[AC-AISVC-02, AC-AISVC-16] 多个需求合并 #1
|
|
@ -10,6 +10,7 @@
|
|||
<el-menu-item index="/kb">知识库管理</el-menu-item>
|
||||
<el-menu-item index="/rag-lab">RAG 实验室</el-menu-item>
|
||||
<el-menu-item index="/monitoring">会话监控</el-menu-item>
|
||||
<el-menu-item index="/admin/embedding">嵌入模型配置</el-menu-item>
|
||||
<div class="flex-grow" />
|
||||
<div class="tenant-selector">
|
||||
<el-select v-model="currentTenantId" placeholder="选择租户" @change="handleTenantChange">
|
||||
|
|
|
|||
|
|
@ -1,8 +1,5 @@
|
|||
import request from '@/utils/request'
|
||||
|
||||
/**
|
||||
* 获取 Dashboard 统计数据
|
||||
*/
|
||||
export function getDashboardStats() {
|
||||
return request({
|
||||
url: '/admin/dashboard/stats',
|
||||
|
|
|
|||
|
|
@ -52,21 +52,21 @@ export interface SupportedFormatsResponse {
|
|||
|
||||
export function getProviders() {
|
||||
return request({
|
||||
url: '/admin/embedding/providers',
|
||||
url: '/embedding/providers',
|
||||
method: 'get'
|
||||
})
|
||||
}
|
||||
|
||||
export function getConfig() {
|
||||
return request({
|
||||
url: '/admin/embedding/config',
|
||||
url: '/embedding/config',
|
||||
method: 'get'
|
||||
})
|
||||
}
|
||||
|
||||
export function saveConfig(data: EmbeddingConfigUpdate) {
|
||||
return request({
|
||||
url: '/admin/embedding/config',
|
||||
url: '/embedding/config',
|
||||
method: 'put',
|
||||
data
|
||||
})
|
||||
|
|
@ -74,7 +74,7 @@ export function saveConfig(data: EmbeddingConfigUpdate) {
|
|||
|
||||
export function testEmbedding(data: EmbeddingTestRequest): Promise<EmbeddingTestResult> {
|
||||
return request({
|
||||
url: '/admin/embedding/test',
|
||||
url: '/embedding/test',
|
||||
method: 'post',
|
||||
data
|
||||
})
|
||||
|
|
@ -82,7 +82,7 @@ export function testEmbedding(data: EmbeddingTestRequest): Promise<EmbeddingTest
|
|||
|
||||
export function getSupportedFormats() {
|
||||
return request({
|
||||
url: '/admin/embedding/formats',
|
||||
url: '/embedding/formats',
|
||||
method: 'get'
|
||||
})
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,8 +1,5 @@
|
|||
import request from '@/utils/request'
|
||||
|
||||
/**
|
||||
* 查询知识库列表
|
||||
*/
|
||||
export function listKnowledgeBases() {
|
||||
return request({
|
||||
url: '/admin/kb/knowledge-bases',
|
||||
|
|
@ -10,9 +7,6 @@ export function listKnowledgeBases() {
|
|||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* 查询文档列表 [AC-ASA-08]
|
||||
*/
|
||||
export function listDocuments(params: any) {
|
||||
return request({
|
||||
url: '/admin/kb/documents',
|
||||
|
|
@ -21,9 +15,6 @@ export function listDocuments(params: any) {
|
|||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* 上传文档 [AC-ASA-01]
|
||||
*/
|
||||
export function uploadDocument(data: FormData) {
|
||||
return request({
|
||||
url: '/admin/kb/documents',
|
||||
|
|
@ -32,9 +23,6 @@ export function uploadDocument(data: FormData) {
|
|||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* 查询索引任务详情 [AC-ASA-02]
|
||||
*/
|
||||
export function getIndexJob(jobId: string) {
|
||||
return request({
|
||||
url: `/admin/kb/index/jobs/${jobId}`,
|
||||
|
|
@ -42,9 +30,6 @@ export function getIndexJob(jobId: string) {
|
|||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* 删除文档 [AC-ASA-08]
|
||||
*/
|
||||
export function deleteDocument(docId: string) {
|
||||
return request({
|
||||
url: `/admin/kb/documents/${docId}`,
|
||||
|
|
|
|||
|
|
@ -1,8 +1,5 @@
|
|||
import request from '@/utils/request'
|
||||
|
||||
/**
|
||||
* 查询会话列表 [AC-ASA-09]
|
||||
*/
|
||||
export function listSessions(params: any) {
|
||||
return request({
|
||||
url: '/admin/sessions',
|
||||
|
|
@ -11,9 +8,6 @@ export function listSessions(params: any) {
|
|||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取会话详情 [AC-ASA-07]
|
||||
*/
|
||||
export function getSessionDetail(sessionId: string) {
|
||||
return request({
|
||||
url: `/admin/sessions/${sessionId}`,
|
||||
|
|
|
|||
|
|
@ -1,8 +1,5 @@
|
|||
import request from '@/utils/request'
|
||||
|
||||
/**
|
||||
* 运行 RAG 调试实验 [AC-ASA-05]
|
||||
*/
|
||||
export function runRagExperiment(data: { query: string, kbIds?: string[], params?: any }) {
|
||||
return request({
|
||||
url: '/admin/rag/experiments/run',
|
||||
|
|
|
|||
|
|
@ -0,0 +1,73 @@
|
|||
<template>
|
||||
<el-select
|
||||
:model-value="modelValue"
|
||||
:loading="loading"
|
||||
:placeholder="placeholder"
|
||||
:disabled="disabled"
|
||||
:clearable="clearable"
|
||||
@update:model-value="handleChange"
|
||||
>
|
||||
<el-option
|
||||
v-for="provider in providers"
|
||||
:key="provider.name"
|
||||
:label="provider.display_name"
|
||||
:value="provider.name"
|
||||
>
|
||||
<div class="provider-option">
|
||||
<span class="provider-name">{{ provider.display_name }}</span>
|
||||
<span v-if="provider.description" class="provider-desc">{{ provider.description }}</span>
|
||||
</div>
|
||||
</el-option>
|
||||
</el-select>
|
||||
</template>
|
||||
|
||||
<script setup lang="ts">
|
||||
import type { EmbeddingProviderInfo } from '@/types/embedding'
|
||||
|
||||
const props = withDefaults(
|
||||
defineProps<{
|
||||
modelValue?: string
|
||||
providers: EmbeddingProviderInfo[]
|
||||
loading?: boolean
|
||||
disabled?: boolean
|
||||
clearable?: boolean
|
||||
placeholder?: string
|
||||
}>(),
|
||||
{
|
||||
modelValue: '',
|
||||
loading: false,
|
||||
disabled: false,
|
||||
clearable: false,
|
||||
placeholder: '请选择嵌入模型提供者'
|
||||
}
|
||||
)
|
||||
|
||||
const emit = defineEmits<{
|
||||
'update:modelValue': [value: string]
|
||||
change: [provider: EmbeddingProviderInfo | undefined]
|
||||
}>()
|
||||
|
||||
const handleChange = (value: string) => {
|
||||
emit('update:modelValue', value)
|
||||
const selectedProvider = props.providers.find((p) => p.name === value)
|
||||
emit('change', selectedProvider)
|
||||
}
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.provider-option {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
line-height: 1.4;
|
||||
}
|
||||
|
||||
.provider-name {
|
||||
font-weight: 500;
|
||||
}
|
||||
|
||||
.provider-desc {
|
||||
font-size: 12px;
|
||||
color: var(--el-text-color-secondary);
|
||||
margin-top: 2px;
|
||||
}
|
||||
</style>
|
||||
|
|
@ -1,90 +1,111 @@
|
|||
<template>
|
||||
<el-card shadow="never" class="test-panel">
|
||||
<el-card shadow="hover" class="test-panel">
|
||||
<template #header>
|
||||
<div class="card-header">
|
||||
<span>连接测试</span>
|
||||
<div class="header-left">
|
||||
<div class="icon-wrapper">
|
||||
<el-icon><Connection /></el-icon>
|
||||
</div>
|
||||
<span class="header-title">连接测试</span>
|
||||
</div>
|
||||
<el-tag v-if="testResult" :type="testResult.success ? 'success' : 'danger'" size="small" effect="dark">
|
||||
{{ testResult.success ? '连接成功' : '连接失败' }}
|
||||
</el-tag>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<div class="test-content">
|
||||
<el-form :model="testForm" label-width="80px">
|
||||
<el-form-item label="测试文本">
|
||||
<el-input
|
||||
v-model="testForm.test_text"
|
||||
type="textarea"
|
||||
:rows="3"
|
||||
placeholder="请输入测试文本（可选，默认使用系统预设文本）"
|
||||
clearable
|
||||
/>
|
||||
</el-form-item>
|
||||
<el-form-item>
|
||||
<el-button
|
||||
type="primary"
|
||||
:loading="loading"
|
||||
:disabled="!config?.provider"
|
||||
@click="handleTest"
|
||||
>
|
||||
<el-icon v-if="!loading"><Connection /></el-icon>
|
||||
{{ loading ? '测试中...' : '测试连接' }}
|
||||
</el-button>
|
||||
</el-form-item>
|
||||
</el-form>
|
||||
|
||||
<div v-if="testResult" class="test-result">
|
||||
<el-divider />
|
||||
|
||||
<el-alert
|
||||
v-if="testResult.success"
|
||||
:title="testResult.message || '连接成功'"
|
||||
type="success"
|
||||
:closable="false"
|
||||
show-icon
|
||||
class="result-alert"
|
||||
<div class="test-form-section">
|
||||
<div class="section-label">
|
||||
<el-icon><Edit /></el-icon>
|
||||
<span>测试文本</span>
|
||||
</div>
|
||||
<el-input
|
||||
v-model="testForm.test_text"
|
||||
type="textarea"
|
||||
:rows="3"
|
||||
placeholder="请输入测试文本（可选，默认使用系统预设文本）"
|
||||
clearable
|
||||
class="test-textarea"
|
||||
/>
|
||||
<el-button
|
||||
type="primary"
|
||||
size="large"
|
||||
:loading="loading"
|
||||
:disabled="!config?.provider"
|
||||
class="test-button"
|
||||
@click="handleTest"
|
||||
>
|
||||
<template #default>
|
||||
<div class="success-details">
|
||||
<div class="detail-item">
|
||||
<span class="label">向量维度：</span>
|
||||
<el-tag type="success">{{ testResult.dimension }}</el-tag>
|
||||
</div>
|
||||
<div v-if="testResult.latency_ms" class="detail-item">
|
||||
<span class="label">响应延迟：</span>
|
||||
<el-tag type="info">{{ testResult.latency_ms.toFixed(2) }} ms</el-tag>
|
||||
</div>
|
||||
</div>
|
||||
</template>
|
||||
</el-alert>
|
||||
|
||||
<el-alert
|
||||
v-else
|
||||
:title="testResult.error || '连接失败'"
|
||||
type="error"
|
||||
:closable="false"
|
||||
show-icon
|
||||
class="result-alert"
|
||||
>
|
||||
<template #default>
|
||||
<div class="error-details">
|
||||
<p class="error-message">{{ testResult.error || '未知错误' }}</p>
|
||||
<div class="troubleshooting">
|
||||
<p class="troubleshoot-title">排查建议：</p>
|
||||
<ul class="troubleshoot-list">
|
||||
<li v-for="(tip, index) in troubleshootingTips" :key="index">
|
||||
{{ tip }}
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</template>
|
||||
</el-alert>
|
||||
<el-icon v-if="!loading"><Connection /></el-icon>
|
||||
{{ loading ? '测试中...' : '测试连接' }}
|
||||
</el-button>
|
||||
</div>
|
||||
|
||||
<transition name="result-fade">
|
||||
<div v-if="testResult" class="test-result">
|
||||
<el-divider />
|
||||
|
||||
<div v-if="testResult.success" class="success-result">
|
||||
<div class="result-header">
|
||||
<div class="success-icon">
|
||||
<el-icon><CircleCheck /></el-icon>
|
||||
</div>
|
||||
<span class="result-title">{{ testResult.message || '连接成功' }}</span>
|
||||
</div>
|
||||
<div class="success-details">
|
||||
<div class="detail-card">
|
||||
<div class="detail-icon">
|
||||
<el-icon><Grid /></el-icon>
|
||||
</div>
|
||||
<div class="detail-info">
|
||||
<span class="detail-label">向量维度</span>
|
||||
<span class="detail-value">{{ testResult.dimension }}</span>
|
||||
</div>
|
||||
</div>
|
||||
<div v-if="testResult.latency_ms" class="detail-card">
|
||||
<div class="detail-icon">
|
||||
<el-icon><Timer /></el-icon>
|
||||
</div>
|
||||
<div class="detail-info">
|
||||
<span class="detail-label">响应延迟</span>
|
||||
<span class="detail-value">{{ testResult.latency_ms.toFixed(2) }} ms</span>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div v-else class="error-result">
|
||||
<div class="result-header">
|
||||
<div class="error-icon">
|
||||
<el-icon><CircleClose /></el-icon>
|
||||
</div>
|
||||
<span class="result-title error">连接失败</span>
|
||||
</div>
|
||||
<div class="error-message-box">
|
||||
<p class="error-text">{{ testResult.error || '未知错误' }}</p>
|
||||
</div>
|
||||
<div class="troubleshooting">
|
||||
<div class="troubleshoot-header">
|
||||
<el-icon><Warning /></el-icon>
|
||||
<span>排查建议</span>
|
||||
</div>
|
||||
<ul class="troubleshoot-list">
|
||||
<li v-for="(tip, index) in troubleshootingTips" :key="index">
|
||||
<el-icon class="list-icon"><Right /></el-icon>
|
||||
{{ tip }}
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</transition>
|
||||
</div>
|
||||
</el-card>
|
||||
</template>
|
||||
|
||||
<script setup lang="ts">
|
||||
import { ref, computed } from 'vue'
|
||||
import { Connection } from '@element-plus/icons-vue'
|
||||
import { Connection, Edit, CircleCheck, CircleClose, Timer, Grid, Warning, Right } from '@element-plus/icons-vue'
|
||||
import { testEmbedding, type EmbeddingConfigUpdate, type EmbeddingTestResult } from '@/api/embedding'
|
||||
|
||||
const props = defineProps<{
|
||||
|
|
@ -159,72 +180,281 @@ const handleTest = async () => {
|
|||
|
||||
<style scoped>
|
||||
.test-panel {
|
||||
margin-top: 20px;
|
||||
border-radius: 16px;
|
||||
border: none;
|
||||
background: rgba(255, 255, 255, 0.98);
|
||||
backdrop-filter: blur(10px);
|
||||
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.1);
|
||||
transition: all 0.3s ease;
|
||||
}
|
||||
|
||||
.test-panel:hover {
|
||||
box-shadow: 0 12px 48px rgba(0, 0, 0, 0.15);
|
||||
transform: translateY(-4px);
|
||||
}
|
||||
|
||||
.card-header {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
.header-left {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 12px;
|
||||
}
|
||||
|
||||
.icon-wrapper {
|
||||
width: 40px;
|
||||
height: 40px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
||||
border-radius: 10px;
|
||||
color: #ffffff;
|
||||
font-size: 20px;
|
||||
}
|
||||
|
||||
.header-title {
|
||||
font-size: 16px;
|
||||
font-weight: 600;
|
||||
color: #303133;
|
||||
}
|
||||
|
||||
.test-content {
|
||||
padding: 0 10px;
|
||||
padding: 8px 0;
|
||||
}
|
||||
|
||||
.test-form-section {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 16px;
|
||||
}
|
||||
|
||||
.section-label {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 8px;
|
||||
font-size: 14px;
|
||||
font-weight: 600;
|
||||
color: #606266;
|
||||
}
|
||||
|
||||
.section-label .el-icon {
|
||||
color: #667eea;
|
||||
}
|
||||
|
||||
.test-textarea {
|
||||
border-radius: 10px;
|
||||
}
|
||||
|
||||
.test-textarea :deep(.el-textarea__inner) {
|
||||
border-radius: 10px;
|
||||
border: 1px solid #dcdfe6;
|
||||
transition: all 0.3s ease;
|
||||
}
|
||||
|
||||
.test-textarea :deep(.el-textarea__inner:focus) {
|
||||
border-color: #667eea;
|
||||
box-shadow: 0 0 0 2px rgba(102, 126, 234, 0.2);
|
||||
}
|
||||
|
||||
.test-button {
|
||||
align-self: flex-start;
|
||||
border-radius: 10px;
|
||||
padding: 12px 24px;
|
||||
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
||||
border: none;
|
||||
transition: all 0.3s ease;
|
||||
}
|
||||
|
||||
.test-button:hover:not(:disabled) {
|
||||
transform: translateY(-2px);
|
||||
box-shadow: 0 4px 12px rgba(102, 126, 234, 0.4);
|
||||
}
|
||||
|
||||
.test-button:disabled {
|
||||
opacity: 0.6;
|
||||
}
|
||||
|
||||
.test-result {
|
||||
margin-top: 10px;
|
||||
animation: fadeIn 0.4s ease-out;
|
||||
}
|
||||
|
||||
.result-alert {
|
||||
margin-top: 10px;
|
||||
@keyframes fadeIn {
|
||||
from {
|
||||
opacity: 0;
|
||||
transform: translateY(10px);
|
||||
}
|
||||
to {
|
||||
opacity: 1;
|
||||
transform: translateY(0);
|
||||
}
|
||||
}
|
||||
|
||||
.result-header {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 12px;
|
||||
margin-bottom: 16px;
|
||||
}
|
||||
|
||||
.success-icon,
|
||||
.error-icon {
|
||||
width: 36px;
|
||||
height: 36px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
border-radius: 50%;
|
||||
font-size: 20px;
|
||||
}
|
||||
|
||||
.success-icon {
|
||||
background: linear-gradient(135deg, #67c23a 0%, #85ce61 100%);
|
||||
color: #ffffff;
|
||||
}
|
||||
|
||||
.error-icon {
|
||||
background: linear-gradient(135deg, #f56c6c 0%, #f89898 100%);
|
||||
color: #ffffff;
|
||||
}
|
||||
|
||||
.result-title {
|
||||
font-size: 16px;
|
||||
font-weight: 600;
|
||||
color: #67c23a;
|
||||
}
|
||||
|
||||
.result-title.error {
|
||||
color: #f56c6c;
|
||||
}
|
||||
|
||||
.success-details {
|
||||
margin-top: 12px;
|
||||
display: flex;
|
||||
gap: 16px;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.detail-item {
|
||||
display: inline-flex;
|
||||
.detail-card {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
margin-right: 20px;
|
||||
margin-bottom: 8px;
|
||||
gap: 12px;
|
||||
padding: 14px 18px;
|
||||
background: linear-gradient(135deg, #f0f9eb 0%, #e1f3d8 100%);
|
||||
border-radius: 12px;
|
||||
border: 1px solid #e1f3d8;
|
||||
}
|
||||
|
||||
.detail-item .label {
|
||||
color: #606266;
|
||||
margin-right: 8px;
|
||||
.detail-icon {
|
||||
width: 40px;
|
||||
height: 40px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
background: linear-gradient(135deg, #67c23a 0%, #85ce61 100%);
|
||||
border-radius: 10px;
|
||||
color: #ffffff;
|
||||
font-size: 18px;
|
||||
}
|
||||
|
||||
.error-details {
|
||||
margin-top: 8px;
|
||||
.detail-info {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
.error-message {
|
||||
.detail-label {
|
||||
font-size: 12px;
|
||||
color: #909399;
|
||||
}
|
||||
|
||||
.detail-value {
|
||||
font-size: 18px;
|
||||
font-weight: 700;
|
||||
color: #303133;
|
||||
}
|
||||
|
||||
.error-result {
|
||||
animation: shake 0.5s ease-out;
|
||||
}
|
||||
|
||||
@keyframes shake {
|
||||
0%, 100% { transform: translateX(0); }
|
||||
25% { transform: translateX(-5px); }
|
||||
75% { transform: translateX(5px); }
|
||||
}
|
||||
|
||||
.error-message-box {
|
||||
padding: 14px 16px;
|
||||
background: linear-gradient(135deg, #fef0f0 0%, #fde2e2 100%);
|
||||
border-radius: 10px;
|
||||
border-left: 3px solid #f56c6c;
|
||||
margin-bottom: 16px;
|
||||
}
|
||||
|
||||
.error-text {
|
||||
margin: 0;
|
||||
color: #f56c6c;
|
||||
margin-bottom: 12px;
|
||||
font-size: 14px;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
.troubleshooting {
|
||||
background-color: #fef0f0;
|
||||
padding: 12px;
|
||||
border-radius: 4px;
|
||||
margin-top: 8px;
|
||||
padding: 16px;
|
||||
background: linear-gradient(135deg, #fdf6ec 0%, #faecd8 100%);
|
||||
border-radius: 12px;
|
||||
border: 1px solid #faecd8;
|
||||
}
|
||||
|
||||
.troubleshoot-title {
|
||||
.troubleshoot-header {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 8px;
|
||||
margin-bottom: 12px;
|
||||
font-weight: 600;
|
||||
color: #f56c6c;
|
||||
margin-bottom: 8px;
|
||||
color: #e6a23c;
|
||||
}
|
||||
|
||||
.troubleshoot-list {
|
||||
margin: 0;
|
||||
padding-left: 20px;
|
||||
color: #909399;
|
||||
padding: 0;
|
||||
list-style: none;
|
||||
}
|
||||
|
||||
.troubleshoot-list li {
|
||||
margin-bottom: 4px;
|
||||
display: flex;
|
||||
align-items: flex-start;
|
||||
gap: 8px;
|
||||
margin-bottom: 8px;
|
||||
color: #606266;
|
||||
font-size: 13px;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
.list-icon {
|
||||
margin-top: 4px;
|
||||
color: #e6a23c;
|
||||
font-size: 12px;
|
||||
}
|
||||
|
||||
.result-fade-enter-active {
|
||||
transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
|
||||
}
|
||||
|
||||
.result-fade-leave-active {
|
||||
transition: all 0.3s cubic-bezier(1, 0.5, 0.8, 1);
|
||||
}
|
||||
|
||||
.result-fade-enter-from {
|
||||
opacity: 0;
|
||||
transform: translateY(20px);
|
||||
}
|
||||
|
||||
.result-fade-leave-to {
|
||||
opacity: 0;
|
||||
transform: translateY(-10px);
|
||||
}
|
||||
</style>
|
||||
|
|
|
|||
|
|
@ -0,0 +1,161 @@
|
|||
<template>
|
||||
<div class="supported-formats">
|
||||
<div v-loading="loading" class="formats-content">
|
||||
<transition-group name="tag-fade" tag="div" class="formats-grid">
|
||||
<el-tooltip
|
||||
v-for="format in formats"
|
||||
:key="format.extension"
|
||||
:content="format.description"
|
||||
placement="top"
|
||||
:disabled="!format.description"
|
||||
effect="light"
|
||||
>
|
||||
<div class="format-item">
|
||||
<div class="format-icon">
|
||||
<span class="extension">{{ format.extension }}</span>
|
||||
</div>
|
||||
<div class="format-info">
|
||||
<span class="format-name">{{ format.name }}</span>
|
||||
</div>
|
||||
</div>
|
||||
</el-tooltip>
|
||||
</transition-group>
|
||||
<el-empty v-if="!loading && formats.length === 0" description="暂无支持的格式" :image-size="80">
|
||||
<template #image>
|
||||
<div class="empty-icon">
|
||||
<el-icon><Document /></el-icon>
|
||||
</div>
|
||||
</template>
|
||||
</el-empty>
|
||||
</div>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<script setup lang="ts">
|
||||
import { computed, onMounted } from 'vue'
|
||||
import { Document } from '@element-plus/icons-vue'
|
||||
import { useEmbeddingStore } from '@/stores/embedding'
|
||||
|
||||
const embeddingStore = useEmbeddingStore()
|
||||
|
||||
const formats = computed(() => embeddingStore.formats)
|
||||
const loading = computed(() => embeddingStore.formatsLoading)
|
||||
|
||||
onMounted(() => {
|
||||
if (formats.value.length === 0) {
|
||||
embeddingStore.loadFormats()
|
||||
}
|
||||
})
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.supported-formats {
|
||||
padding: 8px 0;
|
||||
}
|
||||
|
||||
.formats-content {
|
||||
min-height: 60px;
|
||||
}
|
||||
|
||||
.formats-grid {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 12px;
|
||||
}
|
||||
|
||||
.format-item {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 10px;
|
||||
padding: 10px 14px;
|
||||
background: linear-gradient(135deg, #f8f9fc 0%, #eef1f5 100%);
|
||||
border-radius: 10px;
|
||||
border: 1px solid #e4e7ed;
|
||||
cursor: default;
|
||||
transition: all 0.3s ease;
|
||||
}
|
||||
|
||||
.format-item:hover {
|
||||
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
||||
border-color: transparent;
|
||||
transform: translateY(-2px);
|
||||
box-shadow: 0 4px 12px rgba(102, 126, 234, 0.3);
|
||||
}
|
||||
|
||||
.format-item:hover .extension,
|
||||
.format-item:hover .format-name {
|
||||
color: #ffffff;
|
||||
}
|
||||
|
||||
.format-icon {
|
||||
width: 36px;
|
||||
height: 36px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
||||
border-radius: 8px;
|
||||
}
|
||||
|
||||
.format-item:hover .format-icon {
|
||||
background: rgba(255, 255, 255, 0.2);
|
||||
}
|
||||
|
||||
.extension {
|
||||
font-size: 11px;
|
||||
font-weight: 700;
|
||||
color: #ffffff;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 0.5px;
|
||||
}
|
||||
|
||||
.format-info {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
.format-name {
|
||||
font-size: 13px;
|
||||
font-weight: 600;
|
||||
color: #303133;
|
||||
transition: color 0.3s ease;
|
||||
}
|
||||
|
||||
.empty-icon {
|
||||
width: 80px;
|
||||
height: 80px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
background: linear-gradient(135deg, #f5f7fa 0%, #e8ecf1 100%);
|
||||
border-radius: 50%;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
.empty-icon .el-icon {
|
||||
font-size: 40px;
|
||||
color: #c0c4cc;
|
||||
}
|
||||
|
||||
.tag-fade-enter-active {
|
||||
transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
|
||||
}
|
||||
|
||||
.tag-fade-leave-active {
|
||||
transition: all 0.3s cubic-bezier(1, 0.5, 0.8, 1);
|
||||
}
|
||||
|
||||
.tag-fade-enter-from {
|
||||
opacity: 0;
|
||||
transform: scale(0.8);
|
||||
}
|
||||
|
||||
.tag-fade-leave-to {
|
||||
opacity: 0;
|
||||
transform: scale(0.8);
|
||||
}
|
||||
|
||||
.tag-fade-move {
|
||||
transition: transform 0.3s ease;
|
||||
}
|
||||
</style>
|
||||
|
|
@ -28,6 +28,12 @@ const routes: Array<RouteRecordRaw> = [
|
|||
name: 'Monitoring',
|
||||
component: () => import('@/views/monitoring/index.vue'),
|
||||
meta: { title: '会话监控' }
|
||||
},
|
||||
{
|
||||
path: '/admin/embedding',
|
||||
name: 'EmbeddingConfig',
|
||||
component: () => import('@/views/admin/embedding/index.vue'),
|
||||
meta: { title: '嵌入模型配置' }
|
||||
}
|
||||
]
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,164 @@
|
|||
import { defineStore } from 'pinia'
|
||||
import { ref, computed } from 'vue'
|
||||
import {
|
||||
getProviders,
|
||||
getConfig,
|
||||
saveConfig,
|
||||
testEmbedding,
|
||||
getSupportedFormats,
|
||||
type EmbeddingProviderInfo,
|
||||
type EmbeddingConfig,
|
||||
type EmbeddingConfigUpdate,
|
||||
type EmbeddingTestResult,
|
||||
type DocumentFormat
|
||||
} from '@/api/embedding'
|
||||
|
||||
export const useEmbeddingStore = defineStore('embedding', () => {
|
||||
const providers = ref<EmbeddingProviderInfo[]>([])
|
||||
const currentConfig = ref<EmbeddingConfig>({
|
||||
provider: '',
|
||||
config: {}
|
||||
})
|
||||
const formats = ref<DocumentFormat[]>([])
|
||||
const loading = ref(false)
|
||||
const providersLoading = ref(false)
|
||||
const formatsLoading = ref(false)
|
||||
const testResult = ref<EmbeddingTestResult | null>(null)
|
||||
const testLoading = ref(false)
|
||||
|
||||
const currentProvider = computed(() => {
|
||||
return providers.value.find(p => p.name === currentConfig.value.provider)
|
||||
})
|
||||
|
||||
const configSchema = computed(() => {
|
||||
return currentProvider.value?.config_schema || { properties: {} }
|
||||
})
|
||||
|
||||
const loadProviders = async () => {
|
||||
providersLoading.value = true
|
||||
try {
|
||||
const res: any = await getProviders()
|
||||
providers.value = res?.providers || res?.data?.providers || []
|
||||
} catch (error) {
|
||||
console.error('Failed to load providers:', error)
|
||||
throw error
|
||||
} finally {
|
||||
providersLoading.value = false
|
||||
}
|
||||
}
|
||||
|
||||
const loadConfig = async () => {
|
||||
loading.value = true
|
||||
try {
|
||||
const res: any = await getConfig()
|
||||
const config = res?.data || res
|
||||
if (config) {
|
||||
currentConfig.value = {
|
||||
provider: config.provider || '',
|
||||
config: config.config || {},
|
||||
updated_at: config.updated_at
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('Failed to load config:', error)
|
||||
throw error
|
||||
} finally {
|
||||
loading.value = false
|
||||
}
|
||||
}
|
||||
|
||||
const saveCurrentConfig = async () => {
|
||||
loading.value = true
|
||||
try {
|
||||
const updateData: EmbeddingConfigUpdate = {
|
||||
provider: currentConfig.value.provider,
|
||||
config: currentConfig.value.config
|
||||
}
|
||||
await saveConfig(updateData)
|
||||
} catch (error) {
|
||||
console.error('Failed to save config:', error)
|
||||
throw error
|
||||
} finally {
|
||||
loading.value = false
|
||||
}
|
||||
}
|
||||
|
||||
const runTest = async (testText?: string) => {
|
||||
testLoading.value = true
|
||||
testResult.value = null
|
||||
try {
|
||||
const result = await testEmbedding({
|
||||
test_text: testText,
|
||||
config: {
|
||||
provider: currentConfig.value.provider,
|
||||
config: currentConfig.value.config
|
||||
}
|
||||
})
|
||||
testResult.value = result
|
||||
} catch (error: any) {
|
||||
testResult.value = {
|
||||
success: false,
|
||||
dimension: 0,
|
||||
error: error?.message || '连接测试失败'
|
||||
}
|
||||
} finally {
|
||||
testLoading.value = false
|
||||
}
|
||||
}
|
||||
|
||||
const loadFormats = async () => {
|
||||
formatsLoading.value = true
|
||||
try {
|
||||
const res: any = await getSupportedFormats()
|
||||
formats.value = res?.formats || res?.data?.formats || []
|
||||
} catch (error) {
|
||||
console.error('Failed to load formats:', error)
|
||||
throw error
|
||||
} finally {
|
||||
formatsLoading.value = false
|
||||
}
|
||||
}
|
||||
|
||||
const setProvider = (providerName: string) => {
|
||||
currentConfig.value.provider = providerName
|
||||
const provider = providers.value.find(p => p.name === providerName)
|
||||
if (provider?.config_schema?.properties) {
|
||||
const newConfig: Record<string, any> = {}
|
||||
Object.entries(provider.config_schema.properties).forEach(([key, field]: [string, any]) => {
|
||||
newConfig[key] = field.default !== undefined ? field.default : ''
|
||||
})
|
||||
currentConfig.value.config = newConfig
|
||||
} else {
|
||||
currentConfig.value.config = {}
|
||||
}
|
||||
}
|
||||
|
||||
const updateConfigValue = (key: string, value: any) => {
|
||||
currentConfig.value.config[key] = value
|
||||
}
|
||||
|
||||
const clearTestResult = () => {
|
||||
testResult.value = null
|
||||
}
|
||||
|
||||
return {
|
||||
providers,
|
||||
currentConfig,
|
||||
formats,
|
||||
loading,
|
||||
providersLoading,
|
||||
formatsLoading,
|
||||
testResult,
|
||||
testLoading,
|
||||
currentProvider,
|
||||
configSchema,
|
||||
loadProviders,
|
||||
loadConfig,
|
||||
saveCurrentConfig,
|
||||
runTest,
|
||||
loadFormats,
|
||||
setProvider,
|
||||
updateConfigValue,
|
||||
clearTestResult
|
||||
}
|
||||
})
|
||||
|
|
@ -0,0 +1,49 @@
|
|||
export interface EmbeddingProviderInfo {
|
||||
name: string
|
||||
display_name: string
|
||||
description?: string
|
||||
config_schema: Record<string, any>
|
||||
}
|
||||
|
||||
export interface EmbeddingConfig {
|
||||
provider: string
|
||||
config: Record<string, any>
|
||||
updated_at?: string
|
||||
}
|
||||
|
||||
export interface EmbeddingConfigUpdate {
|
||||
provider: string
|
||||
config?: Record<string, any>
|
||||
}
|
||||
|
||||
export interface EmbeddingTestResult {
|
||||
success: boolean
|
||||
dimension: number
|
||||
latency_ms?: number
|
||||
message?: string
|
||||
error?: string
|
||||
}
|
||||
|
||||
export interface DocumentFormat {
|
||||
extension: string
|
||||
name: string
|
||||
description?: string
|
||||
}
|
||||
|
||||
export interface EmbeddingProvidersResponse {
|
||||
providers: EmbeddingProviderInfo[]
|
||||
}
|
||||
|
||||
export interface EmbeddingConfigUpdateResponse {
|
||||
success: boolean
|
||||
message: string
|
||||
}
|
||||
|
||||
export interface SupportedFormatsResponse {
|
||||
formats: DocumentFormat[]
|
||||
}
|
||||
|
||||
export interface EmbeddingTestRequest {
|
||||
test_text?: string
|
||||
config?: EmbeddingConfigUpdate
|
||||
}
|
||||
|
|
@ -0,0 +1,504 @@
|
|||
<template>
|
||||
<div class="embedding-config-page">
|
||||
<div class="page-header">
|
||||
<div class="header-content">
|
||||
<div class="title-section">
|
||||
<h1 class="page-title">嵌入模型配置</h1>
|
||||
<p class="page-desc">配置和管理系统使用的嵌入模型，支持多种提供者切换。配置修改后需保存才能生效。</p>
|
||||
</div>
|
||||
<div class="header-actions">
|
||||
<el-tag v-if="currentConfig.updated_at" type="info" size="large" effect="plain">
|
||||
<el-icon class="tag-icon"><Clock /></el-icon>
|
||||
上次更新: {{ formatDate(currentConfig.updated_at) }}
|
||||
</el-tag>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<el-row :gutter="24" v-loading="pageLoading" element-loading-text="加载中...">
|
||||
<el-col :xs="24" :sm="24" :md="12" :lg="12">
|
||||
<div class="config-card-wrapper">
|
||||
<el-card shadow="hover" class="config-card">
|
||||
<template #header>
|
||||
<div class="card-header">
|
||||
<div class="header-left">
|
||||
<div class="icon-wrapper">
|
||||
<el-icon><Setting /></el-icon>
|
||||
</div>
|
||||
<span class="header-title">模型配置</span>
|
||||
</div>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<div class="card-content">
|
||||
<div class="provider-select-section">
|
||||
<div class="section-label">
|
||||
<el-icon><Connection /></el-icon>
|
||||
<span>选择提供者</span>
|
||||
</div>
|
||||
<EmbeddingProviderSelect
|
||||
v-model="currentConfig.provider"
|
||||
:providers="providers"
|
||||
:loading="providersLoading"
|
||||
placeholder="请选择嵌入模型提供者"
|
||||
@change="handleProviderChange"
|
||||
/>
|
||||
<transition name="fade">
|
||||
<div v-if="currentProvider" class="provider-info">
|
||||
<el-icon class="info-icon"><InfoFilled /></el-icon>
|
||||
<span class="info-text">{{ currentProvider.description }}</span>
|
||||
</div>
|
||||
</transition>
|
||||
</div>
|
||||
|
||||
<el-divider />
|
||||
|
||||
<transition name="slide-fade" mode="out-in">
|
||||
<div v-if="currentConfig.provider" key="form" class="config-form-section">
|
||||
<EmbeddingConfigForm
|
||||
ref="configFormRef"
|
||||
:schema="configSchema"
|
||||
v-model="currentConfig.config"
|
||||
label-width="140px"
|
||||
/>
|
||||
</div>
|
||||
<el-empty v-else key="empty" description="请先选择一个嵌入模型提供者" :image-size="120">
|
||||
<template #image>
|
||||
<div class="empty-icon">
|
||||
<el-icon><Box /></el-icon>
|
||||
</div>
|
||||
</template>
|
||||
</el-empty>
|
||||
</transition>
|
||||
</div>
|
||||
|
||||
<template #footer>
|
||||
<div class="card-footer">
|
||||
<el-button size="large" @click="handleReset">
|
||||
<el-icon><RefreshLeft /></el-icon>
|
||||
重置
|
||||
</el-button>
|
||||
<el-button type="primary" size="large" :loading="saving" @click="handleSave">
|
||||
<el-icon><Check /></el-icon>
|
||||
保存配置
|
||||
</el-button>
|
||||
</div>
|
||||
</template>
|
||||
</el-card>
|
||||
</div>
|
||||
</el-col>
|
||||
|
||||
<el-col :xs="24" :sm="24" :md="12" :lg="12">
|
||||
<div class="right-column">
|
||||
<div class="test-panel-wrapper">
|
||||
<EmbeddingTestPanel
|
||||
:config="{ provider: currentConfig.provider, config: currentConfig.config }"
|
||||
/>
|
||||
</div>
|
||||
|
||||
<el-card shadow="hover" class="formats-card">
|
||||
<template #header>
|
||||
<div class="card-header">
|
||||
<div class="header-left">
|
||||
<div class="icon-wrapper">
|
||||
<el-icon><Document /></el-icon>
|
||||
</div>
|
||||
<span class="header-title">支持的文档格式</span>
|
||||
</div>
|
||||
</div>
|
||||
</template>
|
||||
<SupportedFormats />
|
||||
</el-card>
|
||||
</div>
|
||||
</el-col>
|
||||
</el-row>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<script setup lang="ts">
|
||||
import { ref, computed, onMounted } from 'vue'
|
||||
import { ElMessage, ElMessageBox } from 'element-plus'
|
||||
import { Setting, Connection, InfoFilled, Box, RefreshLeft, Check, Clock, Document } from '@element-plus/icons-vue'
|
||||
import { useEmbeddingStore } from '@/stores/embedding'
|
||||
import EmbeddingProviderSelect from '@/components/embedding/EmbeddingProviderSelect.vue'
|
||||
import EmbeddingConfigForm from '@/components/embedding/EmbeddingConfigForm.vue'
|
||||
import EmbeddingTestPanel from '@/components/embedding/EmbeddingTestPanel.vue'
|
||||
import SupportedFormats from '@/components/embedding/SupportedFormats.vue'
|
||||
|
||||
const embeddingStore = useEmbeddingStore()
|
||||
|
||||
const configFormRef = ref<InstanceType<typeof EmbeddingConfigForm>>()
|
||||
const saving = ref(false)
|
||||
const pageLoading = ref(false)
|
||||
|
||||
const providers = computed(() => embeddingStore.providers)
|
||||
const currentConfig = computed(() => embeddingStore.currentConfig)
|
||||
const currentProvider = computed(() => embeddingStore.currentProvider)
|
||||
const configSchema = computed(() => embeddingStore.configSchema)
|
||||
const providersLoading = computed(() => embeddingStore.providersLoading)
|
||||
|
||||
const formatDate = (dateStr: string) => {
|
||||
if (!dateStr) return ''
|
||||
const date = new Date(dateStr)
|
||||
return date.toLocaleString('zh-CN', {
|
||||
year: 'numeric',
|
||||
month: '2-digit',
|
||||
day: '2-digit',
|
||||
hour: '2-digit',
|
||||
minute: '2-digit'
|
||||
})
|
||||
}
|
||||
|
||||
const handleProviderChange = (provider: any) => {
|
||||
if (provider) {
|
||||
embeddingStore.setProvider(provider.name)
|
||||
}
|
||||
}
|
||||
|
||||
const handleSave = async () => {
|
||||
if (!currentConfig.value.provider) {
|
||||
ElMessage.warning('请先选择嵌入模型提供者')
|
||||
return
|
||||
}
|
||||
|
||||
try {
|
||||
const valid = await configFormRef.value?.validate()
|
||||
if (!valid) {
|
||||
return
|
||||
}
|
||||
} catch (error) {
|
||||
ElMessage.warning('请检查配置表单中的必填项')
|
||||
return
|
||||
}
|
||||
|
||||
saving.value = true
|
||||
try {
|
||||
await embeddingStore.saveCurrentConfig()
|
||||
ElMessage.success('配置保存成功')
|
||||
} catch (error) {
|
||||
ElMessage.error('配置保存失败')
|
||||
} finally {
|
||||
saving.value = false
|
||||
}
|
||||
}
|
||||
|
||||
const handleReset = async () => {
|
||||
try {
|
||||
await ElMessageBox.confirm('确定要重置配置吗？将恢复为当前保存的配置。', '确认重置', {
|
||||
confirmButtonText: '确定',
|
||||
cancelButtonText: '取消',
|
||||
type: 'warning'
|
||||
})
|
||||
await embeddingStore.loadConfig()
|
||||
ElMessage.success('配置已重置')
|
||||
} catch (error) {
|
||||
// 用户取消
|
||||
}
|
||||
}
|
||||
|
||||
const initPage = async () => {
|
||||
pageLoading.value = true
|
||||
try {
|
||||
await Promise.all([
|
||||
embeddingStore.loadProviders(),
|
||||
embeddingStore.loadConfig(),
|
||||
embeddingStore.loadFormats()
|
||||
])
|
||||
} catch (error) {
|
||||
ElMessage.error('初始化页面失败')
|
||||
} finally {
|
||||
pageLoading.value = false
|
||||
}
|
||||
}
|
||||
|
||||
onMounted(() => {
|
||||
initPage()
|
||||
})
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.embedding-config-page {
|
||||
padding: 24px;
|
||||
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
||||
min-height: calc(100vh - 60px);
|
||||
}
|
||||
|
||||
.page-header {
|
||||
margin-bottom: 32px;
|
||||
animation: slideDown 0.6s ease-out;
|
||||
}
|
||||
|
||||
@keyframes slideDown {
|
||||
from {
|
||||
opacity: 0;
|
||||
transform: translateY(-20px);
|
||||
}
|
||||
to {
|
||||
opacity: 1;
|
||||
transform: translateY(0);
|
||||
}
|
||||
}
|
||||
|
||||
.header-content {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: flex-start;
|
||||
gap: 20px;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.title-section {
|
||||
flex: 1;
|
||||
min-width: 300px;
|
||||
}
|
||||
|
||||
.page-title {
|
||||
margin: 0 0 12px 0;
|
||||
font-size: 28px;
|
||||
font-weight: 700;
|
||||
color: #ffffff;
|
||||
letter-spacing: -0.5px;
|
||||
text-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
|
||||
}
|
||||
|
||||
.page-desc {
|
||||
margin: 0;
|
||||
font-size: 14px;
|
||||
color: rgba(255, 255, 255, 0.85);
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
.header-actions {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.tag-icon {
|
||||
margin-right: 4px;
|
||||
}
|
||||
|
||||
.config-card-wrapper,
|
||||
.test-panel-wrapper,
|
||||
.formats-card {
|
||||
animation: fadeInUp 0.6s ease-out;
|
||||
}
|
||||
|
||||
@keyframes fadeInUp {
|
||||
from {
|
||||
opacity: 0;
|
||||
transform: translateY(30px);
|
||||
}
|
||||
to {
|
||||
opacity: 1;
|
||||
transform: translateY(0);
|
||||
}
|
||||
}
|
||||
|
||||
.config-card {
|
||||
border-radius: 16px;
|
||||
border: none;
|
||||
background: rgba(255, 255, 255, 0.98);
|
||||
backdrop-filter: blur(10px);
|
||||
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.1);
|
||||
transition: all 0.3s ease;
|
||||
}
|
||||
|
||||
.config-card:hover {
|
||||
box-shadow: 0 12px 48px rgba(0, 0, 0, 0.15);
|
||||
transform: translateY(-4px);
|
||||
}
|
||||
|
||||
.card-header {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
.header-left {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 12px;
|
||||
}
|
||||
|
||||
.icon-wrapper {
|
||||
width: 40px;
|
||||
height: 40px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
||||
border-radius: 10px;
|
||||
color: #ffffff;
|
||||
font-size: 20px;
|
||||
}
|
||||
|
||||
.header-title {
|
||||
font-size: 16px;
|
||||
font-weight: 600;
|
||||
color: #303133;
|
||||
}
|
||||
|
||||
.card-content {
|
||||
padding: 8px 0;
|
||||
}
|
||||
|
||||
.provider-select-section {
|
||||
margin-bottom: 16px;
|
||||
}
|
||||
|
||||
.section-label {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 8px;
|
||||
margin-bottom: 12px;
|
||||
font-size: 14px;
|
||||
font-weight: 600;
|
||||
color: #606266;
|
||||
}
|
||||
|
||||
.section-label .el-icon {
|
||||
color: #667eea;
|
||||
}
|
||||
|
||||
.provider-info {
|
||||
display: flex;
|
||||
align-items: flex-start;
|
||||
gap: 8px;
|
||||
margin-top: 12px;
|
||||
padding: 14px 16px;
|
||||
background: linear-gradient(135deg, #f5f7fa 0%, #e8ecf1 100%);
|
||||
border-radius: 10px;
|
||||
font-size: 13px;
|
||||
color: #606266;
|
||||
line-height: 1.6;
|
||||
border-left: 3px solid #667eea;
|
||||
}
|
||||
|
||||
.info-icon {
|
||||
margin-top: 2px;
|
||||
color: #667eea;
|
||||
font-size: 16px;
|
||||
}
|
||||
|
||||
.info-text {
|
||||
flex: 1;
|
||||
}
|
||||
|
||||
.config-form-section {
|
||||
max-height: 400px;
|
||||
overflow-y: auto;
|
||||
padding-right: 8px;
|
||||
}
|
||||
|
||||
.config-form-section::-webkit-scrollbar {
|
||||
width: 6px;
|
||||
}
|
||||
|
||||
.config-form-section::-webkit-scrollbar-track {
|
||||
background: #f1f1f1;
|
||||
border-radius: 3px;
|
||||
}
|
||||
|
||||
.config-form-section::-webkit-scrollbar-thumb {
|
||||
background: #c0c4cc;
|
||||
border-radius: 3px;
|
||||
}
|
||||
|
||||
.config-form-section::-webkit-scrollbar-thumb:hover {
|
||||
background: #a0a4ac;
|
||||
}
|
||||
|
||||
.card-footer {
|
||||
display: flex;
|
||||
justify-content: flex-end;
|
||||
gap: 12px;
|
||||
padding-top: 8px;
|
||||
}
|
||||
|
||||
.right-column {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 24px;
|
||||
}
|
||||
|
||||
.formats-card {
|
||||
border-radius: 16px;
|
||||
border: none;
|
||||
background: rgba(255, 255, 255, 0.98);
|
||||
backdrop-filter: blur(10px);
|
||||
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.1);
|
||||
transition: all 0.3s ease;
|
||||
}
|
||||
|
||||
.formats-card:hover {
|
||||
box-shadow: 0 12px 48px rgba(0, 0, 0, 0.15);
|
||||
transform: translateY(-4px);
|
||||
}
|
||||
|
||||
.empty-icon {
|
||||
width: 120px;
|
||||
height: 120px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
background: linear-gradient(135deg, #f5f7fa 0%, #e8ecf1 100%);
|
||||
border-radius: 50%;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
.empty-icon .el-icon {
|
||||
font-size: 60px;
|
||||
color: #c0c4cc;
|
||||
}
|
||||
|
||||
.fade-enter-active,
|
||||
.fade-leave-active {
|
||||
transition: opacity 0.3s ease;
|
||||
}
|
||||
|
||||
.fade-enter-from,
|
||||
.fade-leave-to {
|
||||
opacity: 0;
|
||||
}
|
||||
|
||||
.slide-fade-enter-active {
|
||||
transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
|
||||
}
|
||||
|
||||
.slide-fade-leave-active {
|
||||
transition: all 0.3s cubic-bezier(1, 0.5, 0.8, 1);
|
||||
}
|
||||
|
||||
.slide-fade-enter-from {
|
||||
opacity: 0;
|
||||
transform: translateX(-20px);
|
||||
}
|
||||
|
||||
.slide-fade-leave-to {
|
||||
opacity: 0;
|
||||
transform: translateX(20px);
|
||||
}
|
||||
|
||||
@media (max-width: 768px) {
|
||||
.embedding-config-page {
|
||||
padding: 16px;
|
||||
}
|
||||
|
||||
.page-title {
|
||||
font-size: 24px;
|
||||
}
|
||||
|
||||
.header-content {
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
.title-section {
|
||||
min-width: 100%;
|
||||
}
|
||||
|
||||
.config-form-section {
|
||||
max-height: 300px;
|
||||
}
|
||||
}
|
||||
</style>
|
||||
|
|
@ -6,7 +6,8 @@ Admin API routes for AI Service management.
|
|||
from app.api.admin.dashboard import router as dashboard_router
|
||||
from app.api.admin.embedding import router as embedding_router
|
||||
from app.api.admin.kb import router as kb_router
|
||||
from app.api.admin.llm import router as llm_router
|
||||
from app.api.admin.rag import router as rag_router
|
||||
from app.api.admin.sessions import router as sessions_router
|
||||
|
||||
__all__ = ["dashboard_router", "embedding_router", "kb_router", "rag_router", "sessions_router"]
|
||||
__all__ = ["dashboard_router", "embedding_router", "kb_router", "llm_router", "rag_router", "sessions_router"]
|
||||
|
|
|
|||
|
|
@ -0,0 +1,146 @@
|
|||
"""
|
||||
LLM Configuration Management API.
|
||||
[AC-ASA-14, AC-ASA-15, AC-ASA-16, AC-ASA-17, AC-ASA-18] LLM provider management endpoints.
|
||||
"""
|
||||
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, Request
|
||||
|
||||
from app.core.tenant import get_tenant_id
|
||||
from app.services.llm.factory import (
|
||||
LLMConfigManager,
|
||||
LLMProviderFactory,
|
||||
get_llm_config_manager,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/admin/llm", tags=["LLM Management"])
|
||||
|
||||
|
||||
@router.get("/providers")
|
||||
async def list_providers(request: Request) -> dict[str, Any]:
|
||||
"""
|
||||
List all available LLM providers.
|
||||
[AC-ASA-15] Returns provider list with configuration schemas.
|
||||
"""
|
||||
tenant_id = get_tenant_id(request)
|
||||
logger.info(f"[AC-ASA-15] Listing LLM providers for tenant={tenant_id}")
|
||||
|
||||
providers = LLMProviderFactory.get_providers()
|
||||
return {
|
||||
"providers": [
|
||||
{
|
||||
"name": p.name,
|
||||
"display_name": p.display_name,
|
||||
"description": p.description,
|
||||
"config_schema": p.config_schema,
|
||||
}
|
||||
for p in providers
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
@router.get("/config")
|
||||
async def get_config(request: Request) -> dict[str, Any]:
|
||||
"""
|
||||
Get current LLM configuration.
|
||||
[AC-ASA-14] Returns current provider and config.
|
||||
"""
|
||||
tenant_id = get_tenant_id(request)
|
||||
logger.info(f"[AC-ASA-14] Getting LLM config for tenant={tenant_id}")
|
||||
|
||||
manager = get_llm_config_manager()
|
||||
config = manager.get_current_config()
|
||||
|
||||
masked_config = _mask_secrets(config.get("config", {}))
|
||||
|
||||
return {
|
||||
"provider": config["provider"],
|
||||
"config": masked_config,
|
||||
}
|
||||
|
||||
|
||||
@router.put("/config")
|
||||
async def update_config(
|
||||
request: Request,
|
||||
body: dict[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
Update LLM configuration.
|
||||
[AC-ASA-16] Updates provider and config with validation.
|
||||
"""
|
||||
tenant_id = get_tenant_id(request)
|
||||
provider = body.get("provider")
|
||||
config = body.get("config", {})
|
||||
|
||||
logger.info(f"[AC-ASA-16] Updating LLM config for tenant={tenant_id}, provider={provider}")
|
||||
|
||||
if not provider:
|
||||
return {
|
||||
"success": False,
|
||||
"message": "Provider is required",
|
||||
}
|
||||
|
||||
try:
|
||||
manager = get_llm_config_manager()
|
||||
await manager.update_config(provider, config)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"message": f"LLM configuration updated to {provider}",
|
||||
}
|
||||
|
||||
except ValueError as e:
|
||||
logger.error(f"[AC-ASA-16] Invalid LLM config: {e}")
|
||||
return {
|
||||
"success": False,
|
||||
"message": str(e),
|
||||
}
|
||||
|
||||
|
||||
@router.post("/test")
|
||||
async def test_connection(
|
||||
request: Request,
|
||||
body: dict[str, Any] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
Test LLM connection.
|
||||
[AC-ASA-17, AC-ASA-18] Tests connection and returns response.
|
||||
"""
|
||||
tenant_id = get_tenant_id(request)
|
||||
body = body or {}
|
||||
|
||||
test_prompt = body.get("test_prompt", "你好，请简单介绍一下自己。")
|
||||
provider = body.get("provider")
|
||||
config = body.get("config")
|
||||
|
||||
logger.info(
|
||||
f"[AC-ASA-17] Testing LLM connection for tenant={tenant_id}, "
|
||||
f"provider={provider or 'current'}"
|
||||
)
|
||||
|
||||
manager = get_llm_config_manager()
|
||||
result = await manager.test_connection(
|
||||
test_prompt=test_prompt,
|
||||
provider=provider,
|
||||
config=config,
|
||||
)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def _mask_secrets(config: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Mask secret fields in config for display."""
|
||||
masked = {}
|
||||
for key, value in config.items():
|
||||
if key in ("api_key", "password", "secret"):
|
||||
if value:
|
||||
masked[key] = f"{str(value)[:4]}***"
|
||||
else:
|
||||
masked[key] = ""
|
||||
else:
|
||||
masked[key] = value
|
||||
return masked
|
||||
|
|
@ -1,24 +1,24 @@
|
|||
"""
|
||||
RAG Lab endpoints for debugging and experimentation.
|
||||
[AC-ASA-05] RAG experiment debugging with retrieval results and prompt visualization.
|
||||
[AC-ASA-05, AC-ASA-19, AC-ASA-20, AC-ASA-21, AC-ASA-22] RAG experiment with AI output.
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
import time
|
||||
from typing import Annotated, Any, List
|
||||
|
||||
from fastapi import APIRouter, Depends, Body
|
||||
from fastapi.responses import JSONResponse
|
||||
from fastapi.responses import JSONResponse, StreamingResponse
|
||||
from pydantic import BaseModel, Field
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from app.core.config import get_settings
|
||||
from app.core.database import get_session
|
||||
from app.core.exceptions import MissingTenantIdException
|
||||
from app.core.tenant import get_tenant_id
|
||||
from app.core.qdrant_client import get_qdrant_client
|
||||
from app.models import ErrorResponse
|
||||
from app.services.retrieval.vector_retriever import get_vector_retriever
|
||||
from app.services.retrieval.base import RetrievalContext
|
||||
from app.services.llm.factory import get_llm_config_manager
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
|
@ -36,16 +36,37 @@ def get_current_tenant_id() -> str:
|
|||
class RAGExperimentRequest(BaseModel):
|
||||
query: str = Field(..., description="Query text for retrieval")
|
||||
kb_ids: List[str] | None = Field(default=None, description="Knowledge base IDs to search")
|
||||
params: dict[str, Any] | None = Field(default=None, description="Retrieval parameters")
|
||||
top_k: int = Field(default=5, description="Number of results to retrieve")
|
||||
score_threshold: float = Field(default=0.5, description="Minimum similarity score")
|
||||
generate_response: bool = Field(default=True, description="Whether to generate AI response")
|
||||
llm_provider: str | None = Field(default=None, description="Specific LLM provider to use")
|
||||
|
||||
|
||||
class AIResponse(BaseModel):
|
||||
content: str
|
||||
prompt_tokens: int = 0
|
||||
completion_tokens: int = 0
|
||||
total_tokens: int = 0
|
||||
latency_ms: float = 0
|
||||
model: str = ""
|
||||
|
||||
|
||||
class RAGExperimentResult(BaseModel):
|
||||
query: str
|
||||
retrieval_results: List[dict] = []
|
||||
final_prompt: str = ""
|
||||
ai_response: AIResponse | None = None
|
||||
total_latency_ms: float = 0
|
||||
diagnostics: dict[str, Any] = {}
|
||||
|
||||
|
||||
@router.post(
|
||||
"/experiments/run",
|
||||
operation_id="runRagExperiment",
|
||||
summary="Run RAG debugging experiment",
|
||||
description="[AC-ASA-05] Trigger RAG experiment with retrieval and prompt generation.",
|
||||
summary="Run RAG debugging experiment with AI output",
|
||||
description="[AC-ASA-05, AC-ASA-19, AC-ASA-21, AC-ASA-22] Trigger RAG experiment with retrieval, prompt generation, and AI response.",
|
||||
responses={
|
||||
200: {"description": "Experiment results with retrieval and prompt"},
|
||||
200: {"description": "Experiment results with retrieval, prompt, and AI response"},
|
||||
401: {"description": "Unauthorized", "model": ErrorResponse},
|
||||
403: {"description": "Forbidden", "model": ErrorResponse},
|
||||
},
|
||||
|
|
@ -55,18 +76,19 @@ async def run_rag_experiment(
|
|||
request: RAGExperimentRequest = Body(...),
|
||||
) -> JSONResponse:
|
||||
"""
|
||||
[AC-ASA-05] Run RAG experiment and return retrieval results with final prompt.
|
||||
[AC-ASA-05, AC-ASA-19, AC-ASA-21, AC-ASA-22] Run RAG experiment and return retrieval results with AI response.
|
||||
"""
|
||||
start_time = time.time()
|
||||
|
||||
logger.info(
|
||||
f"[AC-ASA-05] Running RAG experiment: tenant={tenant_id}, "
|
||||
f"query={request.query[:50]}..., kb_ids={request.kb_ids}"
|
||||
f"query={request.query[:50]}..., kb_ids={request.kb_ids}, "
|
||||
f"generate_response={request.generate_response}"
|
||||
)
|
||||
|
||||
settings = get_settings()
|
||||
|
||||
params = request.params or {}
|
||||
top_k = params.get("topK", settings.rag_top_k)
|
||||
threshold = params.get("threshold", settings.rag_score_threshold)
|
||||
top_k = request.top_k or settings.rag_top_k
|
||||
threshold = request.score_threshold or settings.rag_score_threshold
|
||||
|
||||
try:
|
||||
retriever = await get_vector_retriever()
|
||||
|
|
@ -94,14 +116,26 @@ async def run_rag_experiment(
|
|||
final_prompt = _build_final_prompt(request.query, retrieval_results)
|
||||
|
||||
logger.info(
|
||||
f"[AC-ASA-05] RAG experiment complete: hits={len(retrieval_results)}, "
|
||||
f"[AC-ASA-05] RAG retrieval complete: hits={len(retrieval_results)}, "
|
||||
f"max_score={result.max_score:.3f}"
|
||||
)
|
||||
|
||||
ai_response = None
|
||||
if request.generate_response:
|
||||
ai_response = await _generate_ai_response(
|
||||
final_prompt,
|
||||
provider=request.llm_provider,
|
||||
)
|
||||
|
||||
total_latency_ms = (time.time() - start_time) * 1000
|
||||
|
||||
return JSONResponse(
|
||||
content={
|
||||
"retrievalResults": retrieval_results,
|
||||
"finalPrompt": final_prompt,
|
||||
"query": request.query,
|
||||
"retrieval_results": retrieval_results,
|
||||
"final_prompt": final_prompt,
|
||||
"ai_response": ai_response.model_dump() if ai_response else None,
|
||||
"total_latency_ms": round(total_latency_ms, 2),
|
||||
"diagnostics": result.diagnostics,
|
||||
}
|
||||
)
|
||||
|
|
@ -112,10 +146,22 @@ async def run_rag_experiment(
|
|||
fallback_results = _get_fallback_results(request.query)
|
||||
fallback_prompt = _build_final_prompt(request.query, fallback_results)
|
||||
|
||||
ai_response = None
|
||||
if request.generate_response:
|
||||
ai_response = await _generate_ai_response(
|
||||
fallback_prompt,
|
||||
provider=request.llm_provider,
|
||||
)
|
||||
|
||||
total_latency_ms = (time.time() - start_time) * 1000
|
||||
|
||||
return JSONResponse(
|
||||
content={
|
||||
"retrievalResults": fallback_results,
|
||||
"finalPrompt": fallback_prompt,
|
||||
"query": request.query,
|
||||
"retrieval_results": fallback_results,
|
||||
"final_prompt": fallback_prompt,
|
||||
"ai_response": ai_response.model_dump() if ai_response else None,
|
||||
"total_latency_ms": round(total_latency_ms, 2),
|
||||
"diagnostics": {
|
||||
"error": str(e),
|
||||
"fallback": True,
|
||||
|
|
@ -124,6 +170,130 @@ async def run_rag_experiment(
|
|||
)
|
||||
|
||||
|
||||
@router.post(
|
||||
"/experiments/stream",
|
||||
operation_id="runRagExperimentStream",
|
||||
summary="Run RAG experiment with streaming AI output",
|
||||
description="[AC-ASA-20] Trigger RAG experiment with SSE streaming for AI response.",
|
||||
responses={
|
||||
200: {"description": "SSE stream with retrieval results and AI response"},
|
||||
401: {"description": "Unauthorized", "model": ErrorResponse},
|
||||
403: {"description": "Forbidden", "model": ErrorResponse},
|
||||
},
|
||||
)
|
||||
async def run_rag_experiment_stream(
|
||||
tenant_id: Annotated[str, Depends(get_current_tenant_id)],
|
||||
request: RAGExperimentRequest = Body(...),
|
||||
) -> StreamingResponse:
|
||||
"""
|
||||
[AC-ASA-20] Run RAG experiment with SSE streaming for AI response.
|
||||
"""
|
||||
logger.info(
|
||||
f"[AC-ASA-20] Running RAG experiment stream: tenant={tenant_id}, "
|
||||
f"query={request.query[:50]}..."
|
||||
)
|
||||
|
||||
settings = get_settings()
|
||||
top_k = request.top_k or settings.rag_top_k
|
||||
threshold = request.score_threshold or settings.rag_score_threshold
|
||||
|
||||
async def event_generator():
|
||||
try:
|
||||
retriever = await get_vector_retriever()
|
||||
|
||||
retrieval_ctx = RetrievalContext(
|
||||
tenant_id=tenant_id,
|
||||
query=request.query,
|
||||
session_id="rag_experiment_stream",
|
||||
channel_type="admin",
|
||||
metadata={"kb_ids": request.kb_ids},
|
||||
)
|
||||
|
||||
result = await retriever.retrieve(retrieval_ctx)
|
||||
|
||||
retrieval_results = [
|
||||
{
|
||||
"content": hit.text,
|
||||
"score": hit.score,
|
||||
"source": hit.source,
|
||||
"metadata": hit.metadata,
|
||||
}
|
||||
for hit in result.hits
|
||||
]
|
||||
|
||||
final_prompt = _build_final_prompt(request.query, retrieval_results)
|
||||
|
||||
yield f"event: retrieval\ndata: {json.dumps({'results': retrieval_results, 'count': len(retrieval_results)})}\n\n"
|
||||
|
||||
yield f"event: prompt\ndata: {json.dumps({'prompt': final_prompt})}\n\n"
|
||||
|
||||
if request.generate_response:
|
||||
manager = get_llm_config_manager()
|
||||
client = manager.get_client()
|
||||
|
||||
full_content = ""
|
||||
async for chunk in client.stream_generate(
|
||||
messages=[{"role": "user", "content": final_prompt}],
|
||||
):
|
||||
if chunk.delta:
|
||||
full_content += chunk.delta
|
||||
yield f"event: message\ndata: {json.dumps({'delta': chunk.delta})}\n\n"
|
||||
|
||||
yield f"event: final\ndata: {json.dumps({'content': full_content, 'finish_reason': 'stop'})}\n\n"
|
||||
else:
|
||||
yield f"event: final\ndata: {json.dumps({'content': '', 'finish_reason': 'skipped'})}\n\n"
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[AC-ASA-20] RAG experiment stream failed: {e}")
|
||||
yield f"event: error\ndata: {json.dumps({'error': str(e)})}\n\n"
|
||||
|
||||
return StreamingResponse(
|
||||
event_generator(),
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive",
|
||||
"X-Accel-Buffering": "no",
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
async def _generate_ai_response(
|
||||
prompt: str,
|
||||
provider: str | None = None,
|
||||
) -> AIResponse | None:
|
||||
"""
|
||||
[AC-ASA-19, AC-ASA-21] Generate AI response from prompt.
|
||||
"""
|
||||
import time
|
||||
|
||||
try:
|
||||
manager = get_llm_config_manager()
|
||||
client = manager.get_client()
|
||||
|
||||
start_time = time.time()
|
||||
response = await client.generate(
|
||||
messages=[{"role": "user", "content": prompt}],
|
||||
)
|
||||
latency_ms = (time.time() - start_time) * 1000
|
||||
|
||||
return AIResponse(
|
||||
content=response.content,
|
||||
prompt_tokens=response.usage.get("prompt_tokens", 0),
|
||||
completion_tokens=response.usage.get("completion_tokens", 0),
|
||||
total_tokens=response.usage.get("total_tokens", 0),
|
||||
latency_ms=round(latency_ms, 2),
|
||||
model=response.model,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[AC-ASA-19] AI response generation failed: {e}")
|
||||
return AIResponse(
|
||||
content=f"AI 响应生成失败: {str(e)}",
|
||||
latency_ms=0,
|
||||
)
|
||||
|
||||
|
||||
def _build_final_prompt(query: str, retrieval_results: list[dict]) -> str:
|
||||
"""
|
||||
Build the final prompt from query and retrieval results.
|
||||
|
|
@ -138,14 +308,14 @@ def _build_final_prompt(query: str, retrieval_results: list[dict]) -> str:
|
|||
for i, hit in enumerate(retrieval_results[:5])
|
||||
])
|
||||
|
||||
return f"""基于以下检索到的信息，回答用户问题：
|
||||
return f"""基于以下检索到的信息，作为一个回答简洁精准的客服，回答用户问题：
|
||||
|
||||
用户问题：{query}
|
||||
|
||||
检索结果：
|
||||
{evidence_text}
|
||||
|
||||
请基于以上信息生成专业、准确的回答。"""
|
||||
请基于以上信息生成专业、准确的回答，注意输出内容应该格式整齐，不包含json符号等。"""
|
||||
|
||||
|
||||
def _get_fallback_results(query: str) -> list[dict]:
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ from fastapi.middleware.cors import CORSMiddleware
|
|||
from fastapi.responses import JSONResponse
|
||||
|
||||
from app.api import chat_router, health_router
|
||||
from app.api.admin import dashboard_router, embedding_router, kb_router, rag_router, sessions_router
|
||||
from app.api.admin import dashboard_router, embedding_router, kb_router, llm_router, rag_router, sessions_router
|
||||
from app.core.config import get_settings
|
||||
from app.core.database import close_db, init_db
|
||||
from app.core.exceptions import (
|
||||
|
|
@ -115,6 +115,7 @@ app.include_router(chat_router)
|
|||
app.include_router(dashboard_router)
|
||||
app.include_router(embedding_router)
|
||||
app.include_router(kb_router)
|
||||
app.include_router(llm_router)
|
||||
app.include_router(rag_router)
|
||||
app.include_router(sessions_router)
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,332 @@
|
|||
"""
|
||||
LLM Provider Factory and Configuration Management.
|
||||
[AC-ASA-14, AC-ASA-15, AC-ASA-16, AC-ASA-17, AC-ASA-18] LLM provider management.
|
||||
|
||||
Design pattern: Factory pattern for pluggable LLM providers.
|
||||
"""
|
||||
|
||||
import logging
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any
|
||||
|
||||
from app.services.llm.base import LLMClient, LLMConfig
|
||||
from app.services.llm.openai_client import OpenAIClient
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class LLMProviderInfo:
|
||||
"""Information about an LLM provider."""
|
||||
name: str
|
||||
display_name: str
|
||||
description: str
|
||||
config_schema: dict[str, Any]
|
||||
|
||||
|
||||
LLM_PROVIDERS: dict[str, LLMProviderInfo] = {
|
||||
"openai": LLMProviderInfo(
|
||||
name="openai",
|
||||
display_name="OpenAI",
|
||||
description="OpenAI GPT 系列模型 (GPT-4, GPT-3.5 等)",
|
||||
config_schema={
|
||||
"api_key": {
|
||||
"type": "string",
|
||||
"description": "API Key",
|
||||
"required": True,
|
||||
"secret": True,
|
||||
},
|
||||
"base_url": {
|
||||
"type": "string",
|
||||
"description": "API Base URL",
|
||||
"default": "https://api.openai.com/v1",
|
||||
},
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "模型名称",
|
||||
"default": "gpt-4o-mini",
|
||||
},
|
||||
"max_tokens": {
|
||||
"type": "integer",
|
||||
"description": "最大输出 Token 数",
|
||||
"default": 2048,
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number",
|
||||
"description": "温度参数 (0-2)",
|
||||
"default": 0.7,
|
||||
},
|
||||
},
|
||||
),
|
||||
"ollama": LLMProviderInfo(
|
||||
name="ollama",
|
||||
display_name="Ollama",
|
||||
description="Ollama 本地模型 (Llama, Qwen 等)",
|
||||
config_schema={
|
||||
"base_url": {
|
||||
"type": "string",
|
||||
"description": "Ollama API 地址",
|
||||
"default": "http://localhost:11434/v1",
|
||||
},
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "模型名称",
|
||||
"default": "llama3.2",
|
||||
},
|
||||
"max_tokens": {
|
||||
"type": "integer",
|
||||
"description": "最大输出 Token 数",
|
||||
"default": 2048,
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number",
|
||||
"description": "温度参数 (0-2)",
|
||||
"default": 0.7,
|
||||
},
|
||||
},
|
||||
),
|
||||
"azure": LLMProviderInfo(
|
||||
name="azure",
|
||||
display_name="Azure OpenAI",
|
||||
description="Azure OpenAI 服务",
|
||||
config_schema={
|
||||
"api_key": {
|
||||
"type": "string",
|
||||
"description": "API Key",
|
||||
"required": True,
|
||||
"secret": True,
|
||||
},
|
||||
"base_url": {
|
||||
"type": "string",
|
||||
"description": "Azure Endpoint",
|
||||
"required": True,
|
||||
},
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "部署名称",
|
||||
"required": True,
|
||||
},
|
||||
"api_version": {
|
||||
"type": "string",
|
||||
"description": "API 版本",
|
||||
"default": "2024-02-15-preview",
|
||||
},
|
||||
"max_tokens": {
|
||||
"type": "integer",
|
||||
"description": "最大输出 Token 数",
|
||||
"default": 2048,
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number",
|
||||
"description": "温度参数 (0-2)",
|
||||
"default": 0.7,
|
||||
},
|
||||
},
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
class LLMProviderFactory:
|
||||
"""
|
||||
Factory for creating LLM clients.
|
||||
[AC-ASA-14, AC-ASA-15] Dynamic provider creation.
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def get_providers(cls) -> list[LLMProviderInfo]:
|
||||
"""Get all registered LLM providers."""
|
||||
return list(LLM_PROVIDERS.values())
|
||||
|
||||
@classmethod
|
||||
def get_provider_info(cls, name: str) -> LLMProviderInfo | None:
|
||||
"""Get provider info by name."""
|
||||
return LLM_PROVIDERS.get(name)
|
||||
|
||||
@classmethod
|
||||
def create_client(
|
||||
cls,
|
||||
provider: str,
|
||||
config: dict[str, Any],
|
||||
) -> LLMClient:
|
||||
"""
|
||||
Create an LLM client for the specified provider.
|
||||
[AC-ASA-15] Factory method for client creation.
|
||||
|
||||
Args:
|
||||
provider: Provider name (openai, ollama, azure)
|
||||
config: Provider configuration
|
||||
|
||||
Returns:
|
||||
LLMClient instance
|
||||
|
||||
Raises:
|
||||
ValueError: If provider is not supported
|
||||
"""
|
||||
if provider not in LLM_PROVIDERS:
|
||||
raise ValueError(f"Unsupported LLM provider: {provider}")
|
||||
|
||||
if provider in ("openai", "ollama", "azure"):
|
||||
return OpenAIClient(
|
||||
api_key=config.get("api_key"),
|
||||
base_url=config.get("base_url"),
|
||||
model=config.get("model"),
|
||||
default_config=LLMConfig(
|
||||
model=config.get("model", "gpt-4o-mini"),
|
||||
max_tokens=config.get("max_tokens", 2048),
|
||||
temperature=config.get("temperature", 0.7),
|
||||
),
|
||||
)
|
||||
|
||||
raise ValueError(f"Unsupported LLM provider: {provider}")
|
||||
|
||||
|
||||
class LLMConfigManager:
|
||||
"""
|
||||
Manager for LLM configuration.
|
||||
[AC-ASA-16, AC-ASA-17, AC-ASA-18] Configuration management with hot-reload.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self._current_provider: str = "openai"
|
||||
self._current_config: dict[str, Any] = {}
|
||||
self._client: LLMClient | None = None
|
||||
|
||||
def get_current_config(self) -> dict[str, Any]:
|
||||
"""Get current LLM configuration."""
|
||||
return {
|
||||
"provider": self._current_provider,
|
||||
"config": self._current_config,
|
||||
}
|
||||
|
||||
async def update_config(
|
||||
self,
|
||||
provider: str,
|
||||
config: dict[str, Any],
|
||||
) -> bool:
|
||||
"""
|
||||
Update LLM configuration.
|
||||
[AC-ASA-16] Hot-reload configuration.
|
||||
|
||||
Args:
|
||||
provider: Provider name
|
||||
config: New configuration
|
||||
|
||||
Returns:
|
||||
True if update successful
|
||||
"""
|
||||
if provider not in LLM_PROVIDERS:
|
||||
raise ValueError(f"Unsupported LLM provider: {provider}")
|
||||
|
||||
provider_info = LLM_PROVIDERS[provider]
|
||||
validated_config = self._validate_config(provider_info, config)
|
||||
|
||||
if self._client:
|
||||
await self._client.close()
|
||||
self._client = None
|
||||
|
||||
self._current_provider = provider
|
||||
self._current_config = validated_config
|
||||
|
||||
logger.info(f"[AC-ASA-16] LLM config updated: provider={provider}")
|
||||
return True
|
||||
|
||||
def _validate_config(
|
||||
self,
|
||||
provider_info: LLMProviderInfo,
|
||||
config: dict[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
"""Validate configuration against provider schema."""
|
||||
validated = {}
|
||||
for key, schema in provider_info.config_schema.items():
|
||||
if key in config:
|
||||
validated[key] = config[key]
|
||||
elif "default" in schema:
|
||||
validated[key] = schema["default"]
|
||||
elif schema.get("required"):
|
||||
raise ValueError(f"Missing required config: {key}")
|
||||
return validated
|
||||
|
||||
def get_client(self) -> LLMClient:
|
||||
"""Get or create LLM client with current config."""
|
||||
if self._client is None:
|
||||
self._client = LLMProviderFactory.create_client(
|
||||
self._current_provider,
|
||||
self._current_config,
|
||||
)
|
||||
return self._client
|
||||
|
||||
async def test_connection(
|
||||
self,
|
||||
test_prompt: str = "你好，请简单介绍一下自己。",
|
||||
provider: str | None = None,
|
||||
config: dict[str, Any] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
Test LLM connection.
|
||||
[AC-ASA-17, AC-ASA-18] Connection testing.
|
||||
|
||||
Args:
|
||||
test_prompt: Test prompt to send
|
||||
provider: Optional provider to test (uses current if not specified)
|
||||
config: Optional config to test (uses current if not specified)
|
||||
|
||||
Returns:
|
||||
Test result with success status, response, and metrics
|
||||
"""
|
||||
import time
|
||||
|
||||
test_provider = provider or self._current_provider
|
||||
test_config = config or self._current_config
|
||||
|
||||
if test_provider not in LLM_PROVIDERS:
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"Unsupported provider: {test_provider}",
|
||||
}
|
||||
|
||||
try:
|
||||
client = LLMProviderFactory.create_client(test_provider, test_config)
|
||||
|
||||
start_time = time.time()
|
||||
response = await client.generate(
|
||||
messages=[{"role": "user", "content": test_prompt}],
|
||||
)
|
||||
latency_ms = (time.time() - start_time) * 1000
|
||||
|
||||
await client.close()
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"response": response.content,
|
||||
"latency_ms": round(latency_ms, 2),
|
||||
"prompt_tokens": response.usage.get("prompt_tokens", 0),
|
||||
"completion_tokens": response.usage.get("completion_tokens", 0),
|
||||
"total_tokens": response.usage.get("total_tokens", 0),
|
||||
"model": response.model,
|
||||
"message": f"连接成功，模型: {response.model}",
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[AC-ASA-18] LLM test failed: {e}")
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(e),
|
||||
"message": f"连接失败: {str(e)}",
|
||||
}
|
||||
|
||||
async def close(self) -> None:
|
||||
"""Close the current client."""
|
||||
if self._client:
|
||||
await self._client.close()
|
||||
self._client = None
|
||||
|
||||
|
||||
_llm_config_manager: LLMConfigManager | None = None
|
||||
|
||||
|
||||
def get_llm_config_manager() -> LLMConfigManager:
|
||||
"""Get or create LLM config manager instance."""
|
||||
global _llm_config_manager
|
||||
if _llm_config_manager is None:
|
||||
_llm_config_manager = LLMConfigManager()
|
||||
return _llm_config_manager
|
||||
|
|
@ -16,6 +16,10 @@ dependencies = [
|
|||
"asyncpg>=0.29.0",
|
||||
"qdrant-client>=1.7.0",
|
||||
"tiktoken>=0.5.0",
|
||||
"openpyxl>=3.1.0",
|
||||
"python-docx>=1.1.0",
|
||||
"pymupdf>=1.23.0",
|
||||
"pdfplumber>=0.10.0",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
|
|
|
|||
|
|
@ -0,0 +1,80 @@
|
|||
"""
|
||||
Check Qdrant vector database contents - detailed view.
|
||||
"""
|
||||
import asyncio
|
||||
import sys
|
||||
sys.path.insert(0, ".")
|
||||
|
||||
from qdrant_client import AsyncQdrantClient
|
||||
from app.core.config import get_settings
|
||||
from collections import defaultdict
|
||||
|
||||
settings = get_settings()
|
||||
|
||||
|
||||
async def check_qdrant():
|
||||
"""Check Qdrant collections and vectors."""
|
||||
client = AsyncQdrantClient(url=settings.qdrant_url, check_compatibility=False)
|
||||
|
||||
print(f"\n{'='*60}")
|
||||
print(f"Qdrant URL: {settings.qdrant_url}")
|
||||
print(f"{'='*60}\n")
|
||||
|
||||
# List all collections
|
||||
collections = await client.get_collections()
|
||||
|
||||
# Check kb_default collection
|
||||
for c in collections.collections:
|
||||
if c.name == "kb_default":
|
||||
print(f"\n--- Collection: {c.name} ---")
|
||||
|
||||
# Get collection info
|
||||
info = await client.get_collection(c.name)
|
||||
print(f" Total vectors: {info.points_count}")
|
||||
|
||||
# Scroll through all points and group by source
|
||||
all_points = []
|
||||
offset = None
|
||||
|
||||
while True:
|
||||
points, offset = await client.scroll(
|
||||
collection_name=c.name,
|
||||
limit=100,
|
||||
offset=offset,
|
||||
with_payload=True,
|
||||
with_vectors=False,
|
||||
)
|
||||
all_points.extend(points)
|
||||
if offset is None:
|
||||
break
|
||||
|
||||
# Group by source
|
||||
by_source = defaultdict(list)
|
||||
for p in all_points:
|
||||
source = p.payload.get("source", "unknown") if p.payload else "unknown"
|
||||
by_source[source].append(p)
|
||||
|
||||
print(f"\n Documents by source:")
|
||||
for source, points in by_source.items():
|
||||
print(f"\n Source: {source}")
|
||||
print(f" Chunks: {len(points)}")
|
||||
|
||||
# Check first chunk content
|
||||
first_point = points[0]
|
||||
text = first_point.payload.get("text", "") if first_point.payload else ""
|
||||
|
||||
# Check if it's binary garbage or proper text
|
||||
is_garbage = any(ord(c) > 0xFFFF or (ord(c) < 32 and c not in '\n\r\t') for c in text[:200])
|
||||
|
||||
if is_garbage:
|
||||
print(f" Status: ❌ BINARY GARBAGE (parsing failed)")
|
||||
else:
|
||||
print(f" Status: ✅ PROPER TEXT (parsed correctly)")
|
||||
|
||||
print(f" Preview: {text[:150]}...")
|
||||
|
||||
await client.close()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(check_qdrant())
|
||||
|
|
@ -0,0 +1,115 @@
|
|||
"""
|
||||
Clean up garbage data from Qdrant vector database.
|
||||
Removes vectors that contain binary garbage (failed parsing results).
|
||||
"""
|
||||
import asyncio
|
||||
import sys
|
||||
sys.path.insert(0, ".")
|
||||
|
||||
from qdrant_client import AsyncQdrantClient
|
||||
from qdrant_client.models import PointIdsList
|
||||
from app.core.config import get_settings
|
||||
from collections import defaultdict
|
||||
|
||||
settings = get_settings()
|
||||
|
||||
|
||||
def is_garbage_text(text: str) -> bool:
|
||||
"""Check if text contains binary garbage."""
|
||||
if not text:
|
||||
return True
|
||||
|
||||
sample = text[:500]
|
||||
|
||||
garbage_chars = sum(1 for c in sample if ord(c) > 0xFFFF or (ord(c) < 32 and c not in '\n\r\t'))
|
||||
|
||||
return garbage_chars > len(sample) * 0.1
|
||||
|
||||
|
||||
async def cleanup_garbage():
|
||||
"""Clean up garbage data from Qdrant."""
|
||||
client = AsyncQdrantClient(url=settings.qdrant_url, check_compatibility=False)
|
||||
|
||||
print(f"\n{'='*60}")
|
||||
print(f"Cleaning up garbage data from Qdrant")
|
||||
print(f"URL: {settings.qdrant_url}")
|
||||
print(f"{'='*60}\n")
|
||||
|
||||
collections = await client.get_collections()
|
||||
|
||||
for c in collections.collections:
|
||||
if not c.name.startswith(settings.qdrant_collection_prefix):
|
||||
continue
|
||||
|
||||
print(f"\n--- Collection: {c.name} ---")
|
||||
|
||||
info = await client.get_collection(c.name)
|
||||
print(f" Total vectors: {info.points_count}")
|
||||
|
||||
all_points = []
|
||||
offset = None
|
||||
|
||||
while True:
|
||||
points, offset = await client.scroll(
|
||||
collection_name=c.name,
|
||||
limit=100,
|
||||
offset=offset,
|
||||
with_payload=True,
|
||||
with_vectors=False,
|
||||
)
|
||||
all_points.extend(points)
|
||||
if offset is None:
|
||||
break
|
||||
|
||||
by_source = defaultdict(list)
|
||||
for p in all_points:
|
||||
source = p.payload.get("source", "unknown") if p.payload else "unknown"
|
||||
by_source[source].append(p)
|
||||
|
||||
garbage_sources = []
|
||||
good_sources = []
|
||||
|
||||
for source, points in by_source.items():
|
||||
first_point = points[0]
|
||||
text = first_point.payload.get("text", "") if first_point.payload else ""
|
||||
|
||||
if is_garbage_text(text):
|
||||
garbage_sources.append((source, points))
|
||||
else:
|
||||
good_sources.append((source, points))
|
||||
|
||||
print(f"\n Good documents: {len(good_sources)}")
|
||||
print(f" Garbage documents: {len(garbage_sources)}")
|
||||
|
||||
if garbage_sources:
|
||||
print(f"\n Garbage documents to delete:")
|
||||
for source, points in garbage_sources:
|
||||
print(f" - {source} ({len(points)} chunks)")
|
||||
preview = ""
|
||||
if points[0].payload:
|
||||
preview = points[0].payload.get("text", "")[:80]
|
||||
print(f" Preview: {repr(preview)}...")
|
||||
|
||||
confirm = input("\n Delete these garbage documents? (y/n): ")
|
||||
|
||||
if confirm.lower() == 'y':
|
||||
for source, points in garbage_sources:
|
||||
point_ids = [p.id for p in points]
|
||||
|
||||
await client.delete(
|
||||
collection_name=c.name,
|
||||
points_selector=PointIdsList(points=point_ids)
|
||||
)
|
||||
print(f" Deleted {len(point_ids)} vectors for source {source}")
|
||||
|
||||
print(f"\n Cleanup complete!")
|
||||
else:
|
||||
print(f"\n Cancelled.")
|
||||
else:
|
||||
print(f"\n No garbage data found.")
|
||||
|
||||
await client.close()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(cleanup_garbage())
|
||||
|
|
@ -0,0 +1,40 @@
|
|||
"""
|
||||
Test Excel parsing directly.
|
||||
"""
|
||||
import sys
|
||||
sys.path.insert(0, ".")
|
||||
|
||||
from app.services.document import parse_document, get_supported_document_formats
|
||||
|
||||
print("Supported formats:", get_supported_document_formats())
|
||||
print()
|
||||
|
||||
# Test with a sample xlsx file if available
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
# Find any xlsx files in the uploads directory
|
||||
uploads_dir = Path("uploads")
|
||||
if uploads_dir.exists():
|
||||
xlsx_files = list(uploads_dir.glob("**/*.xlsx"))
|
||||
print(f"Found {len(xlsx_files)} xlsx files")
|
||||
|
||||
for f in xlsx_files[:1]: # Test first one
|
||||
print(f"\nTesting: {f}")
|
||||
try:
|
||||
result = parse_document(str(f))
|
||||
print(f" SUCCESS: chars={len(result.text)}")
|
||||
print(f" metadata: {result.metadata}")
|
||||
print(f" preview: {result.text[:500]}...")
|
||||
except Exception as e:
|
||||
print(f" FAILED: {type(e).__name__}: {e}")
|
||||
else:
|
||||
print("No uploads directory found")
|
||||
|
||||
# Test openpyxl directly
|
||||
print("\n--- Testing openpyxl directly ---")
|
||||
try:
|
||||
import openpyxl
|
||||
print(f"openpyxl version: {openpyxl.__version__}")
|
||||
except ImportError as e:
|
||||
print(f"openpyxl NOT installed: {e}")
|
||||
|
|
@ -3,7 +3,8 @@ module: ai-service-admin
|
|||
feature: ASA
|
||||
status: in_progress
|
||||
created: 2026-02-24
|
||||
last_updated: 2026-02-24
|
||||
last_updated: "2026-02-24"
|
||||
version: "0.3.0"
|
||||
---
|
||||
|
||||
# AI 中台管理界面（ai-service-admin）进度文档
|
||||
|
|
@ -28,41 +29,60 @@ last_updated: 2026-02-24
|
|||
- [x] Phase 3: RAG 实验室 (100%) [P3-01 ~ P3-04]
|
||||
- [x] Phase 4: 会话监控与详情 (100%) [P4-01 ~ P4-03]
|
||||
- [x] Phase 5: 后端管理接口实现 (100%) [Backend Admin APIs]
|
||||
- [ ] Phase 6: 嵌入模型管理 (0%) [P5-01 ~ P5-08]
|
||||
- [ ] Phase 7: LLM 配置与 RAG 调试输出 (0%) [P6-01 ~ P6-10] 🔄当前
|
||||
|
||||
## current_phase
|
||||
|
||||
**goal**: 知识库管理模块开发，实现文档上传、列表展示与状态轮询
|
||||
**goal**: 实现 LLM 模型配置页面及 RAG 实验室 AI 输出调试功能
|
||||
|
||||
### sub_tasks
|
||||
|
||||
- [x] (P1-01) 初始化 `ai-service-admin` 前端工程（Vue 3 + Element Plus + RuoYi-Vue 基座对齐），落地基础目录结构与路由骨架
|
||||
- [x] (P1-02) 接入 Pinia：实现 `tenant` store（`currentTenantId`）并持久化（localStorage），提供切换租户能力
|
||||
- [x] (P1-03) Axios/SDK 请求层封装：创建统一 `request` 实例，自动注入必填 Header `X-Tenant-Id`
|
||||
- [x] (P1-04) 全局异常拦截：实现 401/403 响应拦截策略
|
||||
- [x] (P1-05) 基础组件封装：`BaseTable`、`BaseForm` 并给出示例页
|
||||
- [x] (P2-01) 创建 `openapi.deps.yaml` 明确依赖契约 (L1) [AC-ASA-08]
|
||||
- [x] (P2-02) 实现知识库列表 API 对接及分页展示 [AC-ASA-08]
|
||||
- [x] (P2-03) 实现文档上传功能（Multipart/form-data）[AC-ASA-01]
|
||||
- [x] (P2-04) 实现索引任务状态轮询机制（3s 间隔）[AC-ASA-02]
|
||||
- [x] (P2-05) 失败任务错误详情弹窗展示 [AC-ASA-02]
|
||||
- [x] (P5-01) 实现后端 GET /admin/kb/documents 文档列表接口 [AC-ASA-08]
|
||||
- [x] (P5-02) 实现后端 POST /admin/kb/documents 文档上传接口 [AC-ASA-01]
|
||||
- [x] (P5-03) 实现后端 GET /admin/kb/index/jobs/{jobId} 索引任务查询接口 [AC-ASA-02]
|
||||
- [x] (P5-04) 实现后端 POST /admin/rag/experiments/run RAG实验接口 [AC-ASA-05]
|
||||
- [x] (P5-05) 实现后端 GET /admin/sessions 会话列表接口 [AC-ASA-09]
|
||||
- [x] (P5-06) 实现后端 GET /admin/sessions/{sessionId} 会话详情接口 [AC-ASA-07]
|
||||
#### Phase 1-5 已完成
|
||||
- [x] (P1-01) 初始化前端工程
|
||||
- [x] (P1-02) 接入 Pinia tenant store
|
||||
- [x] (P1-03) Axios 请求层封装
|
||||
- [x] (P1-04) 全局异常拦截
|
||||
- [x] (P1-05) 基础组件封装
|
||||
- [x] (P2-01~P2-05) 知识库管理功能
|
||||
- [x] (P3-01~P3-04) RAG 实验室功能
|
||||
- [x] (P4-01~P4-03) 会话监控功能
|
||||
- [x] (P5-01~P5-06) 后端管理接口实现
|
||||
|
||||
#### Phase 6: 嵌入模型管理（待处理）
|
||||
- [ ] (P5-01) API 服务层与类型定义 [AC-ASA-08, AC-ASA-09]
|
||||
- [ ] (P5-02) 提供者选择组件 [AC-ASA-09]
|
||||
- [ ] (P5-03) 动态配置表单 [AC-ASA-09, AC-ASA-10]
|
||||
- [ ] (P5-04) 测试连接组件 [AC-ASA-11, AC-ASA-12]
|
||||
- [ ] (P5-05) 支持格式组件 [AC-ASA-13]
|
||||
- [ ] (P5-06) 页面骨架与路由 [AC-ASA-08]
|
||||
- [ ] (P5-07) 配置加载与保存 [AC-ASA-08, AC-ASA-10]
|
||||
- [ ] (P5-08) 组件整合与测试 [AC-ASA-08~AC-ASA-13]
|
||||
|
||||
#### Phase 7: LLM 配置与 RAG 调试输出（当前）
|
||||
- [ ] (P6-01) LLM API 服务层与类型定义：创建 src/api/llm.ts 和 src/types/llm.ts [AC-ASA-14, AC-ASA-15]
|
||||
- [ ] (P6-02) LLM 提供者选择组件：创建 LLMProviderSelect.vue [AC-ASA-15]
|
||||
- [ ] (P6-03) LLM 动态配置表单：创建 LLMConfigForm.vue [AC-ASA-15, AC-ASA-16]
|
||||
- [ ] (P6-04) LLM 测试连接组件：创建 LLMTestPanel.vue [AC-ASA-17, AC-ASA-18]
|
||||
- [ ] (P6-05) LLM 配置页面：创建 /admin/llm 页面 [AC-ASA-14, AC-ASA-16]
|
||||
- [ ] (P6-06) AI 回复展示组件：创建 AIResponseViewer.vue [AC-ASA-19]
|
||||
- [ ] (P6-07) 流式输出支持：实现 SSE 流式输出展示 [AC-ASA-20]
|
||||
- [ ] (P6-08) Token 统计展示：展示 Token 消耗、响应耗时 [AC-ASA-21]
|
||||
- [ ] (P6-09) LLM 选择器：在 RAG 实验室中添加 LLM 配置选择器 [AC-ASA-22]
|
||||
- [ ] (P6-10) RAG 实验室整合：将 AI 输出组件整合到 RAG 实验室 [AC-ASA-19~AC-ASA-22]
|
||||
|
||||
### next_action
|
||||
|
||||
**immediate**: 后端管理接口已实现完成，等待前端联调
|
||||
**immediate**: 并行启动 3 个窗口执行 Phase 6 和 Phase 7 任务
|
||||
|
||||
**details**:
|
||||
- file: "ai-service/app/api/admin/"
|
||||
- action: "后端 7 个管理接口已全部实现，包含 Mock 数据返回，支持前端并行开发"
|
||||
- reference: "spec/ai-service/openapi.admin.yaml"
|
||||
- file: "ai-service-admin/src/"
|
||||
- action: "窗口1: 嵌入管理组件; 窗口2: LLM 配置组件; 窗口3: RAG 实验室增强"
|
||||
- reference: "spec/ai-service-admin/openapi.deps.yaml"
|
||||
- constraints:
|
||||
- 所有接口均已实现 X-Tenant-Id Header 校验
|
||||
- 返回数据格式与契约定义一致
|
||||
- 每个任务必须包含 AC 标记
|
||||
- 完成后更新 spec/ai-service-admin/tasks.md
|
||||
- commit message 格式: `feat(ASA-P6/P7): <desc> [AC-ASA-XX]`
|
||||
|
||||
### backend_implementation_summary
|
||||
|
||||
|
|
@ -147,6 +167,30 @@ export const useTenantStore = defineStore('tenant', {
|
|||
- ai-service/app/main.py - 注册管理路由
|
||||
- docs/progress/ai-service-admin-progress.md - 更新进度
|
||||
|
||||
- session: "Session #3 (2026-02-24) - 嵌入模型管理需求规划"
|
||||
completed:
|
||||
- 更新 spec/ai-service-admin/requirements.md 添加 v0.2.0 迭代需求
|
||||
- 更新 spec/ai-service-admin/tasks.md 添加 Phase 5 任务
|
||||
- 更新 spec/ai-service-admin/openapi.deps.yaml 添加嵌入管理接口
|
||||
- 更新进度文档添加 Phase 6 任务
|
||||
changes:
|
||||
- spec/ai-service-admin/requirements.md - 新增 AC-ASA-08~AC-ASA-13
|
||||
- spec/ai-service-admin/tasks.md - 新增 P5-01~P5-08 任务
|
||||
- spec/ai-service-admin/openapi.deps.yaml - 完整重写，添加嵌入管理接口
|
||||
- docs/progress/ai-service-admin-progress.md - 添加 Phase 6
|
||||
|
||||
- session: "Session #4 (2026-02-24) - LLM 配置与 RAG 调试输出需求规划"
|
||||
completed:
|
||||
- 更新 spec/ai-service-admin/requirements.md 添加 v0.3.0 迭代需求
|
||||
- 更新 spec/ai-service-admin/tasks.md 添加 Phase 6 任务
|
||||
- 更新 spec/ai-service-admin/openapi.deps.yaml 添加 LLM 管理和 RAG 实验增强接口
|
||||
- 更新进度文档添加 Phase 7 任务
|
||||
changes:
|
||||
- spec/ai-service-admin/requirements.md - 新增 AC-ASA-14~AC-ASA-22
|
||||
- spec/ai-service-admin/tasks.md - 新增 P6-01~P6-10 任务
|
||||
- spec/ai-service-admin/openapi.deps.yaml - 添加 LLM 配置接口和 RAG 实验增强接口
|
||||
- docs/progress/ai-service-admin-progress.md - 添加 Phase 7
|
||||
|
||||
## startup_guide
|
||||
|
||||
1. **Step 1**: 读取本进度文档（了解当前位置与下一步）
|
||||
|
|
@ -159,9 +203,12 @@ export const useTenantStore = defineStore('tenant', {
|
|||
|
||||
| Phase | 名称 | 任务数 | 状态 |
|
||||
|-------|------|--------|------|
|
||||
| Phase 1 | 基础建设 | 5 | ⏳ 待开始 |
|
||||
| Phase 2 | 知识库管理 | 5 | ⏳ 待开始 |
|
||||
| Phase 3 | RAG 实验室 | 4 | ⏳ 待开始 |
|
||||
| Phase 4 | 会话监控与详情 | 3 | ⏳ 待开始 |
|
||||
| Phase 1 | 基础建设 | 5 | ✅ 完成 |
|
||||
| Phase 2 | 知识库管理 | 5 | ✅ 完成 |
|
||||
| Phase 3 | RAG 实验室 | 4 | ✅ 完成 |
|
||||
| Phase 4 | 会话监控与详情 | 3 | ✅ 完成 |
|
||||
| Phase 5 | 后端管理接口实现 | 6 | ✅ 完成 |
|
||||
| Phase 6 | 嵌入模型管理 | 8 | ⏳ 待处理 |
|
||||
| Phase 7 | LLM 配置与 RAG 调试输出 | 10 | 🔄 进行中 |
|
||||
|
||||
**总计: 17 个任务**
|
||||
**总计: 41 个任务 | 已完成: 23 个 | 待处理: 8 个 | 进行中: 10 个**
|
||||
|
|
|
|||
|
|
@ -1,6 +1,592 @@
|
|||
openapi: 3.1.0
|
||||
info:
|
||||
title: \" AI Service Admin "Dependencies\
|
||||
description: \ai-service-admin" 模块依赖的外<E79A84>?API 契约（Consumer "需求侧）\
|
||||
version: \0.1.0\
|
||||
x-contract-level: L1
|
||||
openapi: 3.1.0
|
||||
info:
|
||||
title: "AI Service Admin Dependencies"
|
||||
description: "ai-service-admin 模块依赖的外部 API 契约（Consumer 需求侧）"
|
||||
version: "0.3.0"
|
||||
x-contract-level: L1
|
||||
|
||||
servers:
|
||||
- url: http://localhost:8000
|
||||
description: 本地开发服务器
|
||||
|
||||
paths:
|
||||
/admin/embedding/providers:
|
||||
get:
|
||||
operationId: listEmbeddingProviders
|
||||
summary: 获取可用的嵌入模型提供者列表
|
||||
tags:
|
||||
- Embedding Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
responses:
|
||||
'200':
|
||||
description: 成功返回提供者列表
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
providers:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/EmbeddingProviderInfo'
|
||||
|
||||
/admin/embedding/config:
|
||||
get:
|
||||
operationId: getEmbeddingConfig
|
||||
summary: 获取当前嵌入模型配置
|
||||
tags:
|
||||
- Embedding Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
responses:
|
||||
'200':
|
||||
description: 成功返回当前配置
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/EmbeddingConfig'
|
||||
put:
|
||||
operationId: updateEmbeddingConfig
|
||||
summary: 更新嵌入模型配置
|
||||
tags:
|
||||
- Embedding Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/EmbeddingConfigUpdate'
|
||||
responses:
|
||||
'200':
|
||||
description: 配置更新成功
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
success:
|
||||
type: boolean
|
||||
message:
|
||||
type: string
|
||||
|
||||
/admin/embedding/test:
|
||||
post:
|
||||
operationId: testEmbedding
|
||||
summary: 测试嵌入模型连接
|
||||
tags:
|
||||
- Embedding Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: false
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
test_text:
|
||||
type: string
|
||||
description: 测试文本（可选）
|
||||
config:
|
||||
$ref: '#/components/schemas/EmbeddingConfigUpdate'
|
||||
responses:
|
||||
'200':
|
||||
description: 测试成功
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/EmbeddingTestResult'
|
||||
|
||||
/admin/embedding/formats:
|
||||
get:
|
||||
operationId: getSupportedFormats
|
||||
summary: 获取支持的文档格式列表
|
||||
tags:
|
||||
- Embedding Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
responses:
|
||||
'200':
|
||||
description: 成功返回支持格式列表
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
formats:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/DocumentFormat'
|
||||
|
||||
/admin/llm/providers:
|
||||
get:
|
||||
operationId: listLLMProviders
|
||||
summary: 获取可用的 LLM 提供者列表
|
||||
tags:
|
||||
- LLM Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
responses:
|
||||
'200':
|
||||
description: 成功返回提供者列表
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
providers:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/LLMProviderInfo'
|
||||
|
||||
/admin/llm/config:
|
||||
get:
|
||||
operationId: getLLMConfig
|
||||
summary: 获取当前 LLM 配置
|
||||
tags:
|
||||
- LLM Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
responses:
|
||||
'200':
|
||||
description: 成功返回当前配置
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/LLMConfig'
|
||||
put:
|
||||
operationId: updateLLMConfig
|
||||
summary: 更新 LLM 配置
|
||||
tags:
|
||||
- LLM Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/LLMConfigUpdate'
|
||||
responses:
|
||||
'200':
|
||||
description: 配置更新成功
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
success:
|
||||
type: boolean
|
||||
message:
|
||||
type: string
|
||||
|
||||
/admin/llm/test:
|
||||
post:
|
||||
operationId: testLLM
|
||||
summary: 测试 LLM 连接
|
||||
tags:
|
||||
- LLM Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: false
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
test_prompt:
|
||||
type: string
|
||||
description: 测试提示词（可选）
|
||||
example: "你好，请简单介绍一下自己。"
|
||||
config:
|
||||
$ref: '#/components/schemas/LLMConfigUpdate'
|
||||
responses:
|
||||
'200':
|
||||
description: 测试成功
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/LLMTestResult'
|
||||
|
||||
/admin/rag/experiments/run:
|
||||
post:
|
||||
operationId: runRagExperiment
|
||||
summary: 运行 RAG 实验（含 AI 输出）
|
||||
tags:
|
||||
- RAG Lab
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RagExperimentRequest'
|
||||
responses:
|
||||
'200':
|
||||
description: 实验完成
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RagExperimentResult'
|
||||
|
||||
/admin/rag/experiments/stream:
|
||||
post:
|
||||
operationId: runRagExperimentStream
|
||||
summary: 运行 RAG 实验（流式输出）
|
||||
tags:
|
||||
- RAG Lab
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RagExperimentRequest'
|
||||
responses:
|
||||
'200':
|
||||
description: SSE 流式输出
|
||||
content:
|
||||
text/event-stream:
|
||||
schema:
|
||||
type: string
|
||||
|
||||
components:
|
||||
schemas:
|
||||
EmbeddingProviderInfo:
|
||||
type: object
|
||||
required:
|
||||
- name
|
||||
- display_name
|
||||
- config_schema
|
||||
properties:
|
||||
name:
|
||||
type: string
|
||||
description: 提供者唯一标识
|
||||
example: "ollama"
|
||||
display_name:
|
||||
type: string
|
||||
description: 提供者显示名称
|
||||
example: "Ollama 本地模型"
|
||||
description:
|
||||
type: string
|
||||
description: 提供者描述
|
||||
example: "使用 Ollama 运行的本地嵌入模型"
|
||||
config_schema:
|
||||
type: object
|
||||
description: 配置参数定义（JSON Schema 格式）
|
||||
additionalProperties: true
|
||||
|
||||
EmbeddingConfig:
|
||||
type: object
|
||||
required:
|
||||
- provider
|
||||
- config
|
||||
properties:
|
||||
provider:
|
||||
type: string
|
||||
description: 当前激活的提供者
|
||||
example: "ollama"
|
||||
config:
|
||||
type: object
|
||||
description: 提供者配置参数
|
||||
additionalProperties: true
|
||||
updated_at:
|
||||
type: string
|
||||
format: date-time
|
||||
description: 配置最后更新时间
|
||||
|
||||
EmbeddingConfigUpdate:
|
||||
type: object
|
||||
required:
|
||||
- provider
|
||||
properties:
|
||||
provider:
|
||||
type: string
|
||||
description: 提供者标识
|
||||
example: "ollama"
|
||||
config:
|
||||
type: object
|
||||
description: 提供者配置参数
|
||||
additionalProperties: true
|
||||
|
||||
EmbeddingTestResult:
|
||||
type: object
|
||||
required:
|
||||
- success
|
||||
- dimension
|
||||
properties:
|
||||
success:
|
||||
type: boolean
|
||||
description: 测试是否成功
|
||||
dimension:
|
||||
type: integer
|
||||
description: 返回的向量维度
|
||||
example: 768
|
||||
latency_ms:
|
||||
type: number
|
||||
description: 响应延迟（毫秒）
|
||||
example: 125.5
|
||||
message:
|
||||
type: string
|
||||
description: 测试结果消息
|
||||
example: "连接成功，向量维度: 768"
|
||||
error:
|
||||
type: string
|
||||
description: 错误信息（失败时）
|
||||
example: "连接超时"
|
||||
|
||||
DocumentFormat:
|
||||
type: object
|
||||
required:
|
||||
- extension
|
||||
- name
|
||||
properties:
|
||||
extension:
|
||||
type: string
|
||||
description: 文件扩展名
|
||||
example: ".pdf"
|
||||
name:
|
||||
type: string
|
||||
description: 格式名称
|
||||
example: "PDF 文档"
|
||||
description:
|
||||
type: string
|
||||
description: 格式描述
|
||||
example: "使用 PyMuPDF 解析 PDF 文档"
|
||||
|
||||
LLMProviderInfo:
|
||||
type: object
|
||||
required:
|
||||
- name
|
||||
- display_name
|
||||
- config_schema
|
||||
properties:
|
||||
name:
|
||||
type: string
|
||||
description: 提供者唯一标识
|
||||
example: "openai"
|
||||
display_name:
|
||||
type: string
|
||||
description: 提供者显示名称
|
||||
example: "OpenAI"
|
||||
description:
|
||||
type: string
|
||||
description: 提供者描述
|
||||
example: "OpenAI GPT 系列模型"
|
||||
config_schema:
|
||||
type: object
|
||||
description: 配置参数定义（JSON Schema 格式）
|
||||
additionalProperties: true
|
||||
|
||||
LLMConfig:
|
||||
type: object
|
||||
required:
|
||||
- provider
|
||||
- config
|
||||
properties:
|
||||
provider:
|
||||
type: string
|
||||
description: 当前激活的提供者
|
||||
example: "openai"
|
||||
config:
|
||||
type: object
|
||||
description: 提供者配置参数
|
||||
additionalProperties: true
|
||||
example:
|
||||
api_key: "sk-xxx"
|
||||
base_url: "https://api.openai.com/v1"
|
||||
model: "gpt-4o-mini"
|
||||
updated_at:
|
||||
type: string
|
||||
format: date-time
|
||||
description: 配置最后更新时间
|
||||
|
||||
LLMConfigUpdate:
|
||||
type: object
|
||||
required:
|
||||
- provider
|
||||
properties:
|
||||
provider:
|
||||
type: string
|
||||
description: 提供者标识
|
||||
example: "openai"
|
||||
config:
|
||||
type: object
|
||||
description: 提供者配置参数
|
||||
additionalProperties: true
|
||||
|
||||
LLMTestResult:
|
||||
type: object
|
||||
required:
|
||||
- success
|
||||
properties:
|
||||
success:
|
||||
type: boolean
|
||||
description: 测试是否成功
|
||||
response:
|
||||
type: string
|
||||
description: LLM 响应内容
|
||||
example: "你好！我是一个 AI 助手..."
|
||||
latency_ms:
|
||||
type: number
|
||||
description: 响应延迟（毫秒）
|
||||
example: 1250.5
|
||||
prompt_tokens:
|
||||
type: integer
|
||||
description: 输入 Token 数
|
||||
example: 15
|
||||
completion_tokens:
|
||||
type: integer
|
||||
description: 输出 Token 数
|
||||
example: 50
|
||||
total_tokens:
|
||||
type: integer
|
||||
description: 总 Token 数
|
||||
example: 65
|
||||
message:
|
||||
type: string
|
||||
description: 测试结果消息
|
||||
example: "连接成功"
|
||||
error:
|
||||
type: string
|
||||
description: 错误信息（失败时）
|
||||
example: "API Key 无效"
|
||||
|
||||
RagExperimentRequest:
|
||||
type: object
|
||||
required:
|
||||
- query
|
||||
properties:
|
||||
query:
|
||||
type: string
|
||||
description: 查询文本
|
||||
example: "什么是 RAG？"
|
||||
kb_ids:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: 知识库 ID 列表
|
||||
top_k:
|
||||
type: integer
|
||||
description: 检索数量
|
||||
default: 5
|
||||
score_threshold:
|
||||
type: number
|
||||
description: 相似度阈值
|
||||
default: 0.5
|
||||
llm_provider:
|
||||
type: string
|
||||
description: 指定 LLM 提供者（可选）
|
||||
example: "openai"
|
||||
generate_response:
|
||||
type: boolean
|
||||
description: 是否生成 AI 回复
|
||||
default: true
|
||||
|
||||
RagExperimentResult:
|
||||
type: object
|
||||
properties:
|
||||
query:
|
||||
type: string
|
||||
description: 原始查询
|
||||
retrieval_results:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/RetrievalResult'
|
||||
final_prompt:
|
||||
type: string
|
||||
description: 最终拼接的 Prompt
|
||||
ai_response:
|
||||
$ref: '#/components/schemas/AIResponse'
|
||||
total_latency_ms:
|
||||
type: number
|
||||
description: 总耗时（毫秒）
|
||||
|
||||
RetrievalResult:
|
||||
type: object
|
||||
properties:
|
||||
content:
|
||||
type: string
|
||||
description: 检索到的内容
|
||||
score:
|
||||
type: number
|
||||
description: 相似度分数
|
||||
source:
|
||||
type: string
|
||||
description: 来源文档
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties: true
|
||||
description: 元数据
|
||||
|
||||
AIResponse:
|
||||
type: object
|
||||
properties:
|
||||
content:
|
||||
type: string
|
||||
description: AI 回复内容
|
||||
prompt_tokens:
|
||||
type: integer
|
||||
description: 输入 Token 数
|
||||
completion_tokens:
|
||||
type: integer
|
||||
description: 输出 Token 数
|
||||
total_tokens:
|
||||
type: integer
|
||||
description: 总 Token 数
|
||||
latency_ms:
|
||||
type: number
|
||||
description: 生成耗时（毫秒）
|
||||
model:
|
||||
type: string
|
||||
description: 使用的模型
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
feature_id: "ASA"
|
||||
title: "AI 中台管理界面（ai-service-admin）需求规范"
|
||||
status: "draft"
|
||||
version: "0.1.0"
|
||||
version: "0.3.0"
|
||||
owners:
|
||||
- "product"
|
||||
- "frontend"
|
||||
|
|
@ -70,3 +70,92 @@ source:
|
|||
| AC-ASA-03 | /admin/config/prompt-templates/{tplId}/publish | POST | 发布指定版本 |
|
||||
| AC-ASA-05 | /admin/rag/experiments/run | POST | 触发调试实验 |
|
||||
| AC-ASA-07 | /admin/sessions/{sessionId} | GET | 获取全链路详情 |
|
||||
|
||||
---
|
||||
|
||||
## 7. 迭代需求：嵌入模型管理（v0.2.0）
|
||||
|
||||
> 说明：本节为 v0.2.0 迭代新增，用于支持嵌入模型的界面配置与管理。
|
||||
|
||||
### 7.1 嵌入模型配置管理
|
||||
|
||||
- [AC-ASA-08] WHEN 用户访问嵌入模型配置页面 THEN 系统 SHALL 展示当前激活的嵌入模型提供者及其配置参数。
|
||||
|
||||
- [AC-ASA-09] WHEN 用户切换嵌入模型提供者 THEN 系统 SHALL 动态展示该提供者的配置参数表单，并保留当前配置值。
|
||||
|
||||
- [AC-ASA-10] WHEN 用户修改嵌入模型配置并保存 THEN 系统 SHALL 验证配置有效性，更新配置并提示操作结果。
|
||||
|
||||
- [AC-ASA-11] WHEN 用户点击"测试连接"按钮 THEN 系统 SHALL 调用嵌入模型生成测试向量，展示连接状态、向量维度和响应延迟。
|
||||
|
||||
- [AC-ASA-12] WHEN 嵌入模型连接测试失败 THEN 系统 SHALL 展示详细错误信息，帮助用户排查配置问题。
|
||||
|
||||
### 7.2 文档格式支持展示
|
||||
|
||||
- [AC-ASA-13] WHEN 用户查看嵌入模型配置页面 THEN 系统 SHALL 展示当前支持的文档格式列表（PDF、Word、Excel、TXT 等）。
|
||||
|
||||
### 7.3 用户故事（迭代追加）
|
||||
|
||||
- [US-ASA-06] 作为系统管理员，我希望在界面上配置和切换嵌入模型，以便快速适配不同的业务场景而无需修改代码。
|
||||
|
||||
- [US-ASA-07] 作为系统管理员，我希望在保存配置前测试嵌入模型连接，以便确保配置正确后再正式启用。
|
||||
|
||||
### 7.4 追踪映射（迭代追加）
|
||||
|
||||
| AC ID | Endpoint | 方法 | 备注 |
|
||||
|------|----------|------|-----|
|
||||
| AC-ASA-08 | /admin/embedding/config | GET | 获取当前配置 |
|
||||
| AC-ASA-09 | /admin/embedding/providers | GET | 获取提供者列表及配置定义 |
|
||||
| AC-ASA-10 | /admin/embedding/config | PUT | 更新配置 |
|
||||
| AC-ASA-11 | /admin/embedding/test | POST | 测试连接 |
|
||||
| AC-ASA-12 | /admin/embedding/test | POST | 测试失败错误展示 |
|
||||
| AC-ASA-13 | /admin/embedding/formats | GET | 获取支持格式 |
|
||||
|
||||
---
|
||||
|
||||
## 8. 迭代需求：LLM 模型配置与 RAG 调试输出（v0.3.0）
|
||||
|
||||
> 说明：本节为 v0.3.0 迭代新增，用于支持 LLM 模型的界面配置及 RAG 实验室的 AI 输出调试。
|
||||
|
||||
### 8.1 LLM 模型配置管理
|
||||
|
||||
- [AC-ASA-14] WHEN 用户访问 LLM 模型配置页面 THEN 系统 SHALL 展示当前激活的 LLM 提供者及其配置参数（API Key、Base URL、模型名称等）。
|
||||
|
||||
- [AC-ASA-15] WHEN 用户切换 LLM 提供者 THEN 系统 SHALL 动态展示该提供者的配置参数表单，并保留当前配置值。
|
||||
|
||||
- [AC-ASA-16] WHEN 用户修改 LLM 模型配置并保存 THEN 系统 SHALL 验证配置有效性，更新配置并提示操作结果。
|
||||
|
||||
- [AC-ASA-17] WHEN 用户点击"测试连接"按钮 THEN 系统 SHALL 调用 LLM 生成测试回复，展示连接状态、模型响应和耗时。
|
||||
|
||||
- [AC-ASA-18] WHEN LLM 连接测试失败 THEN 系统 SHALL 展示详细错误信息，帮助用户排查配置问题。
|
||||
|
||||
### 8.2 RAG 实验室 AI 输出展示
|
||||
|
||||
- [AC-ASA-19] WHEN 用户运行 RAG 实验后 THEN 系统 SHALL 在结果区域新增"AI 回复"展示区，显示基于检索结果生成的 AI 最终输出。
|
||||
|
||||
- [AC-ASA-20] WHEN AI 回复生成中 THEN 系统 SHALL 展示 Loading 状态，支持流式输出展示（SSE）。
|
||||
|
||||
- [AC-ASA-21] WHEN AI 回复生成完成 THEN 系统 SHALL 展示完整的回复内容、Token 消耗统计、响应耗时。
|
||||
|
||||
- [AC-ASA-22] WHEN 用户选择不同的 LLM 配置 THEN 系统 SHALL 使用选定的 LLM 模型生成回复，便于对比不同模型效果。
|
||||
|
||||
### 8.3 用户故事（迭代追加）
|
||||
|
||||
- [US-ASA-08] 作为系统管理员，我希望在界面上配置和切换不同的 LLM 提供者（如 OpenAI、Ollama、Azure 等），以便快速适配不同的业务场景。
|
||||
|
||||
- [US-ASA-09] 作为 AI 开发者，我希望在 RAG 实验室中看到 AI 的最终输出，以便完整调试 RAG 链路效果，而不仅仅是检索结果。
|
||||
|
||||
- [US-ASA-10] 作为 Prompt 工程师，我希望对比不同 LLM 模型在相同检索结果下的回复效果，以便选择最适合业务场景的模型。
|
||||
|
||||
### 8.4 追踪映射（迭代追加）
|
||||
|
||||
| AC ID | Endpoint | 方法 | 备注 |
|
||||
|------|----------|------|-----|
|
||||
| AC-ASA-14 | /admin/llm/config | GET | 获取当前 LLM 配置 |
|
||||
| AC-ASA-15 | /admin/llm/providers | GET | 获取 LLM 提供者列表 |
|
||||
| AC-ASA-16 | /admin/llm/config | PUT | 更新 LLM 配置 |
|
||||
| AC-ASA-17 | /admin/llm/test | POST | 测试 LLM 连接 |
|
||||
| AC-ASA-18 | /admin/llm/test | POST | LLM 测试失败错误展示 |
|
||||
| AC-ASA-19 | /admin/rag/experiments/run | POST | RAG 实验增加 AI 输出 |
|
||||
| AC-ASA-20 | /admin/rag/experiments/stream | POST | RAG 实验流式输出（SSE） |
|
||||
| AC-ASA-21 | /admin/rag/experiments/run | POST | Token 统计与耗时 |
|
||||
| AC-ASA-22 | /admin/rag/experiments/run | POST | 支持指定 LLM 配置 |
|
||||
|
|
|
|||
|
|
@ -123,29 +123,29 @@ principles:
|
|||
|
||||
> 页面导向：嵌入模型配置页面，支持提供者切换、参数配置、连接测试。
|
||||
|
||||
- [ ] (P5-01) 嵌入模型配置页面骨架：创建 `/admin/embedding` 路由，布局包含提供者选择区、配置表单区、测试连接区、支持格式展示区。
|
||||
- AC: [AC-ASA-08]
|
||||
- [ ] (P5-01) API 服务层与类型定义：创建 src/api/embedding.ts 和 src/types/embedding.ts
|
||||
- AC: [AC-ASA-08, AC-ASA-09]
|
||||
|
||||
- [x] (P5-02) 提供者选择组件：实现 `EmbeddingProviderSelect` 下拉组件，对接 `/admin/embedding/providers`，展示提供者列表（name、display_name、description）。
|
||||
- [ ] (P5-02) 提供者选择组件：实现 `EmbeddingProviderSelect` 下拉组件，对接 `/admin/embedding/providers`
|
||||
- AC: [AC-ASA-09]
|
||||
|
||||
- [x] (P5-03) 动态配置表单：根据选中提供者的 `config_schema` 动态渲染配置表单（支持 string、integer、number 类型），实现表单校验。
|
||||
- [ ] (P5-03) 动态配置表单：根据 `config_schema` 动态渲染配置表单，实现表单校验
|
||||
- AC: [AC-ASA-09, AC-ASA-10]
|
||||
|
||||
- [ ] (P5-04) 当前配置加载：页面初始化时调用 `/admin/embedding/config` 获取当前配置，填充表单默认值。
|
||||
- [ ] (P5-04) 测试连接组件：实现 `EmbeddingTestPanel`，展示测试结果和错误信息
|
||||
- AC: [AC-ASA-11, AC-ASA-12]
|
||||
|
||||
- [ ] (P5-05) 支持格式组件：实现 `SupportedFormats`，展示支持的文档格式列表
|
||||
- AC: [AC-ASA-13]
|
||||
|
||||
- [ ] (P5-06) 页面骨架与路由：创建 `/admin/embedding` 页面，布局包含各功能区
|
||||
- AC: [AC-ASA-08]
|
||||
|
||||
- [ ] (P5-05) 配置保存功能：实现保存按钮，调用 `PUT /admin/embedding/config`，处理成功/失败响应并提示用户。
|
||||
- AC: [AC-ASA-10]
|
||||
- [ ] (P5-07) 配置加载与保存：实现配置加载、保存逻辑
|
||||
- AC: [AC-ASA-08, AC-ASA-10]
|
||||
|
||||
- [x] (P5-06) 测试连接功能：实现测试按钮，调用 `POST /admin/embedding/test`，展示测试结果（success、dimension、latency_ms、message）。
|
||||
- AC: [AC-ASA-11]
|
||||
|
||||
- [x] (P5-07) 测试失败错误展示：测试失败时展示详细错误信息（error 字段），并提供排查建议。
|
||||
- AC: [AC-ASA-12]
|
||||
|
||||
- [ ] (P5-08) 支持格式展示：调用 `/admin/embedding/formats` 获取支持的文档格式列表，以标签或卡片形式展示。
|
||||
- AC: [AC-ASA-13]
|
||||
- [ ] (P5-08) 组件整合与测试：整合所有组件完成功能闭环
|
||||
- AC: [AC-ASA-08~AC-ASA-13]
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -153,11 +153,68 @@ principles:
|
|||
|
||||
| 任务 | 描述 | 状态 |
|
||||
|------|------|------|
|
||||
| P5-01 | 嵌入模型配置页面骨架 | ⏳ 待处理 |
|
||||
| P5-02 | 提供者选择组件 | ✅ 已完成 |
|
||||
| P5-03 | 动态配置表单 | ✅ 已完成 |
|
||||
| P5-04 | 当前配置加载 | ⏳ 待处理 |
|
||||
| P5-05 | 配置保存功能 | ⏳ 待处理 |
|
||||
| P5-06 | 测试连接功能 | ✅ 已完成 |
|
||||
| P5-07 | 测试失败错误展示 | ✅ 已完成 |
|
||||
| P5-08 | 支持格式展示 | ⏳ 待处理 |
|
||||
| P5-01 | API 服务层与类型定义 | ⏳ 待处理 |
|
||||
| P5-02 | 提供者选择组件 | ⏳ 待处理 |
|
||||
| P5-03 | 动态配置表单 | ⏳ 待处理 |
|
||||
| P5-04 | 测试连接组件 | ⏳ 待处理 |
|
||||
| P5-05 | 支持格式组件 | ⏳ 待处理 |
|
||||
| P5-06 | 页面骨架与路由 | ⏳ 待处理 |
|
||||
| P5-07 | 配置加载与保存 | ⏳ 待处理 |
|
||||
| P5-08 | 组件整合与测试 | ⏳ 待处理 |
|
||||
|
||||
---
|
||||
|
||||
## Phase 6: LLM 模型配置与 RAG 调试输出（v0.3.0）
|
||||
|
||||
> 页面导向：LLM 模型配置页面 + RAG 实验室 AI 输出增强。
|
||||
|
||||
### 6.1 LLM 模型配置
|
||||
|
||||
- [ ] (P6-01) LLM API 服务层与类型定义：创建 src/api/llm.ts 和 src/types/llm.ts
|
||||
- AC: [AC-ASA-14, AC-ASA-15]
|
||||
|
||||
- [ ] (P6-02) LLM 提供者选择组件：实现 `LLMProviderSelect` 下拉组件
|
||||
- AC: [AC-ASA-15]
|
||||
|
||||
- [ ] (P6-03) LLM 动态配置表单：根据 `config_schema` 动态渲染配置表单
|
||||
- AC: [AC-ASA-15, AC-ASA-16]
|
||||
|
||||
- [ ] (P6-04) LLM 测试连接组件：实现 `LLMTestPanel`，展示测试回复和耗时
|
||||
- AC: [AC-ASA-17, AC-ASA-18]
|
||||
|
||||
- [ ] (P6-05) LLM 配置页面：创建 `/admin/llm` 页面，整合所有组件
|
||||
- AC: [AC-ASA-14, AC-ASA-16]
|
||||
|
||||
### 6.2 RAG 实验室 AI 输出增强
|
||||
|
||||
- [ ] (P6-06) AI 回复展示组件：实现 `AIResponseViewer`，展示 AI 最终输出
|
||||
- AC: [AC-ASA-19]
|
||||
|
||||
- [ ] (P6-07) 流式输出支持：实现 SSE 流式输出展示，支持实时显示 AI 回复
|
||||
- AC: [AC-ASA-20]
|
||||
|
||||
- [ ] (P6-08) Token 统计展示：展示 Token 消耗、响应耗时等统计信息
|
||||
- AC: [AC-ASA-21]
|
||||
|
||||
- [ ] (P6-09) LLM 选择器：在 RAG 实验室中添加 LLM 配置选择器
|
||||
- AC: [AC-ASA-22]
|
||||
|
||||
- [ ] (P6-10) RAG 实验室整合：将 AI 输出组件整合到 RAG 实验室页面
|
||||
- AC: [AC-ASA-19~AC-ASA-22]
|
||||
|
||||
---
|
||||
|
||||
## Phase 6 任务进度追踪
|
||||
|
||||
| 任务 | 描述 | 状态 |
|
||||
|------|------|------|
|
||||
| P6-01 | LLM API 服务层与类型定义 | ⏳ 待处理 |
|
||||
| P6-02 | LLM 提供者选择组件 | ⏳ 待处理 |
|
||||
| P6-03 | LLM 动态配置表单 | ⏳ 待处理 |
|
||||
| P6-04 | LLM 测试连接组件 | ⏳ 待处理 |
|
||||
| P6-05 | LLM 配置页面 | ⏳ 待处理 |
|
||||
| P6-06 | AI 回复展示组件 | ⏳ 待处理 |
|
||||
| P6-07 | 流式输出支持 | ⏳ 待处理 |
|
||||
| P6-08 | Token 统计展示 | ⏳ 待处理 |
|
||||
| P6-09 | LLM 选择器 | ⏳ 待处理 |
|
||||
| P6-10 | RAG 实验室整合 | ⏳ 待处理 |
|
||||
|
|
|
|||
|
|
@ -25,6 +25,10 @@ tags:
|
|||
description: 健康检查
|
||||
- name: Embedding Management
|
||||
description: 嵌入模型管理
|
||||
- name: LLM Management
|
||||
description: LLM 模型管理
|
||||
- name: RAG Lab
|
||||
description: RAG 实验室
|
||||
|
||||
paths:
|
||||
/ai/chat:
|
||||
|
|
@ -536,3 +540,428 @@ components:
|
|||
type: string
|
||||
description: 错误信息（失败时）
|
||||
example: "连接超时"
|
||||
|
||||
LLMProviderInfo:
|
||||
type: object
|
||||
description: LLM 提供者信息
|
||||
required:
|
||||
- name
|
||||
- display_name
|
||||
- config_schema
|
||||
properties:
|
||||
name:
|
||||
type: string
|
||||
description: 提供者唯一标识
|
||||
example: "openai"
|
||||
display_name:
|
||||
type: string
|
||||
description: 提供者显示名称
|
||||
example: "OpenAI"
|
||||
description:
|
||||
type: string
|
||||
description: 提供者描述
|
||||
example: "OpenAI GPT 系列模型"
|
||||
config_schema:
|
||||
type: object
|
||||
description: 配置参数定义（JSON Schema 格式）
|
||||
additionalProperties: true
|
||||
|
||||
LLMConfig:
|
||||
type: object
|
||||
description: 当前 LLM 配置
|
||||
required:
|
||||
- provider
|
||||
- config
|
||||
properties:
|
||||
provider:
|
||||
type: string
|
||||
description: 当前激活的提供者
|
||||
example: "openai"
|
||||
config:
|
||||
type: object
|
||||
description: 提供者配置参数（敏感字段已脱敏）
|
||||
additionalProperties: true
|
||||
example:
|
||||
api_key: "sk-***"
|
||||
base_url: "https://api.openai.com/v1"
|
||||
model: "gpt-4o-mini"
|
||||
updated_at:
|
||||
type: string
|
||||
format: date-time
|
||||
description: 配置最后更新时间
|
||||
|
||||
LLMConfigUpdate:
|
||||
type: object
|
||||
description: LLM 配置更新请求
|
||||
required:
|
||||
- provider
|
||||
properties:
|
||||
provider:
|
||||
type: string
|
||||
description: 提供者标识
|
||||
example: "openai"
|
||||
config:
|
||||
type: object
|
||||
description: 提供者配置参数
|
||||
additionalProperties: true
|
||||
|
||||
LLMTestResult:
|
||||
type: object
|
||||
description: LLM 测试结果
|
||||
required:
|
||||
- success
|
||||
properties:
|
||||
success:
|
||||
type: boolean
|
||||
description: 测试是否成功
|
||||
response:
|
||||
type: string
|
||||
description: LLM 响应内容
|
||||
example: "你好！我是一个 AI 助手..."
|
||||
latency_ms:
|
||||
type: number
|
||||
description: 响应延迟（毫秒）
|
||||
example: 1250.5
|
||||
prompt_tokens:
|
||||
type: integer
|
||||
description: 输入 Token 数
|
||||
example: 15
|
||||
completion_tokens:
|
||||
type: integer
|
||||
description: 输出 Token 数
|
||||
example: 50
|
||||
total_tokens:
|
||||
type: integer
|
||||
description: 总 Token 数
|
||||
example: 65
|
||||
model:
|
||||
type: string
|
||||
description: 使用的模型
|
||||
example: "gpt-4o-mini"
|
||||
message:
|
||||
type: string
|
||||
description: 测试结果消息
|
||||
example: "连接成功"
|
||||
error:
|
||||
type: string
|
||||
description: 错误信息（失败时）
|
||||
example: "API Key 无效"
|
||||
|
||||
RagExperimentRequest:
|
||||
type: object
|
||||
description: RAG 实验请求
|
||||
required:
|
||||
- query
|
||||
properties:
|
||||
query:
|
||||
type: string
|
||||
description: 查询文本
|
||||
example: "什么是 RAG？"
|
||||
kb_ids:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: 知识库 ID 列表
|
||||
top_k:
|
||||
type: integer
|
||||
description: 检索数量
|
||||
default: 5
|
||||
score_threshold:
|
||||
type: number
|
||||
description: 相似度阈值
|
||||
default: 0.5
|
||||
generate_response:
|
||||
type: boolean
|
||||
description: 是否生成 AI 回复
|
||||
default: true
|
||||
llm_provider:
|
||||
type: string
|
||||
description: 指定 LLM 提供者（可选）
|
||||
example: "openai"
|
||||
|
||||
RagExperimentResult:
|
||||
type: object
|
||||
description: RAG 实验结果
|
||||
properties:
|
||||
query:
|
||||
type: string
|
||||
description: 原始查询
|
||||
retrieval_results:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/RetrievalResult'
|
||||
final_prompt:
|
||||
type: string
|
||||
description: 最终拼接的 Prompt
|
||||
ai_response:
|
||||
$ref: '#/components/schemas/AIResponse'
|
||||
total_latency_ms:
|
||||
type: number
|
||||
description: 总耗时（毫秒）
|
||||
diagnostics:
|
||||
type: object
|
||||
additionalProperties: true
|
||||
description: 诊断信息
|
||||
|
||||
RetrievalResult:
|
||||
type: object
|
||||
description: 检索结果
|
||||
properties:
|
||||
content:
|
||||
type: string
|
||||
description: 检索到的内容
|
||||
score:
|
||||
type: number
|
||||
description: 相似度分数
|
||||
source:
|
||||
type: string
|
||||
description: 来源文档
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties: true
|
||||
description: 元数据
|
||||
|
||||
AIResponse:
|
||||
type: object
|
||||
description: AI 回复
|
||||
properties:
|
||||
content:
|
||||
type: string
|
||||
description: AI 回复内容
|
||||
prompt_tokens:
|
||||
type: integer
|
||||
description: 输入 Token 数
|
||||
completion_tokens:
|
||||
type: integer
|
||||
description: 输出 Token 数
|
||||
total_tokens:
|
||||
type: integer
|
||||
description: 总 Token 数
|
||||
latency_ms:
|
||||
type: number
|
||||
description: 生成耗时（毫秒）
|
||||
model:
|
||||
type: string
|
||||
description: 使用的模型
|
||||
|
||||
/admin/llm/providers:
|
||||
get:
|
||||
operationId: listLLMProviders
|
||||
summary: 获取可用的 LLM 提供者列表
|
||||
description: |
|
||||
[AC-ASA-15] 返回所有支持的 LLM 提供者及其配置参数定义。
|
||||
支持的提供者：OpenAI、Ollama、Azure OpenAI
|
||||
tags:
|
||||
- LLM Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
responses:
|
||||
'200':
|
||||
description: 成功返回提供者列表
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
providers:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/LLMProviderInfo'
|
||||
'401':
|
||||
description: 未授权
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ErrorResponse'
|
||||
|
||||
/admin/llm/config:
|
||||
get:
|
||||
operationId: getLLMConfig
|
||||
summary: 获取当前 LLM 配置
|
||||
description: |
|
||||
[AC-ASA-14] 返回当前激活的 LLM 提供者及其配置参数。
|
||||
敏感字段（如 API Key）会被脱敏显示。
|
||||
tags:
|
||||
- LLM Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
responses:
|
||||
'200':
|
||||
description: 成功返回当前配置
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/LLMConfig'
|
||||
'401':
|
||||
description: 未授权
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ErrorResponse'
|
||||
put:
|
||||
operationId: updateLLMConfig
|
||||
summary: 更新 LLM 配置
|
||||
description: |
|
||||
[AC-ASA-16] 更新 LLM 提供者和配置参数。
|
||||
配置更新后立即生效，无需重启服务。
|
||||
tags:
|
||||
- LLM Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/LLMConfigUpdate'
|
||||
responses:
|
||||
'200':
|
||||
description: 配置更新成功
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
success:
|
||||
type: boolean
|
||||
message:
|
||||
type: string
|
||||
'400':
|
||||
description: 请求参数错误
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ErrorResponse'
|
||||
'401':
|
||||
description: 未授权
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ErrorResponse'
|
||||
|
||||
/admin/llm/test:
|
||||
post:
|
||||
operationId: testLLM
|
||||
summary: 测试 LLM 连接
|
||||
description: |
|
||||
[AC-ASA-17, AC-ASA-18] 测试 LLM 提供者连接。
|
||||
发送测试提示词并返回响应结果，包含 Token 消耗和延迟统计。
|
||||
tags:
|
||||
- LLM Management
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: false
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
test_prompt:
|
||||
type: string
|
||||
description: 测试提示词（可选）
|
||||
example: "你好，请简单介绍一下自己。"
|
||||
provider:
|
||||
type: string
|
||||
description: 指定测试的提供者（可选，默认使用当前配置）
|
||||
config:
|
||||
$ref: '#/components/schemas/LLMConfigUpdate'
|
||||
responses:
|
||||
'200':
|
||||
description: 测试完成
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/LLMTestResult'
|
||||
'401':
|
||||
description: 未授权
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ErrorResponse'
|
||||
|
||||
/admin/rag/experiments/run:
|
||||
post:
|
||||
operationId: runRagExperiment
|
||||
summary: 运行 RAG 实验（含 AI 输出）
|
||||
description: |
|
||||
[AC-ASA-05, AC-ASA-19, AC-ASA-21, AC-ASA-22] 运行 RAG 实验。
|
||||
返回检索结果、最终 Prompt 和 AI 回复。
|
||||
tags:
|
||||
- RAG Lab
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RagExperimentRequest'
|
||||
responses:
|
||||
'200':
|
||||
description: 实验完成
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RagExperimentResult'
|
||||
'401':
|
||||
description: 未授权
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ErrorResponse'
|
||||
|
||||
/admin/rag/experiments/stream:
|
||||
post:
|
||||
operationId: runRagExperimentStream
|
||||
summary: 运行 RAG 实验（流式输出）
|
||||
description: |
|
||||
[AC-ASA-20] 运行 RAG 实验并以 SSE 流式输出 AI 回复。
|
||||
事件类型：retrieval、prompt、message、final、error
|
||||
tags:
|
||||
- RAG Lab
|
||||
parameters:
|
||||
- name: X-Tenant-Id
|
||||
in: header
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RagExperimentRequest'
|
||||
responses:
|
||||
'200':
|
||||
description: SSE 流式输出
|
||||
content:
|
||||
text/event-stream:
|
||||
schema:
|
||||
type: string
|
||||
'401':
|
||||
description: 未授权
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ErrorResponse'
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
feature_id: "AISVC"
|
||||
title: "Python AI 中台（ai-service）进度追踪"
|
||||
status: "completed"
|
||||
version: "0.3.0"
|
||||
version: "0.4.0"
|
||||
last_updated: "2026-02-24"
|
||||
---
|
||||
|
||||
|
|
@ -54,6 +54,66 @@ last_updated: "2026-02-24"
|
|||
| Phase 5 | 集成测试 | 100% | ✅ 完成 |
|
||||
| Phase 6 | 前后端联调 | 100% | ✅ 完成 |
|
||||
| Phase 7 | 嵌入模型可插拔与文档解析 | 100% | ✅ 完成 |
|
||||
| Phase 8 | LLM 配置与 RAG 调试输出 | 100% | ✅ 完成 |
|
||||
|
||||
**测试统计: 184 tests passing**
|
||||
|
||||
---
|
||||
|
||||
## Phase 8: LLM 配置与 RAG 调试输出（v0.4.0 迭代）
|
||||
|
||||
### 8.1 设计目标
|
||||
|
||||
- LLM 提供者可插拔设计
|
||||
- 支持界面配置不同供应商的 AI
|
||||
- RAG 实验室支持 AI 输出调试
|
||||
|
||||
### 8.2 实现详情 (2026-02-24)
|
||||
|
||||
#### LLM 服务实现
|
||||
- 创建 LLMProviderFactory 工厂类 (`app/services/llm/factory.py`)
|
||||
- 支持 OpenAI、Ollama、Azure OpenAI 三种提供者
|
||||
- 实现 LLMConfigManager 配置热更新
|
||||
- 实现连接测试功能
|
||||
|
||||
#### API 端点实现
|
||||
- GET /admin/llm/providers - 获取 LLM 提供者列表
|
||||
- GET /admin/llm/config - 获取当前 LLM 配置
|
||||
- PUT /admin/llm/config - 更新 LLM 配置
|
||||
- POST /admin/llm/test - 测试 LLM 连接
|
||||
|
||||
#### RAG 实验增强
|
||||
- 更新 POST /admin/rag/experiments/run - 支持 AI 回复生成
|
||||
- 新增 POST /admin/rag/experiments/stream - SSE 流式输出
|
||||
- 支持 Token 统计和响应耗时
|
||||
- 支持指定 LLM 提供者
|
||||
|
||||
### 8.3 任务进度
|
||||
|
||||
| 任务 | 描述 | 状态 |
|
||||
|------|------|------|
|
||||
| T8.1 | LLMProviderFactory 工厂类 | ✅ 完成 |
|
||||
| T8.2 | LLMConfigManager 配置管理 | ✅ 完成 |
|
||||
| T8.3 | GET /admin/llm/providers | ✅ 完成 |
|
||||
| T8.4 | GET /admin/llm/config | ✅ 完成 |
|
||||
| T8.5 | PUT /admin/llm/config | ✅ 完成 |
|
||||
| T8.6 | POST /admin/llm/test | ✅ 完成 |
|
||||
| T8.7 | RAG 实验支持 AI 回复 | ✅ 完成 |
|
||||
| T8.8 | RAG 实验流式输出 | ✅ 完成 |
|
||||
| T8.9 | 支持指定 LLM 提供者 | ✅ 完成 |
|
||||
| T8.10 | 更新 OpenAPI 契约 | ✅ 完成 |
|
||||
|
||||
---
|
||||
|
||||
## v0.4.0 完成总结
|
||||
|
||||
**Phase 8 已全部完成**
|
||||
|
||||
| 模块 | 文件数 | 状态 |
|
||||
|------|--------|------|
|
||||
| LLM 服务 | 1 | ✅ |
|
||||
| API 端点 | 2 | ✅ |
|
||||
| OpenAPI 契约 | 1 | ✅ |
|
||||
|
||||
**测试统计: 184 tests passing**
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
---
|
||||
feature_id: "AISVC"
|
||||
title: "Python AI 中台（ai-service）需求规范"
|
||||
status: "draft"
|
||||
version: "0.3.0"
|
||||
status: "completed"
|
||||
version: "0.4.0"
|
||||
owners:
|
||||
- "product"
|
||||
- "backend"
|
||||
|
|
@ -264,3 +264,45 @@ source:
|
|||
| AC-AISVC-39 | /admin/embedding/config | GET | getEmbeddingConfig | 当前配置查询 |
|
||||
| AC-AISVC-40 | /admin/embedding/config | PUT | updateEmbeddingConfig | 配置更新 |
|
||||
| AC-AISVC-41 | /admin/embedding/test | POST | testEmbedding | 连接测试 |
|
||||
|
||||
---
|
||||
|
||||
## 11. 迭代需求：LLM 模型配置与 RAG 调试输出（v0.4.0）
|
||||
|
||||
> 说明：本节为 v0.4.0 迭代新增，用于支持 LLM 模型的界面配置及 RAG 实验室的 AI 输出调试。
|
||||
|
||||
### 11.1 LLM 模型配置管理
|
||||
|
||||
- [AC-AISVC-42] WHEN 前端通过 `GET /admin/llm/providers` 获取 LLM 提供者列表 THEN 系统 SHALL 返回所有支持的 LLM 提供者及其配置参数定义。
|
||||
|
||||
- [AC-AISVC-43] WHEN 前端通过 `GET /admin/llm/config` 获取当前 LLM 配置 THEN 系统 SHALL 返回当前激活的 LLM 提供者及其配置参数（敏感字段脱敏）。
|
||||
|
||||
- [AC-AISVC-44] WHEN 前端通过 `PUT /admin/llm/config` 更新 LLM 配置 THEN 系统 SHALL 验证配置有效性，更新配置并立即生效。
|
||||
|
||||
- [AC-AISVC-45] WHEN 前端通过 `POST /admin/llm/test` 测试 LLM 连接 THEN 系统 SHALL 调用 LLM 生成测试回复，返回响应内容、Token 消耗和延迟统计。
|
||||
|
||||
- [AC-AISVC-46] WHEN LLM 连接测试失败 THEN 系统 SHALL 返回详细错误信息，帮助用户排查配置问题。
|
||||
|
||||
### 11.2 RAG 实验室 AI 输出增强
|
||||
|
||||
- [AC-AISVC-47] WHEN 前端通过 `POST /admin/rag/experiments/run` 运行 RAG 实验 THEN 系统 SHALL 返回检索结果、最终 Prompt 和 AI 回复。
|
||||
|
||||
- [AC-AISVC-48] WHEN 前端通过 `POST /admin/rag/experiments/stream` 运行 RAG 实验 THEN 系统 SHALL 以 SSE 流式输出 AI 回复。
|
||||
|
||||
- [AC-AISVC-49] WHEN RAG 实验生成 AI 回复 THEN 系统 SHALL 返回 Token 消耗统计和响应耗时。
|
||||
|
||||
- [AC-AISVC-50] WHEN RAG 实验请求指定 `llm_provider` THEN 系统 SHALL 使用指定的 LLM 提供者生成回复。
|
||||
|
||||
### 11.3 追踪映射（v0.4.0 迭代）
|
||||
|
||||
| AC ID | Endpoint | 方法 | Operation | 描述 |
|
||||
|-------|----------|------|-----------|------|
|
||||
| AC-AISVC-42 | /admin/llm/providers | GET | listLLMProviders | LLM 提供者列表 |
|
||||
| AC-AISVC-43 | /admin/llm/config | GET | getLLMConfig | 当前 LLM 配置查询 |
|
||||
| AC-AISVC-44 | /admin/llm/config | PUT | updateLLMConfig | LLM 配置更新 |
|
||||
| AC-AISVC-45 | /admin/llm/test | POST | testLLM | LLM 连接测试 |
|
||||
| AC-AISVC-46 | /admin/llm/test | POST | testLLM | LLM 测试失败处理 |
|
||||
| AC-AISVC-47 | /admin/rag/experiments/run | POST | runRagExperiment | RAG 实验含 AI 输出 |
|
||||
| AC-AISVC-48 | /admin/rag/experiments/stream | POST | runRagExperimentStream | RAG 实验流式输出 |
|
||||
| AC-AISVC-49 | /admin/rag/experiments/run | POST | runRagExperiment | Token 统计 |
|
||||
| AC-AISVC-50 | /admin/rag/experiments/run | POST | runRagExperiment | 指定 LLM 提供者 |
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
feature_id: "AISVC"
|
||||
title: "Python AI 中台（ai-service）任务清单"
|
||||
status: "completed"
|
||||
version: "0.3.0"
|
||||
version: "0.4.0"
|
||||
last_updated: "2026-02-24"
|
||||
---
|
||||
|
||||
|
|
@ -83,7 +83,7 @@ last_updated: "2026-02-24"
|
|||
|
||||
## 5. 完成总结
|
||||
|
||||
**Phase 1-7 已全部完成**
|
||||
**Phase 1-7 已全部完成，Phase 8 进行中**
|
||||
|
||||
| Phase | 描述 | 任务数 | 状态 |
|
||||
|-------|------|--------|------|
|
||||
|
|
@ -94,8 +94,9 @@ last_updated: "2026-02-24"
|
|||
| Phase 5 | 集成测试 | 3 | ✅ 完成 |
|
||||
| Phase 6 | 前后端联调真实对接 | 9 | ✅ 完成 |
|
||||
| Phase 7 | 嵌入模型可插拔与文档解析 | 21 | ✅ 完成 |
|
||||
| Phase 8 | LLM 配置与 RAG 调试输出 | 10 | ⏳ 进行中 |
|
||||
|
||||
**已完成: 53 个任务**
|
||||
**已完成: 53 个任务 | 进行中: 10 个任务**
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -121,3 +122,17 @@ last_updated: "2026-02-24"
|
|||
- [x] T7.19 编写嵌入服务单元测试 `[AC-AISVC-29, AC-AISVC-30, AC-AISVC-31, AC-AISVC-32]` ✅
|
||||
- [x] T7.20 编写文档解析单元测试 `[AC-AISVC-33, AC-AISVC-34, AC-AISVC-35, AC-AISVC-36, AC-AISVC-37]` ✅
|
||||
- [x] T7.21 编写嵌入管理 API 集成测试 `[AC-AISVC-38, AC-AISVC-39, AC-AISVC-40, AC-AISVC-41]` ✅
|
||||
|
||||
---
|
||||
|
||||
### Phase 8: LLM 配置与 RAG 调试输出（v0.4.0 迭代）
|
||||
- [x] T8.1 设计 `LLMProviderFactory` 工厂类：支持根据配置动态加载提供者 `[AC-AISVC-42]` ✅
|
||||
- [x] T8.2 实现 `LLMConfigManager` 配置管理：支持动态配置与热更新 `[AC-AISVC-43, AC-AISVC-44]` ✅
|
||||
- [x] T8.3 实现 `GET /admin/llm/providers` API：返回可用提供者列表 `[AC-AISVC-42]` ✅
|
||||
- [x] T8.4 实现 `GET /admin/llm/config` API：返回当前配置 `[AC-AISVC-43]` ✅
|
||||
- [x] T8.5 实现 `PUT /admin/llm/config` API：更新配置 `[AC-AISVC-44]` ✅
|
||||
- [x] T8.6 实现 `POST /admin/llm/test` API：测试 LLM 连接 `[AC-AISVC-45, AC-AISVC-46]` ✅
|
||||
- [x] T8.7 更新 RAG 实验接口：支持 AI 回复生成 `[AC-AISVC-47, AC-AISVC-49]` ✅
|
||||
- [x] T8.8 实现 RAG 实验流式输出：SSE 流式 AI 回复 `[AC-AISVC-48]` ✅
|
||||
- [x] T8.9 支持指定 LLM 提供者：RAG 实验可选择不同 LLM `[AC-AISVC-50]` ✅
|
||||
- [x] T8.10 更新 OpenAPI 契约：添加 LLM 管理和 RAG 实验增强接口 ✅
|
||||
|
|
|
|||
|
|
@ -0,0 +1,18 @@
|
|||
这是一个测试文档，用于验证RAG检索功能。
|
||||
|
||||
世界设定：
|
||||
这是一个奇幻世界，名为艾泽拉斯。这个世界由多个大陆组成，包括东部王国、卡利姆多和诺森德。
|
||||
|
||||
主要种族：
|
||||
1. 人类 - 居住在东部王国，拥有强大的骑士和法师
|
||||
2. 精灵 - 分为暗夜精灵和高等精灵，擅长弓箭和魔法
|
||||
3. 矮人 - 居住在山脉中，善于锻造和采矿
|
||||
4. 兽人 - 来自外域，拥有强大的战士
|
||||
|
||||
魔法系统：
|
||||
这个世界充满了魔法能量，法师可以从空气中汲取魔力施放法术。
|
||||
主要魔法类型包括：火焰、冰霜、奥术、暗影和神圣。
|
||||
|
||||
历史背景：
|
||||
这个世界经历了多次大战，最近的一次是天灾军团的入侵。
|
||||
巫妖王阿尔萨斯率领亡灵大军试图征服整个世界。
|
||||
Loading…
Reference in New Issue