orakzai-io
Initial
194aaa5
Raw History Blame Contribute Delete
2.55 kB
# SQLAlchemy models: Document, Chunk (Vector dimension 384), User
import uuid
from datetime import datetime
from sqlalchemy import String, Text, Integer, DateTime, ForeignKey, func
from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column, relationship
from sqlalchemy.dialects.postgresql import UUID
from pgvector.sqlalchemy import Vector # type: ignore[import-untyped]
from fastapi_users.db import SQLAlchemyBaseUserTableUUID
class Base(DeclarativeBase):
pass
class User(SQLAlchemyBaseUserTableUUID, Base):
__tablename__ = "users"
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), server_default=func.now())
documents: Mapped[list["Document"]] = relationship("Document", back_populates="user", cascade="all, delete-orphan")
class Document(Base):
__tablename__ = "documents"
id: Mapped[uuid.UUID] = mapped_column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
user_id: Mapped[uuid.UUID] = mapped_column(
UUID(as_uuid=True), ForeignKey("users.id", ondelete="CASCADE"), nullable=False
)
filename: Mapped[str] = mapped_column(String(255), nullable=False)
content_hash: Mapped[str] = mapped_column(String(64), nullable=False, unique=True)
file_path: Mapped[str] = mapped_column(String(512), nullable=False)
status: Mapped[str] = mapped_column(String(20), nullable=False, default="uploading")
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), server_default=func.now())
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
chunks: Mapped[list["Chunk"]] = relationship("Chunk", back_populates="document", cascade="all, delete-orphan")
user: Mapped["User"] = relationship("User", back_populates="documents")
class Chunk(Base):
__tablename__ = "chunks"
id: Mapped[uuid.UUID] = mapped_column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
document_id: Mapped[uuid.UUID] = mapped_column(
UUID(as_uuid=True), ForeignKey("documents.id", ondelete="CASCADE"), nullable=False
)
content: Mapped[str] = mapped_column(Text, nullable=False)
# pgvector column — no native Mapped type exists for Vector
embedding = mapped_column(Vector(384), nullable=False)
chunk_index: Mapped[int] = mapped_column(Integer, nullable=False)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), server_default=func.now())
document: Mapped["Document"] = relationship("Document", back_populates="chunks")