| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683 |
- <!doctype html>
- <html lang="zh" class="no-js">
- <head>
-
- <meta charset="utf-8">
- <meta name="viewport" content="width=device-width,initial-scale=1">
-
-
-
-
- <link rel="prev" href="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">
-
-
- <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">
-
-
- <link rel="icon" href="../img/AI.jpg">
- <meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.21">
-
-
-
- <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>
-
-
-
- <link rel="stylesheet" href="../assets/stylesheets/main.2a3383ac.min.css">
-
-
-
-
-
-
-
-
-
-
- <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
- <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
- <style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
-
-
-
- <link rel="stylesheet" href="../stylesheets/extra.css">
-
- <script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
-
-
-
-
-
- </head>
-
-
- <body dir="ltr">
-
-
- <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
- <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
- <label class="md-overlay" for="__drawer"></label>
- <div data-md-component="skip">
-
-
- <a href="#_1" class="md-skip">
- 跳转至
- </a>
-
- </div>
- <div data-md-component="announce">
-
- </div>
-
-
-
-
- <header class="md-header md-header--shadow" data-md-component="header">
- <nav class="md-header__inner md-grid" aria-label="页眉">
- <a href="../index.html" title="企业知识库RAG智能问答项目V1.0" class="md-header__button md-logo" aria-label="企业知识库RAG智能问答项目V1.0" data-md-component="logo">
-
- <img src="../img/AI.jpg" alt="logo">
- </a>
- <label class="md-header__button md-icon" for="__drawer">
-
- <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
- </label>
- <div class="md-header__title" data-md-component="header-title">
- <div class="md-header__ellipsis">
- <div class="md-header__topic">
- <span class="md-ellipsis">
- 企业知识库RAG智能问答项目V1.0
- </span>
- </div>
- <div class="md-header__topic" data-md-component="header-topic">
- <span class="md-ellipsis">
-
- 3.3 基于Mysql数据库实现问答系统
-
- </span>
- </div>
- </div>
- </div>
-
-
- <script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
-
-
-
-
-
- <label class="md-header__button md-icon" for="__search">
-
- <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
- </label>
- <div class="md-search" data-md-component="search" role="dialog">
- <label class="md-search__overlay" for="__search"></label>
- <div class="md-search__inner" role="search">
- <form class="md-search__form" name="search">
- <input type="text" class="md-search__input" name="query" aria-label="搜索" placeholder="搜索" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
- <label class="md-search__icon md-icon" for="__search">
-
- <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
-
- <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
- </label>
- <nav class="md-search__options" aria-label="查找">
-
- <button type="reset" class="md-search__icon md-icon" title="清空当前内容" aria-label="清空当前内容" tabindex="-1">
-
- <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
- </button>
- </nav>
-
- </form>
- <div class="md-search__output">
- <div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
- <div class="md-search-result" data-md-component="search-result">
- <div class="md-search-result__meta">
- 正在初始化搜索引擎
- </div>
- <ol class="md-search-result__list" role="presentation"></ol>
- </div>
- </div>
- </div>
- </div>
- </div>
-
-
-
- </nav>
-
- </header>
-
- <div class="md-container" data-md-component="container">
-
-
-
-
-
-
- <main class="md-main" data-md-component="main">
- <div class="md-main__inner md-grid">
-
-
-
- <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
- <div class="md-sidebar__scrollwrap">
- <div class="md-sidebar__inner">
-
- <nav class="md-nav md-nav--primary" aria-label="导航栏" data-md-level="0">
- <label class="md-nav__title" for="__drawer">
- <a href="../index.html" title="企业知识库RAG智能问答项目V1.0" class="md-nav__button md-logo" aria-label="企业知识库RAG智能问答项目V1.0" data-md-component="logo">
-
- <img src="../img/AI.jpg" alt="logo">
- </a>
- 企业知识库RAG智能问答项目V1.0
- </label>
-
- <ul class="md-nav__list" data-md-scrollfix>
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../index.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 知识库内容
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item md-nav__item--nested">
-
-
-
- <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
-
-
- <label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
-
-
-
- <span class="md-ellipsis">
- ① 项目概述
-
- </span>
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
- <label class="md-nav__title" for="__nav_2">
- <span class="md-nav__icon md-icon"></span>
- ① 项目概述
- </label>
- <ul class="md-nav__list" data-md-scrollfix>
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A0%20%E9%A1%B9%E7%9B%AE%E6%A6%82%E8%BF%B0/1.1%20%E9%A1%B9%E7%9B%AE%E6%9E%B6%E6%9E%84.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 1.1 项目架构
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A0%20%E9%A1%B9%E7%9B%AE%E6%A6%82%E8%BF%B0/1.2%20%E9%A1%B9%E7%9B%AE%E7%8E%AF%E5%A2%83%28window%29.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 1.2 项目环境(window)
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A0%20%E9%A1%B9%E7%9B%AE%E6%A6%82%E8%BF%B0/1.3%20%E9%A1%B9%E7%9B%AE%E7%8E%AF%E5%A2%83%28mac%29.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 1.3 项目环境(mac)
-
- </span>
-
- </a>
- </li>
-
-
-
- </ul>
- </nav>
-
- </li>
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item md-nav__item--nested">
-
-
-
- <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" >
-
-
- <label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
-
-
-
- <span class="md-ellipsis">
- ② 项目工具
-
- </span>
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
- <label class="md-nav__title" for="__nav_3">
- <span class="md-nav__icon md-icon"></span>
- ② 项目工具
- </label>
- <ul class="md-nav__list" data-md-scrollfix>
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A1%20%E9%A1%B9%E7%9B%AE%E5%B7%A5%E5%85%B7/2.1%20Ollama%E5%A4%A7%E6%A8%A1%E5%9E%8B%E9%AB%98%E6%95%88%E7%AE%A1%E7%90%86%E5%B7%A5%E5%85%B7.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 2.1 Ollama大模型高效管理工具
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A1%20%E9%A1%B9%E7%9B%AE%E5%B7%A5%E5%85%B7/2.2%20LangChain%E5%9F%BA%E7%A1%80%E7%9F%A5%E8%AF%86.md.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 2.2 LangChain基础知识.md
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A1%20%E9%A1%B9%E7%9B%AE%E5%B7%A5%E5%85%B7/2.3%20%E5%90%91%E9%87%8F%E7%B4%A2%E5%BC%95%EF%BC%9AHNSW%E3%80%81IVF%E4%B8%8EIVF_PQ.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 2.3 向量索引:HNSW、IVF与IVF_PQ
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A1%20%E9%A1%B9%E7%9B%AE%E5%B7%A5%E5%85%B7/2.4%20Milvus%E5%90%91%E9%87%8F%E6%95%B0%E6%8D%AE%E5%BA%93.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 2.4 Milvus向量数据库
-
- </span>
-
- </a>
- </li>
-
-
-
- </ul>
- </nav>
-
- </li>
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item md-nav__item--active md-nav__item--nested">
-
-
-
- <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" checked>
-
-
- <label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
-
-
-
- <span class="md-ellipsis">
- ③ 基于Mysql库的问答系统
-
- </span>
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="true">
- <label class="md-nav__title" for="__nav_4">
- <span class="md-nav__icon md-icon"></span>
- ③ 基于Mysql库的问答系统
- </label>
- <ul class="md-nav__list" data-md-scrollfix>
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="3.1%20Python%E6%97%A5%E5%BF%97%E4%BB%8B%E7%BB%8D%E4%B8%8E%E5%BA%94%E7%94%A8.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 3.1 Python日志介绍与应用
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="3.2%20Redis%E6%95%B0%E6%8D%AE%E5%BA%93%E7%AE%80%E4%BB%8B%E4%B8%8E%E4%BD%BF%E7%94%A8.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 3.2 Redis数据库简介与使用
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item md-nav__item--active">
-
- <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
-
-
-
- <label class="md-nav__link md-nav__link--active" for="__toc">
-
-
-
- <span class="md-ellipsis">
- 3.3 基于Mysql数据库实现问答系统
-
- </span>
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <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">
-
-
-
- <span class="md-ellipsis">
- 3.3 基于Mysql数据库实现问答系统
-
- </span>
-
- </a>
-
-
- <nav class="md-nav md-nav--secondary" aria-label="目录">
-
-
-
-
- <label class="md-nav__title" for="__toc">
- <span class="md-nav__icon md-icon"></span>
- 目录
- </label>
- <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
-
- <li class="md-nav__item">
- <a href="#_1" class="md-nav__link">
- <span class="md-ellipsis">
- 学习目标
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#fqa" class="md-nav__link">
- <span class="md-ellipsis">
- 一、FQA系统概述
- </span>
- </a>
-
- <nav class="md-nav" aria-label="一、FQA系统概述">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#1" class="md-nav__link">
- <span class="md-ellipsis">
- 1 系统流程
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#2" class="md-nav__link">
- <span class="md-ellipsis">
- 2 项目结构
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_2" class="md-nav__link">
- <span class="md-ellipsis">
- 三、代码实现
- </span>
- </a>
-
- <nav class="md-nav" aria-label="三、代码实现">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#1-configini" class="md-nav__link">
- <span class="md-ellipsis">
- 1 配置文件 (config.ini)
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#2_1" class="md-nav__link">
- <span class="md-ellipsis">
- 2 配置管理
- </span>
- </a>
-
- <nav class="md-nav" aria-label="2 配置管理">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#21" class="md-nav__link">
- <span class="md-ellipsis">
- 2.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#22" class="md-nav__link">
- <span class="md-ellipsis">
- 2.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#23" class="md-nav__link">
- <span class="md-ellipsis">
- 2.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#3" class="md-nav__link">
- <span class="md-ellipsis">
- 3 日志记录
- </span>
- </a>
-
- <nav class="md-nav" aria-label="3 日志记录">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#31" class="md-nav__link">
- <span class="md-ellipsis">
- 3.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#32" class="md-nav__link">
- <span class="md-ellipsis">
- 3.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#33" class="md-nav__link">
- <span class="md-ellipsis">
- 3.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#4-mysql" class="md-nav__link">
- <span class="md-ellipsis">
- 4 MySQL操作模块
- </span>
- </a>
-
- <nav class="md-nav" aria-label="4 MySQL操作模块">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#41" class="md-nav__link">
- <span class="md-ellipsis">
- 4.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#42" class="md-nav__link">
- <span class="md-ellipsis">
- 4.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#43" class="md-nav__link">
- <span class="md-ellipsis">
- 4.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#5-redis" class="md-nav__link">
- <span class="md-ellipsis">
- 5 Redis 缓存操作模块
- </span>
- </a>
-
- <nav class="md-nav" aria-label="5 Redis 缓存操作模块">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#51" class="md-nav__link">
- <span class="md-ellipsis">
- 5.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#52" class="md-nav__link">
- <span class="md-ellipsis">
- 5.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#53" class="md-nav__link">
- <span class="md-ellipsis">
- 5.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#6" class="md-nav__link">
- <span class="md-ellipsis">
- 6 文本预处理模块
- </span>
- </a>
-
- <nav class="md-nav" aria-label="6 文本预处理模块">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#61" class="md-nav__link">
- <span class="md-ellipsis">
- 6.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#62" class="md-nav__link">
- <span class="md-ellipsis">
- 6.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#63" class="md-nav__link">
- <span class="md-ellipsis">
- 6.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#7-bm25softmax" class="md-nav__link">
- <span class="md-ellipsis">
- 7 BM25+Softmax检索模块
- </span>
- </a>
-
- <nav class="md-nav" aria-label="7 BM25+Softmax检索模块">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#71" class="md-nav__link">
- <span class="md-ellipsis">
- 7.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#72" class="md-nav__link">
- <span class="md-ellipsis">
- 7.2 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#mainpy" class="md-nav__link">
- <span class="md-ellipsis">
- 三、主程序 (main.py)
- </span>
- </a>
-
- <nav class="md-nav" aria-label="三、主程序 (main.py)">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#1_1" class="md-nav__link">
- <span class="md-ellipsis">
- 1 代码
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#2_2" class="md-nav__link">
- <span class="md-ellipsis">
- 2 示例运行结果
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_3" class="md-nav__link">
- <span class="md-ellipsis">
- 本章小结
- </span>
- </a>
-
- </li>
-
- </ul>
-
- </nav>
-
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="3.4%20BM25%E7%AE%97%E6%B3%95%E7%AE%80%E4%BB%8B%E4%B8%8E%E5%BA%94%E7%94%A8.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 3.4 BM25算法简介与应用
-
- </span>
-
- </a>
- </li>
-
-
-
- </ul>
- </nav>
-
- </li>
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item md-nav__item--nested">
-
-
-
- <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" >
-
-
- <label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
-
-
-
- <span class="md-ellipsis">
- ④ 基于Milvus库的问答系统
-
- </span>
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
- <label class="md-nav__title" for="__nav_5">
- <span class="md-nav__icon md-icon"></span>
- ④ 基于Milvus库的问答系统
- </label>
- <ul class="md-nav__list" data-md-scrollfix>
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%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">
-
-
-
- <span class="md-ellipsis">
- 4.1 整体架构与工程流程
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%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">
-
-
-
- <span class="md-ellipsis">
- 4.2 基础模块
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <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/4.3%20%E6%96%87%E6%A1%A3%E5%A4%84%E7%90%86%E6%A8%A1%E5%9D%97.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 4.3 文档处理模块
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%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">
-
-
-
- <span class="md-ellipsis">
- 4.4 向量存储
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <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%20prompts%E8%AE%BE%E8%AE%A1%E4%B8%8Equery%E6%84%8F%E5%9B%BE%E8%AF%86%E5%88%AB.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 4.5 prompts设计与query意图识别
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%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%20%E6%A3%80%E7%B4%A2%E7%AD%96%E7%95%A5%E4%B8%8ERAG%E7%B3%BB%E7%BB%9F%E8%AE%BE%E8%AE%A1.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 4.6 检索策略与RAG系统设计
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%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%20RAG%E7%B3%BB%E7%BB%9F%E8%BF%90%E8%A1%8C.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 4.7 RAG系统运行
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%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%20%E6%96%87%E6%A1%A3%E8%A7%A3%E6%9E%90%E5%B7%A5%E5%85%B7%28%E6%89%A9%E5%B1%95%E8%B5%84%E6%96%99%29.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 4.8 文档解析工具(扩展资料)
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%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%20RAG%E4%B8%AD%E7%9A%84Query%E6%94%B9%E5%86%99%28%E6%89%A9%E5%B1%95%E8%B5%84%E6%96%99%29.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 4.9 RAG中的Query改写(扩展资料)
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <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">
-
-
-
- <span class="md-ellipsis">
- 数据集生成与优化(扩展资料)
-
- </span>
-
- </a>
- </li>
-
-
-
- </ul>
- </nav>
-
- </li>
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item md-nav__item--nested">
-
-
-
- <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
-
-
- <label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
-
-
-
- <span class="md-ellipsis">
- ⑤ RAG系统评估
-
- </span>
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
- <label class="md-nav__title" for="__nav_6">
- <span class="md-nav__icon md-icon"></span>
- ⑤ RAG系统评估
- </label>
- <ul class="md-nav__list" data-md-scrollfix>
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A4%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0/5.1%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0%E5%B7%A5%E5%85%B7.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 5.1 RAG系统评估工具
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A4%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0/5.2%20%E5%AE%9E%E7%8E%B0EnterpriseKB-RAG%E7%B3%BB%E7%BB%9F%E7%9A%84%E8%AF%84%E4%BC%B0.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 5.2 实现企业知识库RAG系统的评估
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A4%20RAG%E7%B3%BB%E7%BB%9F%E8%AF%84%E4%BC%B0/5.3%20RAG%E8%AF%84%E4%BC%B0%E6%95%B0%E6%8D%AE%E9%9B%86%E7%9A%84%E6%9E%84%E9%80%A0%28%E6%89%A9%E5%B1%95%29.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 5.3 RAG评估数据集的构造(扩展)
-
- </span>
-
- </a>
- </li>
-
-
-
- </ul>
- </nav>
-
- </li>
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item md-nav__item--nested">
-
-
-
- <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
-
-
- <label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
-
-
-
- <span class="md-ellipsis">
- ⑥ 融合Mysql的RAG系统
-
- </span>
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
- <label class="md-nav__title" for="__nav_7">
- <span class="md-nav__icon md-icon"></span>
- ⑥ 融合Mysql的RAG系统
- </label>
- <ul class="md-nav__list" data-md-scrollfix>
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A5%20%E8%9E%8D%E5%90%88Mysql%E7%9A%84RAG%E7%B3%BB%E7%BB%9F/6.1%20%E8%9E%8D%E5%90%88FQA%E5%92%8C%E7%9F%A5%E8%AF%86%E5%BA%93%E6%9F%A5%E8%AF%A2.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 6.1 融合FQA和知识库查询
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A5%20%E8%9E%8D%E5%90%88Mysql%E7%9A%84RAG%E7%B3%BB%E7%BB%9F/6.2%20%E8%9E%8D%E5%90%88FAQ%20%E5%92%8C%E7%9F%A5%E8%AF%86%E5%BA%93%E6%9F%A5%E8%AF%A2%EF%BC%88%E4%BC%98%E5%8C%96%E7%89%88%EF%BC%89.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 6.2 融合FAQ 和知识库查询(优化版)
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A5%20%E8%9E%8D%E5%90%88Mysql%E7%9A%84RAG%E7%B3%BB%E7%BB%9F/6.3%20%E5%9F%BA%E4%BA%8E%20FastAPI%20%E7%9A%84%20FAQ%20%E4%B8%8E%E7%9F%A5%E8%AF%86%E5%BA%93%E6%9F%A5%E8%AF%A2%E6%8E%A5%E5%8F%A3.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 6.3 基于 FastAPI 的 FAQ 与知识库查询接口
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A5%20%E8%9E%8D%E5%90%88Mysql%E7%9A%84RAG%E7%B3%BB%E7%BB%9F/6.4%20FastAPI%E5%92%8CFlask%E7%9A%84%E5%8C%BA%E5%88%AB%E5%92%8C%E8%81%94%E7%B3%BB%28%E6%89%A9%E5%B1%95%E8%B5%84%E6%96%99%29.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 6.4 FastAPI和Flask的区别和联系(扩展资料)
-
- </span>
-
- </a>
- </li>
-
-
-
- </ul>
- </nav>
-
- </li>
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item md-nav__item--nested">
-
-
-
- <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" >
-
-
- <label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
-
-
-
- <span class="md-ellipsis">
- ⑦ 企业级生产环境部署
-
- </span>
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
- <label class="md-nav__title" for="__nav_8">
- <span class="md-nav__icon md-icon"></span>
- ⑦ 企业级生产环境部署
- </label>
- <ul class="md-nav__list" data-md-scrollfix>
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A6%20%E4%BC%81%E4%B8%9A%E7%BA%A7%E7%94%9F%E4%BA%A7%E7%8E%AF%E5%A2%83%E9%83%A8%E7%BD%B2/7.1%20Docker%E7%9A%84%E5%8E%9F%E7%90%86%E5%92%8C%E5%9F%BA%E6%9C%AC%E4%BD%BF%E7%94%A8.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 7.1 Docker的原理和基本使用
-
- </span>
-
- </a>
- </li>
-
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="../%E2%91%A6%20%E4%BC%81%E4%B8%9A%E7%BA%A7%E7%94%9F%E4%BA%A7%E7%8E%AF%E5%A2%83%E9%83%A8%E7%BD%B2/7.2%20%E6%9C%8D%E5%8A%A1%E9%83%A8%E7%BD%B2.html" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
- 7.2 服务部署
-
- </span>
-
- </a>
- </li>
-
-
-
- </ul>
- </nav>
-
- </li>
-
-
- </ul>
- </nav>
- </div>
- </div>
- </div>
-
-
-
- <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
- <div class="md-sidebar__scrollwrap">
- <div class="md-sidebar__inner">
-
- <nav class="md-nav md-nav--secondary" aria-label="目录">
-
-
-
-
- <label class="md-nav__title" for="__toc">
- <span class="md-nav__icon md-icon"></span>
- 目录
- </label>
- <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
-
- <li class="md-nav__item">
- <a href="#_1" class="md-nav__link">
- <span class="md-ellipsis">
- 学习目标
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#fqa" class="md-nav__link">
- <span class="md-ellipsis">
- 一、FQA系统概述
- </span>
- </a>
-
- <nav class="md-nav" aria-label="一、FQA系统概述">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#1" class="md-nav__link">
- <span class="md-ellipsis">
- 1 系统流程
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#2" class="md-nav__link">
- <span class="md-ellipsis">
- 2 项目结构
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_2" class="md-nav__link">
- <span class="md-ellipsis">
- 三、代码实现
- </span>
- </a>
-
- <nav class="md-nav" aria-label="三、代码实现">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#1-configini" class="md-nav__link">
- <span class="md-ellipsis">
- 1 配置文件 (config.ini)
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#2_1" class="md-nav__link">
- <span class="md-ellipsis">
- 2 配置管理
- </span>
- </a>
-
- <nav class="md-nav" aria-label="2 配置管理">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#21" class="md-nav__link">
- <span class="md-ellipsis">
- 2.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#22" class="md-nav__link">
- <span class="md-ellipsis">
- 2.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#23" class="md-nav__link">
- <span class="md-ellipsis">
- 2.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#3" class="md-nav__link">
- <span class="md-ellipsis">
- 3 日志记录
- </span>
- </a>
-
- <nav class="md-nav" aria-label="3 日志记录">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#31" class="md-nav__link">
- <span class="md-ellipsis">
- 3.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#32" class="md-nav__link">
- <span class="md-ellipsis">
- 3.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#33" class="md-nav__link">
- <span class="md-ellipsis">
- 3.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#4-mysql" class="md-nav__link">
- <span class="md-ellipsis">
- 4 MySQL操作模块
- </span>
- </a>
-
- <nav class="md-nav" aria-label="4 MySQL操作模块">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#41" class="md-nav__link">
- <span class="md-ellipsis">
- 4.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#42" class="md-nav__link">
- <span class="md-ellipsis">
- 4.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#43" class="md-nav__link">
- <span class="md-ellipsis">
- 4.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#5-redis" class="md-nav__link">
- <span class="md-ellipsis">
- 5 Redis 缓存操作模块
- </span>
- </a>
-
- <nav class="md-nav" aria-label="5 Redis 缓存操作模块">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#51" class="md-nav__link">
- <span class="md-ellipsis">
- 5.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#52" class="md-nav__link">
- <span class="md-ellipsis">
- 5.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#53" class="md-nav__link">
- <span class="md-ellipsis">
- 5.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#6" class="md-nav__link">
- <span class="md-ellipsis">
- 6 文本预处理模块
- </span>
- </a>
-
- <nav class="md-nav" aria-label="6 文本预处理模块">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#61" class="md-nav__link">
- <span class="md-ellipsis">
- 6.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#62" class="md-nav__link">
- <span class="md-ellipsis">
- 6.2 代码实现
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#63" class="md-nav__link">
- <span class="md-ellipsis">
- 6.3 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#7-bm25softmax" class="md-nav__link">
- <span class="md-ellipsis">
- 7 BM25+Softmax检索模块
- </span>
- </a>
-
- <nav class="md-nav" aria-label="7 BM25+Softmax检索模块">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#71" class="md-nav__link">
- <span class="md-ellipsis">
- 7.1 功能
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#72" class="md-nav__link">
- <span class="md-ellipsis">
- 7.2 说明
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#mainpy" class="md-nav__link">
- <span class="md-ellipsis">
- 三、主程序 (main.py)
- </span>
- </a>
-
- <nav class="md-nav" aria-label="三、主程序 (main.py)">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#1_1" class="md-nav__link">
- <span class="md-ellipsis">
- 1 代码
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#2_2" class="md-nav__link">
- <span class="md-ellipsis">
- 2 示例运行结果
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_3" class="md-nav__link">
- <span class="md-ellipsis">
- 本章小结
- </span>
- </a>
-
- </li>
-
- </ul>
-
- </nav>
- </div>
- </div>
- </div>
-
-
-
- <div class="md-content" data-md-component="content">
- <article class="md-content__inner md-typeset">
-
-
- <h1>3.3 基于Mysql数据库实现问答系统</h1>
- <h2 id="_1">学习目标<a class="headerlink" href="#_1" title="Permanent link">¶</a></h2>
- <ol>
- <li>理解FQA问答系统的整体流程。</li>
- <li>掌握如何整合MySQL、Redis和BM25算法构建QA问答系统。</li>
- </ol>
- <hr />
- <h2 id="fqa">一、FQA系统概述<a class="headerlink" href="#fqa" title="Permanent link">¶</a></h2>
- <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>0.85且有答案)。若MySQL无可靠答案,则调用RAG系统检索。</p>
- <h3 id="1">1 系统流程<a class="headerlink" href="#1" title="Permanent link">¶</a></h3>
- <ol>
- <li><strong>数据存储</strong>:MySQL存储FQA高频问答对数据。</li>
- <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>
- <li><strong>缓存管理</strong>:Redis仅存储相似度>0.85且有答案的数据。</li>
- <li><strong>答案返回</strong>:</li>
- <li>若MySQL返回可靠答案,直接返回。</li>
- <li>否则,调用RAG系统检索。</li>
- </ol>
- <hr />
- <h3 id="2">2 项目结构<a class="headerlink" href="#2" title="Permanent link">¶</a></h3>
- <div class="highlight"><pre><span></span><code>integrated_qa_system/
- ├── config.ini # 配置文件,包含所有模块的配置
- ├── base/
- │ ├── config.py # 配置管理,加载 config.ini
- │ ├── logger.py # 日志设置
- ├── mysql_qa/
- │ ├── data/
- │ │ ├── JP企业知识库问答.csv # FQA数据集
- │ ├── db/
- │ │ ├── mysql_client.py # MySQL 数据库操作
- │ ├── cache/
- │ │ ├── redis_client.py # Redis 缓存操作
- │ ├── retrieval/
- │ │ ├── bm25_search.py # BM25 搜索
- │ ├── utils/
- │ │ ├── preprocess.py # 文本预处理
- │ ├── main.py # MySQL 系统独立入口,支持查询
- ├── requirements.txt # 依赖文件
- └── logs/
- └── app.log # 日志文件
- </code></pre></div>
- <h2 id="_2">三、代码实现<a class="headerlink" href="#_2" title="Permanent link">¶</a></h2>
- <h3 id="1-configini">1 配置文件 (<code>config.ini</code>)<a class="headerlink" href="#1-configini" title="Permanent link">¶</a></h3>
- <div class="highlight"><pre><span></span><code><span class="c1"># MySQL 配置</span>
- <span class="k">[mysql]</span>
- <span class="na">host</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">localhost</span>
- <span class="na">user</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">root</span>
- <span class="na">password</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">123456</span>
- <span class="na">database</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">subjects_kg</span>
- <span class="c1"># Redis 配置</span>
- <span class="k">[redis]</span>
- <span class="na">host</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">localhost</span>
- <span class="na">port</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">6379</span>
- <span class="na">password</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">1234</span>
- <span class="na">db</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">0</span>
- <span class="c1"># 日志配置</span>
- <span class="k">[logger]</span>
- <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>
- </code></pre></div>
- <h3 id="2_1">2 配置管理<a class="headerlink" href="#2_1" title="Permanent link">¶</a></h3>
- <h4 id="21">2.1 功能<a class="headerlink" href="#21" title="Permanent link">¶</a></h4>
- <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>
- <h4 id="22">2.2 代码实现<a class="headerlink" href="#22" title="Permanent link">¶</a></h4>
- <div class="highlight"><pre><span></span><code><span class="c1"># base/config.py</span>
- <span class="c1"># 导入配置解析库</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">configparser</span>
- <span class="c1"># 导入路径操作库</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
- <span class="k">class</span><span class="w"> </span><span class="nc">Config</span><span class="p">:</span>
- <span class="c1"># 初始化配置,加载 config.ini 文件</span>
- <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">config_file</span><span class="o">=</span><span class="s1">'../config.ini'</span><span class="p">):</span>
- <span class="c1"># 创建配置解析器</span>
- <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>
- <span class="c1"># 读取配置文件</span>
- <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>
- <span class="c1"># MySQL 配置</span>
- <span class="c1"># MySQL 主机地址</span>
- <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>
- <span class="c1"># MySQL 用户名</span>
- <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>
- <span class="c1"># MySQL 密码</span>
- <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>
- <span class="c1"># MySQL 数据库名</span>
- <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>
- <span class="c1"># Redis 配置</span>
- <span class="c1"># Redis 主机地址</span>
- <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>
- <span class="c1"># Redis 端口</span>
- <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>
- <span class="c1"># Redis 密码</span>
- <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>
- <span class="c1"># Redis 数据库编号</span>
- <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>
- <span class="c1"># 日志文件路径</span>
- <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>
- <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
- <span class="n">conf</span> <span class="o">=</span> <span class="n">Config</span><span class="p">()</span>
- <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>
- </code></pre></div>
- <h4 id="23">2.3 说明<a class="headerlink" href="#23" title="Permanent link">¶</a></h4>
- <ul>
- <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>
- <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>
- </ul>
- <hr />
- <h3 id="3">3 日志记录<a class="headerlink" href="#3" title="Permanent link">¶</a></h3>
- <h4 id="31">3.1 功能<a class="headerlink" href="#31" title="Permanent link">¶</a></h4>
- <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>
- <h4 id="32">3.2 代码实现<a class="headerlink" href="#32" title="Permanent link">¶</a></h4>
- <div class="highlight"><pre><span></span><code><span class="c1"># base/logger.py</span>
- <span class="c1"># 导入日志库</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
- <span class="c1"># 导入路径操作库</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
- <span class="c1"># 导入配置类</span>
- <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>
- <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>
- <span class="c1"># 创建日志目录</span>
- <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>
- <span class="c1"># 获取日志器</span>
- <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>
- <span class="c1"># 设置日志级别</span>
- <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>
- <span class="c1"># 避免重复添加处理器</span>
- <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>
- <span class="c1"># 创建文件处理器</span>
- <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>
- <span class="c1"># 设置文件处理器级别</span>
- <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>
- <span class="c1"># 创建控制台处理器</span>
- <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>
- <span class="c1"># 设置控制台处理器级别</span>
- <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>
- <span class="c1"># 设置日志格式</span>
- <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>
- <span class="c1"># 为文件处理器设置格式</span>
- <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>
- <span class="c1"># 为控制台处理器设置格式</span>
- <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>
- <span class="c1"># 添加文件处理器</span>
- <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>
- <span class="c1"># 添加控制台处理器</span>
- <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>
- <span class="c1"># 返回日志器</span>
- <span class="k">return</span> <span class="n">logger</span>
- <span class="c1"># 初始化日志器</span>
- <span class="n">logger</span> <span class="o">=</span> <span class="n">setup_logging</span><span class="p">()</span>
- </code></pre></div>
- <h4 id="33">3.3 说明<a class="headerlink" href="#33" title="Permanent link">¶</a></h4>
- <ul>
- <li><strong>日志级别</strong>:默认设为<code>INFO</code>,记录关键运行信息。</li>
- <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>
- <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>
- </ul>
- <hr />
- <h3 id="4-mysql">4 MySQL操作模块<a class="headerlink" href="#4-mysql" title="Permanent link">¶</a></h3>
- <h4 id="41">4.1 功能<a class="headerlink" href="#41" title="Permanent link">¶</a></h4>
- <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>
- <h4 id="42">4.2 代码实现<a class="headerlink" href="#42" title="Permanent link">¶</a></h4>
- <div class="highlight"><pre><span></span><code><span class="c1"># db/mysql_client.py</span>
- <span class="c1"># 导入 MySQL 连接库</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">pymysql</span>
- <span class="c1"># 导入pandas</span>
- <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>
- <span class="c1"># 导入配置和日志</span>
- <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>
- <span class="k">class</span><span class="w"> </span><span class="nc">MySQLClient</span><span class="p">:</span>
- <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
- <span class="c1"># 初始化日志</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 连接 MySQL 数据库</span>
- <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>
- <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>
- <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>
- <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>
- <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>
- <span class="p">)</span>
- <span class="c1"># 创建游标</span>
- <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>
- <span class="c1"># 记录连接成功</span>
- <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>
- <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>
- <span class="c1"># 记录连接失败</span>
- <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>
- <span class="k">raise</span>
- <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>
- <span class="n">create_table_query</span> <span class="o">=</span> <span class="s1">'''</span>
- <span class="s1"> CREATE TABLE IF NOT EXISTS jpkb (</span>
- <span class="s1"> id INT AUTO_INCREMENT PRIMARY KEY,</span>
- <span class="s1"> subject_name VARCHAR(20),</span>
- <span class="s1"> question VARCHAR(1000),</span>
- <span class="s1"> answer VARCHAR(1000))</span>
- <span class="s1"> '''</span>
- <span class="k">try</span><span class="p">:</span>
- <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>
- <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>
- <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>
- <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>
- <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>
- <span class="k">raise</span>
- <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>
- <span class="k">try</span><span class="p">:</span>
- <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>
- <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>
- <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>
- <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>
- <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>
- <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>
- <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
- <span class="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>
- <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>
- <span class="k">raise</span>
- <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>
- <span class="c1"># 获取所有问题</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 执行查询</span>
- <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>
- <span class="c1"># 获取结果</span>
- <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>
- <span class="c1"># 记录获取成功</span>
- <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>
- <span class="c1"># 返回结果</span>
- <span class="k">return</span> <span class="n">results</span>
- <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>
- <span class="c1"># 记录查询失败</span>
- <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>
- <span class="c1"># 返回空列表</span>
- <span class="k">return</span> <span class="p">[]</span>
- <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>
- <span class="c1"># 获取指定问题的答案</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 执行查询</span>
- <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>
- <span class="c1"># 获取结果</span>
- <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>
- <span class="c1"># 返回答案或 None</span>
- <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>
- <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>
- <span class="c1"># 记录答案获取失败</span>
- <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>
- <span class="c1"># 返回 None</span>
- <span class="k">return</span> <span class="kc">None</span>
- <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>
- <span class="c1"># 关闭数据库连接</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 关闭连接</span>
- <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>
- <span class="c1"># 记录关闭成功</span>
- <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>
- <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>
- <span class="c1"># 记录关闭失败</span>
- <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>
- <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
- <span class="n">mysql_client</span> <span class="o">=</span> <span class="n">MySQLClient</span><span class="p">()</span>
- <span class="n">mysql_client</span><span class="o">.</span><span class="n">create_table</span><span class="p">()</span>
- <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>
- </code></pre></div>
- <h4 id="43">4.3 说明<a class="headerlink" href="#43" title="Permanent link">¶</a></h4>
- <ul>
- <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>
- <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>
- <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>
- </ul>
- <hr />
- <h3 id="5-redis">5 Redis 缓存操作模块<a class="headerlink" href="#5-redis" title="Permanent link">¶</a></h3>
- <h4 id="51">5.1 功能<a class="headerlink" href="#51" title="Permanent link">¶</a></h4>
- <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>
- <h4 id="52">5.2 代码实现<a class="headerlink" href="#52" title="Permanent link">¶</a></h4>
- <div class="highlight"><pre><span></span><code><span class="c1"># cache/redis_client.py</span>
- <span class="c1"># 导入 Redis 客户端</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">redis</span>
- <span class="c1"># 导入 JSON 处理</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
- <span class="c1"># 导入配置和日志</span>
- <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>
- <span class="k">class</span><span class="w"> </span><span class="nc">RedisClient</span><span class="p">:</span>
- <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
- <span class="c1"># 初始化日志</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 连接 Redis</span>
- <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>
- <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>
- <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>
- <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>
- <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>
- <span class="n">decode_responses</span><span class="o">=</span><span class="kc">True</span>
- <span class="p">)</span>
- <span class="c1"># 记录连接成功</span>
- <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>
- <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>
- <span class="c1"># 记录连接失败</span>
- <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>
- <span class="k">raise</span>
- <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>
- <span class="c1"># 存储数据到 Redis</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 存储 JSON 数据</span>
- <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>
- <span class="c1"># 记录存储成功</span>
- <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>
- <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>
- <span class="c1"># 记录存储失败</span>
- <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>
- <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>
- <span class="c1"># 从 Redis 获取数据</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 获取数据</span>
- <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>
- <span class="c1"># 返回解析后的 JSON 数据或 None</span>
- <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>
- <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>
- <span class="c1"># 记录获取失败</span>
- <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>
- <span class="c1"># 返回 None</span>
- <span class="k">return</span> <span class="kc">None</span>
- <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>
- <span class="c1"># 获取查询的缓存答案</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 从 Redis 获取答案</span>
- <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>
- <span class="k">if</span> <span class="n">answer</span><span class="p">:</span>
- <span class="c1"># 记录获取成功</span>
- <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>
- <span class="c1"># 返回答案</span>
- <span class="k">return</span> <span class="n">answer</span>
- <span class="c1"># 返回 None</span>
- <span class="k">return</span> <span class="kc">None</span>
- <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>
- <span class="c1"># 记录查询失败</span>
- <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>
- <span class="c1"># 返回 None</span>
- <span class="k">return</span> <span class="kc">None</span>
- <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
- <span class="n">redcli</span> <span class="o">=</span> <span class="n">RedisClient</span><span class="p">()</span>
- <span class="nb">print</span><span class="p">(</span><span class="n">redcli</span><span class="p">)</span>
- </code></pre></div>
- <h4 id="53">5.3 说明<a class="headerlink" href="#53" title="Permanent link">¶</a></h4>
- <ul>
- <li><strong>Redis 连接</strong>:通过 config.ini 读取 Redis 配置,使用 redis.StrictRedis 建立连接。</li>
- <li><strong>数据操作</strong>: </li>
- <li>set_data:将键值对(值序列化为 JSON)存储到 Redis。</li>
- <li>get_data:根据键获取值并反序列化 JSON。</li>
- <li>get_answer:查询以 answer:{query} 格式存储的答案缓存。</li>
- </ul>
- <h3 id="6">6 文本预处理模块<a class="headerlink" href="#6" title="Permanent link">¶</a></h3>
- <h4 id="61">6.1 功能<a class="headerlink" href="#61" title="Permanent link">¶</a></h4>
- <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>
- <h4 id="62">6.2 代码实现<a class="headerlink" href="#62" title="Permanent link">¶</a></h4>
- <div class="highlight"><pre><span></span><code><span class="c1"># utils/preprocess.py</span>
- <span class="c1"># 导入分词库</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">jieba</span>
- <span class="c1"># 导入日志</span>
- <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>
- <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>
- <span class="c1"># 预处理文本</span>
- <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>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 分词并转换为小写</span>
- <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>
- <span class="k">except</span> <span class="ne">AttributeError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
- <span class="c1"># 记录预处理失败</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">"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>
- <span class="c1"># 返回空列表</span>
- <span class="k">return</span> <span class="p">[]</span>
- </code></pre></div>
- <h4 id="63">6.3 说明<a class="headerlink" href="#63" title="Permanent link">¶</a></h4>
- <ul>
- <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>
- </ul>
- <h3 id="7-bm25softmax">7 BM25+Softmax检索模块<a class="headerlink" href="#7-bm25softmax" title="Permanent link">¶</a></h3>
- <h4 id="71">7.1 功能<a class="headerlink" href="#71" title="Permanent link">¶</a></h4>
- <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>
- <div class="highlight"><pre><span></span><code><span class="c1"># retrieval/bm25_search.py</span>
- <span class="c1"># 导入 BM25 算法</span>
- <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>
- <span class="c1"># 导入数值计算库</span>
- <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>
- <span class="c1"># 导入文本预处理</span>
- <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>
- <span class="c1"># 导入日志</span>
- <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>
- <span class="k">class</span><span class="w"> </span><span class="nc">BM25Search</span><span class="p">:</span>
- <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">redis_client</span><span class="p">,</span> <span class="n">mysql_client</span><span class="p">):</span>
- <span class="c1"># 初始化日志</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
- <span class="c1"># 初始化 Redis 客户端</span>
- <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>
- <span class="c1"># 初始化 MySQL 客户端</span>
- <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>
- <span class="c1"># 初始化 BM25 模型</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">bm25</span> <span class="o">=</span> <span class="kc">None</span>
- <span class="c1"># 初始化问题列表</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">questions</span> <span class="o">=</span> <span class="kc">None</span>
- <span class="c1"># 初始化原始问题</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">original_questions</span> <span class="o">=</span> <span class="kc">None</span>
- <span class="c1"># 加载数据</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">_load_data</span><span class="p">()</span>
- <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>
- <span class="c1"># 加载数据</span>
- <span class="n">original_key</span> <span class="o">=</span> <span class="s2">"qa_original_questions"</span>
- <span class="n">tokenized_key</span> <span class="o">=</span> <span class="s2">"qa_tokenized_questions"</span>
- <span class="c1"># 从 Redis 获取原始问题</span>
- <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>
- <span class="c1"># 从 Redis 获取分词问题</span>
- <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>
- <span class="c1"># 如果 Redis 中没有数据,从 MySQL 加载</span>
- <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>
- <span class="c1"># 从 MySQL 获取问题</span>
- <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>
- <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>
- <span class="c1"># 记录无问题警告</span>
- <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>
- <span class="k">return</span>
- <span class="c1"># 分词问题</span>
- <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>
- <span class="c1"># 存储原始问题到 Redis</span>
- <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>
- <span class="c1"># 存储分词问题到 Redis</span>
- <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>
- <span class="c1"># 设置问题列表</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">questions</span> <span class="o">=</span> <span class="n">tokenized_questions</span>
- <span class="c1"># 初始化 BM25 模型</span>
- <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>
- <span class="c1"># 记录 BM25 初始化成功</span>
- <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>
- <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>
- <span class="c1"># 计算 Softmax 分数</span>
- <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>
- <span class="c1"># 返回归一化分数</span>
- <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>
- <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>
- <span class="c1"># 搜索查询</span>
- <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>
- <span class="c1"># 记录无效查询</span>
- <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>
- <span class="c1"># 返回 None 和 False</span>
- <span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">False</span>
- <span class="c1"># 检查 Redis 缓存</span>
- <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>
- <span class="k">if</span> <span class="n">cached_answer</span><span class="p">:</span>
- <span class="c1"># 返回缓存答案</span>
- <span class="k">return</span> <span class="n">cached_answer</span><span class="p">,</span> <span class="kc">False</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 分词查询</span>
- <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>
- <span class="c1"># 计算 BM25 分数</span>
- <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>
- <span class="c1"># 计算 Softmax 分数</span>
- <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>
- <span class="c1"># 获取最高分索引</span>
- <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>
- <span class="c1"># 获取最高分</span>
- <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>
- <span class="c1"># 检查是否超过阈值</span>
- <span class="k">if</span> <span class="n">best_score</span> <span class="o">>=</span> <span class="n">threshold</span><span class="p">:</span>
- <span class="c1"># 获取原始问题</span>
- <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>
- <span class="c1"># 获取答案</span>
- <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>
- <span class="c1"># 获取答案</span>
- <span class="k">if</span> <span class="n">redis_result</span><span class="p">:</span>
- <span class="n">answer</span> <span class="o">=</span> <span class="n">redis_result</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="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>
- <span class="k">else</span><span class="p">:</span>
- <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>
- <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>
- <span class="k">if</span> <span class="n">answer</span><span class="p">:</span>
- <span class="c1"># 缓存答案</span>
- <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>
- <span class="c1"># 记录搜索成功</span>
- <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>
- <span class="c1"># 返回答案和 False</span>
- <span class="k">return</span> <span class="n">answer</span><span class="p">,</span> <span class="kc">False</span>
- <span class="c1"># 记录无可靠答案</span>
- <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>
- <span class="c1"># 返回 None 和 True</span>
- <span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">True</span>
- <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
- <span class="c1"># 记录搜索失败</span>
- <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>
- <span class="c1"># 返回 None 和 True</span>
- <span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">True</span>
- </code></pre></div>
- <h4 id="72">7.2 说明<a class="headerlink" href="#72" title="Permanent link">¶</a></h4>
- <ul>
- <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>
- <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>
- <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>
- </ul>
- <h2 id="mainpy">三、主程序 (<code>main.py</code>)<a class="headerlink" href="#mainpy" title="Permanent link">¶</a></h2>
- <h3 id="1_1">1 代码<a class="headerlink" href="#1_1" title="Permanent link">¶</a></h3>
- <div class="highlight"><pre><span></span><code><span class="c1"># 导入 MySQL 客户端</span>
- <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>
- <span class="c1"># 导入 Redis 客户端</span>
- <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>
- <span class="c1"># 导入 BM25 搜索</span>
- <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>
- <span class="c1"># 导入日志</span>
- <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>
- <span class="c1"># 导入时间库</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">time</span>
- <span class="k">class</span><span class="w"> </span><span class="nc">MySQLQASystem</span><span class="p">:</span>
- <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
- <span class="c1"># 初始化日志</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span>
- <span class="c1"># 初始化 MySQL 客户端</span>
- <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>
- <span class="c1"># 初始化 Redis 客户端</span>
- <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>
- <span class="c1"># 初始化 BM25 搜索</span>
- <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>
- <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>
- <span class="c1"># 查询 MySQL 系统</span>
- <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>
- <span class="c1"># 记录查询信息</span>
- <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>
- <span class="c1"># 执行 BM25 搜索</span>
- <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>
- <span class="k">if</span> <span class="n">answer</span><span class="p">:</span>
- <span class="c1"># 记录 MySQL 答案</span>
- <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>
- <span class="k">else</span><span class="p">:</span>
- <span class="c1"># 记录无答案</span>
- <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>
- <span class="c1"># 设置默认答案</span>
- <span class="n">answer</span> <span class="o">=</span> <span class="s2">"SQL未找到答案"</span>
- <span class="c1"># 计算处理时间</span>
- <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>
- <span class="c1"># 记录处理时间</span>
- <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>
- <span class="c1"># 返回答案</span>
- <span class="k">return</span> <span class="n">answer</span>
- <span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
- <span class="c1"># 初始化 MySQL 系统</span>
- <span class="n">mysql_system</span> <span class="o">=</span> <span class="n">MySQLQASystem</span><span class="p">()</span>
- <span class="k">try</span><span class="p">:</span>
- <span class="c1"># 打印欢迎信息</span>
- <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>
- <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>
- <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
- <span class="c1"># 获取用户输入</span>
- <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>
- <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>
- <span class="c1"># 记录退出日志</span>
- <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>
- <span class="c1"># 打印退出信息</span>
- <span class="nb">print</span><span class="p">(</span><span class="s2">"再见!"</span><span class="p">)</span>
- <span class="k">break</span>
- <span class="c1"># 执行查询</span>
- <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>
- <span class="c1"># 打印答案</span>
- <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>
- <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
- <span class="c1"># 记录系统错误</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">"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>
- <span class="c1"># 打印错误信息</span>
- <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>
- <span class="k">finally</span><span class="p">:</span>
- <span class="c1"># 关闭 MySQL 连接</span>
- <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>
- <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span>
- <span class="c1"># 运行主程序</span>
- <span class="n">main</span><span class="p">()</span>
- </code></pre></div>
- <hr />
- <h3 id="2_2">2 示例运行结果<a class="headerlink" href="#2_2" title="Permanent link">¶</a></h3>
- <p>假设MySQL中有数据:
- - 问题:"特殊符号如何切割",答案:"使用split函数"
- - 问题:"如何处理字符串",答案:"使用字符串方法"</p>
- <p>查询:"特殊符号的切割"
- <div class="highlight"><pre><span></span><code>2025-04-01 10:00:00,123 - INFO - MySQL连接成功
- 2025-04-01 10:00:00,125 - INFO - Redis连接成功
- 2025-04-01 10:00:00,126 - INFO - BM25模型初始化完成
- 欢迎使用 MySQL 问答系统!
- 输入查询进行问答,输入 'exit' 退出。
- 2025-04-01 10:00:00,127 - INFO - 检索成功,Softmax相似度: 0.892
- 2025-04-01 10:00:00,128 - INFO - 数据存入Redis: answer:特殊符号的切割
- 2025-04-01 10:00:00,129 - INFO - MySQL答案: 使用split函数
- 2025-04-01 10:00:00,130 - INFO - MySQL连接已关闭
- </code></pre></div></p>
- <hr />
- <h2 id="_3">本章小结<a class="headerlink" href="#_3" title="Permanent link">¶</a></h2>
- <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>
- <ul>
- <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>
- <li><strong>工程化</strong>:模块化设计、配置文件、日志记录。</li>
- </ul>
-
- </article>
- </div>
-
-
- <script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
- </div>
-
- </main>
-
- <footer class="md-footer">
-
- <div class="md-footer-meta md-typeset">
- <div class="md-footer-meta__inner md-grid">
- <div class="md-copyright">
-
- <div class="md-copyright__highlight">
- © EnterpriseKB-RAG 2026. Internal knowledge base demo site.
- </div>
-
-
- Made with
- <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
- Material for MkDocs
- </a>
-
- </div>
-
- </div>
- </div>
- </footer>
-
- </div>
- <div class="md-dialog" data-md-component="dialog">
- <div class="md-dialog__inner md-typeset"></div>
- </div>
-
-
-
-
- <script id="__config" type="application/json">{"base": "..", "features": [], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "\u5df2\u590d\u5236", "clipboard.copy": "\u590d\u5236", "search.result.more.one": "\u5728\u8be5\u9875\u4e0a\u8fd8\u6709 1 \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.more.other": "\u5728\u8be5\u9875\u4e0a\u8fd8\u6709 # \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.none": "\u6ca1\u6709\u627e\u5230\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.one": "\u627e\u5230 1 \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.other": "# \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.placeholder": "\u952e\u5165\u4ee5\u5f00\u59cb\u641c\u7d22", "search.result.term.missing": "\u7f3a\u5c11", "select.version": "\u9009\u62e9\u5f53\u524d\u7248\u672c"}, "version": null}</script>
-
-
- <script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
-
- <script src="../javascripts/extra.js"></script>
-
- <script src="../javascripts/mathjax.js"></script>
-
- <!-- <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script>-->
-
- <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
-
-
- </body>
- </html>
|