class="o">=</span> <span class="p">[</span><span class="n">item</span><span class="p">[</span><span class="s2">&quot;query&quot;</span><span class="p">]</span> <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">data</span><span class="p">]</span>
        <span class="n">labels</span> <span class="o">=</span> <span class="p">[</span><span class="n">item</span><span class="p">[</span><span class="s2">&quot;label&quot;</span><span class="p">]</span> <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">data</span><span class="p">]</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">Pipeline</span><span class="p">([</span>
            <span class="p">(</span><span class="s2">&quot;tfidf&quot;</span><span class="p">,</span> <span class="n">TfidfVectorizer</span><span class="p">()),</span>
            <span class="p">(</span><span class="s2">&quot;classifier&quot;</span><span class="p">,</span> <span class="n">MultinomialNB</span><span class="p">()),</span>
        <span class="p">])</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">texts</span><span class="p">,</span> <span class="n">labels</span><span class="p">)</span>
        <span class="n">joblib</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">,</span> <span class="s2">&quot;query_classifier_model.pkl&quot;</span><span class="p">)</span>
        <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;模型训练完成并保存&quot;</span><span class="p">)</span>
</code></pre></div>
<hr />
<h2 id="_4">三、数据集特点与优化<a class="headerlink" href="#_4" title="Permanent link">&para;</a></h2>
<h3 id="1_2">1 数据集特点<a class="headerlink" href="#1_2" title="Permanent link">&para;</a></h3>
<ul>
<li><strong>总数</strong>：6000 条（“通用知识” 3000 条，“企业知识” 3000 条）。</li>
<li><strong>来源</strong>：规则生成 50%（3000 条），Qwen-Plus 生成 50%（3000 条）。</li>
<li><strong>多样性</strong>：</li>
<li>规则生成：模板和同义词替换覆盖多种场景。</li>
<li>Qwen-Plus 生成：自然语言查询贴近真实用户输入。</li>
<li><strong>保存机制</strong>：每 1500 条保存，支持断点续传。</li>
<li><strong>可视化</strong>：<code>tqdm</code> 进度条提供实时反馈。</li>
</ul>
<h3 id="2_2">2 优化效果<a class="headerlink" href="#2_2" title="Permanent link">&para;</a></h3>
<ul>
<li><strong>高效性</strong>：简化生成流程，规则生成瞬时完成。</li>
<li><strong>可靠性</strong>：分阶段保存确保数据安全。</li>
<li><strong>分类性能</strong>：均衡数据集提升 <code>QueryClassifier</code> 准确性。</li>
<li><strong>用户体验</strong>：进度条和保存日志增强交互性。</li>
</ul>
<hr />
<h2 id="_5">章节小结<a class="headerlink" href="#_5" title="Permanent link">&para;</a></h2>
<p>本章节详细介绍了优化后的 <code>generate_query_dataset_hybrid.py</code>：
- <strong>功能</strong>：混合生成 6000 条数据，规则和 Qwen-Plus 各占一半。
- <strong>实现</strong>：通过模板生成 3000 条，Qwen-Plus 生成 3000 条，每 1500 条保存，进度条监控。
- <strong>作用</strong>：为 <code>QueryClassifier</code> 提供高质量数据，优化 EnterpriseKB-RAG 系统分类能力。</p>
<p>学习者掌握了高效的数据生成和保存方法，能够为 RAG 系统提供可靠支持。</p>


              </article>
            </div>
          
          
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
        </div>
        
      </main>
      
        <footer class="md-footer">
  
  <div class="md-footer-meta md-typeset">
    <div class="md-footer-meta__inner md-grid">
      <div class="md-copyright">
  
    <div class="md-copyright__highlight">
      © EnterpriseKB-RAG 2026. Internal knowledge base demo site.
    </div>
  
  
    Made with
    <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
      Material for MkDocs
    </a>
  
</div>
      
    </div>
  </div>
</footer>
      
    </div>
    <div class="md-dialog" data-md-component="dialog">
      <div class="md-dialog__inner md-typeset"></div>
    </div>
    
    
      <script id="__config" type="application/json">{"base": "..", "features": [], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "\u5df2\u590d\u5236", "clipboard.copy": "\u590d\u5236", "search.result.more.one": "\u5728\u8be5\u9875\u4e0a\u8fd8\u6709 1 \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.more.other": "\u5728\u8be5\u9875\u4e0a\u8fd8\u6709 # \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.none": "\u6ca1\u6709\u627e\u5230\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.one": "\u627e\u5230 1 \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.other": "# \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.placeholder": "\u952e\u5165\u4ee5\u5f00\u59cb\u641c\u7d22", "search.result.term.missing": "\u7f3a\u5c11", "select.version": "\u9009\u62e9\u5f53\u524d\u7248\u672c"}, "version": null}</script>
    
    
      <script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
      
        <script src="../javascripts/extra.js"></script>
      
        <script src="../javascripts/mathjax.js"></script>
      
        <!--        <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script>-->
      
        <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
      
    
  </body>
</html>