3.3 基于Mysql数据库实现问答系统.html 117 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682
  1. <!doctype html>
  2. <html lang="zh" class="no-js">
  3. <head>
  4. <meta charset="utf-8">
  5. <meta name="viewport" content="width=device-width,initial-scale=1">
  6. <link rel="prev" href="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">
  7. <link rel="next" href="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">
  8. <link rel="icon" href="../img/AI.jpg">
  9. <meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.21">
  10. <title>3.3 基于Mysql数据库实现问答系统 - 企业知识库RAG智能问答项目V1.0</title>
  11. <link rel="stylesheet" href="../assets/stylesheets/main.2a3383ac.min.css">
  12. <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
  13. <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">
  14. <style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
  15. <link rel="stylesheet" href="../stylesheets/extra.css">
  16. <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>
  17. </head>
  18. <body dir="ltr">
  19. <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
  20. <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
  21. <label class="md-overlay" for="__drawer"></label>
  22. <div data-md-component="skip">
  23. <a href="#_1" class="md-skip">
  24. 跳转至
  25. </a>
  26. </div>
  27. <div data-md-component="announce">
  28. </div>
  29. <header class="md-header md-header--shadow" data-md-component="header">
  30. <nav class="md-header__inner md-grid" aria-label="页眉">
  31. <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">
  32. <img src="../img/AI.jpg" alt="logo">
  33. </a>
  34. <label class="md-header__button md-icon" for="__drawer">
  35. <svg xmlns="http://www.w3.org/2000/svg" viewbox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"></path></svg>
  36. </label>
  37. <div class="md-header__title" data-md-component="header-title">
  38. <div class="md-header__ellipsis">
  39. <div class="md-header__topic">
  40. <span class="md-ellipsis">
  41. 企业知识库RAG智能问答项目V1.0
  42. </span>
  43. </div>
  44. <div class="md-header__topic" data-md-component="header-topic">
  45. <span class="md-ellipsis">
  46. 3.3 基于Mysql数据库实现问答系统
  47. </span>
  48. </div>
  49. </div>
  50. </div>
  51. <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>
  52. <label class="md-header__button md-icon" for="__search">
  53. <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>
  54. </label>
  55. <div class="md-search" data-md-component="search" role="dialog">
  56. <label class="md-search__overlay" for="__search"></label>
  57. <div class="md-search__inner" role="search">
  58. <form class="md-search__form" name="search">
  59. <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>
  60. <label class="md-search__icon md-icon" for="__search">
  61. <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>
  62. <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>
  63. </label>
  64. <nav class="md-search__options" aria-label="查找">
  65. <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">
  66. <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>
  67. </button>
  68. </nav>
  69. </form>
  70. <div class="md-search__output">
  71. <div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
  72. <div class="md-search-result" data-md-component="search-result">
  73. <div class="md-search-result__meta">
  74. 正在初始化搜索引擎
  75. </div>
  76. <ol class="md-search-result__list" role="presentation"></ol>
  77. </div>
  78. </div>
  79. </div>
  80. </div>
  81. </div>
  82. </nav>
  83. </header>
  84. <div class="md-container" data-md-component="container">
  85. <main class="md-main" data-md-component="main">
  86. <div class="md-main__inner md-grid">
  87. <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation">
  88. <div class="md-sidebar__scrollwrap">
  89. <div class="md-sidebar__inner">
  90. <nav class="md-nav md-nav--primary" aria-label="导航栏" data-md-level="0">
  91. <label class="md-nav__title" for="__drawer">
  92. <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">
  93. <img src="../img/AI.jpg" alt="logo">
  94. </a>
  95. 企业知识库RAG智能问答项目V1.0
  96. </label>
  97. <ul class="md-nav__list" data-md-scrollfix>
  98. <li class="md-nav__item">
  99. <a href="../index.html" class="md-nav__link">
  100. <span class="md-ellipsis">
  101. 知识库内容
  102. </span>
  103. </a>
  104. </li>
  105. <li class="md-nav__item md-nav__item--nested">
  106. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2">
  107. <label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
  108. <span class="md-ellipsis">
  109. ① 项目概述
  110. </span>
  111. <span class="md-nav__icon md-icon"></span>
  112. </label>
  113. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
  114. <label class="md-nav__title" for="__nav_2">
  115. <span class="md-nav__icon md-icon"></span>
  116. ① 项目概述
  117. </label>
  118. <ul class="md-nav__list" data-md-scrollfix>
  119. <li class="md-nav__item">
  120. <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">
  121. <span class="md-ellipsis">
  122. 1.1 项目架构
  123. </span>
  124. </a>
  125. </li>
  126. <li class="md-nav__item">
  127. <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">
  128. <span class="md-ellipsis">
  129. 1.2 项目环境(window)
  130. </span>
  131. </a>
  132. </li>
  133. <li class="md-nav__item">
  134. <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">
  135. <span class="md-ellipsis">
  136. 1.3 项目环境(mac)
  137. </span>
  138. </a>
  139. </li>
  140. </ul>
  141. </nav>
  142. </li>
  143. <li class="md-nav__item md-nav__item--nested">
  144. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3">
  145. <label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
  146. <span class="md-ellipsis">
  147. ② 项目工具
  148. </span>
  149. <span class="md-nav__icon md-icon"></span>
  150. </label>
  151. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
  152. <label class="md-nav__title" for="__nav_3">
  153. <span class="md-nav__icon md-icon"></span>
  154. ② 项目工具
  155. </label>
  156. <ul class="md-nav__list" data-md-scrollfix>
  157. <li class="md-nav__item">
  158. <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">
  159. <span class="md-ellipsis">
  160. 2.1 Ollama大模型高效管理工具
  161. </span>
  162. </a>
  163. </li>
  164. <li class="md-nav__item">
  165. <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">
  166. <span class="md-ellipsis">
  167. 2.2 LangChain基础知识.md
  168. </span>
  169. </a>
  170. </li>
  171. <li class="md-nav__item">
  172. <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">
  173. <span class="md-ellipsis">
  174. 2.3 向量索引:HNSW、IVF与IVF_PQ
  175. </span>
  176. </a>
  177. </li>
  178. <li class="md-nav__item">
  179. <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">
  180. <span class="md-ellipsis">
  181. 2.4 Milvus向量数据库
  182. </span>
  183. </a>
  184. </li>
  185. </ul>
  186. </nav>
  187. </li>
  188. <li class="md-nav__item md-nav__item--active md-nav__item--nested">
  189. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" checked>
  190. <label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
  191. <span class="md-ellipsis">
  192. ③ 基于Mysql库的问答系统
  193. </span>
  194. <span class="md-nav__icon md-icon"></span>
  195. </label>
  196. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="true">
  197. <label class="md-nav__title" for="__nav_4">
  198. <span class="md-nav__icon md-icon"></span>
  199. ③ 基于Mysql库的问答系统
  200. </label>
  201. <ul class="md-nav__list" data-md-scrollfix>
  202. <li class="md-nav__item">
  203. <a href="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">
  204. <span class="md-ellipsis">
  205. 3.1 Python日志介绍与应用
  206. </span>
  207. </a>
  208. </li>
  209. <li class="md-nav__item">
  210. <a href="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">
  211. <span class="md-ellipsis">
  212. 3.2 Redis数据库简介与使用
  213. </span>
  214. </a>
  215. </li>
  216. <li class="md-nav__item md-nav__item--active">
  217. <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
  218. <label class="md-nav__link md-nav__link--active" for="__toc">
  219. <span class="md-ellipsis">
  220. 3.3 基于Mysql数据库实现问答系统
  221. </span>
  222. <span class="md-nav__icon md-icon"></span>
  223. </label>
  224. <a href="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 md-nav__link--active">
  225. <span class="md-ellipsis">
  226. 3.3 基于Mysql数据库实现问答系统
  227. </span>
  228. </a>
  229. <nav class="md-nav md-nav--secondary" aria-label="目录">
  230. <label class="md-nav__title" for="__toc">
  231. <span class="md-nav__icon md-icon"></span>
  232. 目录
  233. </label>
  234. <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
  235. <li class="md-nav__item">
  236. <a href="#_1" class="md-nav__link">
  237. <span class="md-ellipsis">
  238. 学习目标
  239. </span>
  240. </a>
  241. </li>
  242. <li class="md-nav__item">
  243. <a href="#fqa" class="md-nav__link">
  244. <span class="md-ellipsis">
  245. 一、FQA系统概述
  246. </span>
  247. </a>
  248. <nav class="md-nav" aria-label="一、FQA系统概述">
  249. <ul class="md-nav__list">
  250. <li class="md-nav__item">
  251. <a href="#1" class="md-nav__link">
  252. <span class="md-ellipsis">
  253. 1 系统流程
  254. </span>
  255. </a>
  256. </li>
  257. <li class="md-nav__item">
  258. <a href="#2" class="md-nav__link">
  259. <span class="md-ellipsis">
  260. 2 项目结构
  261. </span>
  262. </a>
  263. </li>
  264. </ul>
  265. </nav>
  266. </li>
  267. <li class="md-nav__item">
  268. <a href="#_2" class="md-nav__link">
  269. <span class="md-ellipsis">
  270. 三、代码实现
  271. </span>
  272. </a>
  273. <nav class="md-nav" aria-label="三、代码实现">
  274. <ul class="md-nav__list">
  275. <li class="md-nav__item">
  276. <a href="#1-configini" class="md-nav__link">
  277. <span class="md-ellipsis">
  278. 1 配置文件 (config.ini)
  279. </span>
  280. </a>
  281. </li>
  282. <li class="md-nav__item">
  283. <a href="#2_1" class="md-nav__link">
  284. <span class="md-ellipsis">
  285. 2 配置管理
  286. </span>
  287. </a>
  288. <nav class="md-nav" aria-label="2 配置管理">
  289. <ul class="md-nav__list">
  290. <li class="md-nav__item">
  291. <a href="#21" class="md-nav__link">
  292. <span class="md-ellipsis">
  293. 2.1 功能
  294. </span>
  295. </a>
  296. </li>
  297. <li class="md-nav__item">
  298. <a href="#22" class="md-nav__link">
  299. <span class="md-ellipsis">
  300. 2.2 代码实现
  301. </span>
  302. </a>
  303. </li>
  304. <li class="md-nav__item">
  305. <a href="#23" class="md-nav__link">
  306. <span class="md-ellipsis">
  307. 2.3 说明
  308. </span>
  309. </a>
  310. </li>
  311. </ul>
  312. </nav>
  313. </li>
  314. <li class="md-nav__item">
  315. <a href="#3" class="md-nav__link">
  316. <span class="md-ellipsis">
  317. 3 日志记录
  318. </span>
  319. </a>
  320. <nav class="md-nav" aria-label="3 日志记录">
  321. <ul class="md-nav__list">
  322. <li class="md-nav__item">
  323. <a href="#31" class="md-nav__link">
  324. <span class="md-ellipsis">
  325. 3.1 功能
  326. </span>
  327. </a>
  328. </li>
  329. <li class="md-nav__item">
  330. <a href="#32" class="md-nav__link">
  331. <span class="md-ellipsis">
  332. 3.2 代码实现
  333. </span>
  334. </a>
  335. </li>
  336. <li class="md-nav__item">
  337. <a href="#33" class="md-nav__link">
  338. <span class="md-ellipsis">
  339. 3.3 说明
  340. </span>
  341. </a>
  342. </li>
  343. </ul>
  344. </nav>
  345. </li>
  346. <li class="md-nav__item">
  347. <a href="#4-mysql" class="md-nav__link">
  348. <span class="md-ellipsis">
  349. 4 MySQL操作模块
  350. </span>
  351. </a>
  352. <nav class="md-nav" aria-label="4 MySQL操作模块">
  353. <ul class="md-nav__list">
  354. <li class="md-nav__item">
  355. <a href="#41" class="md-nav__link">
  356. <span class="md-ellipsis">
  357. 4.1 功能
  358. </span>
  359. </a>
  360. </li>
  361. <li class="md-nav__item">
  362. <a href="#42" class="md-nav__link">
  363. <span class="md-ellipsis">
  364. 4.2 代码实现
  365. </span>
  366. </a>
  367. </li>
  368. <li class="md-nav__item">
  369. <a href="#43" class="md-nav__link">
  370. <span class="md-ellipsis">
  371. 4.3 说明
  372. </span>
  373. </a>
  374. </li>
  375. </ul>
  376. </nav>
  377. </li>
  378. <li class="md-nav__item">
  379. <a href="#5-redis" class="md-nav__link">
  380. <span class="md-ellipsis">
  381. 5 Redis 缓存操作模块
  382. </span>
  383. </a>
  384. <nav class="md-nav" aria-label="5 Redis 缓存操作模块">
  385. <ul class="md-nav__list">
  386. <li class="md-nav__item">
  387. <a href="#51" class="md-nav__link">
  388. <span class="md-ellipsis">
  389. 5.1 功能
  390. </span>
  391. </a>
  392. </li>
  393. <li class="md-nav__item">
  394. <a href="#52" class="md-nav__link">
  395. <span class="md-ellipsis">
  396. 5.2 代码实现
  397. </span>
  398. </a>
  399. </li>
  400. <li class="md-nav__item">
  401. <a href="#53" class="md-nav__link">
  402. <span class="md-ellipsis">
  403. 5.3 说明
  404. </span>
  405. </a>
  406. </li>
  407. </ul>
  408. </nav>
  409. </li>
  410. <li class="md-nav__item">
  411. <a href="#6" class="md-nav__link">
  412. <span class="md-ellipsis">
  413. 6 文本预处理模块
  414. </span>
  415. </a>
  416. <nav class="md-nav" aria-label="6 文本预处理模块">
  417. <ul class="md-nav__list">
  418. <li class="md-nav__item">
  419. <a href="#61" class="md-nav__link">
  420. <span class="md-ellipsis">
  421. 6.1 功能
  422. </span>
  423. </a>
  424. </li>
  425. <li class="md-nav__item">
  426. <a href="#62" class="md-nav__link">
  427. <span class="md-ellipsis">
  428. 6.2 代码实现
  429. </span>
  430. </a>
  431. </li>
  432. <li class="md-nav__item">
  433. <a href="#63" class="md-nav__link">
  434. <span class="md-ellipsis">
  435. 6.3 说明
  436. </span>
  437. </a>
  438. </li>
  439. </ul>
  440. </nav>
  441. </li>
  442. <li class="md-nav__item">
  443. <a href="#7-bm25softmax" class="md-nav__link">
  444. <span class="md-ellipsis">
  445. 7 BM25+Softmax检索模块
  446. </span>
  447. </a>
  448. <nav class="md-nav" aria-label="7 BM25+Softmax检索模块">
  449. <ul class="md-nav__list">
  450. <li class="md-nav__item">
  451. <a href="#71" class="md-nav__link">
  452. <span class="md-ellipsis">
  453. 7.1 功能
  454. </span>
  455. </a>
  456. </li>
  457. <li class="md-nav__item">
  458. <a href="#72" class="md-nav__link">
  459. <span class="md-ellipsis">
  460. 7.2 说明
  461. </span>
  462. </a>
  463. </li>
  464. </ul>
  465. </nav>
  466. </li>
  467. </ul>
  468. </nav>
  469. </li>
  470. <li class="md-nav__item">
  471. <a href="#mainpy" class="md-nav__link">
  472. <span class="md-ellipsis">
  473. 三、主程序 (main.py)
  474. </span>
  475. </a>
  476. <nav class="md-nav" aria-label="三、主程序 (main.py)">
  477. <ul class="md-nav__list">
  478. <li class="md-nav__item">
  479. <a href="#1_1" class="md-nav__link">
  480. <span class="md-ellipsis">
  481. 1 代码
  482. </span>
  483. </a>
  484. </li>
  485. <li class="md-nav__item">
  486. <a href="#2_2" class="md-nav__link">
  487. <span class="md-ellipsis">
  488. 2 示例运行结果
  489. </span>
  490. </a>
  491. </li>
  492. </ul>
  493. </nav>
  494. </li>
  495. <li class="md-nav__item">
  496. <a href="#_3" class="md-nav__link">
  497. <span class="md-ellipsis">
  498. 本章小结
  499. </span>
  500. </a>
  501. </li>
  502. </ul>
  503. </nav>
  504. </li>
  505. <li class="md-nav__item">
  506. <a href="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">
  507. <span class="md-ellipsis">
  508. 3.4 BM25算法简介与应用
  509. </span>
  510. </a>
  511. </li>
  512. </ul>
  513. </nav>
  514. </li>
  515. <li class="md-nav__item md-nav__item--nested">
  516. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5">
  517. <label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
  518. <span class="md-ellipsis">
  519. ④ 基于Milvus库的问答系统
  520. </span>
  521. <span class="md-nav__icon md-icon"></span>
  522. </label>
  523. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
  524. <label class="md-nav__title" for="__nav_5">
  525. <span class="md-nav__icon md-icon"></span>
  526. ④ 基于Milvus库的问答系统
  527. </label>
  528. <ul class="md-nav__list" data-md-scrollfix>
  529. <li class="md-nav__item">
  530. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/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">
  531. <span class="md-ellipsis">
  532. 4.1 整体架构与工程流程
  533. </span>
  534. </a>
  535. </li>
  536. <li class="md-nav__item">
  537. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/4.2%20%E5%9F%BA%E7%A1%80%E6%A8%A1%E5%9D%97.html" class="md-nav__link">
  538. <span class="md-ellipsis">
  539. 4.2 基础模块
  540. </span>
  541. </a>
  542. </li>
  543. <li class="md-nav__item">
  544. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/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">
  545. <span class="md-ellipsis">
  546. 4.3 文档处理模块
  547. </span>
  548. </a>
  549. </li>
  550. <li class="md-nav__item">
  551. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/4.4%20%E5%90%91%E9%87%8F%E5%AD%98%E5%82%A8.html" class="md-nav__link">
  552. <span class="md-ellipsis">
  553. 4.4 向量存储
  554. </span>
  555. </a>
  556. </li>
  557. <li class="md-nav__item"><a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/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">
  558. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/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">
  559. <span class="md-ellipsis">
  560. 4.6 prompts设计与query意图识别
  561. </span>
  562. </a>
  563. </li>
  564. <li class="md-nav__item">
  565. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/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">
  566. <span class="md-ellipsis">
  567. 4.7 检索策略与RAG系统设计
  568. </span>
  569. </a>
  570. </li>
  571. <li class="md-nav__item">
  572. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/4.8%20RAG%E7%B3%BB%E7%BB%9F%E8%BF%90%E8%A1%8C.html" class="md-nav__link">
  573. <span class="md-ellipsis">
  574. 4.8 RAG系统运行
  575. </span>
  576. </a>
  577. </li>
  578. <li class="md-nav__item">
  579. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/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">
  580. <span class="md-ellipsis">
  581. 4.9 文档解析工具(扩展资料)
  582. </span>
  583. </a>
  584. </li>
  585. <li class="md-nav__item">
  586. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/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">
  587. <span class="md-ellipsis">
  588. 4.10 RAG中的Query改写(扩展资料)
  589. </span>
  590. </a>
  591. </li>
  592. <li class="md-nav__item">
  593. <a href="../%E2%91%A3%20%E5%9F%BA%E4%BA%8EMilvus%E5%BA%93%E7%9A%84%E9%97%AE%E7%AD%94%E7%B3%BB%E7%BB%9F/%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">
  594. <span class="md-ellipsis">
  595. 数据集生成与优化(扩展资料)
  596. </span>
  597. </a>
  598. </li>
  599. </ul>
  600. </nav>
  601. </li>
  602. <li class="md-nav__item md-nav__item--nested">
  603. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6">
  604. <label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
  605. <span class="md-ellipsis">
  606. ⑤ RAG系统评估
  607. </span>
  608. <span class="md-nav__icon md-icon"></span>
  609. </label>
  610. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
  611. <label class="md-nav__title" for="__nav_6">
  612. <span class="md-nav__icon md-icon"></span>
  613. ⑤ RAG系统评估
  614. </label>
  615. <ul class="md-nav__list" data-md-scrollfix>
  616. <li class="md-nav__item">
  617. <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">
  618. <span class="md-ellipsis">
  619. 5.1 RAG系统评估工具
  620. </span>
  621. </a>
  622. </li>
  623. <li class="md-nav__item">
  624. <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">
  625. <span class="md-ellipsis">
  626. 5.2 实现企业知识库RAG系统的评估
  627. </span>
  628. </a>
  629. </li>
  630. <li class="md-nav__item">
  631. <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">
  632. <span class="md-ellipsis">
  633. 5.3 RAG评估数据集的构造(扩展)
  634. </span>
  635. </a>
  636. </li>
  637. </ul>
  638. </nav>
  639. </li>
  640. <li class="md-nav__item md-nav__item--nested">
  641. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7">
  642. <label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
  643. <span class="md-ellipsis">
  644. ⑥ 融合Mysql的RAG系统
  645. </span>
  646. <span class="md-nav__icon md-icon"></span>
  647. </label>
  648. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
  649. <label class="md-nav__title" for="__nav_7">
  650. <span class="md-nav__icon md-icon"></span>
  651. ⑥ 融合Mysql的RAG系统
  652. </label>
  653. <ul class="md-nav__list" data-md-scrollfix>
  654. <li class="md-nav__item">
  655. <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">
  656. <span class="md-ellipsis">
  657. 6.1 融合FQA和知识库查询
  658. </span>
  659. </a>
  660. </li>
  661. <li class="md-nav__item">
  662. <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">
  663. <span class="md-ellipsis">
  664. 6.2 融合FAQ 和知识库查询(优化版)
  665. </span>
  666. </a>
  667. </li>
  668. <li class="md-nav__item">
  669. <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">
  670. <span class="md-ellipsis">
  671. 6.3 基于 FastAPI 的 FAQ 与知识库查询接口
  672. </span>
  673. </a>
  674. </li>
  675. <li class="md-nav__item">
  676. <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">
  677. <span class="md-ellipsis">
  678. 6.4 FastAPI和Flask的区别和联系(扩展资料)
  679. </span>
  680. </a>
  681. </li>
  682. </ul>
  683. </nav>
  684. </li>
  685. <li class="md-nav__item md-nav__item--nested">
  686. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8">
  687. <label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
  688. <span class="md-ellipsis">
  689. ⑦ 企业级生产环境部署
  690. </span>
  691. <span class="md-nav__icon md-icon"></span>
  692. </label>
  693. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
  694. <label class="md-nav__title" for="__nav_8">
  695. <span class="md-nav__icon md-icon"></span>
  696. ⑦ 企业级生产环境部署
  697. </label>
  698. <ul class="md-nav__list" data-md-scrollfix>
  699. <li class="md-nav__item">
  700. <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">
  701. <span class="md-ellipsis">
  702. 7.1 Docker的原理和基本使用
  703. </span>
  704. </a>
  705. </li>
  706. <li class="md-nav__item">
  707. <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">
  708. <span class="md-ellipsis">
  709. 7.2 服务部署
  710. </span>
  711. </a>
  712. </li>
  713. </ul>
  714. </nav>
  715. </li>
  716. </ul>
  717. </nav>
  718. </div>
  719. </div>
  720. </div>
  721. <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc">
  722. <div class="md-sidebar__scrollwrap">
  723. <div class="md-sidebar__inner">
  724. <nav class="md-nav md-nav--secondary" aria-label="目录">
  725. <label class="md-nav__title" for="__toc">
  726. <span class="md-nav__icon md-icon"></span>
  727. 目录
  728. </label>
  729. <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
  730. <li class="md-nav__item">
  731. <a href="#_1" class="md-nav__link">
  732. <span class="md-ellipsis">
  733. 学习目标
  734. </span>
  735. </a>
  736. </li>
  737. <li class="md-nav__item">
  738. <a href="#fqa" class="md-nav__link">
  739. <span class="md-ellipsis">
  740. 一、FQA系统概述
  741. </span>
  742. </a>
  743. <nav class="md-nav" aria-label="一、FQA系统概述">
  744. <ul class="md-nav__list">
  745. <li class="md-nav__item">
  746. <a href="#1" class="md-nav__link">
  747. <span class="md-ellipsis">
  748. 1 系统流程
  749. </span>
  750. </a>
  751. </li>
  752. <li class="md-nav__item">
  753. <a href="#2" class="md-nav__link">
  754. <span class="md-ellipsis">
  755. 2 项目结构
  756. </span>
  757. </a>
  758. </li>
  759. </ul>
  760. </nav>
  761. </li>
  762. <li class="md-nav__item">
  763. <a href="#_2" class="md-nav__link">
  764. <span class="md-ellipsis">
  765. 三、代码实现
  766. </span>
  767. </a>
  768. <nav class="md-nav" aria-label="三、代码实现">
  769. <ul class="md-nav__list">
  770. <li class="md-nav__item">
  771. <a href="#1-configini" class="md-nav__link">
  772. <span class="md-ellipsis">
  773. 1 配置文件 (config.ini)
  774. </span>
  775. </a>
  776. </li>
  777. <li class="md-nav__item">
  778. <a href="#2_1" class="md-nav__link">
  779. <span class="md-ellipsis">
  780. 2 配置管理
  781. </span>
  782. </a>
  783. <nav class="md-nav" aria-label="2 配置管理">
  784. <ul class="md-nav__list">
  785. <li class="md-nav__item">
  786. <a href="#21" class="md-nav__link">
  787. <span class="md-ellipsis">
  788. 2.1 功能
  789. </span>
  790. </a>
  791. </li>
  792. <li class="md-nav__item">
  793. <a href="#22" class="md-nav__link">
  794. <span class="md-ellipsis">
  795. 2.2 代码实现
  796. </span>
  797. </a>
  798. </li>
  799. <li class="md-nav__item">
  800. <a href="#23" class="md-nav__link">
  801. <span class="md-ellipsis">
  802. 2.3 说明
  803. </span>
  804. </a>
  805. </li>
  806. </ul>
  807. </nav>
  808. </li>
  809. <li class="md-nav__item">
  810. <a href="#3" class="md-nav__link">
  811. <span class="md-ellipsis">
  812. 3 日志记录
  813. </span>
  814. </a>
  815. <nav class="md-nav" aria-label="3 日志记录">
  816. <ul class="md-nav__list">
  817. <li class="md-nav__item">
  818. <a href="#31" class="md-nav__link">
  819. <span class="md-ellipsis">
  820. 3.1 功能
  821. </span>
  822. </a>
  823. </li>
  824. <li class="md-nav__item">
  825. <a href="#32" class="md-nav__link">
  826. <span class="md-ellipsis">
  827. 3.2 代码实现
  828. </span>
  829. </a>
  830. </li>
  831. <li class="md-nav__item">
  832. <a href="#33" class="md-nav__link">
  833. <span class="md-ellipsis">
  834. 3.3 说明
  835. </span>
  836. </a>
  837. </li>
  838. </ul>
  839. </nav>
  840. </li>
  841. <li class="md-nav__item">
  842. <a href="#4-mysql" class="md-nav__link">
  843. <span class="md-ellipsis">
  844. 4 MySQL操作模块
  845. </span>
  846. </a>
  847. <nav class="md-nav" aria-label="4 MySQL操作模块">
  848. <ul class="md-nav__list">
  849. <li class="md-nav__item">
  850. <a href="#41" class="md-nav__link">
  851. <span class="md-ellipsis">
  852. 4.1 功能
  853. </span>
  854. </a>
  855. </li>
  856. <li class="md-nav__item">
  857. <a href="#42" class="md-nav__link">
  858. <span class="md-ellipsis">
  859. 4.2 代码实现
  860. </span>
  861. </a>
  862. </li>
  863. <li class="md-nav__item">
  864. <a href="#43" class="md-nav__link">
  865. <span class="md-ellipsis">
  866. 4.3 说明
  867. </span>
  868. </a>
  869. </li>
  870. </ul>
  871. </nav>
  872. </li>
  873. <li class="md-nav__item">
  874. <a href="#5-redis" class="md-nav__link">
  875. <span class="md-ellipsis">
  876. 5 Redis 缓存操作模块
  877. </span>
  878. </a>
  879. <nav class="md-nav" aria-label="5 Redis 缓存操作模块">
  880. <ul class="md-nav__list">
  881. <li class="md-nav__item">
  882. <a href="#51" class="md-nav__link">
  883. <span class="md-ellipsis">
  884. 5.1 功能
  885. </span>
  886. </a>
  887. </li>
  888. <li class="md-nav__item">
  889. <a href="#52" class="md-nav__link">
  890. <span class="md-ellipsis">
  891. 5.2 代码实现
  892. </span>
  893. </a>
  894. </li>
  895. <li class="md-nav__item">
  896. <a href="#53" class="md-nav__link">
  897. <span class="md-ellipsis">
  898. 5.3 说明
  899. </span>
  900. </a>
  901. </li>
  902. </ul>
  903. </nav>
  904. </li>
  905. <li class="md-nav__item">
  906. <a href="#6" class="md-nav__link">
  907. <span class="md-ellipsis">
  908. 6 文本预处理模块
  909. </span>
  910. </a>
  911. <nav class="md-nav" aria-label="6 文本预处理模块">
  912. <ul class="md-nav__list">
  913. <li class="md-nav__item">
  914. <a href="#61" class="md-nav__link">
  915. <span class="md-ellipsis">
  916. 6.1 功能
  917. </span>
  918. </a>
  919. </li>
  920. <li class="md-nav__item">
  921. <a href="#62" class="md-nav__link">
  922. <span class="md-ellipsis">
  923. 6.2 代码实现
  924. </span>
  925. </a>
  926. </li>
  927. <li class="md-nav__item">
  928. <a href="#63" class="md-nav__link">
  929. <span class="md-ellipsis">
  930. 6.3 说明
  931. </span>
  932. </a>
  933. </li>
  934. </ul>
  935. </nav>
  936. </li>
  937. <li class="md-nav__item">
  938. <a href="#7-bm25softmax" class="md-nav__link">
  939. <span class="md-ellipsis">
  940. 7 BM25+Softmax检索模块
  941. </span>
  942. </a>
  943. <nav class="md-nav" aria-label="7 BM25+Softmax检索模块">
  944. <ul class="md-nav__list">
  945. <li class="md-nav__item">
  946. <a href="#71" class="md-nav__link">
  947. <span class="md-ellipsis">
  948. 7.1 功能
  949. </span>
  950. </a>
  951. </li>
  952. <li class="md-nav__item">
  953. <a href="#72" class="md-nav__link">
  954. <span class="md-ellipsis">
  955. 7.2 说明
  956. </span>
  957. </a>
  958. </li>
  959. </ul>
  960. </nav>
  961. </li>
  962. </ul>
  963. </nav>
  964. </li>
  965. <li class="md-nav__item">
  966. <a href="#mainpy" class="md-nav__link">
  967. <span class="md-ellipsis">
  968. 三、主程序 (main.py)
  969. </span>
  970. </a>
  971. <nav class="md-nav" aria-label="三、主程序 (main.py)">
  972. <ul class="md-nav__list">
  973. <li class="md-nav__item">
  974. <a href="#1_1" class="md-nav__link">
  975. <span class="md-ellipsis">
  976. 1 代码
  977. </span>
  978. </a>
  979. </li>
  980. <li class="md-nav__item">
  981. <a href="#2_2" class="md-nav__link">
  982. <span class="md-ellipsis">
  983. 2 示例运行结果
  984. </span>
  985. </a>
  986. </li>
  987. </ul>
  988. </nav>
  989. </li>
  990. <li class="md-nav__item">
  991. <a href="#_3" class="md-nav__link">
  992. <span class="md-ellipsis">
  993. 本章小结
  994. </span>
  995. </a>
  996. </li>
  997. </ul>
  998. </nav>
  999. </div>
  1000. </div>
  1001. </div>
  1002. <div class="md-content" data-md-component="content">
  1003. <article class="md-content__inner md-typeset">
  1004. <h1>3.3 基于Mysql数据库实现问答系统</h1>
  1005. <h2 id="_1">学习目标<a class="headerlink" href="#_1" title="Permanent link">¶</a></h2>
  1006. <ol>
  1007. <li>理解FQA问答系统的整体流程。</li>
  1008. <li>掌握如何整合MySQL、Redis和BM25算法构建QA问答系统。</li>
  1009. </ol>
  1010. <hr>
  1011. <h2 id="fqa">一、FQA系统概述<a class="headerlink" href="#fqa" title="Permanent link">¶</a></h2>
  1012. <p>本系统从MySQL数据库检索问答对,使用BM25算法计算相似度,并通过Softmax归一化将得分转换为概率值,阈值0.85判断答案可靠性。Redis仅缓存高可靠性结果(相似度&gt;0.85且有答案)。若MySQL无可靠答案,则调用RAG系统检索。</p>
  1013. <h3 id="1">1 系统流程<a class="headerlink" href="#1" title="Permanent link">¶</a></h3>
  1014. <ol>
  1015. <li><strong>数据存储</strong>:MySQL存储FQA高频问答对数据。</li>
  1016. <li><strong>问题检索</strong>:BM25计算相似度,Softmax归一化后判断阈值0.85。</li>
  1017. <li><strong>缓存管理</strong>:Redis仅存储相似度&gt;0.85且有答案的数据。</li>
  1018. <li><strong>答案返回</strong>:</li>
  1019. <li>若MySQL返回可靠答案,直接返回。</li>
  1020. <li>否则,调用RAG系统检索。</li>
  1021. </ol>
  1022. <hr>
  1023. <h3 id="2">2 项目结构<a class="headerlink" href="#2" title="Permanent link">¶</a></h3>
  1024. <div class="highlight"><pre><span></span><code>integrated_qa_system/
  1025. ├── config.ini # 配置文件,包含所有模块的配置
  1026. ├── base/
  1027. │ ├── config.py # 配置管理,加载 config.ini
  1028. │ ├── logger.py # 日志设置
  1029. ├── mysql_qa/
  1030. │ ├── data/
  1031. │ │ ├── JP企业知识库问答.csv # FQA数据集
  1032. │ ├── db/
  1033. │ │ ├── mysql_client.py # MySQL 数据库操作
  1034. │ ├── cache/
  1035. │ │ ├── redis_client.py # Redis 缓存操作
  1036. │ ├── retrieval/
  1037. │ │ ├── bm25_search.py # BM25 搜索
  1038. │ ├── utils/
  1039. │ │ ├── preprocess.py # 文本预处理
  1040. │ ├── main.py # MySQL 系统独立入口,支持查询
  1041. ├── requirements.txt # 依赖文件
  1042. └── logs/
  1043. └── app.log # 日志文件
  1044. </code></pre></div>
  1045. <h2 id="_2">三、代码实现<a class="headerlink" href="#_2" title="Permanent link">¶</a></h2>
  1046. <h3 id="1-configini">1 配置文件 (<code>config.ini</code>)<a class="headerlink" href="#1-configini" title="Permanent link">¶</a></h3>
  1047. <div class="highlight"><pre><span></span><code><span class="c1"># MySQL 配置</span>
  1048. <span class="k">[mysql]</span>
  1049. <span class="na">host</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">localhost</span>
  1050. <span class="na">user</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">root</span>
  1051. <span class="na">password</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">123456</span>
  1052. <span class="na">database</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">subjects_kg</span>
  1053. <span class="c1"># Redis 配置</span>
  1054. <span class="k">[redis]</span>
  1055. <span class="na">host</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">localhost</span>
  1056. <span class="na">port</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">6379</span>
  1057. <span class="na">password</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">1234</span>
  1058. <span class="na">db</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">0</span>
  1059. <span class="c1"># 日志配置</span>
  1060. <span class="k">[logger]</span>
  1061. <span class="na">log_file</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">/path/to/your/logs/app.log</span>
  1062. </code></pre></div>
  1063. <h3 id="2_1">2 配置管理<a class="headerlink" href="#2_1" title="Permanent link">¶</a></h3>
  1064. <h4 id="21">2.1 功能<a class="headerlink" href="#21" title="Permanent link">¶</a></h4>
  1065. <p><code>config.py</code>文件定义了<code>Config</code>类,用于集中管理系统中的所有配置参数。这些参数包括数据库连接信息、模型选择、分块策略、API设置等。通过集中管理配置,系统可以方便地调整参数、适配不同环境,并支持通过环境变量进行灵活配置。</p>
  1066. <h4 id="22">2.2 代码实现<a class="headerlink" href="#22" title="Permanent link">¶</a></h4>
  1067. <div class="highlight"><pre><span></span><code><span class="c1"># base/config.py</span>
  1068. <span class="c1"># 导入配置解析库</span>
  1069. <span class="kn">import</span><span class="w"> </span><span class="nn">configparser</span>
  1070. <span class="c1"># 导入路径操作库</span>
  1071. <span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
  1072. <span class="k">class</span><span class="w"> </span><span class="nc">Config</span><span class="p">:</span>
  1073. <span class="c1"># 初始化配置,加载 config.ini 文件</span>
  1074. <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">config_file</span><span class="o">=</span><span class="s1">'../config.ini'</span><span class="p">):</span>
  1075. <span class="c1"># 创建配置解析器</span>
  1076. <span class="bp">self</span><span class="o">.</span><span class="n">config</span> <span class="o">=</span> <span class="n">configparser</span><span class="o">.</span><span class="n">ConfigParser</span><span class="p">()</span>
  1077. <span class="c1"># 读取配置文件</span>
  1078. <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">config_file</span><span class="p">)</span>
  1079. <span class="c1"># MySQL 配置</span>
  1080. <span class="c1"># MySQL 主机地址</span>
  1081. <span class="bp">self</span><span class="o">.</span><span class="n">MYSQL_HOST</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'mysql'</span><span class="p">,</span> <span class="s1">'host'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="s1">'localhost'</span><span class="p">)</span>
  1082. <span class="c1"># MySQL 用户名</span>
  1083. <span class="bp">self</span><span class="o">.</span><span class="n">MYSQL_USER</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'mysql'</span><span class="p">,</span> <span class="s1">'user'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="s1">'root'</span><span class="p">)</span>
  1084. <span class="c1"># MySQL 密码</span>
  1085. <span class="bp">self</span><span class="o">.</span><span class="n">MYSQL_PASSWORD</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'mysql'</span><span class="p">,</span> <span class="s1">'password'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="s1">'123456'</span><span class="p">)</span>
  1086. <span class="c1"># MySQL 数据库名</span>
  1087. <span class="bp">self</span><span class="o">.</span><span class="n">MYSQL_DATABASE</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'mysql'</span><span class="p">,</span> <span class="s1">'database'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="s1">'subjects_kg'</span><span class="p">)</span>
  1088. <span class="c1"># Redis 配置</span>
  1089. <span class="c1"># Redis 主机地址</span>
  1090. <span class="bp">self</span><span class="o">.</span><span class="n">REDIS_HOST</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'redis'</span><span class="p">,</span> <span class="s1">'host'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="s1">'localhost'</span><span class="p">)</span>
  1091. <span class="c1"># Redis 端口</span>
  1092. <span class="bp">self</span><span class="o">.</span><span class="n">REDIS_PORT</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">'redis'</span><span class="p">,</span> <span class="s1">'port'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="mi">6379</span><span class="p">)</span>
  1093. <span class="c1"># Redis 密码</span>
  1094. <span class="bp">self</span><span class="o">.</span><span class="n">REDIS_PASSWORD</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'redis'</span><span class="p">,</span> <span class="s1">'password'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="s1">'1234'</span><span class="p">)</span>
  1095. <span class="c1"># Redis 数据库编号</span>
  1096. <span class="bp">self</span><span class="o">.</span><span class="n">REDIS_DB</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">'redis'</span><span class="p">,</span> <span class="s1">'db'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
  1097. <span class="c1"># 日志文件路径</span>
  1098. <span class="bp">self</span><span class="o">.</span><span class="n">LOG_FILE</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'logger'</span><span class="p">,</span> <span class="s1">'log_file'</span><span class="p">,</span> <span class="n">fallback</span><span class="o">=</span><span class="s1">'logs/app.log'</span><span class="p">)</span>
  1099. <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
  1100. <span class="n">conf</span> <span class="o">=</span> <span class="n">Config</span><span class="p">()</span>
  1101. <span class="nb">print</span><span class="p">(</span><span class="n">conf</span><span class="o">.</span><span class="n">CHILD_CHUNK_SIZE</span><span class="p">)</span>
  1102. </code></pre></div>
  1103. <h4 id="23">2.3 说明<a class="headerlink" href="#23" title="Permanent link">¶</a></h4>
  1104. <ul>
  1105. <li><strong>默认值</strong>:每个参数设有默认值,确保未配置环境变量时系统仍可运行。</li>
  1106. <li><strong>参数分类</strong>:按功能分类(如数据库、模型、分块等),便于管理和维护。</li>
  1107. </ul>
  1108. <hr>
  1109. <h3 id="3">3 日志记录<a class="headerlink" href="#3" title="Permanent link">¶</a></h3>
  1110. <h4 id="31">3.1 功能<a class="headerlink" href="#31" title="Permanent link">¶</a></h4>
  1111. <p><code>logger.py</code>文件定义了<code>setup_logging</code>函数,用于配置系统的日志记录器。日志记录器将运行信息、警告和错误输出到文件和控制台,便于开发、调试和运维人员监控系统状态。</p>
  1112. <h4 id="32">3.2 代码实现<a class="headerlink" href="#32" title="Permanent link">¶</a></h4>
  1113. <div class="highlight"><pre><span></span><code><span class="c1"># base/logger.py</span>
  1114. <span class="c1"># 导入日志库</span>
  1115. <span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
  1116. <span class="c1"># 导入路径操作库</span>
  1117. <span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
  1118. <span class="c1"># 导入配置类</span>
  1119. <span class="kn">from</span><span class="w"> </span><span class="nn">config</span><span class="w"> </span><span class="kn">import</span> <span class="n">Config</span>
  1120. <span class="k">def</span><span class="w"> </span><span class="nf">setup_logging</span><span class="p">(</span><span class="n">log_file</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">LOG_FILE</span><span class="p">):</span>
  1121. <span class="c1"># 创建日志目录</span>
  1122. <span class="n">os</span><span class="o">.</span><span class="n">makedirs</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">log_file</span><span class="p">),</span> <span class="n">exist_ok</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
  1123. <span class="c1"># 获取日志器</span>
  1124. <span class="n">logger</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="s2">"EnterpriseKB-RAG"</span><span class="p">)</span>
  1125. <span class="c1"># 设置日志级别</span>
  1126. <span class="n">logger</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">INFO</span><span class="p">)</span>
  1127. <span class="c1"># 避免重复添加处理器</span>
  1128. <span class="k">if</span> <span class="ow">not</span> <span class="n">logger</span><span class="o">.</span><span class="n">handlers</span><span class="p">:</span>
  1129. <span class="c1"># 创建文件处理器</span>
  1130. <span class="n">file_handler</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">FileHandler</span><span class="p">(</span><span class="n">log_file</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">'utf-8'</span><span class="p">)</span>
  1131. <span class="c1"># 设置文件处理器级别</span>
  1132. <span class="n">file_handler</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">INFO</span><span class="p">)</span>
  1133. <span class="c1"># 创建控制台处理器</span>
  1134. <span class="n">console_handler</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">StreamHandler</span><span class="p">()</span>
  1135. <span class="c1"># 设置控制台处理器级别</span>
  1136. <span class="n">console_handler</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">INFO</span><span class="p">)</span>
  1137. <span class="c1"># 设置日志格式</span>
  1138. <span class="n">formatter</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">Formatter</span><span class="p">(</span><span class="s1">'</span><span class="si">%(asctime)s</span><span class="s1"> - </span><span class="si">%(name)s</span><span class="s1"> - </span><span class="si">%(levelname)s</span><span class="s1"> - </span><span class="si">%(message)s</span><span class="s1">'</span><span class="p">)</span>
  1139. <span class="c1"># 为文件处理器设置格式</span>
  1140. <span class="n">file_handler</span><span class="o">.</span><span class="n">setFormatter</span><span class="p">(</span><span class="n">formatter</span><span class="p">)</span>
  1141. <span class="c1"># 为控制台处理器设置格式</span>
  1142. <span class="n">console_handler</span><span class="o">.</span><span class="n">setFormatter</span><span class="p">(</span><span class="n">formatter</span><span class="p">)</span>
  1143. <span class="c1"># 添加文件处理器</span>
  1144. <span class="n">logger</span><span class="o">.</span><span class="n">addHandler</span><span class="p">(</span><span class="n">file_handler</span><span class="p">)</span>
  1145. <span class="c1"># 添加控制台处理器</span>
  1146. <span class="n">logger</span><span class="o">.</span><span class="n">addHandler</span><span class="p">(</span><span class="n">console_handler</span><span class="p">)</span>
  1147. <span class="c1"># 返回日志器</span>
  1148. <span class="k">return</span> <span class="n">logger</span>
  1149. <span class="c1"># 初始化日志器</span>
  1150. <span class="n">logger</span> <span class="o">=</span> <span class="n">setup_logging</span><span class="p">()</span>
  1151. </code></pre></div>
  1152. <h4 id="33">3.3 说明<a class="headerlink" href="#33" title="Permanent link">¶</a></h4>
  1153. <ul>
  1154. <li><strong>日志级别</strong>:默认设为<code>INFO</code>,记录关键运行信息。</li>
  1155. <li><strong>双重输出</strong>:同时输出到文件和控制台,便于实时监控和后续分析。</li>
  1156. <li><strong>格式化</strong>:日志包含时间戳、名称、级别和内容,便于问题定位。</li>
  1157. </ul>
  1158. <hr>
  1159. <h3 id="4-mysql">4 MySQL操作模块<a class="headerlink" href="#4-mysql" title="Permanent link">¶</a></h3>
  1160. <h4 id="41">4.1 功能<a class="headerlink" href="#41" title="Permanent link">¶</a></h4>
  1161. <p><code>mysql_client.py</code>是一个用于与 MySQL 交互的模块。模块通过读取配置文件连接数据库,支持创建表、从 CSV 文件插入数据、查询问题和答案,以及安全关闭连接。所有操作均通过日志记录,便于调试和监控系统状态。</p>
  1162. <h4 id="42">4.2 代码实现<a class="headerlink" href="#42" title="Permanent link">¶</a></h4>
  1163. <div class="highlight"><pre><span></span><code><span class="c1"># db/mysql_client.py</span>
  1164. <span class="c1"># 导入 MySQL 连接库</span>
  1165. <span class="kn">import</span><span class="w"> </span><span class="nn">pymysql</span>
  1166. <span class="c1"># 导入pandas</span>
  1167. <span class="kn">import</span><span class="w"> </span><span class="nn">pandas</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">pd</span>
  1168. <span class="c1"># 导入配置和日志</span>
  1169. <span class="kn">from</span><span class="w"> </span><span class="nn">base</span><span class="w"> </span><span class="kn">import</span> <span class="n">Config</span><span class="p">,</span> <span class="n">logger</span>
  1170. <span class="k">class</span><span class="w"> </span><span class="nc">MySQLClient</span><span class="p">:</span>
  1171. <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>
  1172. <span class="c1"># 初始化日志</span>
  1173. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
  1174. <span class="k">try</span><span class="p">:</span>
  1175. <span class="c1"># 连接 MySQL 数据库</span>
  1176. <span class="bp">self</span><span class="o">.</span><span class="n">connection</span> <span class="o">=</span> <span class="n">pymysql</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span>
  1177. <span class="n">host</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">MYSQL_HOST</span><span class="p">,</span>
  1178. <span class="n">user</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">MYSQL_USER</span><span class="p">,</span>
  1179. <span class="n">password</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">MYSQL_PASSWORD</span><span class="p">,</span>
  1180. <span class="n">database</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">MYSQL_DATABASE</span>
  1181. <span class="p">)</span>
  1182. <span class="c1"># 创建游标</span>
  1183. <span class="bp">self</span><span class="o">.</span><span class="n">cursor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span>
  1184. <span class="c1"># 记录连接成功</span>
  1185. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"MySQL 连接成功"</span><span class="p">)</span>
  1186. <span class="k">except</span> <span class="n">pymysql</span><span class="o">.</span><span class="n">MySQLError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1187. <span class="c1"># 记录连接失败</span>
  1188. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"MySQL 连接失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1189. <span class="k">raise</span>
  1190. <span class="k">def</span><span class="w"> </span><span class="nf">create_table</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  1191. <span class="n">create_table_query</span> <span class="o">=</span> <span class="s1">'''</span>
  1192. <span class="s1"> CREATE TABLE IF NOT EXISTS jpkb (</span>
  1193. <span class="s1"> id INT AUTO_INCREMENT PRIMARY KEY,</span>
  1194. <span class="s1"> subject_name VARCHAR(20),</span>
  1195. <span class="s1"> question VARCHAR(1000),</span>
  1196. <span class="s1"> answer VARCHAR(1000))</span>
  1197. <span class="s1"> '''</span>
  1198. <span class="k">try</span><span class="p">:</span>
  1199. <span class="bp">self</span><span class="o">.</span><span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">create_table_query</span><span class="p">)</span>
  1200. <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span>
  1201. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"表创建成功"</span><span class="p">)</span>
  1202. <span class="k">except</span> <span class="n">pymysql</span><span class="o">.</span><span class="n">MySQLError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1203. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"表创建失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1204. <span class="k">raise</span>
  1205. <span class="k">def</span><span class="w"> </span><span class="nf">insert_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">csv_path</span><span class="p">):</span>
  1206. <span class="k">try</span><span class="p">:</span>
  1207. <span class="n">data</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="n">csv_path</span><span class="p">)</span>
  1208. <span class="k">for</span> <span class="n">_</span><span class="p">,</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">data</span><span class="o">.</span><span class="n">iterrows</span><span class="p">():</span>
  1209. <span class="n">insert_query</span> <span class="o">=</span> <span class="s2">"INSERT INTO jpkb (subject_name, question, answer) VALUES (</span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">)"</span>
  1210. <span class="bp">self</span><span class="o">.</span><span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">insert_query</span><span class="p">,</span> <span class="p">(</span><span class="n">row</span><span class="p">[</span><span class="s1">'知识域'</span><span class="p">],</span> <span class="n">row</span><span class="p">[</span><span class="s1">'问题'</span><span class="p">],</span> <span class="n">row</span><span class="p">[</span><span class="s1">'答案'</span><span class="p">]))</span>
  1211. <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span>
  1212. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"数据插入成功"</span><span class="p">)</span>
  1213. <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1214. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"数据插入失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1215. <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">rollback</span><span class="p">()</span>
  1216. <span class="k">raise</span>
  1217. <span class="k">def</span><span class="w"> </span><span class="nf">fetch_questions</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  1218. <span class="c1"># 获取所有问题</span>
  1219. <span class="k">try</span><span class="p">:</span>
  1220. <span class="c1"># 执行查询</span>
  1221. <span class="bp">self</span><span class="o">.</span><span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="s2">"SELECT question FROM jpkb"</span><span class="p">)</span>
  1222. <span class="c1"># 获取结果</span>
  1223. <span class="n">results</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cursor</span><span class="o">.</span><span class="n">fetchall</span><span class="p">()</span>
  1224. <span class="c1"># 记录获取成功</span>
  1225. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"成功获取问题"</span><span class="p">)</span>
  1226. <span class="c1"># 返回结果</span>
  1227. <span class="k">return</span> <span class="n">results</span>
  1228. <span class="k">except</span> <span class="n">pymysql</span><span class="o">.</span><span class="n">MySQLError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1229. <span class="c1"># 记录查询失败</span>
  1230. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"查询失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1231. <span class="c1"># 返回空列表</span>
  1232. <span class="k">return</span> <span class="p">[]</span>
  1233. <span class="k">def</span><span class="w"> </span><span class="nf">fetch_answer</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">question</span><span class="p">):</span>
  1234. <span class="c1"># 获取指定问题的答案</span>
  1235. <span class="k">try</span><span class="p">:</span>
  1236. <span class="c1"># 执行查询</span>
  1237. <span class="bp">self</span><span class="o">.</span><span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="s2">"SELECT answer FROM jpkb WHERE question=</span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="p">(</span><span class="n">question</span><span class="p">,))</span>
  1238. <span class="c1"># 获取结果</span>
  1239. <span class="n">result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cursor</span><span class="o">.</span><span class="n">fetchone</span><span class="p">()</span>
  1240. <span class="c1"># 返回答案或 None</span>
  1241. <span class="k">return</span> <span class="n">result</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">if</span> <span class="n">result</span> <span class="k">else</span> <span class="kc">None</span>
  1242. <span class="k">except</span> <span class="n">pymysql</span><span class="o">.</span><span class="n">MySQLError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1243. <span class="c1"># 记录答案获取失败</span>
  1244. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"答案获取失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1245. <span class="c1"># 返回 None</span>
  1246. <span class="k">return</span> <span class="kc">None</span>
  1247. <span class="k">def</span><span class="w"> </span><span class="nf">close</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  1248. <span class="c1"># 关闭数据库连接</span>
  1249. <span class="k">try</span><span class="p">:</span>
  1250. <span class="c1"># 关闭连接</span>
  1251. <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
  1252. <span class="c1"># 记录关闭成功</span>
  1253. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"MySQL 连接已关闭"</span><span class="p">)</span>
  1254. <span class="k">except</span> <span class="n">pymysql</span><span class="o">.</span><span class="n">MySQLError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1255. <span class="c1"># 记录关闭失败</span>
  1256. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"关闭连接失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1257. <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
  1258. <span class="n">mysql_client</span> <span class="o">=</span> <span class="n">MySQLClient</span><span class="p">()</span>
  1259. <span class="n">mysql_client</span><span class="o">.</span><span class="n">create_table</span><span class="p">()</span>
  1260. <span class="n">mysql_client</span><span class="o">.</span><span class="n">insert_data</span><span class="p">(</span><span class="s1">'../data/JP企业知识库问答.csv'</span><span class="p">)</span>
  1261. </code></pre></div>
  1262. <h4 id="43">4.3 说明<a class="headerlink" href="#43" title="Permanent link">¶</a></h4>
  1263. <ul>
  1264. <li><strong>数据库连接</strong>:通过 config.ini 配置文件读取 MySQL 参数,使用 pymysql 建立连接。</li>
  1265. <li><strong>表管理</strong>:创建 jpkb 表,包含字段 id(自增主键)、subject_name(知识域)、question(问题)、answer(答案),使用 IF NOT EXISTS 避免重复创建。</li>
  1266. <li><strong>异常处理</strong>:每个方法均捕获异常,记录错误日志并根据需要回滚事务或抛出异常。</li>
  1267. </ul>
  1268. <hr>
  1269. <h3 id="5-redis">5 Redis 缓存操作模块<a class="headerlink" href="#5-redis" title="Permanent link">¶</a></h3>
  1270. <h4 id="51">5.1 功能<a class="headerlink" href="#51" title="Permanent link">¶</a></h4>
  1271. <p><code>redis_client.py</code>该模块用于与 Redis 数据库交互。模块通过配置文件连接 Redis,支持键值对存储与查询(使用 JSON 序列化)、答案缓存查询,并记录操作日志,便于调试和监控。</p>
  1272. <h4 id="52">5.2 代码实现<a class="headerlink" href="#52" title="Permanent link">¶</a></h4>
  1273. <div class="highlight"><pre><span></span><code><span class="c1"># cache/redis_client.py</span>
  1274. <span class="c1"># 导入 Redis 客户端</span>
  1275. <span class="kn">import</span><span class="w"> </span><span class="nn">redis</span>
  1276. <span class="c1"># 导入 JSON 处理</span>
  1277. <span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
  1278. <span class="c1"># 导入配置和日志</span>
  1279. <span class="kn">from</span><span class="w"> </span><span class="nn">base</span><span class="w"> </span><span class="kn">import</span> <span class="n">Config</span><span class="p">,</span> <span class="n">logger</span>
  1280. <span class="k">class</span><span class="w"> </span><span class="nc">RedisClient</span><span class="p">:</span>
  1281. <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>
  1282. <span class="c1"># 初始化日志</span>
  1283. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
  1284. <span class="k">try</span><span class="p">:</span>
  1285. <span class="c1"># 连接 Redis</span>
  1286. <span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="n">redis</span><span class="o">.</span><span class="n">StrictRedis</span><span class="p">(</span>
  1287. <span class="n">host</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">REDIS_HOST</span><span class="p">,</span>
  1288. <span class="n">port</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">REDIS_PORT</span><span class="p">,</span>
  1289. <span class="n">password</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">REDIS_PASSWORD</span><span class="p">,</span>
  1290. <span class="n">db</span><span class="o">=</span><span class="n">Config</span><span class="p">()</span><span class="o">.</span><span class="n">REDIS_DB</span><span class="p">,</span>
  1291. <span class="n">decode_responses</span><span class="o">=</span><span class="kc">True</span>
  1292. <span class="p">)</span>
  1293. <span class="c1"># 记录连接成功</span>
  1294. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Redis 连接成功"</span><span class="p">)</span>
  1295. <span class="k">except</span> <span class="n">redis</span><span class="o">.</span><span class="n">RedisError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1296. <span class="c1"># 记录连接失败</span>
  1297. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Redis 连接失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1298. <span class="k">raise</span>
  1299. <span class="k">def</span><span class="w"> </span><span class="nf">set_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
  1300. <span class="c1"># 存储数据到 Redis</span>
  1301. <span class="k">try</span><span class="p">:</span>
  1302. <span class="c1"># 存储 JSON 数据</span>
  1303. <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">key</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">value</span><span class="p">))</span>
  1304. <span class="c1"># 记录存储成功</span>
  1305. <span class="bp">self</span><span class="o">.</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">"存储数据到 Redis: </span><span class="si">{</span><span class="n">key</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1306. <span class="k">except</span> <span class="n">redis</span><span class="o">.</span><span class="n">RedisError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1307. <span class="c1"># 记录存储失败</span>
  1308. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Redis 存储失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1309. <span class="k">def</span><span class="w"> </span><span class="nf">get_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">):</span>
  1310. <span class="c1"># 从 Redis 获取数据</span>
  1311. <span class="k">try</span><span class="p">:</span>
  1312. <span class="c1"># 获取数据</span>
  1313. <span class="n">data</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">get</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
  1314. <span class="c1"># 返回解析后的 JSON 数据或 None</span>
  1315. <span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> <span class="k">if</span> <span class="n">data</span> <span class="k">else</span> <span class="kc">None</span>
  1316. <span class="k">except</span> <span class="n">redis</span><span class="o">.</span><span class="n">RedisError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1317. <span class="c1"># 记录获取失败</span>
  1318. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Redis 获取失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1319. <span class="c1"># 返回 None</span>
  1320. <span class="k">return</span> <span class="kc">None</span>
  1321. <span class="k">def</span><span class="w"> </span><span class="nf">get_answer</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span>
  1322. <span class="c1"># 获取查询的缓存答案</span>
  1323. <span class="k">try</span><span class="p">:</span>
  1324. <span class="c1"># 从 Redis 获取答案</span>
  1325. <span class="n">answer</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">get</span><span class="p">(</span><span class="sa">f</span><span class="s2">"answer:</span><span class="si">{</span><span class="n">query</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1326. <span class="k">if</span> <span class="n">answer</span><span class="p">:</span>
  1327. <span class="c1"># 记录获取成功</span>
  1328. <span class="bp">self</span><span class="o">.</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">"从 Redis 获取答案: </span><span class="si">{</span><span class="n">query</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1329. <span class="c1"># 返回答案</span>
  1330. <span class="k">return</span> <span class="n">answer</span>
  1331. <span class="c1"># 返回 None</span>
  1332. <span class="k">return</span> <span class="kc">None</span>
  1333. <span class="k">except</span> <span class="n">redis</span><span class="o">.</span><span class="n">RedisError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1334. <span class="c1"># 记录查询失败</span>
  1335. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Redis 查询失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1336. <span class="c1"># 返回 None</span>
  1337. <span class="k">return</span> <span class="kc">None</span>
  1338. <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
  1339. <span class="n">redcli</span> <span class="o">=</span> <span class="n">RedisClient</span><span class="p">()</span>
  1340. <span class="nb">print</span><span class="p">(</span><span class="n">redcli</span><span class="p">)</span>
  1341. </code></pre></div>
  1342. <h4 id="53">5.3 说明<a class="headerlink" href="#53" title="Permanent link">¶</a></h4>
  1343. <ul>
  1344. <li><strong>Redis 连接</strong>:通过 config.ini 读取 Redis 配置,使用 redis.StrictRedis 建立连接。</li>
  1345. <li><strong>数据操作</strong>: </li>
  1346. <li>set_data:将键值对(值序列化为 JSON)存储到 Redis。</li>
  1347. <li>get_data:根据键获取值并反序列化 JSON。</li>
  1348. <li>get_answer:查询以 answer:{query} 格式存储的答案缓存。</li>
  1349. </ul>
  1350. <h3 id="6">6 文本预处理模块<a class="headerlink" href="#6" title="Permanent link">¶</a></h3>
  1351. <h4 id="61">6.1 功能<a class="headerlink" href="#61" title="Permanent link">¶</a></h4>
  1352. <p><code>preprocess.py</code>是一个基于 jieba 分词库实现文本预处理的模块。该模块将输入文本转换为小写并进行分词,返回分词结果,支持日志记录以监控处理状态。</p>
  1353. <h4 id="62">6.2 代码实现<a class="headerlink" href="#62" title="Permanent link">¶</a></h4>
  1354. <div class="highlight"><pre><span></span><code><span class="c1"># utils/preprocess.py</span>
  1355. <span class="c1"># 导入分词库</span>
  1356. <span class="kn">import</span><span class="w"> </span><span class="nn">jieba</span>
  1357. <span class="c1"># 导入日志</span>
  1358. <span class="kn">from</span><span class="w"> </span><span class="nn">base</span><span class="w"> </span><span class="kn">import</span> <span class="n">logger</span>
  1359. <span class="k">def</span><span class="w"> </span><span class="nf">preprocess_text</span><span class="p">(</span><span class="n">text</span><span class="p">):</span>
  1360. <span class="c1"># 预处理文本</span>
  1361. <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"开始预处理文本"</span><span class="p">)</span>
  1362. <span class="k">try</span><span class="p">:</span>
  1363. <span class="c1"># 分词并转换为小写</span>
  1364. <span class="k">return</span> <span class="n">jieba</span><span class="o">.</span><span class="n">lcut</span><span class="p">(</span><span class="n">text</span><span class="o">.</span><span class="n">lower</span><span class="p">())</span>
  1365. <span class="k">except</span> <span class="ne">AttributeError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1366. <span class="c1"># 记录预处理失败</span>
  1367. <span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"文本预处理失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1368. <span class="c1"># 返回空列表</span>
  1369. <span class="k">return</span> <span class="p">[]</span>
  1370. </code></pre></div>
  1371. <h4 id="63">6.3 说明<a class="headerlink" href="#63" title="Permanent link">¶</a></h4>
  1372. <ul>
  1373. <li><strong>文本处理</strong>:使用 jieba.lcut 对输入文本进行中文分词,并将文本转换为小写以规范化。</li>
  1374. </ul>
  1375. <h3 id="7-bm25softmax">7 BM25+Softmax检索模块<a class="headerlink" href="#7-bm25softmax" title="Permanent link">¶</a></h3>
  1376. <h4 id="71">7.1 功能<a class="headerlink" href="#71" title="Permanent link">¶</a></h4>
  1377. <p><code>bm25_search.py</code> 是一个基于 BM25 算法和 Softmax 归一化的文本检索模块,用于从问题库中检索与查询最匹配的答案。模块结合 Redis 缓存和 MySQL 数据库,支持问题加载、分词、BM25 评分、Softmax 归一化,并记录操作日志。</p>
  1378. <div class="highlight"><pre><span></span><code><span class="c1"># retrieval/bm25_search.py</span>
  1379. <span class="c1"># 导入 BM25 算法</span>
  1380. <span class="kn">from</span><span class="w"> </span><span class="nn">rank_bm25</span><span class="w"> </span><span class="kn">import</span> <span class="n">BM25Okapi</span>
  1381. <span class="c1"># 导入数值计算库</span>
  1382. <span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span>
  1383. <span class="c1"># 导入文本预处理</span>
  1384. <span class="kn">from</span><span class="w"> </span><span class="nn">utils.preprocess</span><span class="w"> </span><span class="kn">import</span> <span class="n">preprocess_text</span>
  1385. <span class="c1"># 导入日志</span>
  1386. <span class="kn">from</span><span class="w"> </span><span class="nn">base</span><span class="w"> </span><span class="kn">import</span> <span class="n">logger</span>
  1387. <span class="k">class</span><span class="w"> </span><span class="nc">BM25Search</span><span class="p">:</span>
  1388. <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">redis_client</span><span class="p">,</span> <span class="n">mysql_client</span><span class="p">):</span>
  1389. <span class="c1"># 初始化日志</span>
  1390. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
  1391. <span class="c1"># 初始化 Redis 客户端</span>
  1392. <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span> <span class="o">=</span> <span class="n">redis_client</span>
  1393. <span class="c1"># 初始化 MySQL 客户端</span>
  1394. <span class="bp">self</span><span class="o">.</span><span class="n">mysql_client</span> <span class="o">=</span> <span class="n">mysql_client</span>
  1395. <span class="c1"># 初始化 BM25 模型</span>
  1396. <span class="bp">self</span><span class="o">.</span><span class="n">bm25</span> <span class="o">=</span> <span class="kc">None</span>
  1397. <span class="c1"># 初始化问题列表</span>
  1398. <span class="bp">self</span><span class="o">.</span><span class="n">questions</span> <span class="o">=</span> <span class="kc">None</span>
  1399. <span class="c1"># 初始化原始问题</span>
  1400. <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span> <span class="o">=</span> <span class="kc">None</span>
  1401. <span class="c1"># 加载数据</span>
  1402. <span class="bp">self</span><span class="o">.</span><span class="n">_load_data</span><span class="p">()</span>
  1403. <span class="k">def</span><span class="w"> </span><span class="nf">_load_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  1404. <span class="c1"># 加载数据</span>
  1405. <span class="n">original_key</span> <span class="o">=</span> <span class="s2">"qa_original_questions"</span>
  1406. <span class="n">tokenized_key</span> <span class="o">=</span> <span class="s2">"qa_tokenized_questions"</span>
  1407. <span class="c1"># 从 Redis 获取原始问题</span>
  1408. <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span><span class="o">.</span><span class="n">get_data</span><span class="p">(</span><span class="n">original_key</span><span class="p">)</span>
  1409. <span class="c1"># 从 Redis 获取分词问题</span>
  1410. <span class="n">tokenized_questions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span><span class="o">.</span><span class="n">get_data</span><span class="p">(</span><span class="n">tokenized_key</span><span class="p">)</span>
  1411. <span class="c1"># 如果 Redis 中没有数据,从 MySQL 加载</span>
  1412. <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">tokenized_questions</span><span class="p">:</span>
  1413. <span class="c1"># 从 MySQL 获取问题</span>
  1414. <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mysql_client</span><span class="o">.</span><span class="n">fetch_questions</span><span class="p">()</span>
  1415. <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span><span class="p">:</span>
  1416. <span class="c1"># 记录无问题警告</span>
  1417. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">"未加载到问题"</span><span class="p">)</span>
  1418. <span class="k">return</span>
  1419. <span class="c1"># 分词问题</span>
  1420. <span class="n">tokenized_questions</span> <span class="o">=</span> <span class="p">[</span><span class="n">preprocess_text</span><span class="p">(</span><span class="n">q</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="k">for</span> <span class="n">q</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span><span class="p">]</span>
  1421. <span class="c1"># 存储原始问题到 Redis</span>
  1422. <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span><span class="o">.</span><span class="n">set_data</span><span class="p">(</span><span class="n">original_key</span><span class="p">,</span> <span class="p">[(</span><span class="n">q</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="k">for</span> <span class="n">q</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span><span class="p">])</span>
  1423. <span class="c1"># 存储分词问题到 Redis</span>
  1424. <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span><span class="o">.</span><span class="n">set_data</span><span class="p">(</span><span class="n">tokenized_key</span><span class="p">,</span> <span class="n">tokenized_questions</span><span class="p">)</span>
  1425. <span class="c1"># 设置问题列表</span>
  1426. <span class="bp">self</span><span class="o">.</span><span class="n">questions</span> <span class="o">=</span> <span class="n">tokenized_questions</span>
  1427. <span class="c1"># 初始化 BM25 模型</span>
  1428. <span class="bp">self</span><span class="o">.</span><span class="n">bm25</span> <span class="o">=</span> <span class="n">BM25Okapi</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">questions</span><span class="p">)</span>
  1429. <span class="c1"># 记录 BM25 初始化成功</span>
  1430. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"BM25 模型初始化完成"</span><span class="p">)</span>
  1431. <span class="k">def</span><span class="w"> </span><span class="nf">_softmax</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">scores</span><span class="p">):</span>
  1432. <span class="c1"># 计算 Softmax 分数</span>
  1433. <span class="n">exp_scores</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="n">scores</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">scores</span><span class="p">))</span>
  1434. <span class="c1"># 返回归一化分数</span>
  1435. <span class="k">return</span> <span class="n">exp_scores</span> <span class="o">/</span> <span class="n">exp_scores</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
  1436. <span class="k">def</span><span class="w"> </span><span class="nf">search</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">threshold</span><span class="o">=</span><span class="mf">0.85</span><span class="p">):</span>
  1437. <span class="c1"># 搜索查询</span>
  1438. <span class="k">if</span> <span class="ow">not</span> <span class="n">query</span> <span class="ow">or</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
  1439. <span class="c1"># 记录无效查询</span>
  1440. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"无效查询"</span><span class="p">)</span>
  1441. <span class="c1"># 返回 None 和 False</span>
  1442. <span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">False</span>
  1443. <span class="c1"># 检查 Redis 缓存</span>
  1444. <span class="n">cached_answer</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span><span class="o">.</span><span class="n">get_answer</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
  1445. <span class="k">if</span> <span class="n">cached_answer</span><span class="p">:</span>
  1446. <span class="c1"># 返回缓存答案</span>
  1447. <span class="k">return</span> <span class="n">cached_answer</span><span class="p">,</span> <span class="kc">False</span>
  1448. <span class="k">try</span><span class="p">:</span>
  1449. <span class="c1"># 分词查询</span>
  1450. <span class="n">query_tokens</span> <span class="o">=</span> <span class="n">preprocess_text</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
  1451. <span class="c1"># 计算 BM25 分数</span>
  1452. <span class="n">scores</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bm25</span><span class="o">.</span><span class="n">get_scores</span><span class="p">(</span><span class="n">query_tokens</span><span class="p">)</span>
  1453. <span class="c1"># 计算 Softmax 分数</span>
  1454. <span class="n">softmax_scores</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_softmax</span><span class="p">(</span><span class="n">scores</span><span class="p">)</span>
  1455. <span class="c1"># 获取最高分索引</span>
  1456. <span class="n">best_idx</span> <span class="o">=</span> <span class="n">softmax_scores</span><span class="o">.</span><span class="n">argmax</span><span class="p">()</span>
  1457. <span class="c1"># 获取最高分</span>
  1458. <span class="n">best_score</span> <span class="o">=</span> <span class="n">softmax_scores</span><span class="p">[</span><span class="n">best_idx</span><span class="p">]</span>
  1459. <span class="c1"># 检查是否超过阈值</span>
  1460. <span class="k">if</span> <span class="n">best_score</span> <span class="o">&gt;=</span> <span class="n">threshold</span><span class="p">:</span>
  1461. <span class="c1"># 获取原始问题</span>
  1462. <span class="n">original_question</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span><span class="p">[</span><span class="n">best_idx</span><span class="p">]</span>
  1463. <span class="c1"># 获取答案</span>
  1464. <span class="n">redis_result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span><span class="o">.</span><span class="n">get_answer</span><span class="p">(</span><span class="n">original_question</span><span class="p">)</span>
  1465. <span class="c1"># 获取答案</span>
  1466. <span class="k">if</span> <span class="n">redis_result</span><span class="p">:</span>
  1467. <span class="n">answer</span> <span class="o">=</span> <span class="n">redis_result</span>
  1468. <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="s1">'从redis中获取到了问题的答案:</span><span class="si">{</span><span class="n">answer</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
  1469. <span class="k">else</span><span class="p">:</span>
  1470. <span class="n">answer</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mysql_client</span><span class="o">.</span><span class="n">fetch_answer</span><span class="p">(</span><span class="n">original_question</span><span class="p">)</span>
  1471. <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="s1">'从mysql中获取到了问题的答案:</span><span class="si">{</span><span class="n">answer</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span>
  1472. <span class="k">if</span> <span class="n">answer</span><span class="p">:</span>
  1473. <span class="c1"># 缓存答案</span>
  1474. <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span><span class="o">.</span><span class="n">set_data</span><span class="p">(</span><span class="sa">f</span><span class="s2">"answer:</span><span class="si">{</span><span class="n">query</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">answer</span><span class="p">)</span>
  1475. <span class="c1"># 记录搜索成功</span>
  1476. <span class="bp">self</span><span class="o">.</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">"搜索成功,Softmax 相似度: </span><span class="si">{</span><span class="n">best_score</span><span class="si">:</span><span class="s2">.3f</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1477. <span class="c1"># 返回答案和 False</span>
  1478. <span class="k">return</span> <span class="n">answer</span><span class="p">,</span> <span class="kc">False</span>
  1479. <span class="c1"># 记录无可靠答案</span>
  1480. <span class="bp">self</span><span class="o">.</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">"未找到可靠答案,最高 Softmax 相似度: </span><span class="si">{</span><span class="n">best_score</span><span class="si">:</span><span class="s2">.3f</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1481. <span class="c1"># 返回 None 和 True</span>
  1482. <span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">True</span>
  1483. <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1484. <span class="c1"># 记录搜索失败</span>
  1485. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"搜索失败: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1486. <span class="c1"># 返回 None 和 True</span>
  1487. <span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">True</span>
  1488. </code></pre></div>
  1489. <h4 id="72">7.2 说明<a class="headerlink" href="#72" title="Permanent link">¶</a></h4>
  1490. <ul>
  1491. <li><strong>数据加载</strong>:优先从 Redis 获取问题和分词数据,若无则从 MySQL 加载并分词后缓存到 Redis。</li>
  1492. <li><strong>BM25 检索</strong>:使用 BM25Okapi 计算查询与问题库的相似度,结合 Softmax 归一化评分。</li>
  1493. <li><strong>答案查询</strong>:通过 Redis 缓存答案,若无缓存则从 MySQL 获取并缓存,阈值(默认 0.85)控制答案可靠性。</li>
  1494. </ul>
  1495. <h2 id="mainpy">三、主程序 (<code>main.py</code>)<a class="headerlink" href="#mainpy" title="Permanent link">¶</a></h2>
  1496. <h3 id="1_1">1 代码<a class="headerlink" href="#1_1" title="Permanent link">¶</a></h3>
  1497. <div class="highlight"><pre><span></span><code><span class="c1"># 导入 MySQL 客户端</span>
  1498. <span class="kn">from</span><span class="w"> </span><span class="nn">db.mysql_client</span><span class="w"> </span><span class="kn">import</span> <span class="n">MySQLClient</span>
  1499. <span class="c1"># 导入 Redis 客户端</span>
  1500. <span class="kn">from</span><span class="w"> </span><span class="nn">cache.redis_client</span><span class="w"> </span><span class="kn">import</span> <span class="n">RedisClient</span>
  1501. <span class="c1"># 导入 BM25 搜索</span>
  1502. <span class="kn">from</span><span class="w"> </span><span class="nn">retrieval.bm25_search</span><span class="w"> </span><span class="kn">import</span> <span class="n">BM25Search</span>
  1503. <span class="c1"># 导入日志</span>
  1504. <span class="kn">from</span><span class="w"> </span><span class="nn">base</span><span class="w"> </span><span class="kn">import</span> <span class="n">logger</span>
  1505. <span class="c1"># 导入时间库</span>
  1506. <span class="kn">import</span><span class="w"> </span><span class="nn">time</span>
  1507. <span class="k">class</span><span class="w"> </span><span class="nc">MySQLQASystem</span><span class="p">:</span>
  1508. <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>
  1509. <span class="c1"># 初始化日志</span>
  1510. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
  1511. <span class="c1"># 初始化 MySQL 客户端</span>
  1512. <span class="bp">self</span><span class="o">.</span><span class="n">mysql_client</span> <span class="o">=</span> <span class="n">MySQLClient</span><span class="p">()</span>
  1513. <span class="c1"># 初始化 Redis 客户端</span>
  1514. <span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span> <span class="o">=</span> <span class="n">RedisClient</span><span class="p">()</span>
  1515. <span class="c1"># 初始化 BM25 搜索</span>
  1516. <span class="bp">self</span><span class="o">.</span><span class="n">bm25_search</span> <span class="o">=</span> <span class="n">BM25Search</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">redis_client</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">mysql_client</span><span class="p">)</span>
  1517. <span class="k">def</span><span class="w"> </span><span class="nf">query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span>
  1518. <span class="c1"># 查询 MySQL 系统</span>
  1519. <span class="n">start_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
  1520. <span class="c1"># 记录查询信息</span>
  1521. <span class="bp">self</span><span class="o">.</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">"处理查询: '</span><span class="si">{</span><span class="n">query</span><span class="si">}</span><span class="s2">'"</span><span class="p">)</span>
  1522. <span class="c1"># 执行 BM25 搜索</span>
  1523. <span class="n">answer</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bm25_search</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">threshold</span><span class="o">=</span><span class="mf">0.85</span><span class="p">)</span>
  1524. <span class="k">if</span> <span class="n">answer</span><span class="p">:</span>
  1525. <span class="c1"># 记录 MySQL 答案</span>
  1526. <span class="bp">self</span><span class="o">.</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">"MySQL 答案: </span><span class="si">{</span><span class="n">answer</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1527. <span class="k">else</span><span class="p">:</span>
  1528. <span class="c1"># 记录无答案</span>
  1529. <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"SQL中未找到答案, 需要调用RAG系统"</span><span class="p">)</span>
  1530. <span class="c1"># 设置默认答案</span>
  1531. <span class="n">answer</span> <span class="o">=</span> <span class="s2">"SQL未找到答案"</span>
  1532. <span class="c1"># 计算处理时间</span>
  1533. <span class="n">processing_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">start_time</span>
  1534. <span class="c1"># 记录处理时间</span>
  1535. <span class="bp">self</span><span class="o">.</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">"查询处理耗时 </span><span class="si">{</span><span class="n">processing_time</span><span class="si">:</span><span class="s2">.2f</span><span class="si">}</span><span class="s2">秒"</span><span class="p">)</span>
  1536. <span class="c1"># 返回答案</span>
  1537. <span class="k">return</span> <span class="n">answer</span>
  1538. <span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
  1539. <span class="c1"># 初始化 MySQL 系统</span>
  1540. <span class="n">mysql_system</span> <span class="o">=</span> <span class="n">MySQLQASystem</span><span class="p">()</span>
  1541. <span class="k">try</span><span class="p">:</span>
  1542. <span class="c1"># 打印欢迎信息</span>
  1543. <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">欢迎使用 MySQL 问答系统!"</span><span class="p">)</span>
  1544. <span class="nb">print</span><span class="p">(</span><span class="s2">"输入查询进行问答,输入 'exit' 退出。"</span><span class="p">)</span>
  1545. <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
  1546. <span class="c1"># 获取用户输入</span>
  1547. <span class="n">query</span> <span class="o">=</span> <span class="nb">input</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">输入查询: "</span><span class="p">)</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
  1548. <span class="k">if</span> <span class="n">query</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="s2">"exit"</span><span class="p">:</span>
  1549. <span class="c1"># 记录退出日志</span>
  1550. <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"退出 MySQL 系统"</span><span class="p">)</span>
  1551. <span class="c1"># 打印退出信息</span>
  1552. <span class="nb">print</span><span class="p">(</span><span class="s2">"再见!"</span><span class="p">)</span>
  1553. <span class="k">break</span>
  1554. <span class="c1"># 执行查询</span>
  1555. <span class="n">answer</span> <span class="o">=</span> <span class="n">mysql_system</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
  1556. <span class="c1"># 打印答案</span>
  1557. <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\n</span><span class="s2">答案: </span><span class="si">{</span><span class="n">answer</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1558. <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  1559. <span class="c1"># 记录系统错误</span>
  1560. <span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="sa">f</span><span class="s2">"系统错误: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1561. <span class="c1"># 打印错误信息</span>
  1562. <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"发生错误: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
  1563. <span class="k">finally</span><span class="p">:</span>
  1564. <span class="c1"># 关闭 MySQL 连接</span>
  1565. <span class="n">mysql_system</span><span class="o">.</span><span class="n">mysql_client</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
  1566. <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span>
  1567. <span class="c1"># 运行主程序</span>
  1568. <span class="n">main</span><span class="p">()</span>
  1569. </code></pre></div>
  1570. <hr>
  1571. <h3 id="2_2">2 示例运行结果<a class="headerlink" href="#2_2" title="Permanent link">¶</a></h3>
  1572. <p>假设MySQL中有数据:
  1573. - 问题:"特殊符号如何切割",答案:"使用split函数"
  1574. - 问题:"如何处理字符串",答案:"使用字符串方法"</p>
  1575. <p>查询:"特殊符号的切割"
  1576. </p><div class="highlight"><pre><span></span><code>2025-04-01 10:00:00,123 - INFO - MySQL连接成功
  1577. 2025-04-01 10:00:00,125 - INFO - Redis连接成功
  1578. 2025-04-01 10:00:00,126 - INFO - BM25模型初始化完成
  1579. 欢迎使用 MySQL 问答系统!
  1580. 输入查询进行问答,输入 'exit' 退出。
  1581. 2025-04-01 10:00:00,127 - INFO - 检索成功,Softmax相似度: 0.892
  1582. 2025-04-01 10:00:00,128 - INFO - 数据存入Redis: answer:特殊符号的切割
  1583. 2025-04-01 10:00:00,129 - INFO - MySQL答案: 使用split函数
  1584. 2025-04-01 10:00:00,130 - INFO - MySQL连接已关闭
  1585. </code></pre></div>
  1586. <hr>
  1587. <h2 id="_3">本章小结<a class="headerlink" href="#_3" title="Permanent link">¶</a></h2>
  1588. <p>本章整合Mysql和Redis功能,实现了基于余弦相似度问答的QA系统:</p>
  1589. <ul>
  1590. <li><strong>流程</strong>:MySQL存储数据,Redis缓存优化,TF-IDF和余弦相似度匹配问题。</li>
  1591. <li><strong>工程化</strong>:模块化设计、配置文件、日志记录。</li>
  1592. </ul>
  1593. </article>
  1594. </div>
  1595. <script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
  1596. </div>
  1597. </main>
  1598. <footer class="md-footer">
  1599. <div class="md-footer-meta md-typeset">
  1600. <div class="md-footer-meta__inner md-grid">
  1601. <div class="md-copyright">
  1602. <div class="md-copyright__highlight">
  1603. © EnterpriseKB-RAG 2026. Internal knowledge base demo site.
  1604. </div>
  1605. Made with
  1606. <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
  1607. Material for MkDocs
  1608. </a>
  1609. </div>
  1610. </div>
  1611. </div>
  1612. </footer>
  1613. </div>
  1614. <div class="md-dialog" data-md-component="dialog">
  1615. <div class="md-dialog__inner md-typeset"></div>
  1616. </div>
  1617. <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>
  1618. <script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
  1619. <script src="../javascripts/extra.js"></script>
  1620. <script src="../javascripts/mathjax.js"></script>
  1621. <!-- <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script>-->
  1622. <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
  1623. </body>
  1624. </html>