File size: 1,682 Bytes
de1e3fc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 | from __future__ import annotations
from datetime import datetime, timezone
import numpy as np
from sqlalchemy import (
DateTime,
ForeignKey,
Integer,
LargeBinary,
String,
UniqueConstraint,
func,
)
from sqlalchemy.orm import Mapped, mapped_column, relationship
from .base import Base
class Embedding(Base):
"""An embedding vector for one picture under one model (spec §7.6).
The vector is stored as L2-normalized float32 bytes so cosine similarity == dot product.
Keeping embeddings in their own table lets us recompute across model versions without
losing history.
"""
__tablename__ = "embeddings"
__table_args__ = (
UniqueConstraint(
"picture_id", "model_name", "model_version", name="uq_embedding_picture_model"
),
)
id: Mapped[int] = mapped_column(primary_key=True)
picture_id: Mapped[int] = mapped_column(ForeignKey("pictures.id"), index=True)
model_name: Mapped[str] = mapped_column(String(80))
model_version: Mapped[str] = mapped_column(String(40))
dim: Mapped[int] = mapped_column(Integer)
vector: Mapped[bytes] = mapped_column(LargeBinary) # float32, L2-normalized
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
server_default=func.now(),
)
picture: Mapped["Picture"] = relationship(back_populates="embeddings") # noqa: F821
def as_array(self) -> np.ndarray:
return np.frombuffer(self.vector, dtype=np.float32)
@staticmethod
def to_bytes(vec: np.ndarray) -> bytes:
return np.asarray(vec, dtype=np.float32).tobytes()
|