111 lines
4.0 KiB
Python
111 lines
4.0 KiB
Python
|
# =============================================================================
|
||
|
|
# RAGFlow API 数据模型
|
||
|
|
# =============================================================================
|
||
|
|
# 说明：定义 RAGFlow API 请求/响应的 Pydantic 数据模型
|
||
|
|
# 参考：https://ragflow.io/docs/http_api_reference
|
||
|
|
|
||
|
|
from typing import Any, Dict, List, Optional
|
||
|
|
|
||
|
|
from pydantic import BaseModel, Field
|
||
|
|
|
||
|
|
|
||
|
|
class RetrievalChunk(BaseModel):
|
||
|
|
"""检索返回的单个文本块。
|
||
|
|
|
||
|
|
Attributes:
|
||
|
|
id: 块唯一ID
|
||
|
|
content: 块内容文本
|
||
|
|
document_id: 所属文档ID
|
||
|
|
document_keyword: 所属文档名称
|
||
|
|
similarity: 综合相似度分数
|
||
|
|
term_similarity: 关键词相似度
|
||
|
|
vector_similarity: 向量相似度
|
||
|
|
highlight: 高亮标记的内容（可选）
|
||
|
|
"""
|
||
|
|
id: str = Field(default="", description="块唯一ID")
|
||
|
|
content: str = Field(default="", description="块内容文本")
|
||
|
|
document_id: str = Field(default="", description="所属文档ID")
|
||
|
|
document_keyword: str = Field(default="", description="所属文档名称")
|
||
|
|
similarity: float = Field(default=0.0, description="综合相似度分数")
|
||
|
|
term_similarity: float = Field(default=0.0, description="关键词相似度")
|
||
|
|
vector_similarity: float = Field(default=0.0, description="向量相似度")
|
||
|
|
highlight: Optional[str] = Field(default=None, description="高亮标记的内容")
|
||
|
|
|
||
|
|
model_config = {"from_attributes": True}
|
||
|
|
|
||
|
|
|
||
|
|
class DocAggregate(BaseModel):
|
||
|
|
"""文档聚合统计。
|
||
|
|
|
||
|
|
Attributes:
|
||
|
|
doc_id: 文档ID
|
||
|
|
doc_name: 文档名称
|
||
|
|
count: 命中的块数量
|
||
|
|
"""
|
||
|
|
doc_id: str = Field(default="", description="文档ID")
|
||
|
|
doc_name: str = Field(default="", description="文档名称")
|
||
|
|
count: int = Field(default=0, description="命中块数量")
|
||
|
|
|
||
|
|
model_config = {"from_attributes": True}
|
||
|
|
|
||
|
|
|
||
|
|
class RetrievalResult(BaseModel):
|
||
|
|
"""检索结果。
|
||
|
|
|
||
|
|
Attributes:
|
||
|
|
chunks: 命中的文本块列表
|
||
|
|
doc_aggs: 按文档聚合统计
|
||
|
|
total: 命中总数
|
||
|
|
"""
|
||
|
|
chunks: List[RetrievalChunk] = Field(default_factory=list, description="命中文本块列表")
|
||
|
|
doc_aggs: List[DocAggregate] = Field(default_factory=list, description="文档聚合统计")
|
||
|
|
total: int = Field(default=0, description="命中总数")
|
||
|
|
|
||
|
|
model_config = {"from_attributes": True}
|
||
|
|
|
||
|
|
|
||
|
|
class DatasetInfo(BaseModel):
|
||
|
|
"""数据集（知识库）信息。
|
||
|
|
|
||
|
|
Attributes:
|
||
|
|
id: 数据集ID
|
||
|
|
name: 数据集名称
|
||
|
|
chunk_method: 分块方法
|
||
|
|
permission: 权限
|
||
|
|
document_count: 文档数量
|
||
|
|
embedding_model: 向量模型
|
||
|
|
create_time: 创建时间
|
||
|
|
update_time: 更新时间
|
||
|
|
"""
|
||
|
|
id: str = Field(default="", description="数据集ID")
|
||
|
|
name: str = Field(default="", description="数据集名称")
|
||
|
|
chunk_method: str = Field(default="naive", description="分块方法")
|
||
|
|
permission: str = Field(default="me", description="权限")
|
||
|
|
document_count: int = Field(default=0, description="文档数量")
|
||
|
|
embedding_model: str = Field(default="", description="向量模型")
|
||
|
|
create_time: Optional[str] = Field(default=None, description="创建时间")
|
||
|
|
update_time: Optional[str] = Field(default=None, description="更新时间")
|
||
|
|
|
||
|
|
model_config = {"from_attributes": True}
|
||
|
|
|
||
|
|
|
||
|
|
class DocumentInfo(BaseModel):
|
||
|
|
"""文档信息。
|
||
|
|
|
||
|
|
Attributes:
|
||
|
|
id: 文档ID
|
||
|
|
name: 文档名称
|
||
|
|
chunk_method: 分块方法
|
||
|
|
chunk_count: 块数量
|
||
|
|
create_time: 创建时间
|
||
|
|
update_time: 更新时间
|
||
|
|
"""
|
||
|
|
id: str = Field(default="", description="文档ID")
|
||
|
|
name: str = Field(default="", description="文档名称")
|
||
|
|
chunk_method: str = Field(default="naive", description="分块方法")
|
||
|
|
chunk_count: int = Field(default=0, description="块数量")
|
||
|
|
create_time: Optional[str] = Field(default=None, description="创建时间")
|
||
|
|
update_time: Optional[str] = Field(default=None, description="更新时间")
|
||
|
|
|
||
|
|
model_config = {"from_attributes": True}
|