feat: v1.2.0 - 图片去重与管理、微信机器人优化、搜索设置可配置

主要功能:
- 图片上传时 OCR 内容去重(3个上传端点统一使用公共函数 _check_ocr_duplicate)
- 图片管理 Tab:展示所有图片、手动删除、一键去重
- 搜索结果详情弹窗增加删除按钮(带确认弹窗)
- 图片管理卡片点击查看详情(复用 showOcrDetailModal)
- 搜索限制和 LLM 批量判断数量可通过网站设置
- MiniMax API 调用添加 reasoning_split=True
- 企业微信机器人:WebSocket 长连接、图片搜索、配置化搜索数量
- 版本号升级至 1.2.0
This commit is contained in:
EduBrain Dev
2026-04-13 22:25:08 +08:00
commit b17786b57b
56 changed files with 9300 additions and 0 deletions

42
app/schemas/search.py Normal file
View File

@@ -0,0 +1,42 @@
"""
语义搜索相关的 Pydantic Schema
"""
from __future__ import annotations
from typing import Optional
from pydantic import BaseModel, Field
class SearchRequest(BaseModel):
"""语义搜索请求"""
query: str = Field(..., min_length=1, max_length=1000, description="搜索查询文本")
top_k: int = Field(default=10, ge=1, le=100, description="返回结果数量")
course_name: Optional[str] = Field(None, description="按课程名称过滤")
teacher_name: Optional[str] = Field(None, description="按讲师名称过滤")
live_date_from: Optional[str] = Field(None, description="直播日期起始 (YYYY-MM-DD)")
live_date_to: Optional[str] = Field(None, description="直播日期结束 (YYYY-MM-DD)")
threshold: float = Field(default=0.5, ge=0.0, le=1.0, description="相似度阈值")
use_fulltext: bool = Field(default=True, description="是否同时使用全文搜索混合排序")
class SearchResult(BaseModel):
"""单条搜索结果"""
chunk_id: int = Field(..., description="分块 ID")
page_id: int = Field(..., description="知识页面 ID")
page_title: str = Field(..., description="页面标题")
content: str = Field(..., description="分块文本内容")
score: float = Field(..., description="相似度分数")
course_name: Optional[str] = None
teacher_name: Optional[str] = None
live_date: Optional[str] = None
highlight: Optional[str] = Field(None, description="高亮摘要")
class SearchResponse(BaseModel):
"""搜索结果响应"""
query: str = Field(..., description="原始查询文本")
total: int = Field(..., description="结果总数")
results: list[SearchResult] = Field(default_factory=list, description="搜索结果列表")
elapsed_ms: float = Field(..., description="搜索耗时(毫秒)")