Files
hyungi_document_server/app/main.py
T
Hyungi Ahn 1e2c004dd4 feat(media): §3 audio STT + video 재생 인프라
plan: ~/.claude/plans/luminous-sprouting-hamster.md §3

스키마:
- migrations/147_audio_segments_table.sql: audio_segments (STT 타임스탬프
  세그먼트)
- migrations/148_audio_segments_idx.sql: (document_id, start_s) idx
- migrations/149_document_media_cols.sql: documents.thumbnail_path +
  needs_conversion
- migrations/150_queue_stage_stt.sql: process_stage += 'stt'
- migrations/151_queue_stage_thumbnail.sql: process_stage += 'thumbnail'
- app/models/audio_segment.py, document.py (thumbnail_path/needs_conversion)

서비스:
- services/stt/{Dockerfile, requirements.txt, server.py} — faster-whisper
  large-v3 GPU 컨테이너. /transcribe (filePath/langs/beamSize) +
  /health + /ready (cuda device_count + model_loaded). NFC/NFD 경로
  resolver (OCR 교훈).
- docker-compose.yml: stt-service 추가 (GPU 1 예약, :3300, NAS ro mount,
  stt_models volume, start_period 300s), fastapi env 에 STT_ENDPOINT.

파이프라인 (의존 §1 category):
- app/workers/stt_worker.py 신규: stage='stt' pickup → STT_ENDPOINT 호출 →
  extracted_text + audio_segments 저장. Timeout 30분.
- app/workers/thumbnail_worker.py 신규: ffmpeg 50% 지점 1장 →
  PKM/Videos/.thumbs/{id}.jpg + thumbnail_path 세팅.
  needs_conversion=true 는 skip.
- app/workers/file_watcher.py 확장: PKM/{Inbox, Recordings, Videos}
  스캔. 확장자→category, audio→stage=stt, video .mp4/.webm→
  stage=thumbnail, video .mov/.mkv/.avi→needs_conversion=true + stage
  없음. settings.roon_library_path prefix skip.
- app/workers/queue_consumer.py 확장: stt + thumbnail workers 등록,
  BATCH_SIZE(stt=1, thumbnail=3), next_stages 에 stt→[classify] 추가
  (audio 는 extract 건너뜀).
- app/Dockerfile: ffmpeg 추가 (썸네일 subprocess 용).

API (의존 §1):
- /api/audio/{id}/segments — AudioSegment ORDER BY start_s
- /api/video/{id}/thumbnail — thumbnail_path FileResponse (쿼리 토큰)
- /api/documents/{id}/file: media_types 에 audio/video mime 포함 (§2
  커밋에 이미 포함). Starlette FileResponse 가 Range 자동.
- upload_document: .mov/.mkv/.avi 웹 업로드 거부 (error_code
  unsupported_codec). NAS 드롭은 file_watcher 가 quarantine 수용.

프론트:
- AudioPlayer.svelte: HTML5 audio + 전사 세그먼트 sticky 패널 + 줄
  클릭 seek. activeIdx 하이라이트.
- VideoPlayer.svelte: HTML5 video direct play + needs_conversion 안내
  카드. poster 는 thumbnail endpoint.
- /audio (목록 grid) + /audio/[id] (플레이어)
- /video (썸네일 grid + 변환 필요 배지) + /video/[id] (플레이어)
- Sidebar.svelte: Mic/Film 아이콘 + audio/video 네비 활성, count
  배지 (§2 /stats/category-counts 재사용).

설정:
- app/core/config.py: stt_endpoint + roon_library_path.

DoD 배포 후 smoke: /ready cuda:true, 회의 mp3 transcribe, audio
extract 없이 classify 진행(queue 회귀), /audio 재생, .mp4 재생,
.mov 웹 400, .mov NAS quarantine, Sidebar 네비 + count.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-24 06:47:36 +09:00

164 lines
6.3 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.audio import router as audio_router
from api.auth import router as auth_router
from api.config import router as config_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.library import router as library_router
from api.memos import router as memos_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 api.video import router as video_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(config_router, prefix="/api/config", tags=["config"])
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(memos_router, prefix="/api/memos", tags=["memos"])
app.include_router(dashboard_router, prefix="/api/dashboard", tags=["dashboard"])
app.include_router(library_router, prefix="/api/library", tags=["library"])
app.include_router(news_router, prefix="/api/news", tags=["news"])
app.include_router(digest_router, prefix="/api/digest", tags=["digest"])
app.include_router(audio_router, prefix="/api/audio", tags=["audio"])
app.include_router(video_router, prefix="/api/video", tags=["video"])
# 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", "/api/config", "/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",
}