131dbd7b7c
동작하는 최소 코드 수준의 v2 스캐폴딩: - docker-compose.yml: postgres, fastapi, kordoc, frontend, caddy - app/: FastAPI 백엔드 (main, core, models, ai, prompts) - services/kordoc/: Node.js 문서 파싱 마이크로서비스 - gpu-server/: AI Gateway + GPU docker-compose - frontend/: SvelteKit 기본 구조 - migrations/: PostgreSQL 초기 스키마 (documents, tasks, processing_queue) - tests/: pytest conftest 기본 설정 - config.yaml, Caddyfile, credentials.env.example 갱신 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
65 lines
2.5 KiB
Python
65 lines
2.5 KiB
Python
"""documents 테이블 ORM"""
|
|
|
|
from datetime import datetime
|
|
|
|
from pgvector.sqlalchemy import Vector
|
|
from sqlalchemy import BigInteger, DateTime, Enum, String, Text
|
|
from sqlalchemy.dialects.postgresql import JSONB
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from core.database import Base
|
|
|
|
|
|
class Document(Base):
|
|
__tablename__ = "documents"
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
|
|
|
|
# 1계층: 원본 파일
|
|
file_path: Mapped[str] = mapped_column(Text, unique=True, nullable=False)
|
|
file_hash: Mapped[str] = mapped_column(String(64), nullable=False)
|
|
file_format: Mapped[str] = mapped_column(String(20), nullable=False)
|
|
file_size: Mapped[int | None] = mapped_column(BigInteger)
|
|
file_type: Mapped[str] = mapped_column(
|
|
Enum("immutable", "editable", "note", name="doc_type"),
|
|
default="immutable"
|
|
)
|
|
import_source: Mapped[str | None] = mapped_column(Text)
|
|
|
|
# 2계층: 텍스트 추출
|
|
extracted_text: Mapped[str | None] = mapped_column(Text)
|
|
extracted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
extractor_version: Mapped[str | None] = mapped_column(String(50))
|
|
|
|
# 2계층: AI 가공
|
|
ai_summary: Mapped[str | None] = mapped_column(Text)
|
|
ai_tags: Mapped[dict | None] = mapped_column(JSONB, default=[])
|
|
ai_domain: Mapped[str | None] = mapped_column(String(100))
|
|
ai_sub_group: Mapped[str | None] = mapped_column(String(100))
|
|
ai_model_version: Mapped[str | None] = mapped_column(String(50))
|
|
ai_processed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
|
|
# 3계층: 벡터 임베딩
|
|
embedding = mapped_column(Vector(768), nullable=True)
|
|
embed_model_version: Mapped[str | None] = mapped_column(String(50))
|
|
embedded_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
|
|
# 메타데이터
|
|
source_channel: Mapped[str | None] = mapped_column(
|
|
Enum("law_monitor", "devonagent", "email", "web_clip",
|
|
"tksafety", "inbox_route", "manual", "drive_sync",
|
|
name="source_channel")
|
|
)
|
|
data_origin: Mapped[str | None] = mapped_column(
|
|
Enum("work", "external", name="data_origin")
|
|
)
|
|
title: Mapped[str | None] = mapped_column(Text)
|
|
|
|
# 타임스탬프
|
|
created_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), default=datetime.now
|
|
)
|
|
updated_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), default=datetime.now, onupdate=datetime.now
|
|
)
|