Files
leocrm/app/plugins/builtins/unified_search/models.py
T

78 lines
2.9 KiB
Python

"""SQLAlchemy models for the Unified Search plugin."""
from __future__ import annotations
import uuid
from sqlalchemy import ForeignKey, Index, Integer, String, Text
from sqlalchemy.dialects.postgresql import JSONB
from sqlalchemy.dialects.postgresql import UUID as PGUUID
from sqlalchemy.orm import Mapped, mapped_column
from app.core.db import Base, TenantMixin
from app.models.owned_mixin import OwnedMixin
class SearchProviderRegistry(Base, TenantMixin, OwnedMixin):
"""Registry of active search providers per tenant."""
__tablename__ = "unified_search_providers"
__table_args__ = (
Index("ix_usp_tenant", "tenant_id"),
)
id: Mapped[uuid.UUID] = mapped_column(
PGUUID(as_uuid=True), primary_key=True, default=uuid.uuid4
)
entity_type: Mapped[str] = mapped_column(String(50), nullable=False)
plugin_name: Mapped[str] = mapped_column(String(80), nullable=False)
is_active: Mapped[bool] = mapped_column(
nullable=False, default=True
)
config: Mapped[dict] = mapped_column(JSONB, nullable=False, default=dict)
class SearchIndexLog(Base, TenantMixin, OwnedMixin):
"""Log of indexing actions for audit and debugging."""
__tablename__ = "unified_search_index_log"
__table_args__ = (
Index("ix_usil_tenant", "tenant_id"),
Index("ix_usil_entity", "entity_type", "entity_id"),
)
id: Mapped[uuid.UUID] = mapped_column(
PGUUID(as_uuid=True), primary_key=True, default=uuid.uuid4
)
entity_type: Mapped[str] = mapped_column(String(50), nullable=False)
entity_id: Mapped[uuid.UUID] = mapped_column(PGUUID(as_uuid=True), nullable=False)
action: Mapped[str] = mapped_column(String(20), nullable=False)
status: Mapped[str] = mapped_column(String(20), nullable=False, default="pending")
error_message: Mapped[str | None] = mapped_column(Text, nullable=True)
from pgvector.sqlalchemy import Vector # noqa: E402 — optional dependency import after model defs
class DocumentChunk(Base, TenantMixin, OwnedMixin):
"""Chunk of a DMS file's extracted text, with its own embedding for RAG."""
__tablename__ = "document_chunks"
__table_args__ = (
Index("ix_document_chunks_tenant", "tenant_id"),
Index("ix_document_chunks_file", "file_id"),
Index("ix_document_chunks_tenant_file", "tenant_id", "file_id"),
)
id: Mapped[uuid.UUID] = mapped_column(
PGUUID(as_uuid=True), primary_key=True, default=uuid.uuid4
)
file_id: Mapped[uuid.UUID] = mapped_column(
PGUUID(as_uuid=True), ForeignKey("files.id", ondelete="CASCADE"), nullable=False
)
chunk_index: Mapped[int] = mapped_column(Integer, nullable=False)
chunk_text: Mapped[str] = mapped_column(Text, nullable=False)
chunk_hash: Mapped[str] = mapped_column(String(64), nullable=False)
embedding: Mapped[list[float] | None] = mapped_column(
Vector(768), nullable=True
)