Files
hyungi_document_server/app/main.py
Hyungi Ahn 75a1919342 feat(digest): Phase 4 Global News Digest (cluster-level batch summarization)
7일 rolling window 뉴스를 country × topic 2-level로 묶어 매일 04:00 KST 배치 생성.
search 파이프라인 미사용. documents → clustering → cluster-level LLM summarization → digest.

핵심 결정:
- adaptive threshold (0.75/0.78/0.80) + EMA centroid (α=0.7) + time-decay (λ=ln(2)/3)
- min_articles=3, max_topics=10/country, top-5 MMR diversity, ai_summary[:300] truncate
- cluster-level LLM only, drop금지 fallback (topic_label="주요 뉴스 묶음" + top member ai_summary[:200])
- importance_score country별 0~1 normalize + raw_weight_sum 별도 보존, max(score, 0.01) floor
- per-call timeout 25s + pipeline hard cap 600s
- DELETE+INSERT idempotent (UNIQUE digest_date), AIClient._call_chat 직접 호출 (client.py 수정 없음)

신규:
- migrations/101_global_digests.sql (2테이블 정규화)
- app/models/digest.py (GlobalDigest + DigestTopic ORM)
- app/services/digest/{loader,clustering,selection,summarizer,pipeline}.py
- app/workers/digest_worker.py (PIPELINE_HARD_CAP + CLI 진입점)
- app/api/digest.py (/latest, ?date|country, /regenerate, inline Pydantic)
- app/prompts/digest_topic.txt (JSON-only + 절대 금지 블록)

main.py 4줄: import 2 + scheduler add_job 1 + include_router 1.
plan: ~/.claude/plans/quiet-herding-tome.md
2026-04-09 07:45:11 +09:00

154 lines
5.7 KiB
Python

"""hyungi_Document_Server — FastAPI 엔트리포인트"""
from contextlib import asynccontextmanager
from fastapi import FastAPI, Request
from fastapi.responses import RedirectResponse
from sqlalchemy import func, select, text
from api.auth import router as auth_router
from api.dashboard import router as dashboard_router
from api.digest import router as digest_router
from api.documents import router as documents_router
from api.news import router as news_router
from api.search import router as search_router
from api.setup import router as setup_router
from core.config import settings
from core.database import async_session, engine, init_db
from models.user import User
@asynccontextmanager
async def lifespan(app: FastAPI):
"""앱 시작/종료 시 실행되는 lifespan 핸들러"""
import asyncio
from apscheduler.schedulers.asyncio import AsyncIOScheduler
from apscheduler.triggers.cron import CronTrigger
from services.search.query_analyzer import prewarm_analyzer
from workers.daily_digest import run as daily_digest_run
from workers.digest_worker import run as global_digest_run
from workers.file_watcher import watch_inbox
from workers.law_monitor import run as law_monitor_run
from workers.mailplus_archive import run as mailplus_run
from workers.news_collector import run as news_collector_run
from workers.queue_consumer import consume_queue
# 시작: DB 연결 확인
await init_db()
# NAS 마운트 확인 (NFS 미마운트 시 로컬 빈 디렉토리에 쓰는 것 방지)
from pathlib import Path
nas_check = Path(settings.nas_mount_path) / "PKM"
if not nas_check.is_dir():
raise RuntimeError(
f"NAS 마운트 확인 실패: {nas_check} 디렉토리 없음. "
f"NFS 마운트 상태를 확인하세요."
)
# APScheduler: 백그라운드 작업
scheduler = AsyncIOScheduler(timezone="Asia/Seoul")
# 상시 실행
scheduler.add_job(consume_queue, "interval", minutes=1, id="queue_consumer")
scheduler.add_job(watch_inbox, "interval", minutes=5, id="file_watcher")
# 일일 스케줄 (KST)
scheduler.add_job(law_monitor_run, CronTrigger(hour=7), id="law_monitor")
scheduler.add_job(mailplus_run, CronTrigger(hour=7), id="mailplus_morning")
scheduler.add_job(mailplus_run, CronTrigger(hour=18), id="mailplus_evening")
scheduler.add_job(daily_digest_run, CronTrigger(hour=20), id="daily_digest")
scheduler.add_job(global_digest_run, CronTrigger(hour=4, minute=0), id="global_digest")
scheduler.add_job(news_collector_run, "interval", hours=6, id="news_collector")
scheduler.start()
# Phase 2.1 (async 구조): QueryAnalyzer prewarm.
# 대표 쿼리 15~20개를 background task로 분석해 cache 적재.
# 첫 사용자 요청부터 cache hit rate 70~80% 목표.
# 논블로킹 — startup을 막지 않음. MLX 부하 완화 위해 delay_between=0.5.
prewarm_task = asyncio.create_task(prewarm_analyzer())
prewarm_task.add_done_callback(
lambda t: t.exception() and None # 예외는 query_analyzer 내부에서 로깅
)
yield
# 종료: 스케줄러 → DB 순서로 정리
scheduler.shutdown(wait=False)
await engine.dispose()
app = FastAPI(
title="hyungi_Document_Server",
description="Self-hosted PKM 웹 애플리케이션 API",
version="2.0.0",
lifespan=lifespan,
)
# ─── 라우터 등록 ───
app.include_router(setup_router, prefix="/api/setup", tags=["setup"])
app.include_router(auth_router, prefix="/api/auth", tags=["auth"])
app.include_router(documents_router, prefix="/api/documents", tags=["documents"])
app.include_router(search_router, prefix="/api/search", tags=["search"])
app.include_router(dashboard_router, prefix="/api/dashboard", tags=["dashboard"])
app.include_router(news_router, prefix="/api/news", tags=["news"])
app.include_router(digest_router, prefix="/api/digest", tags=["digest"])
# TODO: Phase 5에서 추가
# app.include_router(tasks.router, prefix="/api/tasks", tags=["tasks"])
# app.include_router(export.router, prefix="/api/export", tags=["export"])
# ─── 셋업 미들웨어: 유저 0명이면 /setup으로 리다이렉트 ───
SETUP_BYPASS_PREFIXES = (
"/api/setup", "/setup", "/health", "/docs", "/openapi.json", "/redoc",
)
@app.middleware("http")
async def setup_redirect_middleware(request: Request, call_next):
path = request.url.path
# 바이패스 경로는 항상 통과
if any(path.startswith(p) for p in SETUP_BYPASS_PREFIXES):
return await call_next(request)
# 유저 존재 여부 확인
try:
async with async_session() as session:
result = await session.execute(select(func.count(User.id)))
user_count = result.scalar()
if user_count == 0:
return RedirectResponse(url="/setup")
except Exception:
pass # DB 연결 실패 시 통과 (health에서 확인 가능)
return await call_next(request)
# ─── 셋업 페이지 라우트 (API가 아닌 HTML 페이지) ───
@app.get("/setup")
async def setup_page_redirect(request: Request):
"""셋업 위자드 페이지로 포워딩"""
from api.setup import setup_page
from core.database import get_session
async for session in get_session():
return await setup_page(request, session)
@app.get("/health")
async def health_check():
"""헬스체크 — DB 연결 상태 포함"""
db_ok = False
try:
async with engine.connect() as conn:
await conn.execute(text("SELECT 1"))
db_ok = True
except Exception:
pass
return {
"status": "ok" if db_ok else "degraded",
"version": "2.0.0",
"database": "connected" if db_ok else "disconnected",
}