zengli
/
coding-agent


			
							12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414
							<!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="4.3%20%E6%96%87%E6%A1%A3%E5%A4%84%E7%90%86%E6%A8%A1%E5%9D%97.html">
      
      
        <link rel="next" href="4.5%20BERT%E5%9F%BA%E7%A1%80%E4%B8%8E%E4%BB%BB%E5%8A%A1%E5%BE%AE%E8%B0%83.html">
      
      
      <link rel="icon" href="../img/AI.jpg">
      <meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.21">
    
    
        <title>4.4 向量存储 - 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&amp;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"></path></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">
            
              4.4 向量存储
            
          </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"></path></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"></path></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"></path></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"></path></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 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">
    4.4 向量存储
    
  </span>
  

          <span class="md-nav__icon md-icon"></span>
        </label>
      
      <a href="4.4%20%E5%90%91%E9%87%8F%E5%AD%98%E5%82%A8.html" class="md-nav__link md-nav__link--active">
        
  
  <span class="md-ellipsis">
    4.4 向量存储
    
  </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、模块功能概述
    </span>
  </a>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_3" class="md-nav__link">
    <span class="md-ellipsis">
      二、初始化方法
    </span>
  </a>
  
    <nav class="md-nav" aria-label="二、初始化方法">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </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>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_4" class="md-nav__link">
    <span class="md-ellipsis">
      三、创建或加载集合
    </span>
  </a>
  
    <nav class="md-nav" aria-label="三、创建或加载集合">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_1" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </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
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_1" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4_1" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_5" class="md-nav__link">
    <span class="md-ellipsis">
      四、添加文档
    </span>
  </a>
  
    <nav class="md-nav" aria-label="四、添加文档">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_2" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_2" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_2" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4_2" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_6" class="md-nav__link">
    <span class="md-ellipsis">
      五、混合检索与重排序
    </span>
  </a>
  
    <nav class="md-nav" aria-label="五、混合检索与重排序">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_3" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_3" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_3" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4_3" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_7" class="md-nav__link">
    <span class="md-ellipsis">
      六、获取唯一父文档
    </span>
  </a>
  
    <nav class="md-nav" aria-label="六、获取唯一父文档">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_4" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_4" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_4" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4_4" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_8" class="md-nav__link">
    <span class="md-ellipsis">
      七、从查询结果创建文档
    </span>
  </a>
  
    <nav class="md-nav" aria-label="七、从查询结果创建文档">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_5" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_5" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_5" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_9" class="md-nav__link">
    <span class="md-ellipsis">
      本章小结
    </span>
  </a>
  
</li>
      
    </ul>
  
</nav>
      
    </li>
  

    <li class="md-nav__item"><a href="4.5%20BERT%E5%9F%BA%E7%A1%80%E4%B8%8E%E4%BB%BB%E5%8A%A1%E5%BE%AE%E8%B0%83.html" class="md-nav__link"><span class="md-ellipsis">4.5 BERT基础与任务微调</span></a></li><li class="md-nav__item">
      <a href="4.6%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">
    4.6 prompts设计与query意图识别
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.7%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">
    4.7 检索策略与RAG系统设计
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.8%20RAG%E7%B3%BB%E7%BB%9F%E8%BF%90%E8%A1%8C.html" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    4.8 RAG系统运行
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.9%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">
    4.9 文档解析工具(扩展资料)
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="4.10%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">
    4.10 RAG中的Query改写(扩展资料)
    
  </span>
  

      </a>
    </li>
  

    <li class="md-nav__item">
      <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">
        
  
  <span class="md-ellipsis">
    数据集生成与优化(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_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、模块功能概述
    </span>
  </a>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_3" class="md-nav__link">
    <span class="md-ellipsis">
      二、初始化方法
    </span>
  </a>
  
    <nav class="md-nav" aria-label="二、初始化方法">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </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>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_4" class="md-nav__link">
    <span class="md-ellipsis">
      三、创建或加载集合
    </span>
  </a>
  
    <nav class="md-nav" aria-label="三、创建或加载集合">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_1" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </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
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_1" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4_1" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_5" class="md-nav__link">
    <span class="md-ellipsis">
      四、添加文档
    </span>
  </a>
  
    <nav class="md-nav" aria-label="四、添加文档">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_2" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_2" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_2" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4_2" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_6" class="md-nav__link">
    <span class="md-ellipsis">
      五、混合检索与重排序
    </span>
  </a>
  
    <nav class="md-nav" aria-label="五、混合检索与重排序">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_3" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_3" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_3" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4_3" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_7" class="md-nav__link">
    <span class="md-ellipsis">
      六、获取唯一父文档
    </span>
  </a>
  
    <nav class="md-nav" aria-label="六、获取唯一父文档">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_4" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_4" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_4" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4_4" class="md-nav__link">
    <span class="md-ellipsis">
      4 说明
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_8" class="md-nav__link">
    <span class="md-ellipsis">
      七、从查询结果创建文档
    </span>
  </a>
  
    <nav class="md-nav" aria-label="七、从查询结果创建文档">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1_5" class="md-nav__link">
    <span class="md-ellipsis">
      1 功能
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2_5" class="md-nav__link">
    <span class="md-ellipsis">
      2 代码示例
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3_5" class="md-nav__link">
    <span class="md-ellipsis">
      3 实现步骤
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
        <li class="md-nav__item">
  <a href="#_9" class="md-nav__link">
    <span class="md-ellipsis">
      本章小结
    </span>
  </a>
  
</li>
      
    </ul>
  
</nav>
                  </div>
                </div>
              </div>
            
          
            <div class="md-content" data-md-component="content">
              <article class="md-content__inner md-typeset">
                
                  
  <h1>4.4 向量存储</h1>

<div class="admonition note" data-bert-bridge="true"><p class="admonition-title">学习衔接</p><p>本节会调用重排序模型。若还不清楚它为什么要把“问题＋候选文档”一起输入，以及分数从哪里来，可以在下一节 4.5 学习 BERT 与交叉编码原理，再回看这里的 pairs、predict 和排序过程。 <a href="4.5%20BERT%E5%9F%BA%E7%A1%80%E4%B8%8E%E4%BB%BB%E5%8A%A1%E5%BE%AE%E8%B0%83.html#reranking">阅读 4.5 对应内容</a></p></div><h3 id="_1">学习目标<a class="headerlink" href="#_1" title="Permanent link">¶</a></h3>
<ul>
<li>1.理解向量存储在RAG系统中的功能和重要性。</li>
<li>2.学会创建和管理向量数据库。</li>
<li>3.掌握如何将文本转化为向量并存入数据库。</li>
<li>4.理解混合检索与重排序的实现原理。</li>
</ul>
<h3 id="_2">一、模块功能概述<a class="headerlink" href="#_2" title="Permanent link">¶</a></h3>
<p><code>vector_store.py</code>是企业知识库RAG系统的核心模块之一，封装了与Milvus向量数据库的交互逻辑。它负责将文档转化为向量存储到数据库中，并提供高效的混合检索功能。通过结合BGE-M3嵌入模型和重排序机制，该模块确保系统能够快速检索到与用户查询最相关的文档。</p>
<p><code>VectorStore</code>类提供了以下主要功能：</p>
<ul>
<li><strong>初始化与集合管理</strong>：创建或加载Milvus向量数据库集合。</li>
<li><strong>文档向量化与存储</strong>：将分块后的文档转换为向量并存储。</li>
<li><strong>混合检索与重排序</strong>：结合稠密和稀疏向量进行检索，并通过重排序优化结果。</li>
</ul>
<p>以下将逐一讲解每个方法的实现细节。</p>
<p>导入必备工具包：</p>
<div class="highlight"><pre><span></span><code><span class="c1"># 导入 BGE-M3 嵌入函数，用于生成文档和查询的向量表示</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">milvus_model.hybrid</span><span class="w"> </span><span class="kn">import</span> <span class="n">BGEM3EmbeddingFunction</span>
<span class="c1"># 导入 Milvus 相关类，用于操作向量数据库</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pymilvus</span><span class="w"> </span><span class="kn">import</span> <span class="n">MilvusClient</span><span class="p">,</span> <span class="n">DataType</span><span class="p">,</span> <span class="n">AnnSearchRequest</span><span class="p">,</span> <span class="n">WeightedRanker</span>
<span class="c1"># 导入 Document 类，用于创建文档对象</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">langchain_core.documents</span><span class="w"> </span><span class="kn">import</span> <span class="n">Document</span>
<span class="c1"># 导入 CrossEncoder，用于重排序和 NLI 判断</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">sentence_transformers</span><span class="w"> </span><span class="kn">import</span> <span class="n">CrossEncoder</span>
<span class="c1"># 导入 hashlib 模块，用于生成唯一 ID 的哈希值</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">hashlib</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">base.config</span><span class="w"> </span><span class="kn">import</span> <span class="n">config</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">base.logger</span><span class="w"> </span><span class="kn">import</span> <span class="n">logger</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
</code></pre></div>
<hr>
<h3 id="_3">二、初始化方法<a class="headerlink" href="#_3" title="Permanent link">¶</a></h3>
<h4 id="1">1 功能<a class="headerlink" href="#1" title="Permanent link">¶</a></h4>
<p><code>__init__</code>方法初始化<code>VectorStore</code>类的实例，设置基本参数并调用集合创建或加载方法。</p>
<h4 id="2">2 代码示例<a class="headerlink" href="#2" title="Permanent link">¶</a></h4>
<div class="highlight"><pre><span></span><code><span class="c1"># core/vector_store.py</span>
<span class="c1"># 定义 VectorStore 类，封装向量存储和检索功能</span>

<span class="n">local_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="vm">__file__</span><span class="p">))</span>
<span class="n">rag_qa_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">local_path</span><span class="p">))</span>
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">rag_qa_path</span><span class="p">)</span>
<span class="n">project_root</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">rag_qa_path</span><span class="p">)</span>
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">project_root</span><span class="p">)</span>


<span class="k">class</span><span class="w"> </span><span class="nc">VectorStore</span><span class="p">:</span>
    <span class="c1"># 初始化方法，设置向量存储的基本参数</span>
    <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
                 <span class="n">collection_name</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">MILVUS_COLLECTION_NAME</span><span class="p">,</span>
                 <span class="n">host</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">MILVUS_HOST</span><span class="p">,</span>
                 <span class="n">port</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">MILVUS_PORT</span><span class="p">,</span>
                 <span class="n">database</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">MILVUS_DATABASE_NAME</span><span class="p">):</span>
        <span class="c1"># 设置 Milvus 集合名称</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">collection_name</span> <span class="o">=</span> <span class="n">collection_name</span>
        <span class="c1"># 设置 Milvus 主机地址</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">host</span> <span class="o">=</span> <span class="n">host</span>
        <span class="c1"># 设置 Milvus 端口号</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">port</span> <span class="o">=</span> <span class="n">port</span>
        <span class="c1"># 设置 Milvus 数据库名称</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">database</span> <span class="o">=</span> <span class="n">database</span>
        <span class="c1"># 设置日志记录器</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
        <span class="n">rerank_model_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">MODELS_DIR</span><span class="p">,</span> <span class="s1">'bge-reranker-large'</span><span class="p">)</span>
        <span class="c1"># 初始化 BGE-Reranker 模型，用于重排序检索结果</span>
        <span class="c1"># TODO device代表设备： mps:m1系列的mac/ cpu: cpu / cuda: nvidia的gpu。和操作系统无关</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">reranker</span> <span class="o">=</span> <span class="n">CrossEncoder</span><span class="p">(</span><span class="n">rerank_model_path</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s1">'cpu'</span><span class="p">)</span>
        <span class="c1"># 初始化 BGE-M3 嵌入函数，使用 CPU 设备，不启用 FP16</span>
        <span class="n">bge_m3_model_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">MODELS_DIR</span><span class="p">,</span> <span class="s1">'bge-m3'</span><span class="p">)</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">embedding_function</span> <span class="o">=</span> <span class="n">BGEM3EmbeddingFunction</span><span class="p">(</span>
            <span class="n">model_name_or_path</span><span class="o">=</span><span class="n">bge_m3_model_path</span>
            <span class="p">,</span> <span class="n">use_f16</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
             <span class="n">device</span><span class="o">=</span><span class="s1">'cpu'</span>
        <span class="p">)</span>
        <span class="c1"># 获取稠密向量的维度</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">dense_dim</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">embedding_function</span><span class="o">.</span><span class="n">dim</span><span class="p">[</span><span class="s2">"dense"</span><span class="p">]</span>
        <span class="c1"># 初始化 Milvus 客户端，连接到指定主机和数据库</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="n">MilvusClient</span><span class="p">(</span><span class="n">uri</span><span class="o">=</span><span class="sa">f</span><span class="s2">"http://</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">host</span><span class="si">}</span><span class="s2">:</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">db_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">database</span><span class="p">)</span>
        <span class="c1"># 调用方法创建或加载 Milvus 集合</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">_create_or_load_collection</span><span class="p">()</span>
</code></pre></div>
<h4 id="3">3 实现步骤<a class="headerlink" href="#3" title="Permanent link">¶</a></h4>
<ol>
<li><strong>参数设置</strong>：</li>
<li>使用<code>Config</code>中的默认值初始化集合名称、主机、端口和数据库名称。</li>
<li><strong>模型初始化</strong>：</li>
<li><code>reranker</code>：加载BGE-Reranker模型，用于后续重排序。</li>
<li><code>embedding_function</code>：初始化BGE-M3嵌入模型，禁用FP16，使用CPU运行。</li>
<li><code>dense_dim</code>：获取稠密向量的维度。</li>
<li><strong>客户端连接</strong>：</li>
<li>创建<code>MilvusClient</code>实例，连接到指定主机和数据库。</li>
<li><strong>集合管理</strong>：</li>
<li>调用<code>_create_or_load_collection</code>方法，确保集合可用。</li>
</ol>
<h4 id="4">4 说明<a class="headerlink" href="#4" title="Permanent link">¶</a></h4>
<ul>
<li><strong>BGE-M3模型</strong>：提供稠密和稀疏向量生成能力。</li>
<li><strong>灵活性</strong>：通过参数支持自定义配置。</li>
</ul>
<hr>
<h3 id="_4">三、创建或加载集合<a class="headerlink" href="#_4" title="Permanent link">¶</a></h3>
<h4 id="1_1">1 功能<a class="headerlink" href="#1_1" title="Permanent link">¶</a></h4>
<p><code>_create_or_load_collection</code>方法检查并创建或加载Milvus集合，定义字段结构和索引参数。</p>
<h4 id="2_1">2 代码示例<a class="headerlink" href="#2_1" title="Permanent link">¶</a></h4>
<div class="highlight"><pre><span></span><code><span class="c1"># 定义私有方法，创建或加载 Milvus 集合</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_create_or_load_collection</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
    <span class="c1"># 检查指定集合是否已存在</span>
    <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">has_collection</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">collection_name</span><span class="p">):</span>
        <span class="c1"># 创建集合 Schema，禁用自动 ID，启用动态字段</span>
        <span class="n">schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">create_schema</span><span class="p">(</span><span class="n">auto_id</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">enable_dynamic_field</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
        <span class="c1"># 添加 ID 字段，作为主键，VARCHAR 类型，最大长度 100</span>
        <span class="n">schema</span><span class="o">.</span><span class="n">add_field</span><span class="p">(</span><span class="n">field_name</span><span class="o">=</span><span class="s2">"id"</span><span class="p">,</span> <span class="n">datatype</span><span class="o">=</span><span class="n">DataType</span><span class="o">.</span><span class="n">VARCHAR</span><span class="p">,</span> <span class="n">is_primary</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">max_length</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span>
        <span class="c1"># 添加文本字段，VARCHAR 类型，最大长度 65535</span>
        <span class="n">schema</span><span class="o">.</span><span class="n">add_field</span><span class="p">(</span><span class="n">field_name</span><span class="o">=</span><span class="s2">"text"</span><span class="p">,</span> <span class="n">datatype</span><span class="o">=</span><span class="n">DataType</span><span class="o">.</span><span class="n">VARCHAR</span><span class="p">,</span> <span class="n">max_length</span><span class="o">=</span><span class="mi">65535</span><span class="p">)</span>
        <span class="c1"># 添加稠密向量字段，FLOAT_VECTOR 类型，维度由嵌入函数指定</span>
        <span class="n">schema</span><span class="o">.</span><span class="n">add_field</span><span class="p">(</span><span class="n">field_name</span><span class="o">=</span><span class="s2">"dense_vector"</span><span class="p">,</span> <span class="n">datatype</span><span class="o">=</span><span class="n">DataType</span><span class="o">.</span><span class="n">FLOAT_VECTOR</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dense_dim</span><span class="p">)</span>
        <span class="c1"># 添加稀疏向量字段，SPARSE_FLOAT_VECTOR 类型</span>
        <span class="n">schema</span><span class="o">.</span><span class="n">add_field</span><span class="p">(</span><span class="n">field_name</span><span class="o">=</span><span class="s2">"sparse_vector"</span><span class="p">,</span> <span class="n">datatype</span><span class="o">=</span><span class="n">DataType</span><span class="o">.</span><span class="n">SPARSE_FLOAT_VECTOR</span><span class="p">)</span>
        <span class="c1"># 添加父块 ID 字段，VARCHAR 类型，最大长度 100</span>
        <span class="n">schema</span><span class="o">.</span><span class="n">add_field</span><span class="p">(</span><span class="n">field_name</span><span class="o">=</span><span class="s2">"parent_id"</span><span class="p">,</span> <span class="n">datatype</span><span class="o">=</span><span class="n">DataType</span><span class="o">.</span><span class="n">VARCHAR</span><span class="p">,</span> <span class="n">max_length</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span>
        <span class="c1"># 添加父块内容字段，VARCHAR 类型，最大长度 65535</span>
        <span class="n">schema</span><span class="o">.</span><span class="n">add_field</span><span class="p">(</span><span class="n">field_name</span><span class="o">=</span><span class="s2">"parent_content"</span><span class="p">,</span> <span class="n">datatype</span><span class="o">=</span><span class="n">DataType</span><span class="o">.</span><span class="n">VARCHAR</span><span class="p">,</span> <span class="n">max_length</span><span class="o">=</span><span class="mi">65535</span><span class="p">)</span>
        <span class="c1"># 添加知识域字段，VARCHAR 类型，最大长度 50</span>
        <span class="n">schema</span><span class="o">.</span><span class="n">add_field</span><span class="p">(</span><span class="n">field_name</span><span class="o">=</span><span class="s2">"source"</span><span class="p">,</span> <span class="n">datatype</span><span class="o">=</span><span class="n">DataType</span><span class="o">.</span><span class="n">VARCHAR</span><span class="p">,</span> <span class="n">max_length</span><span class="o">=</span><span class="mi">50</span><span class="p">)</span>
        <span class="c1"># 添加时间戳字段，VARCHAR 类型，最大长度 50</span>
        <span class="n">schema</span><span class="o">.</span><span class="n">add_field</span><span class="p">(</span><span class="n">field_name</span><span class="o">=</span><span class="s2">"timestamp"</span><span class="p">,</span> <span class="n">datatype</span><span class="o">=</span><span class="n">DataType</span><span class="o">.</span><span class="n">VARCHAR</span><span class="p">,</span> <span class="n">max_length</span><span class="o">=</span><span class="mi">50</span><span class="p">)</span>

        <span class="c1"># 创建索引参数对象</span>
        <span class="n">index_params</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">prepare_index_params</span><span class="p">()</span>
        <span class="c1"># 为稠密向量字段添加 IVF_FLAT 索引，度量类型为内积 (IP)</span>
        <span class="n">index_params</span><span class="o">.</span><span class="n">add_index</span><span class="p">(</span>
            <span class="n">field_name</span><span class="o">=</span><span class="s2">"dense_vector"</span><span class="p">,</span>
            <span class="n">index_name</span><span class="o">=</span><span class="s2">"dense_index"</span><span class="p">,</span>
            <span class="n">index_type</span><span class="o">=</span><span class="s2">"IVF_FLAT"</span><span class="p">,</span>
            <span class="n">metric_type</span><span class="o">=</span><span class="s2">"IP"</span><span class="p">,</span>
            <span class="n">params</span><span class="o">=</span><span class="p">{</span><span class="s2">"nlist"</span><span class="p">:</span> <span class="mi">128</span><span class="p">}</span>
        <span class="p">)</span>
        <span class="c1"># 为稀疏向量字段添加 SPARSE_INVERTED_INDEX 索引，度量类型为内积 (IP)</span>
        <span class="n">index_params</span><span class="o">.</span><span class="n">add_index</span><span class="p">(</span>
            <span class="n">field_name</span><span class="o">=</span><span class="s2">"sparse_vector"</span><span class="p">,</span>
            <span class="n">index_name</span><span class="o">=</span><span class="s2">"sparse_index"</span><span class="p">,</span>
            <span class="n">index_type</span><span class="o">=</span><span class="s2">"SPARSE_INVERTED_INDEX"</span><span class="p">,</span>
            <span class="n">metric_type</span><span class="o">=</span><span class="s2">"IP"</span><span class="p">,</span>
            <span class="n">params</span><span class="o">=</span><span class="p">{</span><span class="s2">"drop_ratio_build"</span><span class="p">:</span> <span class="mf">0.2</span><span class="p">}</span>
        <span class="p">)</span>

        <span class="c1"># 创建 Milvus 集合，应用定义的 Schema 和索引参数</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">create_collection</span><span class="p">(</span><span class="n">collection_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">collection_name</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">,</span>
                                     <span class="n">index_params</span><span class="o">=</span><span class="n">index_params</span><span class="p">)</span>
        <span class="c1"># 记录创建集合的日志</span>
        <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">"已创建集合 </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">collection_name</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
    <span class="c1"># 如果集合已存在</span>
    <span class="k">else</span><span class="p">:</span>
        <span class="c1"># 记录加载集合的日志</span>
        <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">"已加载集合 </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">collection_name</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
    <span class="c1"># 将集合加载到内存，确保可立即查询</span>
    <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">load_collection</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">collection_name</span><span class="p">)</span>
</code></pre></div>
<h4 id="3_1">3 实现步骤<a class="headerlink" href="#3_1" title="Permanent link">¶</a></h4>
<ol>
<li><strong>检查集合是否存在</strong>：</li>
<li>使用<code>has_collection</code>判断是否需要创建新集合。</li>
<li><strong>定义Schema</strong>：</li>
<li>设置字段：包括<code>id</code>（主键）、<code>text</code>（原文）、向量字段和元数据字段。</li>
<li>禁用自动ID，启用动态字段。</li>
<li><strong>创建索引</strong>：</li>
<li>稠密向量使用<code>IVF_FLAT</code>索引，稀疏向量使用<code>SPARSE_INVERTED_INDEX</code>。</li>
<li><strong>创建并加载集合</strong>：</li>
<li>调用<code>create_collection</code>创建集合，并加载到内存。</li>
</ol>
<h4 id="4_1">4 说明<a class="headerlink" href="#4_1" title="Permanent link">¶</a></h4>
<ul>
<li><strong>字段设计</strong>：支持多种数据类型和元数据管理。</li>
<li><strong>索引优化</strong>：平衡检索速度和精度。</li>
</ul>
<hr>
<h3 id="_5">四、添加文档<a class="headerlink" href="#_5" title="Permanent link">¶</a></h3>
<h4 id="1_2">1 功能<a class="headerlink" href="#1_2" title="Permanent link">¶</a></h4>
<p><code>add_documents</code>方法将分块后的文档转换为向量并存储到Milvus集合中。</p>
<h4 id="2_2">2 代码示例<a class="headerlink" href="#2_2" title="Permanent link">¶</a></h4>
<div class="highlight"><pre><span></span><code><span class="c1"># 定义方法，向向量存储添加文档</span>
<span class="k">def</span><span class="w"> </span><span class="nf">add_documents</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">documents</span><span class="p">):</span>
    <span class="c1"># 提取所有文档的内容列表</span>
    <span class="n">texts</span> <span class="o">=</span> <span class="p">[</span><span class="n">doc</span><span class="o">.</span><span class="n">page_content</span> <span class="k">for</span> <span class="n">doc</span> <span class="ow">in</span> <span class="n">documents</span><span class="p">]</span>
    <span class="c1"># 使用 BGE-M3 嵌入函数生成文档的嵌入</span>
    <span class="n">embeddings</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">embedding_function</span><span class="p">(</span><span class="n">texts</span><span class="p">)</span>
    <span class="c1"># 初始化空列表，用于存储插入的数据</span>
    <span class="n">data</span> <span class="o">=</span> <span class="p">[]</span>
    <span class="c1"># 遍历每个文档，带上索引 i</span>
    <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">doc</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">documents</span><span class="p">):</span>
        <span class="c1"># 生成文档内容的 MD5 哈希值，作为唯一 ID</span>
        <span class="n">text_hash</span> <span class="o">=</span> <span class="n">hashlib</span><span class="o">.</span><span class="n">md5</span><span class="p">(</span><span class="n">doc</span><span class="o">.</span><span class="n">page_content</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">))</span><span class="o">.</span><span class="n">hexdigest</span><span class="p">()</span>
        <span class="c1"># 初始化稀疏向量字典</span>
        <span class="n">sparse_vector</span> <span class="o">=</span> <span class="p">{}</span>
        <span class="c1"># 获取第 i 行的稀疏向量数据</span>
        <span class="n">row</span> <span class="o">=</span> <span class="n">embeddings</span><span class="p">[</span><span class="s1">'sparse'</span><span class="p">][[</span><span class="n">index</span><span class="p">],:]</span>
        <span class="c1"># 获取稀疏向量的非零值索引</span>
        <span class="n">indices</span> <span class="o">=</span> <span class="n">row</span><span class="o">.</span><span class="n">indices</span>
        <span class="c1"># 获取稀疏向量的非零值</span>
        <span class="n">values</span> <span class="o">=</span> <span class="n">row</span><span class="o">.</span><span class="n">data</span>
        <span class="c1"># 将索引和值配对，填充稀疏向量字典</span>
        <span class="k">for</span> <span class="n">idx</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">indices</span><span class="p">,</span> <span class="n">values</span><span class="p">):</span>
            <span class="n">sparse_vector</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
        <span class="c1"># 创建数据字典，包含所有字段</span>
        <span class="n">data</span><span class="o">.</span><span class="n">append</span><span class="p">({</span>
            <span class="s2">"id"</span><span class="p">:</span> <span class="n">text_hash</span><span class="p">,</span>
            <span class="s2">"text"</span><span class="p">:</span> <span class="n">doc</span><span class="o">.</span><span class="n">page_content</span><span class="p">,</span>
            <span class="s2">"dense_vector"</span><span class="p">:</span> <span class="n">embeddings</span><span class="p">[</span><span class="s2">"dense"</span><span class="p">][</span><span class="n">i</span><span class="p">],</span>
            <span class="s2">"sparse_vector"</span><span class="p">:</span> <span class="n">sparse_vector</span><span class="p">,</span>
            <span class="s2">"parent_id"</span><span class="p">:</span> <span class="n">doc</span><span class="o">.</span><span class="n">metadata</span><span class="p">[</span><span class="s2">"parent_id"</span><span class="p">],</span>
            <span class="s2">"parent_content"</span><span class="p">:</span> <span class="n">doc</span><span class="o">.</span><span class="n">metadata</span><span class="p">[</span><span class="s2">"parent_content"</span><span class="p">],</span>
            <span class="s2">"source"</span><span class="p">:</span> <span class="n">doc</span><span class="o">.</span><span class="n">metadata</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"source"</span><span class="p">,</span> <span class="s2">"unknown"</span><span class="p">),</span>
            <span class="s2">"timestamp"</span><span class="p">:</span> <span class="n">doc</span><span class="o">.</span><span class="n">metadata</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"timestamp"</span><span class="p">,</span> <span class="s2">"unknown"</span><span class="p">)</span>
        <span class="p">})</span>
    <span class="c1"># 检查是否有数据需要插入</span>
    <span class="k">if</span> <span class="n">data</span><span class="p">:</span>
        <span class="c1"># 使用 upsert 操作插入数据，覆盖重复 ID</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">upsert</span><span class="p">(</span><span class="n">collection_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">collection_name</span><span class="p">,</span> <span class="n">data</span><span class="o">=</span><span class="n">data</span><span class="p">)</span>
        <span class="c1"># 记录插入或更新的文档数量日志</span>
        <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">"已插入或更新 </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">)</span><span class="si">}</span><span class="s2"> 个文档"</span><span class="p">)</span>
</code></pre></div>
<h4 id="3_2">3 实现步骤<a class="headerlink" href="#3_2" title="Permanent link">¶</a></h4>
<ol>
<li><strong>提取文本</strong>：</li>
<li>从文档对象中提取文本内容。</li>
<li><strong>生成向量</strong>：</li>
<li>使用BGE-M3模型生成稠密和稀疏向量。</li>
<li><strong>构造数据</strong>：</li>
<li>为每篇文档生成唯一ID（MD5哈希）。</li>
<li>将向量和元数据组织成字典。</li>
<li><strong>存储数据</strong>：</li>
<li>使用<code>upsert</code>操作插入或更新数据。</li>
</ol>
<h4 id="4_2">4 说明<a class="headerlink" href="#4_2" title="Permanent link">¶</a></h4>
<ul>
<li><strong>唯一性</strong>：通过MD5哈希确保ID唯一。</li>
<li><strong>稀疏向量处理</strong>：将稀疏矩阵转换为字典格式。</li>
</ul>
<hr>
<h3 id="_6">五、混合检索与重排序<a class="headerlink" href="#_6" title="Permanent link">¶</a></h3>
<h4 id="1_3">1 功能<a class="headerlink" href="#1_3" title="Permanent link">¶</a></h4>
<p><code>hybrid_search_with_rerank</code>方法实现混合检索并重排序，返回最相关文档。</p>
<h4 id="2_3">2 代码示例<a class="headerlink" href="#2_3" title="Permanent link">¶</a></h4>
<div class="highlight"><pre><span></span><code><span class="c1"># 定义方法，执行混合检索并重排序</span>
<span class="k">def</span><span class="w"> </span><span class="nf">hybrid_search_with_rerank</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">RETRIEVAL_K</span><span class="p">,</span> <span class="n">source_filter</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
    <span class="c1"># 使用 BGE-M3 嵌入函数生成查询的嵌入</span>
    <span class="n">query_embeddings</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">embedding_function</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">query</span><span class="p">)])</span>
    <span class="c1"># 获取查询的稠密向量</span>
    <span class="n">dense_query_vector</span> <span class="o">=</span> <span class="n">query_embeddings</span><span class="p">[</span><span class="s2">"dense"</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
    <span class="c1"># 初始化查询的稀疏向量字典</span>
    <span class="n">sparse_query_vector</span> <span class="o">=</span> <span class="p">{}</span>
    <span class="c1"># 获取查询稀疏向量的第 0 行数据</span>
    <span class="n">row</span> <span class="o">=</span> <span class="n">query_embeddings</span><span class="p">[</span><span class="s2">"sparse"</span><span class="p">][[</span><span class="n">index</span><span class="p">],:]</span>
    <span class="c1"># 获取稀疏向量的非零值索引</span>
    <span class="n">indices</span> <span class="o">=</span> <span class="n">row</span><span class="o">.</span><span class="n">indices</span>
    <span class="c1"># 获取稀疏向量的非零值</span>
    <span class="n">values</span> <span class="o">=</span> <span class="n">row</span><span class="o">.</span><span class="n">data</span>
    <span class="c1"># 将索引和值配对，填充稀疏向量字典</span>
    <span class="k">for</span> <span class="n">idx</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">indices</span><span class="p">,</span> <span class="n">values</span><span class="p">):</span>
        <span class="n">sparse_query_vector</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>

    <span class="c1"># 初始化过滤表达式，默认不过滤</span>
    <span class="n">filter_expr</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"source == '</span><span class="si">{</span><span class="n">source_filter</span><span class="si">}</span><span class="s2">'"</span> <span class="k">if</span> <span class="n">source_filter</span> <span class="k">else</span> <span class="s2">""</span>
    <span class="c1"># 创建稠密向量搜索请求</span>
    <span class="n">dense_request</span> <span class="o">=</span> <span class="n">AnnSearchRequest</span><span class="p">(</span>
        <span class="n">data</span><span class="o">=</span><span class="p">[</span><span class="n">dense_query_vector</span><span class="p">],</span>
        <span class="n">anns_field</span><span class="o">=</span><span class="s2">"dense_vector"</span><span class="p">,</span>
        <span class="n">param</span><span class="o">=</span><span class="p">{</span><span class="s2">"metric_type"</span><span class="p">:</span> <span class="s2">"IP"</span><span class="p">,</span> <span class="s2">"params"</span><span class="p">:</span> <span class="p">{</span><span class="s2">"nprobe"</span><span class="p">:</span> <span class="mi">10</span><span class="p">}},</span>
        <span class="n">limit</span><span class="o">=</span><span class="n">k</span><span class="p">,</span>
        <span class="n">expr</span><span class="o">=</span><span class="n">filter_expr</span>
    <span class="p">)</span>
    <span class="c1"># 创建稀疏向量搜索请求</span>
    <span class="n">sparse_request</span> <span class="o">=</span> <span class="n">AnnSearchRequest</span><span class="p">(</span>
        <span class="n">data</span><span class="o">=</span><span class="p">[</span><span class="n">sparse_query_vector</span><span class="p">],</span>
        <span class="n">anns_field</span><span class="o">=</span><span class="s2">"sparse_vector"</span><span class="p">,</span>
        <span class="n">param</span><span class="o">=</span><span class="p">{</span><span class="s2">"metric_type"</span><span class="p">:</span> <span class="s2">"IP"</span><span class="p">,</span> <span class="s2">"params"</span><span class="p">:</span> <span class="p">{}},</span>
        <span class="n">limit</span><span class="o">=</span><span class="n">k</span><span class="p">,</span>
        <span class="n">expr</span><span class="o">=</span><span class="n">filter_expr</span>
    <span class="p">)</span>

    <span class="c1"># 创建加权排序器，稀疏向量权重 0.7，稠密向量权重 1.0</span>
    <span class="n">ranker</span> <span class="o">=</span> <span class="n">WeightedRanker</span><span class="p">(</span><span class="mf">0.7</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span>
    <span class="c1"># 执行混合搜索，返回 Top-K 结果</span>
    <span class="n">results</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">hybrid_search</span><span class="p">(</span>
        <span class="n">collection_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">collection_name</span><span class="p">,</span>
        <span class="n">reqs</span><span class="o">=</span><span class="p">[</span><span class="n">dense_request</span><span class="p">,</span> <span class="n">sparse_request</span><span class="p">],</span>
        <span class="n">ranker</span><span class="o">=</span><span class="n">ranker</span><span class="p">,</span>
        <span class="n">limit</span><span class="o">=</span><span class="n">k</span><span class="p">,</span>
        <span class="n">output_fields</span><span class="o">=</span><span class="p">[</span><span class="s2">"text"</span><span class="p">,</span> <span class="s2">"parent_id"</span><span class="p">,</span> <span class="s2">"parent_content"</span><span class="p">,</span> <span class="s2">"source"</span><span class="p">,</span> <span class="s2">"timestamp"</span><span class="p">]</span>
    <span class="p">)[</span><span class="mi">0</span><span class="p">]</span>

    <span class="c1"># 将搜索结果转换为 Document 对象列表</span>
    <span class="n">sub_chunks</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_doc_from_hit</span><span class="p">(</span><span class="n">hit</span><span class="p">[</span><span class="s2">"entity"</span><span class="p">])</span> <span class="k">for</span> <span class="n">hit</span> <span class="ow">in</span> <span class="n">results</span><span class="p">]</span>
    <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'sub_chunks--&gt;</span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">sub_chunks</span><span class="p">)</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
    <span class="c1"># 从子块中提取去重的父文档</span>
    <span class="n">parent_docs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_unique_parent_docs</span><span class="p">(</span><span class="n">sub_chunks</span><span class="p">)</span>
    <span class="c1"># 如果只有1个文档，直接返回跳过重排序</span>
    <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">parent_docs</span><span class="p">)</span> <span class="o">&lt;</span> <span class="mi">2</span><span class="p">:</span>
      <span class="k">return</span> <span class="n">parent_docs</span><span class="p">[:</span><span class="n">conf</span><span class="o">.</span><span class="n">CANDIDATE_M</span><span class="p">]</span> 
    <span class="c1"># 如果有父文档，进行重排序</span>
    <span class="k">if</span> <span class="n">parent_docs</span><span class="p">:</span>
        <span class="c1"># 创建查询与文档内容的配对列表</span>
        <span class="n">pairs</span> <span class="o">=</span> <span class="p">[[</span><span class="n">query</span><span class="p">,</span> <span class="n">doc</span><span class="o">.</span><span class="n">page_content</span><span class="p">]</span> <span class="k">for</span> <span class="n">doc</span> <span class="ow">in</span> <span class="n">parent_docs</span><span class="p">]</span>
        <span class="c1"># 使用 BGE-Reranker 计算每个配对的得分</span>
        <span class="n">scores</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">reranker</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">pairs</span><span class="p">)</span>
        <span class="c1"># 根据得分从高到低排序文档</span>
        <span class="n">ranked_parent_docs</span> <span class="o">=</span> <span class="p">[</span><span class="n">doc</span> <span class="k">for</span> <span class="n">_</span><span class="p">,</span> <span class="n">doc</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="n">scores</span><span class="p">,</span> <span class="n">parent_docs</span><span class="p">),</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)]</span>
    <span class="c1"># 如果没有父文档，返回空列表</span>
    <span class="k">else</span><span class="p">:</span>
        <span class="n">ranked_parent_docs</span> <span class="o">=</span> <span class="p">[]</span>

    <span class="c1"># 返回前 k 个重排序后的文档</span>
    <span class="k">return</span> <span class="n">ranked_parent_docs</span><span class="p">[:</span><span class="n">conf</span><span class="o">.</span><span class="n">CANDIDATE_M</span><span class="p">]</span>
</code></pre></div>
<h4 id="3_3">3 实现步骤<a class="headerlink" href="#3_3" title="Permanent link">¶</a></h4>
<ol>
<li><strong>生成查询向量</strong>：</li>
<li>使用BGE-M3生成稠密和稀疏向量。</li>
<li><strong>构造检索请求</strong>：</li>
<li>为稠密和稀疏向量分别创建<code>AnnSearchRequest</code>。</li>
<li><strong>混合检索</strong>：</li>
<li>使用<code>WeightedRanker</code>融合结果。</li>
<li><strong>重排序</strong>：</li>
<li>使用<code>CrossEncoder</code>重新排序父文档。</li>
</ol>
<h4 id="4_3">4 说明<a class="headerlink" href="#4_3" title="Permanent link">¶</a></h4>
<ul>
<li><strong>混合检索</strong>：提升覆盖率和准确性。</li>
<li><strong>重排序</strong>：确保最相关文档优先。</li>
</ul>
<hr>
<h3 id="_7">六、获取唯一父文档<a class="headerlink" href="#_7" title="Permanent link">¶</a></h3>
<h4 id="1_4">1 功能<a class="headerlink" href="#1_4" title="Permanent link">¶</a></h4>
<p><code>_get_unique_parent_docs</code>方法从子块中提取去重的父文档。</p>
<h4 id="2_4">2 代码示例<a class="headerlink" href="#2_4" title="Permanent link">¶</a></h4>
<div class="highlight"><pre><span></span><code><span class="c1"># 定义私有方法，从子块中提取去重的父文档</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_get_unique_parent_docs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sub_chunks</span><span class="p">):</span>
    <span class="c1"># 初始化集合，用于存储已处理的父块内容（去重）</span>
    <span class="n">parent_contents</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
    <span class="c1"># 初始化列表，用于存储唯一父文档</span>
    <span class="n">unique_docs</span> <span class="o">=</span> <span class="p">[]</span>
    <span class="c1"># 遍历所有子块</span>
    <span class="k">for</span> <span class="n">chunk</span> <span class="ow">in</span> <span class="n">sub_chunks</span><span class="p">:</span>
        <span class="c1"># 获取子块的父块内容，默认为子块内容</span>
        <span class="n">parent_content</span> <span class="o">=</span> <span class="n">chunk</span><span class="o">.</span><span class="n">metadata</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"parent_content"</span><span class="p">,</span> <span class="n">chunk</span><span class="o">.</span><span class="n">page_content</span><span class="p">)</span>
        <span class="c1"># 检查父块内容是否非空且未重复</span>
        <span class="k">if</span> <span class="n">parent_content</span> <span class="ow">and</span> <span class="n">parent_content</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">parent_contents</span><span class="p">:</span>
            <span class="c1"># 创建新的 Document 对象，包含父块内容和元数据</span>
            <span class="n">unique_docs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">Document</span><span class="p">(</span><span class="n">page_content</span><span class="o">=</span><span class="n">parent_content</span><span class="p">,</span> <span class="n">metadata</span><span class="o">=</span><span class="n">chunk</span><span class="o">.</span><span class="n">metadata</span><span class="p">))</span>
            <span class="c1"># 将父块内容添加到去重集合</span>
            <span class="n">parent_contents</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">parent_content</span><span class="p">)</span>
    <span class="c1"># 返回去重后的父文档列表</span>
    <span class="k">return</span> <span class="n">unique_docs</span>
</code></pre></div>
<h4 id="3_4">3 实现步骤<a class="headerlink" href="#3_4" title="Permanent link">¶</a></h4>
<ol>
<li><strong>去重</strong>：</li>
<li>使用集合记录已处理的父内容。</li>
<li><strong>构造文档</strong>：</li>
<li>创建包含父内容的<code>Document</code>对象。</li>
</ol>
<h4 id="4_4">4 说明<a class="headerlink" href="#4_4" title="Permanent link">¶</a></h4>
<ul>
<li><strong>去重逻辑</strong>：避免重复父文档。</li>
<li><strong>元数据保留</strong>：保持完整性。</li>
</ul>
<hr>
<h3 id="_8">七、从查询结果创建文档<a class="headerlink" href="#_8" title="Permanent link">¶</a></h3>
<h4 id="1_5">1 功能<a class="headerlink" href="#1_5" title="Permanent link">¶</a></h4>
<p><code>_doc_from_hit</code>方法将Milvus查询结果转换为<code>Document</code>对象。</p>
<h4 id="2_5">2 代码示例<a class="headerlink" href="#2_5" title="Permanent link">¶</a></h4>
<div class="highlight"><pre><span></span><code><span class="c1"># 定义私有方法，从 Milvus 查询结果创建 Document 对象</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_doc_from_hit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hit</span><span class="p">):</span>
    <span class="c1"># 创建并返回 Document 对象，填充内容和元数据</span>
    <span class="k">return</span> <span class="n">Document</span><span class="p">(</span>
        <span class="n">page_content</span><span class="o">=</span><span class="n">hit</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"text"</span><span class="p">),</span>
        <span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
            <span class="s2">"parent_id"</span><span class="p">:</span> <span class="n">hit</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"parent_id"</span><span class="p">),</span>
            <span class="s2">"parent_content"</span><span class="p">:</span> <span class="n">hit</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"parent_content"</span><span class="p">),</span>
            <span class="s2">"source"</span><span class="p">:</span> <span class="n">hit</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"source"</span><span class="p">),</span>
            <span class="s2">"timestamp"</span><span class="p">:</span> <span class="n">hit</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"timestamp"</span><span class="p">)</span>
        <span class="p">}</span>
    <span class="p">)</span>
</code></pre></div>
<h4 id="3_5">3 实现步骤<a class="headerlink" href="#3_5" title="Permanent link">¶</a></h4>
<ol>
<li><strong>提取内容和元数据</strong>：</li>
<li>从查询结果中获取字段。</li>
<li><strong>创建对象</strong>：</li>
<li>构造<code>Document</code>实例。</li>
</ol>
<hr>
<h3 id="_9">本章小结<a class="headerlink" href="#_9" title="Permanent link">¶</a></h3>
<p>本章节全面讲解了<code>vector_store.py</code>模块的每个方法：</p>
<ul>
<li>
<p><strong>初始化</strong>：设置参数和模型，为向量存储做好准备。</p>
</li>
<li>
<p><strong>创建集合</strong>：定义结构和索引，构建高效数据库。</p>
</li>
<li><strong>添加文档</strong>：实现文档向量化与存储。</li>
<li><strong>混合检索</strong>：结合稠密和稀疏向量并重排序，返回最相关结果。</li>
<li><strong>辅助方法</strong>：支持去重和文档转换。</li>
</ul>
<p>学习者通过本章节掌握了向量存储的完整流程，为RAG系统的检索功能奠定了基础。</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>