feat(chat): 基于 RAG 的笔记内容 AI 问答功能

实现类似 Google NotebookLM 的效果:笔记生成后自动向量化,
用户可针对笔记内容进行 LLM 问答。

### 后端
- 新增 VectorStoreManager(ChromaDB),按标题/转录分块建立向量索引
- 新增 chat_service.py RAG 问答:检索相关片段 → 构建 prompt → 调用 LLM
- 新增 /chat/index, /chat/ask, /chat/status API 端点
- 笔记生成完成后自动建立向量索引

### 前端
- 使用 @ant-design/x Bubble.List + Sender 组件构建聊天面板
- 新增 chatStore(Zustand + persist)持久化聊天记录
- MarkdownViewer 右侧嵌入 ChatPanel,通过"AI 问答"按钮切换
- 首次打开自动检查/触发索引,支持重新索引

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
huangjianwu
2026-03-23 14:38:39 +08:00
parent 1cd8c33983
commit efadbc267d
13 changed files with 730 additions and 2 deletions

View File

@@ -0,0 +1,41 @@
import request from '@/utils/request'
export interface ChatMessage {
role: 'user' | 'assistant'
content: string
}
export interface ChatSource {
text: string
source_type: 'markdown' | 'transcript'
section_title?: string
start_time?: number
end_time?: number
}
export interface AskResponse {
answer: string
sources: ChatSource[]
}
export interface ChatStatusResponse {
indexed: boolean
}
export const indexTask = async (taskId: string): Promise<void> => {
return await request.post('/chat/index', { task_id: taskId })
}
export const askQuestion = async (data: {
task_id: string
question: string
history: ChatMessage[]
provider_id: string
model_name: string
}): Promise<AskResponse> => {
return await request.post('/chat/ask', data, { timeout: 60000 })
}
export const getChatStatus = async (taskId: string): Promise<ChatStatusResponse> => {
return await request.get(`/chat/status?task_id=${taskId}`)
}