35 lines
952 B
Python
35 lines
952 B
Python
"""Embedding 向量生成数据模型 (M5)。"""
|
|
|
|
from datetime import datetime
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class EmbeddingResult(BaseModel):
|
|
"""单篇文章的嵌入向量结果，M5 最终落盘格式。"""
|
|
|
|
# 来源标识
|
|
url_hash: str
|
|
source_id: str
|
|
|
|
# 嵌入向量（1024 维 float 列表）
|
|
vector: list[float] = Field(..., description="1024 维浮点向量")
|
|
dimension: int = 1024
|
|
|
|
# 嵌入文本（用于检索时调试/可视化）
|
|
embedded_text: str = Field(default="", description="拼接后送入 embedder 的文本")
|
|
|
|
# 调用元信息
|
|
provider: str = "dashscope"
|
|
model: str = ""
|
|
embedded_at: datetime = Field(default_factory=datetime.now)
|
|
|
|
|
|
class EmbeddingError(Exception):
|
|
"""Embedding 调用失败。"""
|
|
|
|
def __init__(self, reason: str, *, attempts: int = 0) -> None:
|
|
super().__init__(reason)
|
|
self.reason = reason
|
|
self.attempts = attempts
|