378fbc7845
GPU 서버에 untracked로만 존재하던 Phase 0.1 코드를 정식 commit: - app/models/chunk.py — DocumentChunk ORM (country/source/domain 메타 포함) - app/workers/chunk_worker.py — 6가지 chunking 전략 (legal/news/markdown/email/long_pdf/default) - migrations/014_document_chunks.sql — pgvector + FTS + trigram 인덱스 - app/models/queue.py — ProcessingQueue enum에 'chunk' stage 추가 - app/workers/queue_consumer.py — chunk stage 등록, classify→[embed,chunk] 자동 연결 Phase 1 reranker 통합 작업의 전제 조건. document_chunks 테이블 기반 retrieval에 사용.
35 lines
1.4 KiB
Python
35 lines
1.4 KiB
Python
"""processing_queue 테이블 ORM (비동기 가공 큐)"""
|
|
|
|
from datetime import datetime
|
|
|
|
from sqlalchemy import BigInteger, DateTime, Enum, ForeignKey, SmallInteger, Text, UniqueConstraint
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from core.database import Base
|
|
|
|
|
|
class ProcessingQueue(Base):
|
|
__tablename__ = "processing_queue"
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
|
|
document_id: Mapped[int] = mapped_column(BigInteger, ForeignKey("documents.id"), nullable=False)
|
|
stage: Mapped[str] = mapped_column(
|
|
Enum("extract", "classify", "summarize", "embed", "chunk", "preview", name="process_stage"), nullable=False
|
|
)
|
|
status: Mapped[str] = mapped_column(
|
|
Enum("pending", "processing", "completed", "failed", name="process_status"),
|
|
default="pending"
|
|
)
|
|
attempts: Mapped[int] = mapped_column(SmallInteger, default=0)
|
|
max_attempts: Mapped[int] = mapped_column(SmallInteger, default=3)
|
|
error_message: Mapped[str | None] = mapped_column(Text)
|
|
created_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), default=datetime.now
|
|
)
|
|
started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
completed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
|
|
__table_args__ = (
|
|
UniqueConstraint("document_id", "stage", "status"),
|
|
)
|