kplam
dce9e31bde
- 新增 JWT 认证模块，支持登录/注册/用户管理 - 新增文件上传接口，支持 .txt/.md/.html/.pdf/.docx 等格式解析入库 - 新增检索结果 AI 总结功能 - 新增文本去重缓存机制 - 新增全局认证夹具简化测试 - 新增配置项与环境变量支持 - 完善文档与测试覆盖
45 lines
2.1 KiB
Python
45 lines
2.1 KiB
Python
"""检索请求与响应的数据模型"""
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class SearchRequest(BaseModel):
|
|
"""检索请求"""
|
|
|
|
query: str = Field(description="查询文本")
|
|
top_k: int | None = Field(default=None, description="返回结果数，为空时使用 settings.retrieval_final_k")
|
|
summarize: bool = Field(default=False, description="是否对检索结果生成 AI 总结")
|
|
|
|
|
|
class SearchHit(BaseModel):
|
|
"""单条检索命中结果"""
|
|
|
|
text: str = Field(description="原文 chunk 内容")
|
|
doc_id: str = Field(description="所属文档 ID")
|
|
title: str = Field(default="", description="文档标题")
|
|
section_path: str = Field(default="", description="chunk 所在的章节路径")
|
|
score: float = Field(description="相关性得分")
|
|
doc_summary: str = Field(default="", description="L1 文档总结，仅用于上下文标注")
|
|
|
|
|
|
class ExtractedInfo(BaseModel):
|
|
"""AI 从 query 中提取的关键信息"""
|
|
|
|
rewrite: str = Field(default="", description="改写后的 query")
|
|
keywords: list[str] = Field(default_factory=list, description="关键词")
|
|
entities: list[str] = Field(default_factory=list, description="实体（人名/产品/技术等）")
|
|
intent: str = Field(default="", description="查询意图分类")
|
|
time_range: str = Field(default="", description="时间范围，空表示无")
|
|
categories: list[str] = Field(default_factory=list, description="命中类目名（含未达阈值的候选）")
|
|
|
|
|
|
class SearchResponse(BaseModel):
|
|
"""检索响应"""
|
|
|
|
query: str = Field(description="原始查询文本")
|
|
hits: list[SearchHit] = Field(default_factory=list, description="命中结果列表")
|
|
routed_categories: list[str] = Field(default_factory=list, description="query 路由命中的类目")
|
|
fallback: bool = Field(default=False, description="是否走了全库兜底路径")
|
|
extracted_info: ExtractedInfo | None = Field(default=None, description="AI 提取的 query 关键信息")
|
|
summary: str | None = Field(default=None, description="检索结果 AI 总结，仅 summarize=true 时返回")
|