Files
hyungi_document_server/app/workers/queue_consumer.py
T
Hyungi Ahn b46a75758b feat(memos): 내장 메모 기능 — 파일 없는 문서(file_type='note')
Document Server에 Memos 앱 대체 기능 내장. 메모를 documents 테이블의
file_type='note' 레코드로 관리하여 기존 AI 파이프라인(classify/embed/
chunk/search/ask) 재활용.

Backend:
- migration 105: source_channel 'memo', file_path NULL 허용,
  user_tags/pinned/ask_includable 컬럼, 메모 인덱스
- api/memos.py: CRUD 7개 엔드포인트 + #태그 파싱 + stale AI 초기화
  + 큐 pending 중복 방지
- queue_consumer: note extract/preview skip
- documents API: file_path NULL 가드, 목록에서 메모 제외
- search /ask: ask_includable=false 문서 evidence 제외

Frontend:
- /memos 타임라인 페이지 (빠른 입력 + 피드 + 인라인 편집 + 태그 필터)
- QuickMemoButton FAB (Ctrl+M, 모든 페이지)
- Sidebar 메모 링크

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 16:00:00 +09:00

163 lines
6.8 KiB
Python

"""처리 큐 소비자 — APScheduler에서 1분 간격으로 호출"""
from datetime import datetime, timedelta, timezone
from sqlalchemy import select, update
from core.database import async_session
from core.utils import setup_logger
from models.queue import ProcessingQueue
logger = setup_logger("queue_consumer")
# stage별 배치 크기
BATCH_SIZE = {"extract": 5, "classify": 3, "summarize": 3, "embed": 1, "chunk": 1, "preview": 2}
STALE_THRESHOLD_MINUTES = 10
async def reset_stale_items():
"""processing 상태로 10분 이상 방치된 항목 복구"""
cutoff = datetime.now(timezone.utc) - timedelta(minutes=STALE_THRESHOLD_MINUTES)
async with async_session() as session:
result = await session.execute(
update(ProcessingQueue)
.where(
ProcessingQueue.status == "processing",
ProcessingQueue.started_at < cutoff,
)
.values(status="pending", started_at=None)
)
if result.rowcount > 0:
await session.commit()
logger.warning(f"stale 항목 {result.rowcount}건 복구")
async def enqueue_next_stage(document_id: int, current_stage: str):
"""현재 stage 완료 후 다음 stage를 pending으로 등록"""
next_stages = {"extract": ["classify", "preview"], "classify": ["embed", "chunk"]}
stages = next_stages.get(current_stage, [])
if not stages:
return
async with async_session() as session:
for next_stage in stages:
existing = await session.execute(
select(ProcessingQueue).where(
ProcessingQueue.document_id == document_id,
ProcessingQueue.stage == next_stage,
ProcessingQueue.status.in_(["pending", "processing"]),
)
)
if existing.scalar_one_or_none():
continue
session.add(ProcessingQueue(
document_id=document_id,
stage=next_stage,
status="pending",
))
await session.commit()
async def consume_queue():
"""큐에서 pending 항목을 가져와 stage별 워커 실행"""
from workers.classify_worker import process as classify_process
from workers.chunk_worker import process as chunk_process
from workers.embed_worker import process as embed_process
from workers.extract_worker import process as extract_process
from workers.preview_worker import process as preview_process
from workers.summarize_worker import process as summarize_process
workers = {
"extract": extract_process,
"classify": classify_process,
"summarize": summarize_process,
"embed": embed_process,
"chunk": chunk_process,
"preview": preview_process,
}
await reset_stale_items()
for stage, worker_fn in workers.items():
batch_size = BATCH_SIZE.get(stage, 3)
# pending 항목 조회
async with async_session() as session:
result = await session.execute(
select(ProcessingQueue.id, ProcessingQueue.document_id)
.where(
ProcessingQueue.stage == stage,
ProcessingQueue.status == "pending",
)
.order_by(ProcessingQueue.created_at)
.limit(batch_size)
)
pending_items = result.all()
# 각 항목을 독립 세션에서 처리
for queue_id, document_id in pending_items:
# 상태를 processing으로 변경
async with async_session() as session:
item = await session.get(ProcessingQueue, queue_id)
if not item or item.status != "pending":
continue
item.status = "processing"
item.started_at = datetime.now(timezone.utc)
item.attempts += 1
await session.commit()
# 워커 실행 (독립 세션)
try:
# note(메모)는 이미 extracted_text가 있으므로 extract/preview skip
if stage in ("extract", "preview"):
from models.document import Document
async with async_session() as check_session:
doc = await check_session.get(Document, document_id)
if doc and doc.file_type == "note":
async with async_session() as skip_session:
item = await skip_session.get(ProcessingQueue, queue_id)
if item:
item.status = "completed"
item.completed_at = datetime.now(timezone.utc)
await skip_session.commit()
await enqueue_next_stage(document_id, stage)
logger.info(f"[{stage}] document_id={document_id} skip (note)")
continue
async with async_session() as worker_session:
await worker_fn(document_id, worker_session)
await worker_session.commit()
# 완료 처리
async with async_session() as session:
item = await session.get(ProcessingQueue, queue_id)
if not item:
logger.warning(f"[{stage}] queue_id={queue_id} 없음 (삭제됨?), skip")
continue
item.status = "completed"
item.completed_at = datetime.now(timezone.utc)
await session.commit()
await enqueue_next_stage(document_id, stage)
logger.info(f"[{stage}] document_id={document_id} 완료")
except Exception as e:
# 실패 처리
async with async_session() as session:
item = await session.get(ProcessingQueue, queue_id)
if not item:
logger.warning(f"[{stage}] queue_id={queue_id} 없음 (삭제됨?), skip")
continue
# 빈 메시지 방어: str → repr → 클래스명 순 fallback
err_text = str(e) or repr(e) or type(e).__name__
item.error_message = err_text[:500]
if item.attempts >= item.max_attempts:
item.status = "failed"
logger.error(f"[{stage}] document_id={document_id} 영구 실패: {e}")
else:
item.status = "pending"
item.started_at = None
logger.warning(f"[{stage}] document_id={document_id} 재시도 예정 ({item.attempts}/{item.max_attempts}): {e}")
await session.commit()