CINXE.COM

<!DOCTYPE html><html munual-autotracker-init="" qct-pv-id="iAT0KjopFRbEqxZYx_LhA" qct-ip="8.222.208.146"><head><meta charSet="UTF-8"/><meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"/><title>LLM - 标签 - 腾讯云开发者社区-腾讯云</title><meta name="keywords" content="LLM,云+社区标签"/><meta name="subjectTime" content="2023-08-08 10:47:23"/><meta name="description" content=""/><meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1, viewport-fit=cover"/><meta name="format-detection" content="telephone=no"/><link rel="canonical" href="https://cloud.tencent.com/developer/tag/17917"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/gateway/portal/css/global-20209142343.css"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/qcloud/ui/cloud-community/build/base/base-202410111735.css"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/community-pc/build/AskDialog/AskDialog-202204021635.css?max_age=31536000"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/community-pc/build/AskDialog/AskDialog-202204021635.css?max_age=31536000"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/qcloud/ui/community-pc/build/base/base-202410211524.css"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/qcloud/ui/cloud-community/build/base/base-202410111735.css"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/community-pc/build/Tag/Tag-202105140928.css?max_age=31536000"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/community/portal/css/markdown-201810241044.css?max_age=31536000"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/qcloud/draft-master/dist/draft-master-v2.0.142.d4s2ddo9sb.css?max_age=31536000"/><style media="screen">@supports (padding:max(0px)){.set-safe-area .com-main{bottom:calc(max(12px,constant(safe-area-inset-bottom)) + 50px);bottom:calc(max(12px,env(safe-area-inset-bottom)) + 50px)}.set-safe-area .com-main-simple-sec,.set-safe-area .com-main.without-tab-ft,.set-safe-area .com-main.without-ft{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}.set-safe-area .com-main-sec{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}.set-safe-area .com-m-footer,.set-safe-area .sa-fixed-btns{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}.set-safe-area .com-mobile-body{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}}@supports (padding:max(0px)){.set-safe-area .support-wrap,.set-safe-area div.body{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}.set-safe-area .com-responsive-no-ft div.body{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}}.doc-con .J-docShareModal{display: none;} .doc-con .J-docShareCopyTipModalMB{display: none} .with-focus+.com-main-simple-sec, .with-focus+.com-main,.with-focus+.com-body,.with-focus+.qa-body{top:100px} .qa-detail-ask-panel:after{display:none!important;} .sa-fixed-btns .c-btn-weak{background-color: #fff;} .qa-r-editor.draft-editor-host.rno-markdown{height: 290px;overflow-y:auto;} .uc-achievement{line-height:24px;margin-bottom:5px;white-space: initial;overflow:visible;text-overflow:initial} .uc-achievement .uc-achievement-icon{top:0;margin-top:0;}</style></head><body style="position:initial"><div id="react-root" class=""><div class="comp-tag-detail"><div class="cdc-header is-fixed"><div class="cdc-header__placeholder"></div><div class="cdc-header__inner"><div class="cdc-header__top"><div class="cdc-header__top-left"><a href="/?from=20060&from_column=20060" target="_blank" class="cdc-header__top-logo"><i>腾讯云</i></a><div class="cdc-header__top-line"></div><a href="/developer" class="cdc-header__top-logo community"><i>开发者社区</i></a><div class="cdc-header__activity"><div id="cloud-header-product-container"></div></div></div><div class="cdc-header__top-operates"><a href="/document/product?from=20702&from_column=20702" target="_blank" class="cdc-header__link">文档</a><a href="/voc/?from=20703&from_column=20703" target="_blank" class="cdc-header__link">建议反馈</a><a href="https://console.cloud.tencent.com?from=20063&from_column=20063" target="_blank" class="cdc-header__link" track-click="{"areaId":102001,"subAreaId":1}">控制台</a><div class="cdc-header__account"><div class="cdc-header__account-inner"><button class="cdc-btn cdc-header__account-btn cdc-btn--primary">登录/注册</button></div></div></div></div><div class="cdc-header__bottom"><div class="cdc-header__bottom-nav"><a href="/developer" class="cdc-header__bottom-home">首页</a><div class="cdc-header__nav-list"><div class="cdc-header__nav-item">学习</div><div class="cdc-header__nav-item">活动</div><div class="cdc-header__nav-item">专区</div><div class="cdc-header__nav-item">工具</div></div><a href="/tvp?from=20154&from_column=20154" class="cdc-header__tvp" target="_blank">TVP</a><div class="cdc-header__activity"><a class="cdc-header__activity-tit" href="/act?from=20061&from_column=20061" target="_blank">最新优惠活动<div class="cdc-badge"><div class="cdc-badge-inner"><div class="cdc-badge-text"></div></div></div></a></div><div id="community-header-product-container"></div></div><div class="cdc-header__bottom-operates"><div class="cdc-header__search"><div class="cdc-search__wrap"><div class="cdc-search"><span class="cdc-search__text">文章/答案/技术大牛</span><button class="cdc-search__btn">搜索<i class="cdc-search__i search"></i></button></div><div class="cdc-search__dropdown"><div class="cdc-search__bar"><input type="text" class="cdc-search__bar-input" placeholder="文章/答案/技术大牛" value=""/><div class="cdc-search__bar-btns"><button class="cdc-search__btn">搜索<i class="cdc-search__i search"></i></button><button class="cdc-search__btn">关闭<i class="cdc-search__i clear"></i></button></div></div></div></div></div><div class="cdc-header__create"><span class="cdc-header__create-btn not-logged"><span class="cdc-svg-icon-con"><span class="cdc-svg-icon" style="line-height:1;color:#0052D9;width:16px;height:16px"><svg width="16" height="16" viewBox="0 0 16 16" fill="currentcolor" xmlns="http://www.w3.org/2000/svg"><path d="M14.2466 12.0145C14.1698 13.6258 12.8381 14.9131 11.2129 14.9131H11.1579H4.0927H4.03772C2.4125 14.9131 1.08014 13.6258 1.00334 12.0145H1V11.8668V4.07213V4.04627V3.89922H1.00334C1.08014 2.28732 2.4125 1 4.03772 1H9.6473V1.00069H10.0786L8.7688 2.10773H8.43888H7.7916H6.37904H4.03772C2.97234 2.10773 2.10445 2.9777 2.10445 4.04629V4.41869V4.4472V6.39498V11.4269V11.4309V11.8668C2.10445 12.9354 2.97234 13.8053 4.03772 13.8053H6.37904H8.87153H11.2129C12.2782 13.8053 13.1461 12.9355 13.1461 11.8668V11.466V11.454V9.5181V6.39364L14.2506 5.3051V11.8668V12.0145H14.2466ZM10.4324 7.15226L9.63146 7.99761C9.36577 8.2693 8.69326 8.95104 8.48066 9.17631C8.26726 9.40288 8.09039 9.58901 7.95061 9.73544C7.81079 9.88188 7.72667 9.96597 7.70083 9.98656C7.63321 10.0488 7.55703 10.1144 7.47022 10.1846C7.38412 10.2542 7.29404 10.3099 7.20063 10.3516C7.10722 10.4007 6.97072 10.459 6.79049 10.5305C6.61028 10.6001 6.42213 10.6676 6.22468 10.7339C6.02792 10.8002 5.84109 10.8571 5.66484 10.9061C5.48795 10.9538 5.3561 10.9863 5.2693 11.0009C5.08977 11.0214 4.96988 10.993 4.90956 10.9168C4.84931 10.8405 4.83276 10.7107 4.85924 10.5312C4.87315 10.4331 4.9043 10.292 4.95468 10.1078C5.00431 9.92297 5.05802 9.7315 5.11431 9.53341C5.1713 9.33526 5.22629 9.15179 5.27926 8.98484C5.33297 8.8179 5.37599 8.7026 5.40978 8.64032C5.44953 8.54357 5.49463 8.45413 5.54495 8.37399C5.59465 8.29379 5.66616 8.20503 5.75965 8.10766C5.79934 8.06588 5.89281 7.96649 6.03988 7.81018C6.18624 7.65311 6.80114 7.02774 7.02104 6.79783L7.75117 6.03524L8.56212 5.1899L10.6345 3.02466L12.5214 4.93874L10.4324 7.15226ZM13.816 3.58581C13.7166 3.68987 13.6272 3.78064 13.5483 3.85883C13.4694 3.93703 13.4006 4.0066 13.3423 4.06686C13.276 4.13643 13.2144 4.19738 13.1561 4.24903L11.2785 2.33569C11.3785 2.24025 11.4965 2.12565 11.6336 1.99115C11.7707 1.85668 11.8854 1.75061 11.9761 1.67242C12.0934 1.57708 12.2133 1.51013 12.3385 1.47109C12.4525 1.43529 12.5644 1.41805 12.6751 1.41876H12.7056C12.7665 1.42139 12.8268 1.42729 12.8851 1.43724C12.8838 1.4366 12.8811 1.43724 12.8798 1.4366C12.8811 1.4366 12.8838 1.4366 12.8851 1.43724C13.1376 1.48428 13.4019 1.62009 13.6265 1.83743C13.7511 1.95871 13.8524 2.09382 13.9259 2.23296C14.0346 2.43834 14.0863 2.65304 14.0763 2.8491C14.0763 2.87294 14.0783 2.89748 14.0783 2.92201C14.0783 3.03529 14.0571 3.14789 14.0154 3.26055C13.9737 3.37314 13.9067 3.48185 13.816 3.58581Z" fill="#0052D9"></path></svg></span></span>发布<span class="cdc-svg-icon-con cdc-header__create-btn-arrow"><span class="cdc-svg-icon" style="line-height:1;color:inherit;width:16px;height:16px"><svg width="16" height="16" viewBox="0 0 16 16" fill="currentcolor" xmlns="http://www.w3.org/2000/svg"><path d="M8.16377 4L9.57798 5.41421L14.5277 10.364L13.1135 11.7782L8.1638 6.829L3.21402 11.7782L1.7998 10.364L8.16377 4Z"></path></svg></span></span></span></div></div></div></div></div><div class="cdc-m-header with-focus is-fixed"><div class="cdc-m-header__placeholder"></div><div class="cdc-m-header__inner"><div class="cdc-m-guider-banner is-sticky"><div class="cdc-m-guider-banner__guide-mvp" track-exposure="{"areaId":118000}" track-click="{"areaId":118000}"><div class="cdc-m-guider-banner__guide-mvp-text">精选内容/技术社群/优惠产品,<em>尽在小程序</em></div><div class="cdc-m-guider-banner__guide-mvp-btn">立即前往</div></div></div><div class="cdc-m-header__main"><div class="cdc-m-header__trigger"></div><div class="cdc-m-header__logo"><i class="cdc-m-header__logo-icon"></i></div><div class="cdc-m-header__search"><i class="cdc-m-header__search-icon"></i></div><div class="cdc-m-header__operate"><span class="cdc-m-header__operate-icon"></span></div></div></div></div><div class="J-body com-body max-width"><div class="com-crumb"><div class="com-inner"><a href="/developer" class="crumb-item">首页</a><span class="crumb-split"></span><a href="/developer/tags" class="crumb-item">标签</a><span class="crumb-split"></span><span class="crumb-item current">LLM</span></div></div><div track-click="{"areaId":{"areaId":113006}}" track-exposure="{"areaId":{"areaId":113006}}" class="com-tag-intro"><i class="intro-bg"></i><h2 class="intro-title"><em>#</em>LLM</h2><p class="intro-desc"></p><div class="intro-btns"><button type="button" class="c-btn" track-click="{"elementId":1}">关注</button></div></div><div class="com-2-layout"><div class="layout-main"><div class="com-tab large tag-tab"><div class="com-tab-hd large"><ul class="com-tab-ctrl"><li class="com-tab-item actived"><a href="javascript:;">专栏文章<span class="num">(869)</span></a></li><li class="com-tab-item"><a href="/developer/tag/17917?entry=video">技术视频<span class="num">(6)</span></a></li><li class="com-tab-item"><a href="/developer/tag/17917?entry=ask">互动问答<span class="num">(3)</span></a></li></ul></div><div class="com-tab-bd"><com class="com-tab-panel"><div class="com-article-panel-v2-list"><section class="com-article-panel-v2 higher"><a href="/developer/article/2476693" track-click="{"areaId":113001,"objectType":"article","objectId":2476693}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2476693}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Prompt提示工程上手指南(七)Prompt编写实战-基于智能客服问答系统下的Prompt编写</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/11560?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":11560}" class="com-tag-v2">媒体 AI</a><a href="/developer/tag/15406?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":15406}" class="com-tag-v2">prompt</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/10539?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10539}" class="com-tag-v2">人工智能</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9822651/01e9b5a33e434924432cdc9af6632c01.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9822651" track-click="{"objectType":"user","objectId":9822651}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/0f630c59c68f9736ceee01048fd721eb.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9822651" track-click="{"objectType":"user","objectId":9822651}" target="_blank" class="author-info name">fanstuck</a><span class="author-info time"><time dateTime="2024-12-13 16:40:53" title="2024-12-13 16:40:53"> <span>3</span>小时前<span class="com-v-box">2024-12-13 16:40:53</span></time></span></div></div></div><p class="com-article-panel-v2-des">本系列文章从最初的基础原理与入门实践切入，一直延伸到主流策略、引导策略、RAG（检索增强生成）、思维树（ToT）与避免幻觉（Hallucination）的策略这...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>15</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2476693.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2475846" track-click="{"areaId":113001,"objectType":"article","objectId":2475846}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2475846}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Open-WebUI 接入腾讯混元大模型</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17970?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17970}" class="com-tag-v2">腾讯混元大模型</a><a href="/developer/tag/17982?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17982}" class="com-tag-v2">玩转腾讯混元大模型</a><a href="/developer/tag/18033?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":18033}" class="com-tag-v2">第四期热点征文-大模型技术</a><a href="/developer/tag/15053?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":15053}" class="com-tag-v2">openai</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-8322969/e3eb86c9fe4dcb4fe32ae1487c6b8a58.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/8322969" track-click="{"objectType":"user","objectId":8322969}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/ef438a4b5d600af18e7549cbe487bd1c.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/8322969" track-click="{"objectType":"user","objectId":8322969}" target="_blank" class="author-info name">lkevincc</a><span class="author-info time"><time dateTime="2024-12-11 10:59:46" title="2024-12-11 10:59:46"> <span>2</span>天前<span class="com-v-box">2024-12-11 10:59:46</span></time></span></div></div></div><p class="com-article-panel-v2-des">我尝试使用openai协议的api key接入openwebui失败后，由生此文。</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>98</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2475846.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2475631" track-click="{"areaId":113001,"objectType":"article","objectId":2475631}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2475631}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">基于LLM的单元测试生成，你在第几级？</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10752?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10752}" class="com-tag-v2">单元测试</a><a href="/developer/tag/17302?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17302}" class="com-tag-v2">基础</a><a href="/developer/tag/17373?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17373}" class="com-tag-v2">论文</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-8035011/41fd458634d72e3453141764459dfd71.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/8035011" track-click="{"objectType":"user","objectId":8035011}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-8035011/mzubfztt2s.jpeg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/8035011" track-click="{"objectType":"user","objectId":8035011}" target="_blank" class="author-info name">Antony</a><span class="author-info time"><time dateTime="2024-12-10 13:01:13" title="2024-12-10 13:01:13"> <span>3</span>天前<span class="com-v-box">2024-12-10 13:01:13</span></time></span></div></div></div><p class="com-article-panel-v2-des">选定一个被测方法(focal method)，将方法体的源码传给大模型，要求生成单元测试用例。这是不少所谓的可以赋能开发单测的大模型的方案。在某些厂商的demo...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>69</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2475631.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2475624" track-click="{"areaId":113001,"objectType":"article","objectId":2475624}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2475624}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">CAMEL-AI团队参与发表Nature子刊啦!聚焦LLM如何重塑未来医疗 ~</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10570?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10570}" class="com-tag-v2">医疗</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17506?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17506}" class="com-tag-v2">系统</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/10539?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10539}" class="com-tag-v2">人工智能</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-8199873/a6f3853d88aa6fa987abefad2daf58e2.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/8199873" track-click="{"objectType":"user","objectId":8199873}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/6df15c7b18b1f3371d7cdabf07705d88.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/8199873" track-click="{"objectType":"user","objectId":8199873}" target="_blank" class="author-info name">DrugAI</a><span class="author-info time"><time dateTime="2024-12-10 12:55:44" title="2024-12-10 12:55:44"> <span>3</span>天前<span class="com-v-box">2024-12-10 12:55:44</span></time></span></div></div></div><p class="com-article-panel-v2-des">LLM驱动的智能体系统是一种基于大语言模型（LLM）的增强型人工智能系统，通过集成多个模块实现从感知到行动的全流程功能。简单来说，它是一种具备感知、思考、决策和...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>71</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2475624.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2474889" track-click="{"areaId":113001,"objectType":"article","objectId":2474889}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2474889}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">LLM赋能测试活动实现端到端自动化的四个环节八项关键任务</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10669?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10669}" class="com-tag-v2">自动化</a><a href="/developer/tag/10671?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10671}" class="com-tag-v2">运维</a><a href="/developer/tag/10732?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10732}" class="com-tag-v2">自动化测试</a><a href="/developer/tag/17205?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17205}" class="com-tag-v2">测试</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-8035011/eecc96a9309b7a43fa7b2c35aff9991f.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/8035011" track-click="{"objectType":"user","objectId":8035011}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-8035011/mzubfztt2s.jpeg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/8035011" track-click="{"objectType":"user","objectId":8035011}" target="_blank" class="author-info name">Antony</a><span class="author-info time"><time dateTime="2024-12-09 13:02:05" title="2024-12-09 13:02:05"> <span>4</span>天前<span class="com-v-box">2024-12-09 13:02:05</span></time></span></div></div></div><p class="com-article-panel-v2-des">在这个环节不是直接应用LLM，而是说通过LLM pipeline的编排，把测试环境、测试数据的动态获取、测试用例的发起执行等任务通过 LLM tools 模块能...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>100</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2474889.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2474511" track-click="{"areaId":113001,"objectType":"article","objectId":2474511}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2474511}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">LLM 时代：Java 如何设计一个及格的 AIGC 框架</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/10164?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10164}" class="com-tag-v2">java</a><a href="/developer/tag/11746?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":11746}" class="com-tag-v2">aigc</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/3610078/741701b1a0e83e5d2c46584d4d95792d.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/3610078" track-click="{"objectType":"user","objectId":3610078}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/1c56351cbf28b96d68081972914a936d.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/3610078" track-click="{"objectType":"user","objectId":3610078}" target="_blank" class="author-info name">花花Binki</a><div class="c-bubble-trigger com-verification"><i class="verified"></i><div class="c-bubble c-bubble-bottom"><div class="c-bubble-inner" style="padding:8px 10px"><p>通华科技（大连）｜后端开发 (已认证)</p></div></div></div><span class="author-info time"><time dateTime="2024-12-06 22:55:20" title="2024-12-06 22:55:20"> <span>6</span>天前<span class="com-v-box">2024-12-06 22:55:20</span></time></span></div></div></div><p class="com-article-panel-v2-des">大语言模型（LLM）的风口持续了两年的现在，想让他可以为之前的企业应用赋能，首选的第一开发语言还是 Python。但实际上，Java 才是在 Web 应用开发领...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>79</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2474511.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2474048" track-click="{"areaId":113001,"objectType":"article","objectId":2474048}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2474048}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">解密prompt系列44. RAG探索模式？深度思考模式？</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/14918?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":14918}" class="com-tag-v2">nlp</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-6190096/ec09bd2a9be2172b7ef7b6024a6f5fe8.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/6190096" track-click="{"objectType":"user","objectId":6190096}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/84dea5a4f42672f8a734080db2d8086e.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/6190096" track-click="{"objectType":"user","objectId":6190096}" target="_blank" class="author-info name">风雨中的小七</a><span class="author-info time"><time dateTime="2024-12-06 07:58:16" title="2024-12-06 07:58:16"> <span>7</span>天前<span class="com-v-box">2024-12-06 07:58:16</span></time></span></div></div></div><p class="com-article-panel-v2-des">前一阵多步RAG的风吹入了工业界，kimi推出了探索版本，各应用都推出了深度搜索，You.COM更是早就有了Genius的多步模式。其实都是类似multi-ho...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>155</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2474048.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2473664" track-click="{"areaId":113001,"objectType":"article","objectId":2473664}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2473664}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">【NLP】BLEU（Bilingual Evaluation Understudy）评分</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/14918?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":14918}" class="com-tag-v2">nlp</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/10919134" track-click="{"objectType":"user","objectId":10919134}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/bb1ac398708cdc8942f88d84648af82e.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/10919134" track-click="{"objectType":"user","objectId":10919134}" target="_blank" class="author-info name">云帆沧海</a><span class="author-info time"><time dateTime="2024-12-04 17:49:02" title="2024-12-04 17:49:02"> <span>9</span>天前<span class="com-v-box">2024-12-04 17:49:02</span></time></span></div></div></div><p class="com-article-panel-v2-des">BLEU（Bilingual Evaluation Understudy）是一种广泛用于评估机器翻译和自然语言生成任务质量的指标。BLEU-4评分是基于四个n-...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>157</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2473664.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472881" track-click="{"areaId":113001,"objectType":"article","objectId":2472881}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472881}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">ComfyUI Party：将LLM与图片工作流集成，图片、语音、文本、视觉一体！（graphRAG、ollama）</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17562?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17562}" class="com-tag-v2">语音</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/17276?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17276}" class="com-tag-v2">工具</a><a href="/developer/tag/17285?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17285}" class="com-tag-v2">工作流</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/1dfc42d3ab930230f210174299b6e450.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:36:38" title="2024-12-02 19:36:38"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:36:38</span></time></span></div></div></div><p class="com-article-panel-v2-des">这个工具挺酷的，他专注于LLM集成进ComfyUI里面。旨在基于comfyui作为前端，开发一套完整的LLM工作流构建节点，让用户可以快速便捷地构建自己的LLM...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>92</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472881.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472873" track-click="{"areaId":113001,"objectType":"article","objectId":2472873}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472873}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">本地AI文件管理器：AI驱动+私有LLM，免费整理你的文件库</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17276?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17276}" class="com-tag-v2">工具</a><a href="/developer/tag/17341?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17341}" class="com-tag-v2">开发者</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17506?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17506}" class="com-tag-v2">系统</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/e958834a67012d1d526618aa3dcfca6c.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:33:08" title="2024-12-02 19:33:08"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:33:08</span></time></span></div></div></div><p class="com-article-panel-v2-des">借助完全私有且本地运行的LLM（大语言模型），你可以整理PNG文件、JPG、JPEG、GIF、BMP格式的图片。对于文本类文件，你可以使用TXT和DOCX格式，...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>119</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472873.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472870" track-click="{"areaId":113001,"objectType":"article","objectId":2472870}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472870}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">g1：o1推理链开源实现，原理竟如此简单！解决 60-80% 的困扰LLM的简单逻辑问题</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17205?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17205}" class="com-tag-v2">测试</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17566?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17566}" class="com-tag-v2">原理</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/10667?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10667}" class="com-tag-v2">开源</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/71adfe90bf1f54ad5b89e8af501cbaa7.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:32:37" title="2024-12-02 19:32:37"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:32:37</span></time></span></div></div></div><p class="com-article-panel-v2-des">它的提示词是一种动态思维链，允许LLM “思考”并解决一些通常会困扰领先模型的逻辑问题。在每一步中， LLM都可以选择继续另一个推理步骤，或提供最终答案。每个步...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>86</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472870.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472861" track-click="{"areaId":113001,"objectType":"article","objectId":2472861}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472861}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Crawl4AI：AI驱动的网页抓取神器，结合LLM实现自动化数据提取与处理</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10669?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10669}" class="com-tag-v2">自动化</a><a href="/developer/tag/17276?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17276}" class="com-tag-v2">工具</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/10548?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10548}" class="com-tag-v2">网站</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/175c2c65d125ca196db4dfa42c593998.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:21:33" title="2024-12-02 19:21:33"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:21:33</span></time></span></div></div></div><p class="com-article-panel-v2-des">让我们跳转到实际操作中，看看如何做到这一点。这是他们的 GitHub 仓库页面，你可以看到这是一个开源的 LLM 友好型网页爬虫和抓取工具。</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>212</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472861.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472859" track-click="{"areaId":113001,"objectType":"article","objectId":2472859}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472859}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Reflection 70B（已全面测试）：这个开源 LLM 击败了 Claude 3.5 Sonnet 和 GPT-4O？</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/15657?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":15657}" class="com-tag-v2">reflection</a><a href="/developer/tag/17205?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17205}" class="com-tag-v2">测试</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/10667?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10667}" class="com-tag-v2">开源</a><a href="/developer/tag/13755?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":13755}" class="com-tag-v2">gpt</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/f396575778c213d2fd5f108ddbb67ed7.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:20:07" title="2024-12-02 19:20:07"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:20:07</span></time></span></div></div></div><p class="com-article-panel-v2-des">这款模型名为Reflection 70B，之所以取这个名字，是因为它采用了一种新的训练技术，叫做反思微调（Reflection Tuning），这种技术教大语言...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>58</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472859.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472848" track-click="{"areaId":113001,"objectType":"article","objectId":2472848}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472848}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Zed AI + Ollama：最强开源AI代码编辑器，轻松配置本地LLM模型（Phi 3.5 & Llama-3.1）</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10667?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10667}" class="com-tag-v2">开源</a><a href="/developer/tag/17186?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17186}" class="com-tag-v2">编辑器</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17393?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17393}" class="com-tag-v2">配置</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/ed80fd097b716aa5ab81c1d9889088f2.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:16:23" title="2024-12-02 19:16:23"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:16:23</span></time></span></div></div></div><p class="com-article-panel-v2-des">此外，Zed的多LLM配置选项也很nice，你可以从本地模型开始，如果觉得本地模型不行，你可以选择更大的模型来使用。</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>164</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472848.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472845" track-click="{"areaId":113001,"objectType":"article","objectId":2472845}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472845}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">MinerU、Doc2X、OmniParse、llm_aided_ocr 四款流行OCR工具测评（LLM & RAG数据准备）</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/15010?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":15010}" class="com-tag-v2">ocr</a><a href="/developer/tag/17203?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17203}" class="com-tag-v2">部署</a><a href="/developer/tag/17276?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17276}" class="com-tag-v2">工具</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/eb638f69996bd3e33438a33ca92d39e8.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:15:13" title="2024-12-02 19:15:13"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:15:13</span></time></span></div></div></div><p class="com-article-panel-v2-des">删除\m，就会正常，而Doc2X通常很少出现这种情况，我可以预先告诉你，Doc2X是这4个中最好的，但是他也有一些缺陷，我会在后文说。</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>215</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472845.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472843" track-click="{"areaId":113001,"objectType":"article","objectId":2472843}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472843}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Triplex vs. GPT-4：将Graph RAG成本降低98%的革命性模型、知识图谱构建的 SOTA LLM！</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/13769?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":13769}" class="com-tag-v2">graph</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/10471?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10471}" class="com-tag-v2">知识图谱</a><a href="/developer/tag/13755?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":13755}" class="com-tag-v2">gpt</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/eacaad7250478e2f2160a21232b686e3.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:14:54" title="2024-12-02 19:14:54"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:14:54</span></time></span></div></div></div><p class="com-article-panel-v2-des">知识图谱（例如 Microsoft 的Graph RAG）增强了 RAG 方法，但构建成本高昂。Triplex 可将知识图谱创建成本降低 98%，性能优于 GP...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>67</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472843.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472839" track-click="{"areaId":113001,"objectType":"article","objectId":2472839}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472839}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Kimi+Langchain+FastGPT：文档转LLM微调数据集 / QA问答对生成、Kimi 128KAPI免费接入！</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17393?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17393}" class="com-tag-v2">配置</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/17196?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17196}" class="com-tag-v2">表格</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/40dea31b061d7d46e782f7d08338cb1c.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:13:31" title="2024-12-02 19:13:31"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:13:31</span></time></span></div></div></div><p class="com-article-panel-v2-des">今天我将介绍：如何使用Kimi API将文档转换为LLM指令监督微调数据集（Alpaca 格式）以及如何部署FastGPT并接入Kimi API：</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>136</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472839.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472831" track-click="{"areaId":113001,"objectType":"article","objectId":2472831}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472831}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">DeepSeek-Coder-V2.1：最佳编码LLM再度升级！（经过全面测试并击败 Claude，GPT-4o）</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17205?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17205}" class="com-tag-v2">测试</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/13755?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":13755}" class="com-tag-v2">gpt</a><a href="/developer/tag/17189?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17189}" class="com-tag-v2">编码</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/b10de2608b2e885bd07f3b4470d31d5c.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:10:08" title="2024-12-02 19:10:08"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:10:08</span></time></span></div></div></div><p class="com-article-panel-v2-des">DeepSeek-V2又双叒升级了，最强开源模型！（DeepSeek-Chat-V2.1开源 & 全面测试）</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>91</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472831.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472825" track-click="{"areaId":113001,"objectType":"article","objectId":2472825}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472825}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Mem0 AI：开源一天斩获万星！超越 RAG、为LLM、Agent加上超强个性记忆！</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a><a href="/developer/tag/10666?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10666}" class="com-tag-v2">游戏</a><a href="/developer/tag/10667?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10667}" class="com-tag-v2">开源</a><a href="/developer/tag/11736?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":11736}" class="com-tag-v2">agent</a><a href="/developer/tag/17276?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17276}" class="com-tag-v2">工具</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/b64a623d9efb4fbd7ff2b0ab900a8284.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:07:14" title="2024-12-02 19:07:14"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:07:14</span></time></span></div></div></div><p class="com-article-panel-v2-des">最近，OpenAI 投资了 370 万美金给一个叫 Dot 的应用，这个应用背后的核心技术是「超强个性记忆」，现在由 Mem0 开源了。</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>95</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472825.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2472824" track-click="{"areaId":113001,"objectType":"article","objectId":2472824}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2472824}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">Mistral NeMo：这是现在最好的开源LLM！（经过全面测试并击败 Qwen2、DeepSeek-V2 及其他）</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10667?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10667}" class="com-tag-v2">开源</a><a href="/developer/tag/17189?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17189}" class="com-tag-v2">编码</a><a href="/developer/tag/17205?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17205}" class="com-tag-v2">测试</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17917?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17917}" class="com-tag-v2">LLM</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-9836881/bf014f77b1e34bf92ef4d7d21beb6180.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/9836881" track-click="{"objectType":"user","objectId":9836881}" target="_blank" class="author-info name">AI进修生</a><span class="author-info time"><time dateTime="2024-12-02 19:06:15" title="2024-12-02 19:06:15"> <span>11</span>天前<span class="com-v-box">2024-12-02 19:06:15</span></time></span></div></div></div><p class="com-article-panel-v2-des">它在编码任务方面甚至更好，并且也非常擅长做文本到应用程序、文本到前端和其他事情。我将对其进行测试，看看它是否真的可以击败其他LLMs，并且我还将告诉你如何使用它...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>82</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2472824.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section></div><div><div class="c-loading c-loading-tip"><div class="c-loading-inner"><div class="one"></div><div class="two"></div><div class="three"></div></div></div></div></com></div></div></div><div class="layout-side" track-click="" track-exposure=""><div class="com-2-section side"><header class="com-2-section-hd"><h2 class="com-2-section-title without-icon"><span><em>相关</em>产品</span></h2></header><div class="com-2-section-bd"><ul class="com-side-products"><li class="panel-cell"><div class="com-side-product"><a href="" target="_blank" class="panel-link"></a><header class="com-side-product-hd"><div class="com-side-product-object"><img src="//cloudcache.tencent-cloud.com/qcloud/developer/images/release/team/product-default-icon.v1.svg" alt=""/></div><h3 class="com-side-product-title"></h3></header><p class="com-side-product-desc"></p></div></li></ul></div></div><div class="com-2-section side"><header class="com-2-section-hd"><h2 class="com-2-section-title without-icon"><span><em>热门</em>专栏</span></h2></header><div class="com-2-section-bd"><div class="com-side-column-panels-wrap"><div class="com-side-column-panels-cnt"><ul track-click="{"areaId":113004}" track-exposure="{"areaId":113004}" class="com-side-column-panels"><li class="panel-cell"><a href="/developer/column/1081" trackClick="{"objectType":"column","objectId":1081}" class="com-media com-side-column-panel"><div class="com-media-object"><span class="com-2-avatar"><span class="com-2-avatar-inner" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-900000/57548b27ada32a860de54d545a535f2f.png?imageView2/2/w/76/h/7000)"></span></span></div><div class="com-media-body"><h3 class="com-side-column-panel-title">腾讯云服务器团队的专栏</h3><div class="com-side-column-panel-infos"><div class="com-datas"><span class="com-data">206 文章</span><span class="com-data">319 订阅</span></div></div></div></a></li><li class="panel-cell"><a href="/developer/column/1283" trackClick="{"objectType":"column","objectId":1283}" class="com-media com-side-column-panel"><div class="com-media-object"><span class="com-2-avatar"><span class="com-2-avatar-inner" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-170434/568f3e8410f6654284c65b8e886345e3.png?imageView2/2/w/76/h/7000)"></span></span></div><div class="com-media-body"><h3 class="com-side-column-panel-title">腾讯技术工程官方号的专栏</h3><div class="com-side-column-panel-infos"><div class="com-datas"><span class="com-data">1.1K 文章</span><span class="com-data">914 订阅</span></div></div></div></a></li><li class="panel-cell"><a href="/developer/column/1589" trackClick="{"objectType":"column","objectId":1589}" class="com-media com-side-column-panel"><div class="com-media-object"><span class="com-2-avatar"><span class="com-2-avatar-inner" style="background-image:url(https://ask.qcloudimg.com/avatar/1147573/ukwqo56o1w.png?imageView2/2/w/76/h/7000)"></span></span></div><div class="com-media-body"><h3 class="com-side-column-panel-title">深度学习思考者</h3><div class="com-side-column-panel-infos"><div class="com-datas"><span class="com-data">89 文章</span><span class="com-data">42 订阅</span></div></div></div></a></li><li class="panel-cell"><a href="/developer/column/1591" trackClick="{"objectType":"column","objectId":1591}" class="com-media com-side-column-panel"><div class="com-media-object"><span class="com-2-avatar"><span class="com-2-avatar-inner" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-1051732/4d1dd6a8e273842f65600c6efb9c38f8.jpeg?imageView2/2/w/76/h/7000)"></span></span></div><div class="com-media-body"><h3 class="com-side-column-panel-title">素质云笔记</h3><div class="com-side-column-panel-infos"><div class="com-datas"><span class="com-data">421 文章</span><span class="com-data">113 订阅</span></div></div></div></a></li></ul></div></div></div></div></div></div></div><div class="cdc-footer J-footer com-2-footer"><div class="cdc-footer__inner"><div class="cdc-footer__main"><div class="cdc-footer__website"><ul class="cdc-footer__website-group"><li class="cdc-footer__website-column"><div class="cdc-footer__website-box"><h3 class="cdc-footer__website-title">社区</h3><ul class="cdc-footer__website-list"><li class="cdc-footer__website-item"><a href="/developer/column">专栏文章</a></li><li class="cdc-footer__website-item"><a href="/developer/inventory">阅读清单</a></li><li class="cdc-footer__website-item"><a href="/developer/ask">互动问答</a></li><li class="cdc-footer__website-item"><a href="/developer/salon">技术沙龙</a></li><li class="cdc-footer__website-item"><a href="/developer/video">技术视频</a></li><li class="cdc-footer__website-item"><a href="/developer/teams">团队主页</a></li><li class="cdc-footer__website-item"><a href="/developer/timl">腾讯云TI平台</a></li></ul></div></li><li class="cdc-footer__website-column"><div class="cdc-footer__website-box"><h3 class="cdc-footer__website-title">活动</h3><ul class="cdc-footer__website-list"><li class="cdc-footer__website-item"><a href="/developer/support-plan">自媒体同步曝光计划</a></li><li class="cdc-footer__website-item"><a href="/developer/support-plan-invitation">邀请作者入驻</a></li><li class="cdc-footer__website-item"><a href="/developer/article/1535830">自荐上首页</a></li><li class="cdc-footer__website-item"><a href="/developer/competition">技术竞赛</a></li></ul></div></li><li class="cdc-footer__website-column"><div class="cdc-footer__website-box"><h3 class="cdc-footer__website-title">资源</h3><ul class="cdc-footer__website-list"><li class="cdc-footer__website-item"><a href="/developer/specials">技术周刊</a></li><li class="cdc-footer__website-item"><a href="/developer/tags">社区标签</a></li><li class="cdc-footer__website-item"><a href="/developer/devdocs">开发者手册</a></li><li class="cdc-footer__website-item"><a href="/lab?from=20064&from_column=20064">开发者实验室</a></li></ul></div></li><li class="cdc-footer__website-column"><div class="cdc-footer__website-box"><h3 class="cdc-footer__website-title">关于</h3><ul class="cdc-footer__website-list"><li class="cdc-footer__website-item"><a rel="nofollow" href="/developer/article/1006434">社区规范</a></li><li class="cdc-footer__website-item"><a rel="nofollow" href="/developer/article/1006435">免责声明</a></li><li class="cdc-footer__website-item"><a rel="nofollow" href="mailto:cloudcommunity@tencent.com">联系我们</a></li><li class="cdc-footer__website-item"><a rel="nofollow" href="/developer/friendlink">友情链接</a></li></ul></div></li></ul></div><div class="cdc-footer__qr"><h3 class="cdc-footer__qr-title">腾讯云开发者</h3><div class="cdc-footer__qr-object"><img class="cdc-footer__qr-image" src="https://qcloudimg.tencent-cloud.cn/raw/a8907230cd5be483497c7e90b061b861.png" alt="扫码关注腾讯云开发者"/></div><div class="cdc-footer__qr-infos"><p class="cdc-footer__qr-info"><span class="cdc-footer__qr-text">扫码关注腾讯云开发者</span></p><p class="cdc-footer__qr-info"><span class="cdc-footer__qr-text">领取腾讯云代金券</span></p></div></div></div><div class="cdc-footer__recommend"><div class="cdc-footer__recommend-rows"><div class="cdc-footer__recommend-cell"><h3 class="cdc-footer__recommend-title">热门产品</h3><div class="cdc-footer__recommend-wrap"><ul class="cdc-footer__recommend-list"><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="https://dnspod.cloud.tencent.com?from=20064&from_column=20064">域名注册</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cvm?from=20064&from_column=20064">云服务器</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/tbaas?from=20064&from_column=20064">区块链服务</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/mq?from=20064&from_column=20064">消息队列</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/dsa?from=20064&from_column=20064">网络加速</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/tencentdb-catalog?from=20064&from_column=20064">云数据库</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cns?from=20064&from_column=20064">域名解析</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cos?from=20064&from_column=20064">云存储</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/css?from=20064&from_column=20064">视频直播</a></li></ul></div></div><div class="cdc-footer__recommend-cell"><h3 class="cdc-footer__recommend-title">热门推荐</h3><div class="cdc-footer__recommend-wrap"><ul class="cdc-footer__recommend-list"><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/facerecognition?from=20064&from_column=20064">人脸识别</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/tm?from=20064&from_column=20064">腾讯会议</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/act/pro/enterprise2019?from=20064&from_column=20064">企业云</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cdn-scd?from=20064&from_column=20064">CDN加速</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/trtc?from=20064&from_column=20064">视频通话</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/tiia?from=20064&from_column=20064">图像分析</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cdb?from=20064&from_column=20064">MySQL 数据库</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/symantecssl?from=20064&from_column=20064">SSL 证书</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/asr?from=20064&from_column=20064">语音识别</a></li></ul></div></div><div class="cdc-footer__recommend-cell"><h3 class="cdc-footer__recommend-title">更多推荐</h3><div class="cdc-footer__recommend-wrap"><ul class="cdc-footer__recommend-list"><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/solution/data_protection?from=20064&from_column=20064">数据安全</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/clb?from=20064&from_column=20064">负载均衡</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/sms?from=20064&from_column=20064">短信</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/ocr?from=20064&from_column=20064">文字识别</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/vod?from=20064&from_column=20064">云点播</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="https://tm.cloud.tencent.com?from=20064&from_column=20064">商标注册</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/solution/la?from=20064&from_column=20064">小程序开发</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cat?from=20064&from_column=20064">网站监控</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cdm?from=20064&from_column=20064">数据迁移</a></li></ul></div></div></div></div><div class="cdc-footer__copyright"><div class="cdc-footer__copyright-text"><p>Copyright © 2013 - 2024 Tencent Cloud. All Rights Reserved. 腾讯云版权所有 </p><p>深圳市腾讯计算机系统有限公司 ICP备案/许可证号：<a href="https://beian.miit.gov.cn/#/Integrated/index" target="_blank">粤B2-20090059 </a><a href="https://www.beian.gov.cn/portal/index.do" target="_blank">深公网安备号 44030502008569</a></p><p>腾讯云计算（北京）有限责任公司京ICP证150476号 |  <a href="https://beian.miit.gov.cn/#/Integrated/index" target="_blank">京ICP备11018762号</a> |  <a href="https://www.beian.gov.cn/portal/index.do" target="_blank">京公网安备号11010802020287</a></p></div></div></div></div></div><div class="com-widget-global"><div style="position:relative;z-index:8088"><div class="com-widget-global2"><div class="com-widget-global2__btn code"><div class="com-widget-global2__btn-tag">领券</div></div><div class="com-widget-global2__btn top" style="visibility:hidden"></div></div></div></div><div id="dialog-root"></div><div id="rno-dialog-root" class="rno-modal-wrap"></div></div><script>window.isServerContext = false; window.isClientContext = true;</script><script>window.$serverTime = 1734092488870; window.$clientTime = 1734092488870;</script><script class="">window.$ua = {"browser":{"name":"IE","version":"7.0","major":"7"},"cpu":{},"device":{},"engine":{},"os":{"name":"Windows","version":"Vista"}};</script><script src="//cloudcache.tencent-cloud.com/qcloud/developer/scripts/release/libs/dom4/1.8.3/dom4.js"></script><script src="https://cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/vendors/babel/polyfill.6.26.min.js"></script><script src="https://cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/vendors/react/react.16.8.6.min.js"></script><script src="https://cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/vendors/react/react-dom.16.8.6.min.js"></script><script src="https://cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/vendors/jquery-3.2.1.min.js"></script><script src="//cloudcache.tencent-cloud.com/qcloud/developer/scripts/release/base.e1782d07ea.js?max_age=31536000" crossorigin="anonymous"></script><script src="//cloudcache.tencent-cloud.com/qcloud/draft-master/dist/draft-master-v2.0.142.d4s2ddo9sb.js?max_age=31536000"></script><script src="https://cloud.tencent.com/qccomponent/login/api.js"></script><script src="//cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/deps/wechatJsSdk.js?version=1_0_1&max_age=31536000"></script><script src="//cloudcache.tencent-cloud.com/qcloud/developer/scripts/release/common.e23283971f.js?max_age=31536000" crossorigin="anonymous"></script><script src="https://web.sdk.qcloud.com/player/tcplayer/release/v4.7.2/tcplayer.v4.7.2.min.js"></script><script src="//dscache.tencent-cloud.cn/ecache/qcstat/qcloud/qcloudStatApi.js"></script><script src="https://qccommunity.qcloudimg.com/common/exposure-plugin-4.1.15.min.js"></script><script src="https://qccommunity.qcloudimg.com/community-track/qcloud-community-track.min.js"></script><script src="https://dscache.tencent-cloud.com/sdk/dianshi-sdk/loader/umd/dianshi-sdk-loader.v0.0.18.js"></script><script src="//cloudcache.tencent-cloud.com/qcloud/developer/scripts/release/tag/tag-detail.b7b96ccc37.js?max_age=31536000" crossorigin="anonymous"></script><script class=""> window.$render({"tagInfo":{"id":17917,"name":"LLM","icon":"","defaultIcon":"//cloudcache.tencent-cloud.com/open_proj/proj_qcloud_v2/gateway/q-and-a/css/img/tags/tag_comm.svg","shareIcon":"https://cloudcache.tencent-cloud.com/open_proj/proj_qcloud_v2/gateway/q-and-a/css/img/tags/share_comm.png","initial":"L","desc":"","followCount":0,"questionCount":3,"answerCount":1,"unanswerCount":2,"articleCount":869,"devdocCount":0,"vlogCount":6,"boundProductId":0,"stick":{"articleIds":[],"askIds":[],"vlogIds":[]},"createTime":"2023-08-08 10:47:23"},"activeRelatedEntry":"article","timelineData":{"ask":{"fetchStatus":"none","done":false,"nextPageNumber":1,"pageSize":20,"total":0,"list":[]},"article":{"fetchStatus":"loaded","done":false,"nextPageNumber":2,"pageSize":20,"total":869,"list":[{"id":2476693,"articleId":2476693,"title":"Prompt提示工程上手指南(七)Prompt编写实战-基于智能客服问答系统下的Prompt编写","content":"","plain":"","brief":"","summary":"本系列文章从最初的基础原理与入门实践切入，一直延伸到主流策略、引导策略、RAG（检索增强生成）、思维树（ToT）与避免幻觉（Hallucination）的策略这...","abstract":"本系列文章从最初的基础原理与入门实践切入，一直延伸到主流策略、引导策略、RAG（检索增强生成）、思维树（ToT）与避免幻觉（Hallucination）的策略这...","posterSummary":"本系列文章从最初的基础原理与入门实践切入，一直延伸到主流策略、引导策略、RAG（检索增强生成）、思维树（ToT）与避免幻觉（Hallucination）的策略这种渐进的结构方便了对初学者和进阶者的双向照顾。初学者可以先理解基本概念，然后慢慢深入；有一定经验的读者则可以快速跳到策略章节，获取更高阶的经验和方法。在熟练掌握以上技能和熟悉概念理论之后，我们需付出实践，结合场景来实际操作检验一遍，达到融会...","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9822651/01e9b5a33e434924432cdc9af6632c01.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9822651/01e9b5a33e434924432cdc9af6632c01.png","sourceType":1,"sourceDetail":{},"channelType":0,"channelDetail":{},"authorId":9822651,"columnId":101888,"columnIds":[],"writeTime":1734079253,"updateTime":1734079253,"viewCount":15,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/0f630c59c68f9736ceee01048fd721eb.jpg","company":"江咨集团","introduce":"工作职责大数据开发，曾任人工智能工程师，擅长数据挖掘和数据分析。","isProfessionVerified":0,"nickname":"fanstuck","title":"数据开发工程师","uid":9822651,"id":9822651,"name":"fanstuck","avatar":"https://developer.qcloudimg.com/http-save/10011/0f630c59c68f9736ceee01048fd721eb.jpg"},"tags":[{"tagId":11560,"tagName":"媒体 AI","id":11560,"name":"媒体 AI"},{"tagId":15406,"tagName":"prompt","id":15406,"name":"prompt"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":10539,"tagName":"人工智能","id":10539,"name":"人工智能"}]},{"id":2475846,"articleId":2475846,"title":"Open-WebUI 接入腾讯混元大模型","content":"","plain":"","brief":"","summary":"我尝试使用openai协议的api key接入openwebui失败后，由生此文。","abstract":"我尝试使用openai协议的api key接入openwebui失败后，由生此文。","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-8322969/e3eb86c9fe4dcb4fe32ae1487c6b8a58.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-8322969/e3eb86c9fe4dcb4fe32ae1487c6b8a58.png","sourceType":1,"sourceDetail":{},"channelType":0,"channelDetail":{},"authorId":8322969,"columnId":104408,"columnIds":[],"writeTime":1733885986,"updateTime":1733885986,"viewCount":98,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/ef438a4b5d600af18e7549cbe487bd1c.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"lkevincc","title":"","uid":8322969,"id":8322969,"name":"lkevincc","avatar":"https://developer.qcloudimg.com/http-save/10011/ef438a4b5d600af18e7549cbe487bd1c.jpg"},"tags":[{"tagId":17970,"tagName":"腾讯混元大模型","id":17970,"name":"腾讯混元大模型"},{"tagId":17982,"tagName":"玩转腾讯混元大模型","id":17982,"name":"玩转腾讯混元大模型"},{"tagId":18033,"tagName":"第四期热点征文-大模型技术","id":18033,"name":"第四期热点征文-大模型技术"},{"tagId":15053,"tagName":"openai","id":15053,"name":"openai"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"}]},{"id":2475631,"articleId":2475631,"title":"基于LLM的单元测试生成，你在第几级？","content":"","plain":"","brief":"","summary":"选定一个被测方法(focal method)，将方法体的源码传给大模型，要求生成单元测试用例。这是不少所谓的可以赋能开发单测的大模型的方案。在某些厂商的demo...","abstract":"选定一个被测方法(focal method)，将方法体的源码传给大模型，要求生成单元测试用例。这是不少所谓的可以赋能开发单测的大模型的方案。在某些厂商的demo...","posterSummary":"选定一个被测方法(focal method)，将方法体的源码传给大模型，要求生成单元测试用例。这是不少所谓的可以赋能开发单测的大模型的方案。在某些厂商的demo中，求解一个Hello级别的用例生成还是OK的，一旦换到实际项目，就只能呵呵了。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-8035011/41fd458634d72e3453141764459dfd71.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-8035011/41fd458634d72e3453141764459dfd71.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":8035011,"columnId":90324,"columnIds":[],"writeTime":1733806873,"updateTime":1733806873,"viewCount":69,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/http-save/yehe-8035011/mzubfztt2s.jpeg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Antony","title":"","uid":8035011,"id":8035011,"name":"Antony","avatar":"https://ask.qcloudimg.com/http-save/yehe-8035011/mzubfztt2s.jpeg"},"tags":[{"tagId":10752,"tagName":"单元测试","id":10752,"name":"单元测试"},{"tagId":17302,"tagName":"基础","id":17302,"name":"基础"},{"tagId":17373,"tagName":"论文","id":17373,"name":"论文"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"}]},{"id":2475624,"articleId":2475624,"title":"CAMEL-AI团队参与发表Nature子刊啦!聚焦LLM如何重塑未来医疗 ~","content":"","plain":"","brief":"","summary":"LLM驱动的智能体系统是一种基于大语言模型（LLM）的增强型人工智能系统，通过集成多个模块实现从感知到行动的全流程功能。简单来说，它是一种具备感知、思考、决策和...","abstract":"LLM驱动的智能体系统是一种基于大语言模型（LLM）的增强型人工智能系统，通过集成多个模块实现从感知到行动的全流程功能。简单来说，它是一种具备感知、思考、决策和...","posterSummary":"LLM驱动的智能体系统是一种基于大语言模型（LLM）的增强型人工智能系统，通过集成多个模块实现从感知到行动的全流程功能。简单来说，它是一种具备感知、思考、决策和执行能力的“数字智能体”。LLM智能体主要结合了以下关键模块：","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-8199873/a6f3853d88aa6fa987abefad2daf58e2.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-8199873/a6f3853d88aa6fa987abefad2daf58e2.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":8199873,"columnId":90776,"columnIds":[],"writeTime":1733806544,"updateTime":1733806544,"viewCount":71,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/6df15c7b18b1f3371d7cdabf07705d88.jpg","company":"博士在读","introduce":"Data Science and AI Empowered Drug Discovery and Life Science.","isProfessionVerified":0,"nickname":"DrugAI","title":"AI药物发现、计算生物学","uid":8199873,"id":8199873,"name":"DrugAI","avatar":"https://developer.qcloudimg.com/http-save/10011/6df15c7b18b1f3371d7cdabf07705d88.jpg"},"tags":[{"tagId":10570,"tagName":"医疗","id":10570,"name":"医疗"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17506,"tagName":"系统","id":17506,"name":"系统"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":10539,"tagName":"人工智能","id":10539,"name":"人工智能"}]},{"id":2474889,"articleId":2474889,"title":"LLM赋能测试活动实现端到端自动化的四个环节八项关键任务","content":"","plain":"","brief":"","summary":"在这个环节不是直接应用LLM，而是说通过LLM pipeline的编排，把测试环境、测试数据的动态获取、测试用例的发起执行等任务通过 LLM tools 模块能...","abstract":"在这个环节不是直接应用LLM，而是说通过LLM pipeline的编排，把测试环境、测试数据的动态获取、测试用例的发起执行等任务通过 LLM tools 模块能...","posterSummary":"在这个环节不是直接应用LLM，而是说通过LLM pipeline的编排，把测试环境、测试数据的动态获取、测试用例的发起执行等任务通过 LLM tools 模块能进行编排，让其成为整个LLM驱动端到端测试自动化的关键一环。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-8035011/eecc96a9309b7a43fa7b2c35aff9991f.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-8035011/eecc96a9309b7a43fa7b2c35aff9991f.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":8035011,"columnId":90324,"columnIds":[],"writeTime":1733720525,"updateTime":1733720525,"viewCount":100,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/http-save/yehe-8035011/mzubfztt2s.jpeg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Antony","title":"","uid":8035011,"id":8035011,"name":"Antony","avatar":"https://ask.qcloudimg.com/http-save/yehe-8035011/mzubfztt2s.jpeg"},"tags":[{"tagId":10669,"tagName":"自动化","id":10669,"name":"自动化"},{"tagId":10671,"tagName":"运维","id":10671,"name":"运维"},{"tagId":10732,"tagName":"自动化测试","id":10732,"name":"自动化测试"},{"tagId":17205,"tagName":"测试","id":17205,"name":"测试"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"}]},{"id":2474511,"articleId":2474511,"title":"LLM 时代：Java 如何设计一个及格的 AIGC 框架","content":"","plain":"","brief":"","summary":"大语言模型（LLM）的风口持续了两年的现在，想让他可以为之前的企业应用赋能，首选的第一开发语言还是 Python。但实际上，Java 才是在 Web 应用开发领...","abstract":"大语言模型（LLM）的风口持续了两年的现在，想让他可以为之前的企业应用赋能，首选的第一开发语言还是 Python。但实际上，Java 才是在 Web 应用开发领...","posterSummary":"大语言模型（LLM）的风口持续了两年的现在，想让他可以为之前的企业应用赋能，首选的第一开发语言还是 Python。但实际上，Java 才是在 Web 应用开发领域的老大哥。Java 是如何给于大语言模型应用（LLMs）交出答卷的呢？LangChain4j，Spring AI，以及各家模型厂商的 SDK。","description":"","picture":"https://developer.qcloudimg.com/http-save/3610078/741701b1a0e83e5d2c46584d4d95792d.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/3610078/741701b1a0e83e5d2c46584d4d95792d.jpg","sourceType":1,"sourceDetail":{},"channelType":0,"channelDetail":{},"authorId":3610078,"columnId":103882,"columnIds":[],"writeTime":1733496920,"updateTime":1733496920,"viewCount":79,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/1c56351cbf28b96d68081972914a936d.jpg","company":"通华科技（大连）","introduce":"高强度5G冲浪错峰睡觉摆烂全干工程师","isProfessionVerified":1,"nickname":"花花Binki","title":"后端开发","uid":3610078,"id":3610078,"name":"花花Binki","avatar":"https://developer.qcloudimg.com/http-save/10011/1c56351cbf28b96d68081972914a936d.jpg"},"tags":[{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":10164,"tagName":"java","id":10164,"name":"java"},{"tagId":11746,"tagName":"aigc","id":11746,"name":"aigc"}]},{"id":2474048,"articleId":2474048,"title":"解密prompt系列44. RAG探索模式？深度思考模式？","content":"","plain":"","brief":"","summary":"前一阵多步RAG的风吹入了工业界，kimi推出了探索版本，各应用都推出了深度搜索，You.COM更是早就有了Genius的多步模式。其实都是类似multi-ho...","abstract":"前一阵多步RAG的风吹入了工业界，kimi推出了探索版本，各应用都推出了深度搜索，You.COM更是早就有了Genius的多步模式。其实都是类似multi-ho...","posterSummary":"前一阵多步RAG的风吹入了工业界，kimi推出了探索版本，各应用都推出了深度搜索，You.COM更是早就有了Genius的多步模式。其实都是类似multi-hop RAG的实现。之前学术界在讨论multi-hop RAG的时候总是给一些基于历史知识类的问题，什么某年诺贝尔奖的获奖人在哪读的大学呀，给人一种错觉就是这类问题现实世界里真的有人这么提问么？其实还真有！","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-6190096/ec09bd2a9be2172b7ef7b6024a6f5fe8.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-6190096/ec09bd2a9be2172b7ef7b6024a6f5fe8.png","sourceType":1,"sourceDetail":{},"channelType":0,"channelDetail":{},"authorId":6190096,"columnId":80546,"columnIds":[],"writeTime":1733443096,"updateTime":1733443096,"viewCount":155,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/84dea5a4f42672f8a734080db2d8086e.jpg","company":"","introduce":"想做健身博主的算法工程师","isProfessionVerified":0,"nickname":"风雨中的小七","title":"","uid":6190096,"id":6190096,"name":"风雨中的小七","avatar":"https://developer.qcloudimg.com/http-save/10011/84dea5a4f42672f8a734080db2d8086e.jpg"},"tags":[{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":14918,"tagName":"nlp","id":14918,"name":"nlp"}]},{"id":2473664,"articleId":2473664,"title":"【NLP】BLEU（Bilingual Evaluation Understudy）评分","content":"","plain":"","brief":"","summary":"BLEU（Bilingual Evaluation Understudy）是一种广泛用于评估机器翻译和自然语言生成任务质量的指标。BLEU-4评分是基于四个n-...","abstract":"BLEU（Bilingual Evaluation Understudy）是一种广泛用于评估机器翻译和自然语言生成任务质量的指标。BLEU-4评分是基于四个n-...","posterSummary":"BLEU（Bilingual Evaluation Understudy）是一种广泛用于评估机器翻译和自然语言生成任务质量的指标。BLEU-4评分是基于四个n-gram（从单个词到四词组合）匹配度的加权几何平均值，旨在衡量生成文本与参考文本之间的相似性。","description":"","picture":"","coverImageUrl":"","sourceType":1,"sourceDetail":{},"channelType":0,"channelDetail":{},"authorId":10919134,"columnId":103259,"columnIds":[],"writeTime":1733305742,"updateTime":1733305742,"viewCount":157,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/bb1ac398708cdc8942f88d84648af82e.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"云帆沧海","title":"","uid":10919134,"id":10919134,"name":"云帆沧海","avatar":"https://developer.qcloudimg.com/http-save/10011/bb1ac398708cdc8942f88d84648af82e.jpg"},"tags":[{"tagId":14918,"tagName":"nlp","id":14918,"name":"nlp"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"}]},{"id":2472881,"articleId":2472881,"title":"ComfyUI Party：将LLM与图片工作流集成，图片、语音、文本、视觉一体！（graphRAG、ollama）","content":"","plain":"","brief":"","summary":"这个工具挺酷的，他专注于LLM集成进ComfyUI里面。旨在基于comfyui作为前端，开发一套完整的LLM工作流构建节点，让用户可以快速便捷地构建自己的LLM...","abstract":"这个工具挺酷的，他专注于LLM集成进ComfyUI里面。旨在基于comfyui作为前端，开发一套完整的LLM工作流构建节点，让用户可以快速便捷地构建自己的LLM...","posterSummary":"这个工具挺酷的，他专注于LLM集成进ComfyUI里面。旨在基于comfyui作为前端，开发一套完整的LLM工作流构建节点，让用户可以快速便捷地构建自己的LLM工作流，并轻松集成到现有的图片工作流中。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/1dfc42d3ab930230f210174299b6e450.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/1dfc42d3ab930230f210174299b6e450.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733139398,"updateTime":1733139398,"viewCount":92,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":17562,"tagName":"语音","id":17562,"name":"语音"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":17276,"tagName":"工具","id":17276,"name":"工具"},{"tagId":17285,"tagName":"工作流","id":17285,"name":"工作流"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"}]},{"id":2472873,"articleId":2472873,"title":"本地AI文件管理器：AI驱动+私有LLM，免费整理你的文件库","content":"","plain":"","brief":"","summary":"借助完全私有且本地运行的LLM（大语言模型），你可以整理PNG文件、JPG、JPEG、GIF、BMP格式的图片。对于文本类文件，你可以使用TXT和DOCX格式，...","abstract":"借助完全私有且本地运行的LLM（大语言模型），你可以整理PNG文件、JPG、JPEG、GIF、BMP格式的图片。对于文本类文件，你可以使用TXT和DOCX格式，...","posterSummary":"借助完全私有且本地运行的LLM（大语言模型），你可以整理PNG文件、JPG、JPEG、GIF、BMP格式的图片。对于文本类文件，你可以使用TXT和DOCX格式，此外还能整理PDF文件。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/e958834a67012d1d526618aa3dcfca6c.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/e958834a67012d1d526618aa3dcfca6c.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733139188,"updateTime":1733139188,"viewCount":119,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":17276,"tagName":"工具","id":17276,"name":"工具"},{"tagId":17341,"tagName":"开发者","id":17341,"name":"开发者"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17506,"tagName":"系统","id":17506,"name":"系统"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"}]},{"id":2472870,"articleId":2472870,"title":"g1：o1推理链开源实现，原理竟如此简单！解决 60-80% 的困扰LLM的简单逻辑问题","content":"","plain":"","brief":"","summary":"它的提示词是一种动态思维链，允许LLM “思考”并解决一些通常会困扰领先模型的逻辑问题。在每一步中， LLM都可以选择继续另一个推理步骤，或提供最终答案。每个步...","abstract":"它的提示词是一种动态思维链，允许LLM “思考”并解决一些通常会困扰领先模型的逻辑问题。在每一步中， LLM都可以选择继续另一个推理步骤，或提供最终答案。每个步...","posterSummary":"它的提示词是一种动态思维链，允许LLM “思考”并解决一些通常会困扰领先模型的逻辑问题。在每一步中， LLM都可以选择继续另一个推理步骤，或提供最终答案。每个步骤都有标题并且对用户可见。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/71adfe90bf1f54ad5b89e8af501cbaa7.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/71adfe90bf1f54ad5b89e8af501cbaa7.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733139157,"updateTime":1733139157,"viewCount":86,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":17205,"tagName":"测试","id":17205,"name":"测试"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17566,"tagName":"原理","id":17566,"name":"原理"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":10667,"tagName":"开源","id":10667,"name":"开源"}]},{"id":2472861,"articleId":2472861,"title":"Crawl4AI：AI驱动的网页抓取神器，结合LLM实现自动化数据提取与处理","content":"","plain":"","brief":"","summary":"让我们跳转到实际操作中，看看如何做到这一点。这是他们的 GitHub 仓库页面，你可以看到这是一个开源的 LLM 友好型网页爬虫和抓取工具。","abstract":"让我们跳转到实际操作中，看看如何做到这一点。这是他们的 GitHub 仓库页面，你可以看到这是一个开源的 LLM 友好型网页爬虫和抓取工具。","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/175c2c65d125ca196db4dfa42c593998.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/175c2c65d125ca196db4dfa42c593998.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733138493,"updateTime":1733138493,"viewCount":212,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":10669,"tagName":"自动化","id":10669,"name":"自动化"},{"tagId":17276,"tagName":"工具","id":17276,"name":"工具"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":10548,"tagName":"网站","id":10548,"name":"网站"}]},{"id":2472859,"articleId":2472859,"title":"Reflection 70B（已全面测试）：这个开源 LLM 击败了 Claude 3.5 Sonnet 和 GPT-4O？","content":"","plain":"","brief":"","summary":"这款模型名为Reflection 70B，之所以取这个名字，是因为它采用了一种新的训练技术，叫做反思微调（Reflection Tuning），这种技术教大语言...","abstract":"这款模型名为Reflection 70B，之所以取这个名字，是因为它采用了一种新的训练技术，叫做反思微调（Reflection Tuning），这种技术教大语言...","posterSummary":"这款模型名为Reflection 70B，之所以取这个名字，是因为它采用了一种新的训练技术，叫做反思微调（Reflection Tuning），这种技术教大语言模型（LLM）检测自己的推理错误并进行自我纠正。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/f396575778c213d2fd5f108ddbb67ed7.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/f396575778c213d2fd5f108ddbb67ed7.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733138407,"updateTime":1733138407,"viewCount":58,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":15657,"tagName":"reflection","id":15657,"name":"reflection"},{"tagId":17205,"tagName":"测试","id":17205,"name":"测试"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":10667,"tagName":"开源","id":10667,"name":"开源"},{"tagId":13755,"tagName":"gpt","id":13755,"name":"gpt"}]},{"id":2472848,"articleId":2472848,"title":"Zed AI + Ollama：最强开源AI代码编辑器，轻松配置本地LLM模型（Phi 3.5 & Llama-3.1）","content":"","plain":"","brief":"","summary":"此外，Zed的多LLM配置选项也很nice，你可以从本地模型开始，如果觉得本地模型不行，你可以选择更大的模型来使用。","abstract":"此外，Zed的多LLM配置选项也很nice，你可以从本地模型开始，如果觉得本地模型不行，你可以选择更大的模型来使用。","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/ed80fd097b716aa5ab81c1d9889088f2.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/ed80fd097b716aa5ab81c1d9889088f2.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733138183,"updateTime":1733138183,"viewCount":164,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":10667,"tagName":"开源","id":10667,"name":"开源"},{"tagId":17186,"tagName":"编辑器","id":17186,"name":"编辑器"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17393,"tagName":"配置","id":17393,"name":"配置"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"}]},{"id":2472845,"articleId":2472845,"title":"MinerU、Doc2X、OmniParse、llm_aided_ocr 四款流行OCR工具测评（LLM & RAG数据准备）","content":"","plain":"","brief":"","summary":"删除\\m，就会正常，而Doc2X通常很少出现这种情况，我可以预先告诉你，Doc2X是这4个中最好的，但是他也有一些缺陷，我会在后文说。","abstract":"删除\\m，就会正常，而Doc2X通常很少出现这种情况，我可以预先告诉你，Doc2X是这4个中最好的，但是他也有一些缺陷，我会在后文说。","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/eb638f69996bd3e33438a33ca92d39e8.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/eb638f69996bd3e33438a33ca92d39e8.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733138113,"updateTime":1733138113,"viewCount":215,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":15010,"tagName":"ocr","id":15010,"name":"ocr"},{"tagId":17203,"tagName":"部署","id":17203,"name":"部署"},{"tagId":17276,"tagName":"工具","id":17276,"name":"工具"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2472843,"articleId":2472843,"title":"Triplex vs. GPT-4：将Graph RAG成本降低98%的革命性模型、知识图谱构建的 SOTA LLM！","content":"","plain":"","brief":"","summary":"知识图谱（例如 Microsoft 的Graph RAG）增强了 RAG 方法，但构建成本高昂。Triplex 可将知识图谱创建成本降低 98%，性能优于 GP...","abstract":"知识图谱（例如 Microsoft 的Graph RAG）增强了 RAG 方法，但构建成本高昂。Triplex 可将知识图谱创建成本降低 98%，性能优于 GP...","posterSummary":"知识图谱（例如 Microsoft 的Graph RAG）增强了 RAG 方法，但构建成本高昂。Triplex 可将知识图谱创建成本降低 98%，性能优于 GPT-4，成本仅为 GPT-4 的 1/60。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/eacaad7250478e2f2160a21232b686e3.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/eacaad7250478e2f2160a21232b686e3.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733138094,"updateTime":1733138094,"viewCount":67,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":13769,"tagName":"graph","id":13769,"name":"graph"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":10471,"tagName":"知识图谱","id":10471,"name":"知识图谱"},{"tagId":13755,"tagName":"gpt","id":13755,"name":"gpt"}]},{"id":2472839,"articleId":2472839,"title":"Kimi+Langchain+FastGPT：文档转LLM微调数据集 / QA问答对生成、Kimi 128KAPI免费接入！","content":"","plain":"","brief":"","summary":"今天我将介绍：如何使用Kimi API将文档转换为LLM指令监督微调数据集（Alpaca 格式）以及如何部署FastGPT并接入Kimi API：","abstract":"今天我将介绍：如何使用Kimi API将文档转换为LLM指令监督微调数据集（Alpaca 格式）以及如何部署FastGPT并接入Kimi API：","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/40dea31b061d7d46e782f7d08338cb1c.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/40dea31b061d7d46e782f7d08338cb1c.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733138011,"updateTime":1733138011,"viewCount":136,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":17393,"tagName":"配置","id":17393,"name":"配置"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":17196,"tagName":"表格","id":17196,"name":"表格"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"}]},{"id":2472831,"articleId":2472831,"title":"DeepSeek-Coder-V2.1：最佳编码LLM再度升级！（经过全面测试并击败 Claude，GPT-4o）","content":"","plain":"","brief":"","summary":"DeepSeek-V2又双叒升级了，最强开源模型！（DeepSeek-Chat-V2.1开源 & 全面测试）","abstract":"DeepSeek-V2又双叒升级了，最强开源模型！（DeepSeek-Chat-V2.1开源 & 全面测试）","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/b10de2608b2e885bd07f3b4470d31d5c.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/b10de2608b2e885bd07f3b4470d31d5c.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733137808,"updateTime":1733137808,"viewCount":91,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":17205,"tagName":"测试","id":17205,"name":"测试"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":13755,"tagName":"gpt","id":13755,"name":"gpt"},{"tagId":17189,"tagName":"编码","id":17189,"name":"编码"}]},{"id":2472825,"articleId":2472825,"title":"Mem0 AI：开源一天斩获万星！超越 RAG、为LLM、Agent加上超强个性记忆！","content":"","plain":"","brief":"","summary":"最近，OpenAI 投资了 370 万美金给一个叫 Dot 的应用，这个应用背后的核心技术是「超强个性记忆」，现在由 Mem0 开源了。","abstract":"最近，OpenAI 投资了 370 万美金给一个叫 Dot 的应用，这个应用背后的核心技术是「超强个性记忆」，现在由 Mem0 开源了。","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/b64a623d9efb4fbd7ff2b0ab900a8284.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/b64a623d9efb4fbd7ff2b0ab900a8284.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733137634,"updateTime":1733137634,"viewCount":95,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"},{"tagId":10666,"tagName":"游戏","id":10666,"name":"游戏"},{"tagId":10667,"tagName":"开源","id":10667,"name":"开源"},{"tagId":11736,"tagName":"agent","id":11736,"name":"agent"},{"tagId":17276,"tagName":"工具","id":17276,"name":"工具"}]},{"id":2472824,"articleId":2472824,"title":"Mistral NeMo：这是现在最好的开源LLM！（经过全面测试并击败 Qwen2、DeepSeek-V2 及其他）","content":"","plain":"","brief":"","summary":"它在编码任务方面甚至更好，并且也非常擅长做文本到应用程序、文本到前端和其他事情。我将对其进行测试，看看它是否真的可以击败其他LLMs，并且我还将告诉你如何使用它...","abstract":"它在编码任务方面甚至更好，并且也非常擅长做文本到应用程序、文本到前端和其他事情。我将对其进行测试，看看它是否真的可以击败其他LLMs，并且我还将告诉你如何使用它...","posterSummary":"它在编码任务方面甚至更好，并且也非常擅长做文本到应用程序、文本到前端和其他事情。我将对其进行测试，看看它是否真的可以击败其他LLMs，并且我还将告诉你如何使用它。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-9836881/bf014f77b1e34bf92ef4d7d21beb6180.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-9836881/bf014f77b1e34bf92ef4d7d21beb6180.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":9836881,"columnId":104314,"columnIds":[],"writeTime":1733137575,"updateTime":1733137575,"viewCount":82,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"AI进修生","title":"","uid":9836881,"id":9836881,"name":"AI进修生","avatar":"https://developer.qcloudimg.com/http-save/10011/014478f2b75149c90c6c0d48865a5ff0.jpg"},"tags":[{"tagId":10667,"tagName":"开源","id":10667,"name":"开源"},{"tagId":17189,"tagName":"编码","id":17189,"name":"编码"},{"tagId":17205,"tagName":"测试","id":17205,"name":"测试"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17917,"tagName":"LLM","id":17917,"name":"LLM"}]}]},"video":{"fetchStatus":"none","done":false,"nextPageNumber":1,"pageSize":20,"total":0,"list":[]}},"relatedProducts":[{"id":0,"type":1,"name":"","cnName":"","iconUrl":"//cloudcache.tencent-cloud.com/qcloud/developer/images/release/team/product-default-icon.v1.svg","intro":"","introUrl":"","desc":"","documentUrl":"","features":"null","weight":0}],"relatedDevdocs":[],"activeUsers":[],"hotColumns":[{"id":1081,"name":"腾讯云服务器团队的专栏","desc":"","icon":"https://imgcache.qq.com/qcloud/developer/images/release/column-icons/7.png","background":"","status":2,"creatorId":859966,"memberCount":1,"articleCount":206,"followCount":319,"createdTime":1485082539,"creator":{"id":859966,"uid":859966,"name":"腾讯云计算产品团队","label":"腾讯云 CVM","avatar":"https://ask.qcloudimg.com/http-save/yehe-900000/57548b27ada32a860de54d545a535f2f.png","province":"1213","city":"1216","company":"腾讯云","title":"产品团队","school":"","major":"","homePage":"","region":1,"jobType":1,"graduationDate":"","education":0,"specialityIds":[10292,10539,10333,10207,10308],"specialities":[],"gender":1,"trade":"","growthLevel":0,"isProfessionVerified":true,"upvoteCount":0,"followingCount":1,"followerCount":251,"questionCount":0,"answerCount":0,"followQuestionCount":0,"followTagCount":2,"favorAnswerCount":0,"beHandPickedCount":0,"followColumnCount":3,"articleCount":209,"validArticleCount":207}},{"id":1283,"name":"腾讯技术工程官方号的专栏","desc":"","icon":"https://ask.qcloudimg.com/column-icons/1283/170434/hcgwwmih7d.jpg","background":"","status":2,"creatorId":170434,"memberCount":2,"articleCount":1119,"followCount":914,"createdTime":1496643325,"creator":{"id":170434,"uid":170434,"name":"腾讯技术工程官方号","label":"腾讯技术工程事业群官方微信公众号","avatar":"https://ask.qcloudimg.com/http-save/yehe-170434/568f3e8410f6654284c65b8e886345e3.png","province":"1213","city":"1216","company":"腾讯","title":"产品经理","school":"","major":"","homePage":"","region":1,"jobType":1,"graduationDate":"","education":0,"specialityIds":[10539,10244,10149,10333,10245],"specialities":[],"gender":1,"trade":"","growthLevel":0,"isProfessionVerified":true,"upvoteCount":0,"followingCount":1,"followerCount":1580,"questionCount":0,"answerCount":0,"followQuestionCount":0,"followTagCount":0,"favorAnswerCount":0,"beHandPickedCount":0,"followColumnCount":2,"articleCount":1122,"validArticleCount":1119}},{"id":1589,"name":"深度学习思考者","desc":"","icon":"https://imgcache.qq.com/qcloud/developer/images/release/column-icons/4.png","background":"","status":2,"creatorId":1147573,"memberCount":1,"articleCount":89,"followCount":42,"createdTime":1512960483,"creator":{"id":1147573,"uid":1147573,"name":"深度学习思考者","label":"深度学习研究员","avatar":"https://ask.qcloudimg.com/avatar/1147573/ukwqo56o1w.png","province":"","city":"","company":"","title":"","school":"","major":"","homePage":"","region":1,"jobType":1,"graduationDate":"","education":0,"specialityIds":[10149,10333,10539,10169,10332],"specialities":[],"gender":1,"trade":"","growthLevel":0,"isProfessionVerified":false,"upvoteCount":0,"followingCount":1,"followerCount":37,"questionCount":0,"answerCount":0,"followQuestionCount":0,"followTagCount":0,"favorAnswerCount":0,"beHandPickedCount":0,"followColumnCount":2,"articleCount":89,"validArticleCount":89}},{"id":1591,"name":"素质云笔记","desc":"素质云笔记/Recorder... Research Area：多模态+计算机视觉舆情","icon":"https://ask.qcloudimg.com/column-icons/1591/1051732/2xiz3tlcjb.jpg","background":"","status":2,"creatorId":1051732,"memberCount":1,"articleCount":421,"followCount":113,"createdTime":1512960798,"creator":{"id":1051732,"uid":1051732,"name":"悟乙己","label":"可以关注我的知乎：https://www.zhihu.com/people/mattzheng7","avatar":"https://ask.qcloudimg.com/http-save/yehe-1051732/4d1dd6a8e273842f65600c6efb9c38f8.jpeg","province":"1081","city":"","company":"野生","title":"数据科学家","school":"","major":"","homePage":"http://blog.csdn.net/sinat_26917383","region":1,"jobType":1,"graduationDate":"","education":0,"specialityIds":[10149,10169,10539,10333,121],"specialities":[],"gender":1,"trade":"whcm","growthLevel":0,"isProfessionVerified":false,"upvoteCount":0,"followingCount":1,"followerCount":360,"questionCount":0,"answerCount":0,"followQuestionCount":0,"followTagCount":0,"favorAnswerCount":0,"beHandPickedCount":0,"followColumnCount":2,"articleCount":421,"validArticleCount":421}}],"recommendedTags":[],"env":"production","documentBaseTitle":"腾讯云开发者社区-腾讯云","cdnDomain":"cloudcache.tencent-cloud.cn","cssDomain":"cloudcache.tencent-cloud.cn","qcloudDomain":"cloud.tencent.com","consoleDomain":"console.cloud.tencent.com","qcommunity_identify_id":"-D8oY6u2tJ0Xhi3uzmstX","session":{"isLogined":false,"isQcloudUser":false,"isOwner":false,"nickname":"","accountInfoCompleted":false,"phoneCompleted":false,"profile":{},"contactPhoneCompleted":false,"userInfo":{}},"pvId":"iAT0KjopFRbEqxZYx_LhA","userIp":"8.222.208.146","fromMiniProgram":false,"route":{"url":"/developer/tag/17917","path":"/developer/tag/17917","pathname":"/developer/tag/17917","search":null,"query":{},"segments":["developer","tag","17917"]}}); </script><script class=""> if (!Element.prototype.matches) Element.prototype.matches = Element.prototype.msMatchesSelector || Element.prototype.webkitMatchesSelector; if (!Element.prototype.closest) Element.prototype.closest = function(s) { var el = this; if (!document.documentElement.contains(el)) return null; do { if (el.matches(s)) return el; el = el.parentElement; } while (el !== null); return null; }; window.addEventListener('mouseover', function(evt) { const target = evt.target; if (!target) { return; } const aEle = target.closest('a'); if (!aEle) { return; } let href = aEle.getAttribute('href'); if (!href) { return; } href = href.replace(/cloud.tencent.com.cn|cloud.tencent.com|cloud.tencent.cn/g, 'cloud.tencent.com'); aEle.setAttribute('href', href); }, true); </script></body></html>