核心功能: - 文档索引:使用LLM分析提取关键词/摘要/主题/实体 - 查询处理:LLM分析查询意图并扩展关键词 - BM25检索:基于倒排索引的相关性排序 - RAG问答:检索增强生成 技术栈: - Flask + SQLAlchemy - OpenAI API兼容LLM - BM25算法 特点: 不依赖向量模型和向量库
217 lines
8.8 KiB
HTML
217 lines
8.8 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="zh-CN">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<title>文档管理 - LLM Index RAG</title>
|
|
<link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet">
|
|
<link href="https://cdn.jsdelivr.net/npm/bootstrap-icons@1.10.0/font/bootstrap-icons.css" rel="stylesheet">
|
|
<style>
|
|
body { background-color: #f8f9fa; }
|
|
.doc-card { border-radius: 10px; transition: all 0.3s; }
|
|
.doc-card:hover { transform: translateY(-3px); box-shadow: 0 5px 20px rgba(0,0,0,0.1); }
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<nav class="navbar navbar-expand-lg navbar-dark bg-dark">
|
|
<div class="container">
|
|
<a class="navbar-brand" href="/"><i class="bi bi-search"></i> LLM Index RAG</a>
|
|
<div class="navbar-nav ms-auto">
|
|
<a class="nav-link" href="/">首页</a>
|
|
<a class="nav-link active" href="/documents">文档管理</a>
|
|
<a class="nav-link" href="/search">知识检索</a>
|
|
</div>
|
|
</div>
|
|
</nav>
|
|
|
|
<div class="container mt-4">
|
|
<div class="d-flex justify-content-between align-items-center mb-4">
|
|
<h4><i class="bi bi-file-earmark-text"></i> 文档管理</h4>
|
|
<div>
|
|
<button class="btn btn-success" onclick="batchIndex()">
|
|
<i class="bi bi-arrow-repeat"></i> 批量索引
|
|
</button>
|
|
<button class="btn btn-warning" onclick="rebuildIndex()">
|
|
<i class="bi bi-trash"></i> 重建索引
|
|
</button>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- 上传区域 -->
|
|
<div class="card mb-4">
|
|
<div class="card-header">
|
|
<h6 class="mb-0"><i class="bi bi-upload"></i> 上传文档</h6>
|
|
</div>
|
|
<div class="card-body">
|
|
<form id="uploadForm" enctype="multipart/form-data">
|
|
<div class="row">
|
|
<div class="col-md-6">
|
|
<input type="file" class="form-control" name="file" id="docFile" accept=".txt,.md,.pdf,.docx,.html,.json">
|
|
</div>
|
|
<div class="col-md-3">
|
|
<input type="text" class="form-control" name="title" placeholder="文档标题(可选)">
|
|
</div>
|
|
<div class="col-md-3">
|
|
<button type="submit" class="btn btn-primary w-100">
|
|
<i class="bi bi-upload"></i> 上传
|
|
</button>
|
|
</div>
|
|
</div>
|
|
</form>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- 文档列表 -->
|
|
<div class="card">
|
|
<div class="card-header">
|
|
<h6 class="mb-0"><i class="bi bi-list"></i> 文档列表</h6>
|
|
</div>
|
|
<div class="card-body p-0">
|
|
<table class="table table-hover mb-0">
|
|
<thead class="table-light">
|
|
<tr>
|
|
<th>文件名</th>
|
|
<th>类型</th>
|
|
<th>大小</th>
|
|
<th>分块数</th>
|
|
<th>状态</th>
|
|
<th>索引时间</th>
|
|
<th>操作</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody id="docList">
|
|
<tr><td colspan="7" class="text-center py-4">加载中...</td></tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- 分页 -->
|
|
<nav class="mt-3">
|
|
<ul class="pagination justify-content-center" id="pagination"></ul>
|
|
</nav>
|
|
</div>
|
|
|
|
<script>
|
|
let currentPage = 1;
|
|
|
|
// 加载文档列表
|
|
function loadDocs(page = 1) {
|
|
currentPage = page;
|
|
fetch(`/api/documents?page=${page}`)
|
|
.then(r => r.json())
|
|
.then(data => {
|
|
const tbody = document.getElementById('docList');
|
|
tbody.innerHTML = '';
|
|
|
|
data.documents.forEach(doc => {
|
|
const statusBadge = doc.status === 'indexed'
|
|
? '<span class="badge bg-success">已索引</span>'
|
|
: doc.status === 'processing'
|
|
? '<span class="badge bg-warning">处理中</span>'
|
|
: doc.status === 'failed'
|
|
? '<span class="badge bg-danger">失败</span>'
|
|
: '<span class="badge bg-secondary">待索引</span>';
|
|
|
|
tbody.innerHTML += `
|
|
<tr>
|
|
<td>${doc.title || doc.filename}</td>
|
|
<td>${doc.file_type}</td>
|
|
<td>${(doc.file_size / 1024).toFixed(1)}KB</td>
|
|
<td>${doc.chunk_count}</td>
|
|
<td>${statusBadge}</td>
|
|
<td>${doc.indexed_at ? new Date(doc.indexed_at).toLocaleString() : '-'}</td>
|
|
<td>
|
|
${doc.status === 'pending' ? `<button class="btn btn-sm btn-outline-primary" onclick="indexDoc(${doc.id})"><i class="bi bi-arrow-repeat"></i></button>` : ''}
|
|
<button class="btn btn-sm btn-outline-info" onclick="viewDoc(${doc.id})"><i class="bi bi-eye"></i></button>
|
|
<button class="btn btn-sm btn-outline-danger" onclick="deleteDoc(${doc.id})"><i class="bi bi-trash"></i></button>
|
|
</td>
|
|
</tr>
|
|
`;
|
|
});
|
|
|
|
// 分页
|
|
const pagination = document.getElementById('pagination');
|
|
pagination.innerHTML = '';
|
|
for (let i = 1; i <= data.pages; i++) {
|
|
pagination.innerHTML += `
|
|
<li class="page-item ${i === page ? 'active' : ''}">
|
|
<a class="page-link" href="#" onclick="loadDocs(${i})">${i}</a>
|
|
</li>
|
|
`;
|
|
}
|
|
});
|
|
}
|
|
|
|
// 上传文档
|
|
document.getElementById('uploadForm').addEventListener('submit', function(e) {
|
|
e.preventDefault();
|
|
|
|
const formData = new FormData(this);
|
|
|
|
fetch('/api/documents', { method: 'POST', body: formData })
|
|
.then(r => r.json())
|
|
.then(data => {
|
|
if (data.success) {
|
|
alert('上传成功');
|
|
loadDocs();
|
|
} else {
|
|
alert('上传失败: ' + data.error);
|
|
}
|
|
});
|
|
});
|
|
|
|
// 索引文档
|
|
function indexDoc(id) {
|
|
fetch(`/api/index/${id}`, { method: 'POST' })
|
|
.then(r => r.json())
|
|
.then(data => {
|
|
alert(data.success ? '索引完成' : '索引失败');
|
|
loadDocs(currentPage);
|
|
});
|
|
}
|
|
|
|
// 批量索引
|
|
function batchIndex() {
|
|
if (!confirm('确定批量索引所有待索引文档?')) return;
|
|
|
|
fetch('/api/index/batch', { method: 'POST' })
|
|
.then(r => r.json())
|
|
.then(data => {
|
|
alert(`索引完成: 成功${data.success}, 失败${data.failed}`);
|
|
loadDocs();
|
|
});
|
|
}
|
|
|
|
// 重建索引
|
|
function rebuildIndex() {
|
|
if (!confirm('确定重建所有索引?这将清除现有索引!')) return;
|
|
|
|
fetch('/api/index/rebuild', { method: 'POST' })
|
|
.then(r => r.json())
|
|
.then(data => {
|
|
alert(`重建完成: 成功${data.success}, 失败${data.failed}`);
|
|
loadDocs();
|
|
});
|
|
}
|
|
|
|
// 删除文档
|
|
function deleteDoc(id) {
|
|
if (!confirm('确定删除此文档?')) return;
|
|
|
|
fetch(`/api/documents/${id}`, { method: 'DELETE' })
|
|
.then(r => r.json())
|
|
.then(data => {
|
|
if (data.success) loadDocs(currentPage);
|
|
});
|
|
}
|
|
|
|
// 查看文档
|
|
function viewDoc(id) {
|
|
window.location.href = `/documents/${id}`;
|
|
}
|
|
|
|
// 初始化
|
|
loadDocs();
|
|
</script>
|
|
</body>
|
|
</html> |