2026-06-15 15:53:57 +08:00
|
|
|
|
<!DOCTYPE html>
|
|
|
|
|
|
<html lang="zh-CN">
|
|
|
|
|
|
<head>
|
|
|
|
|
|
<meta charset="UTF-8" />
|
|
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
|
|
|
|
<title>Siemens RAGAS 评估控制台</title>
|
|
|
|
|
|
<link rel="stylesheet" href="/static/css/app.css" />
|
|
|
|
|
|
<script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.1/dist/chart.umd.min.js"></script>
|
|
|
|
|
|
</head>
|
|
|
|
|
|
<body>
|
|
|
|
|
|
<div class="app">
|
|
|
|
|
|
<!-- 左侧导航（布局 A） -->
|
|
|
|
|
|
<aside class="sidebar">
|
|
|
|
|
|
<div class="brand">
|
|
|
|
|
|
<div class="brand-mark">RAGAS</div>
|
|
|
|
|
|
<div class="brand-sub">评估控制台</div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<nav class="nav">
|
|
|
|
|
|
<button class="nav-item" data-view="runs">
|
|
|
|
|
|
<span class="nav-ico">▢</span><span>运行列表</span>
|
|
|
|
|
|
</button>
|
|
|
|
|
|
<button class="nav-item" data-view="new">
|
|
|
|
|
|
<span class="nav-ico">＋</span><span>新建评估</span>
|
|
|
|
|
|
</button>
|
2026-06-16 17:55:07 +08:00
|
|
|
|
<button class="nav-item" data-view="report" data-requires-run="1" disabled>
|
2026-06-15 15:53:57 +08:00
|
|
|
|
<span class="nav-ico">▤</span><span>报告详情</span>
|
|
|
|
|
|
</button>
|
2026-06-16 16:25:20 +08:00
|
|
|
|
<button class="nav-item" data-view="profiles">
|
|
|
|
|
|
<span class="nav-ico">⚙</span><span>LLM 配置</span>
|
|
|
|
|
|
</button>
|
2026-06-15 15:53:57 +08:00
|
|
|
|
</nav>
|
|
|
|
|
|
<div class="sidebar-foot">
|
|
|
|
|
|
<span class="dot" id="health-dot"></span>
|
|
|
|
|
|
<span id="health-text">连接中…</span>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</aside>
|
|
|
|
|
|
|
|
|
|
|
|
<!-- 主内容区 -->
|
|
|
|
|
|
<main class="main">
|
|
|
|
|
|
<header class="topbar">
|
|
|
|
|
|
<h1 id="view-title">运行列表</h1>
|
|
|
|
|
|
<button class="btn btn-ghost" id="refresh-btn">刷新</button>
|
|
|
|
|
|
</header>
|
|
|
|
|
|
|
|
|
|
|
|
<!-- 运行列表视图 -->
|
|
|
|
|
|
<section class="view" id="view-runs">
|
|
|
|
|
|
<div id="runs-container" class="runs-grid"></div>
|
|
|
|
|
|
<div class="empty" id="runs-empty" hidden>
|
|
|
|
|
|
<p>暂无评估运行。</p>
|
|
|
|
|
|
<p class="muted">从「新建评估」触发一次，或运行示例数据生成脚本：<code>python scripts/seed_sample_run.py</code></p>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</section>
|
|
|
|
|
|
|
|
|
|
|
|
<!-- 新建评估视图 -->
|
|
|
|
|
|
<section class="view" id="view-new" hidden>
|
|
|
|
|
|
<div class="panel">
|
|
|
|
|
|
<h2>选择场景并运行</h2>
|
|
|
|
|
|
<p class="muted">从 <code>scenarios/</code> 下选择一个场景配置，点击运行后在下方查看实时状态与日志。</p>
|
|
|
|
|
|
<div class="scenario-list" id="scenario-list"></div>
|
|
|
|
|
|
<div class="run-actions">
|
|
|
|
|
|
<button class="btn btn-primary" id="run-btn" disabled>运行评估</button>
|
|
|
|
|
|
<span class="selected-scenario muted" id="selected-scenario">未选择场景</span>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
2026-06-16 16:25:20 +08:00
|
|
|
|
|
|
|
|
|
|
<!-- LLM 角色配置面板（选中场景后显示） -->
|
|
|
|
|
|
<div class="panel llm-assignment-panel" id="llm-assignment-panel" hidden>
|
|
|
|
|
|
<h2>LLM 角色配置 <span class="muted" style="font-size:13px;font-weight:400">（可选）</span></h2>
|
|
|
|
|
|
<p class="muted" style="margin-bottom:14px">为不同任务角色选择已保存的 LLM 配置，留空则使用场景文件中的原始配置。</p>
|
|
|
|
|
|
<div class="llm-role-rows">
|
|
|
|
|
|
<div class="llm-role-row">
|
|
|
|
|
|
<label class="llm-role-label">评测打分 Judge LLM</label>
|
|
|
|
|
|
<select class="select llm-role-select" id="role-judge">
|
|
|
|
|
|
<option value="">— 使用场景原始配置 —</option>
|
|
|
|
|
|
</select>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="llm-role-row">
|
|
|
|
|
|
<label class="llm-role-label">生成答案 Answer LLM</label>
|
|
|
|
|
|
<select class="select llm-role-select" id="role-answer">
|
|
|
|
|
|
<option value="">— 使用场景原始配置 —</option>
|
|
|
|
|
|
</select>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="llm-role-row">
|
|
|
|
|
|
<label class="llm-role-label">生成题库 Dataset LLM</label>
|
|
|
|
|
|
<select class="select llm-role-select" id="role-dataset">
|
|
|
|
|
|
<option value="">— 使用场景原始配置 —</option>
|
|
|
|
|
|
</select>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
2026-06-15 15:53:57 +08:00
|
|
|
|
<div class="panel" id="task-panel" hidden>
|
|
|
|
|
|
<div class="task-head">
|
|
|
|
|
|
<h2>评估进度</h2>
|
|
|
|
|
|
<span class="badge" id="task-status">queued</span>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<pre class="log-box" id="task-log"></pre>
|
|
|
|
|
|
<div class="task-actions">
|
|
|
|
|
|
<button class="btn btn-primary" id="view-report-btn" hidden>查看报告</button>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</section>
|
|
|
|
|
|
|
|
|
|
|
|
<!-- 报告详情视图 -->
|
|
|
|
|
|
<section class="view" id="view-report" hidden>
|
2026-06-17 10:35:56 +08:00
|
|
|
|
<!-- 历史报告切换下拉（顶部，始终可见） -->
|
|
|
|
|
|
<div class="report-switcher no-print" id="report-switcher">
|
|
|
|
|
|
<label class="report-switcher-label">切换报告</label>
|
|
|
|
|
|
<select class="select report-switcher-select" id="report-switcher-select">
|
|
|
|
|
|
<option value="">— 加载中… —</option>
|
|
|
|
|
|
</select>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
2026-06-15 15:53:57 +08:00
|
|
|
|
<div class="empty" id="report-empty">
|
|
|
|
|
|
<p>请先从「运行列表」选择一次运行。</p>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div id="report-content" hidden>
|
|
|
|
|
|
<!-- 顶部元信息条 -->
|
|
|
|
|
|
<div class="report-meta" id="report-meta"></div>
|
2026-06-17 10:28:01 +08:00
|
|
|
|
<div class="report-actions no-print">
|
|
|
|
|
|
<button class="btn btn-ghost btn-export-pdf" id="export-pdf-btn" onclick="Report.exportPdf()">
|
|
|
|
|
|
📄 导出 PDF
|
|
|
|
|
|
</button>
|
|
|
|
|
|
</div>
|
2026-06-15 15:53:57 +08:00
|
|
|
|
|
|
|
|
|
|
<!-- ① 指标均值卡片 -->
|
|
|
|
|
|
<div class="section-label">① 指标均值 OVERVIEW</div>
|
|
|
|
|
|
<div class="metric-cards" id="metric-cards"></div>
|
|
|
|
|
|
|
|
|
|
|
|
<!-- ② 分布 + ③ 分组 并排 -->
|
|
|
|
|
|
<div class="report-row">
|
|
|
|
|
|
<div class="panel report-half">
|
|
|
|
|
|
<div class="panel-head">
|
|
|
|
|
|
<div class="section-label tight">② 分数分布</div>
|
|
|
|
|
|
<select id="dist-metric-select" class="select"></select>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<canvas id="dist-chart" height="160"></canvas>
|
|
|
|
|
|
<p class="muted tiny">暴露长尾失败样本</p>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="panel report-half">
|
|
|
|
|
|
<div class="section-label tight">③ 分组均值</div>
|
|
|
|
|
|
<div id="grouping-tabs" class="grouping-tabs"></div>
|
|
|
|
|
|
<div id="grouping-table"></div>
|
|
|
|
|
|
<p class="muted tiny">定位薄弱类别</p>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
<!-- ④ 最低分样本逐条复核 -->
|
|
|
|
|
|
<div class="section-label">④ 最低分样本（点击展开逐条复核）</div>
|
|
|
|
|
|
<div class="lowest-table" id="lowest-table"></div>
|
2026-06-16 17:26:37 +08:00
|
|
|
|
|
|
|
|
|
|
<!-- ⑤ 优化建议（optimization_advisor: true 时显示） -->
|
|
|
|
|
|
<div id="advice-section" hidden>
|
|
|
|
|
|
<div class="section-label">⑤ 优化建议 OPTIMIZATION ADVICE</div>
|
|
|
|
|
|
<div class="panel advice-panel">
|
|
|
|
|
|
<div class="advice-header">
|
|
|
|
|
|
<span class="advice-badge">AI 诊断报告</span>
|
|
|
|
|
|
<span class="advice-model" id="advice-model-label"></span>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="advice-body" id="advice-body"></div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
2026-06-15 15:53:57 +08:00
|
|
|
|
</div>
|
|
|
|
|
|
</section>
|
2026-06-16 16:25:20 +08:00
|
|
|
|
|
|
|
|
|
|
<!-- LLM 配置视图 -->
|
|
|
|
|
|
<section class="view" id="view-profiles" hidden>
|
|
|
|
|
|
<div class="panel">
|
|
|
|
|
|
<div class="panel-head">
|
|
|
|
|
|
<h2>LLM 配置管理</h2>
|
|
|
|
|
|
<button class="btn btn-primary" id="add-profile-btn">＋ 新建配置</button>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<p class="muted">保存常用 LLM 连接参数，在运行评估时按角色选择。</p>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
<!-- 新建 / 编辑表单（默认隐藏） -->
|
|
|
|
|
|
<div class="panel" id="profile-form-panel" hidden>
|
|
|
|
|
|
<h2 id="profile-form-title">新建 LLM 配置</h2>
|
|
|
|
|
|
<div class="profile-form">
|
|
|
|
|
|
<input type="hidden" id="edit-profile-id" />
|
|
|
|
|
|
<div class="form-row">
|
|
|
|
|
|
<label class="form-label">配置名称 <span class="req">*</span></label>
|
|
|
|
|
|
<input class="form-input" id="pf-name" placeholder="例：DeepSeek Flash（内网）" />
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="form-row">
|
|
|
|
|
|
<label class="form-label">模型名称 <span class="req">*</span></label>
|
|
|
|
|
|
<input class="form-input" id="pf-model" placeholder="例：deepseek-v4-flash" />
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="form-row">
|
|
|
|
|
|
<label class="form-label">Base URL <span class="req">*</span></label>
|
|
|
|
|
|
<input class="form-input" id="pf-base-url" placeholder="例：http://6.86.80.4:30080/v1" />
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="form-row">
|
|
|
|
|
|
<label class="form-label">API Key <span class="req">*</span></label>
|
|
|
|
|
|
<input class="form-input" id="pf-api-key" type="password" placeholder="sk-…" />
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="form-row">
|
|
|
|
|
|
<label class="form-label">超时（秒）</label>
|
|
|
|
|
|
<input class="form-input form-input-sm" id="pf-timeout" type="number" value="30" min="5" max="300" />
|
|
|
|
|
|
</div>
|
|
|
|
|
|
<div class="form-actions">
|
|
|
|
|
|
<button class="btn btn-primary" id="save-profile-btn">保存</button>
|
|
|
|
|
|
<button class="btn" id="cancel-profile-btn">取消</button>
|
|
|
|
|
|
<span class="form-error muted" id="profile-form-error"></span>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
<div id="profile-cards" class="profile-grid"></div>
|
|
|
|
|
|
<div class="empty" id="profiles-empty" hidden>
|
|
|
|
|
|
<p>尚未添加任何 LLM 配置。</p>
|
|
|
|
|
|
<p class="muted">点击「新建配置」添加第一个。</p>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
</section>
|
2026-06-15 15:53:57 +08:00
|
|
|
|
</main>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
<script src="/static/js/api.js"></script>
|
|
|
|
|
|
<script src="/static/js/report.js"></script>
|
2026-06-16 16:25:20 +08:00
|
|
|
|
<script src="/static/js/profiles.js"></script>
|
2026-06-15 15:53:57 +08:00
|
|
|
|
<script src="/static/js/runner.js"></script>
|
|
|
|
|
|
<script src="/static/js/app.js"></script>
|
|
|
|
|
|
</body>
|
|
|
|
|
|
</html>
|
