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

47
app/schemas/ocr.py Normal file
View File

@@ -0,0 +1,47 @@
"""
OCR 相关的 Pydantic Schema
"""
from __future__ import annotations
from datetime import datetime
from typing import Optional
from pydantic import BaseModel, Field
class OCRBlockSchema(BaseModel):
"""OCR 识别的文本块"""
text: str = Field(..., description="文本块内容")
bbox: Optional[list[float]] = Field(None, description="边界框 [x1, y1, x2, y2]")
confidence: float = Field(..., description="置信度 (0-1)")
class OCRResultSchema(BaseModel):
"""OCR 识别结果"""
text: str = Field(..., description="识别全文")
blocks: list[OCRBlockSchema] = Field(default_factory=list, description="文本块列表")
confidence: float = Field(..., description="平均置信度 (0-1)")
provider: str = Field(..., description="使用的 OCR 提供商")
class ImageUploadResponse(BaseModel):
"""图片上传响应"""
id: int
file_path: str
status: str
created_at: datetime
model_config = {"from_attributes": True}
class ImageOCRResponse(BaseModel):
"""图片 OCR 结果响应"""
id: int
file_path: str
ocr_text: Optional[str] = None
confidence: Optional[float] = None
provider: Optional[str] = None
status: str
error_message: Optional[str] = None
created_at: datetime
model_config = {"from_attributes": True}