File size: 1,551 Bytes
7c6ffa6 | 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 | from __future__ import annotations
from datetime import datetime
from typing import TYPE_CHECKING
from sqlalchemy import DateTime, ForeignKey, Integer, String, Text, UniqueConstraint, func
from sqlalchemy.orm import Mapped, mapped_column, relationship
from app.core.database import Base
from app.utils.ids import prefixed_id
if TYPE_CHECKING:
from app.models.document import Document
class DocumentChunk(Base):
__tablename__ = "document_chunks"
__table_args__ = (
UniqueConstraint("document_id", "chunk_index", name="uq_document_chunk_index"),
)
id: Mapped[str] = mapped_column(
String(40),
primary_key=True,
default=lambda: prefixed_id("chunk"),
)
document_id: Mapped[str] = mapped_column(
String(40),
ForeignKey("documents.id", ondelete="CASCADE"),
index=True,
nullable=False,
)
chunk_index: Mapped[int] = mapped_column(Integer, nullable=False)
chunk_text: Mapped[str] = mapped_column(Text, nullable=False)
token_estimate: Mapped[int] = mapped_column(Integer, nullable=False)
page_number: Mapped[int | None] = mapped_column(Integer, nullable=True)
heading: Mapped[str | None] = mapped_column(String(255), nullable=True)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
server_default=func.now(),
nullable=False,
)
embedding: Mapped[str | None] = mapped_column(Text, nullable=True)
document: Mapped["Document"] = relationship("Document", back_populates="chunks")
|