Codex
141 lines
4.7 KiB
Python
141 lines
4.7 KiB
Python
"""
|
|
知识库分段 Schema
|
|
"""
|
|
from typing import Optional, List, Dict, Any
|
|
from datetime import datetime
|
|
|
|
from pydantic import BaseModel, Field, ConfigDict
|
|
|
|
from app.base_schema import CSTDatetime
|
|
|
|
|
|
class SegmentResponse(BaseModel):
|
|
"""分段输出"""
|
|
id: str
|
|
knowledge_base_id: str
|
|
document_id: str
|
|
document_name: str = ""
|
|
position: int = 0
|
|
content: str
|
|
answer: Optional[str] = None
|
|
token_count: int = 0
|
|
char_count: int = 0
|
|
word_count: int = 0
|
|
page_number: Optional[int] = None
|
|
keywords: Optional[List[str]] = None
|
|
metadata: Optional[Dict[str, Any]] = None
|
|
embedding_status: str = "pending"
|
|
enabled: bool = True
|
|
hit_count: int = 0
|
|
sys_create_datetime: Optional[CSTDatetime] = None
|
|
|
|
model_config = ConfigDict(from_attributes=True)
|
|
|
|
|
|
class SegmentListResponse(BaseModel):
|
|
"""分段列表输出"""
|
|
id: str
|
|
document_id: str
|
|
document_name: str = ""
|
|
position: int = 0
|
|
content: str
|
|
answer: Optional[str] = None
|
|
token_count: int = 0
|
|
char_count: int = 0
|
|
word_count: int = 0
|
|
page_number: Optional[int] = None
|
|
keywords: Optional[List[str]] = None
|
|
extra_metadata: Optional[Dict[str, Any]] = None
|
|
enabled: bool = True
|
|
hit_count: int = 0
|
|
embedding_status: str = "pending"
|
|
sys_create_datetime: Optional[CSTDatetime] = None
|
|
|
|
model_config = ConfigDict(from_attributes=True)
|
|
|
|
|
|
class SegmentUpdateInput(BaseModel):
|
|
"""更新分段"""
|
|
content: Optional[str] = Field(None, description="分段内容")
|
|
keywords: Optional[List[str]] = Field(None, description="关键词")
|
|
enabled: Optional[bool] = Field(None, description="是否启用")
|
|
extra_metadata: Optional[Dict[str, Any]] = Field(None, description="元数据")
|
|
|
|
|
|
class SegmentCreateInput(BaseModel):
|
|
"""手动创建分段"""
|
|
content: str = Field(..., min_length=1, description="分段内容")
|
|
answer: Optional[str] = Field(None, description="Q&A 模式的答案")
|
|
keywords: Optional[List[str]] = Field(None, description="关键词")
|
|
|
|
|
|
class ChunkPreviewInput(BaseModel):
|
|
"""分块预览输入"""
|
|
file_id: str = Field(..., description="文件ID")
|
|
chunk_strategy: str = Field(default="recursive", description="分块策略")
|
|
chunk_size: int = Field(default=500, ge=100, le=4000, description="分块大小")
|
|
chunk_overlap: int = Field(default=50, ge=0, le=500, description="分块重叠")
|
|
separator: Optional[str] = Field(None, description="自定义分隔符")
|
|
process_rules: Optional[Dict[str, Any]] = Field(None, description="预处理规则")
|
|
|
|
|
|
class ChunkPreviewItem(BaseModel):
|
|
"""分块预览结果项"""
|
|
position: int = 0
|
|
content: str = ""
|
|
char_count: int = 0
|
|
token_count: int = 0
|
|
word_count: int = 0
|
|
answer: Optional[str] = None
|
|
metadata: Optional[Dict[str, Any]] = None
|
|
|
|
|
|
class ChunkPreviewResponse(BaseModel):
|
|
"""分块预览响应"""
|
|
chunks: List[ChunkPreviewItem] = Field(default_factory=list)
|
|
total: int = 0
|
|
strategy: str = ""
|
|
chunk_size: int = 0
|
|
chunk_overlap: int = 0
|
|
|
|
|
|
class RetrievalInput(BaseModel):
|
|
"""检索输入"""
|
|
model_config = ConfigDict(protected_namespaces=())
|
|
|
|
query: str = Field(..., min_length=1, description="查询文本")
|
|
knowledge_base_ids: List[str] = Field(..., min_length=1, description="知识库ID列表")
|
|
top_k: int = Field(default=5, ge=1, le=20, description="返回数量")
|
|
score_threshold: float = Field(default=0.5, ge=0, le=1, description="相似度阈值")
|
|
retrieval_mode: Optional[str] = Field(None, description="检索模式（不传则使用知识库配置）")
|
|
rerank_enabled: Optional[bool] = Field(None, description="是否启用重排序（不传则使用知识库配置）")
|
|
rerank_model_id: Optional[str] = Field(None, description="重排序模型ID（不传则使用知识库配置）")
|
|
metadata_filter: Optional[Dict[str, Any]] = Field(None, description="元数据过滤条件")
|
|
|
|
|
|
class RetrievalResult(BaseModel):
|
|
"""检索结果"""
|
|
segment_id: str
|
|
document_id: str
|
|
document_name: str = ""
|
|
knowledge_base_id: str
|
|
knowledge_base_name: str = ""
|
|
content: str
|
|
score: float = 0.0
|
|
token_count: int = 0
|
|
page_number: Optional[int] = None
|
|
metadata: Optional[Dict[str, Any]] = None
|
|
keywords: Optional[List[str]] = None
|
|
match_source: Optional[str] = Field(None, description="命中来源: vector/fulltext/annotation")
|
|
parent_content: Optional[str] = Field(None, description="父分段内容（Small-to-Big 模式）")
|
|
|
|
|
|
class RetrievalResponse(BaseModel):
|
|
"""检索响应"""
|
|
results: List[RetrievalResult] = Field(default_factory=list)
|
|
total: int = 0
|
|
query: str = ""
|
|
elapsed_time: int = 0
|
|
retrieval_mode: str = ""
|
|
rerank_applied: bool = False
|