app/documents/chunks_model.py

from datetime import UTC, datetime
from uuid import UUID, uuid4

from sqlalchemy import DateTime, ForeignKey, Integer, Text, Uuid
from sqlalchemy.orm import Mapped, mapped_column

from app.db.base import Base


def _utcnow() -> datetime:
    return datetime.now(UTC)


class DocumentChunk(Base):
    __tablename__ = "document_chunks"

    id: Mapped[UUID] = mapped_column(Uuid, primary_key=True, default=uuid4)
    document_id: Mapped[UUID] = mapped_column(
        Uuid,
        ForeignKey("documents.id", ondelete="CASCADE"),
        nullable=False,
        index=True,
    )
    chunk_index: Mapped[int] = mapped_column(Integer, nullable=False)
    text: Mapped[str] = mapped_column(Text, nullable=False)
    char_start: Mapped[int] = mapped_column(Integer, nullable=False)
    char_end: Mapped[int] = mapped_column(Integer, nullable=False)
    created_at: Mapped[datetime] = mapped_column(
        DateTime(timezone=True), default=_utcnow, nullable=False
    )