mrleo1nidandClaude Opus 5.5
ef29b85320
- migration 00006: track features and embeddings (pgvector, HNSW), analysis queue filled by a trigger on new tracks, wave sessions and impressions, recommender profiles, model versions - analyzer basic-1 (ADR-014): ffmpeg decode, three 30 s excerpts, 256-d timbre/rhythm embedding, tempo by onset autocorrelation, key, loudness, energy, danceability, acousticness, intro length; worker with SKIP LOCKED claims, retries and re-analysis on version change - wave engine v1: candidates (session/taste similarity, fresh, liked artists, rediscover, popular, exploration, seed), filters (dislikes, played in 3 h, already served), heuristic score, activity and mood fit from contexts.yaml with relaxing thresholds, MMR with one track per artist, exploration share, session vector updated by reactions and a change of course after three skips - POST /internal/wave/batch with the catalog index cached in memory and the session kept in Redis Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
71 lines
2.9 KiB
Python
71 lines
2.9 KiB
Python
"""FastAPI-приложение внутреннего API рекомендаций."""
|
|
|
|
import asyncio
|
|
import hmac
|
|
import logging
|
|
from collections.abc import Awaitable, Callable
|
|
from typing import Annotated
|
|
|
|
from fastapi import Depends, FastAPI, Header, HTTPException, status
|
|
from fastapi.responses import JSONResponse
|
|
|
|
from pipu_rec.settings import Settings
|
|
from pipu_rec.wave.engine import MODEL_VER
|
|
from pipu_rec.wave.service import BatchRequest, BatchResponse, WaveService
|
|
|
|
Check = Callable[[], Awaitable[None]]
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
CHECK_TIMEOUT_S = 2.0
|
|
|
|
|
|
def create_app(
|
|
settings: Settings, checks: dict[str, Check] | None = None, wave: WaveService | None = None
|
|
) -> FastAPI:
|
|
app = FastAPI(title="pipu-recommender", version=settings.version, docs_url=None, redoc_url=None)
|
|
checks = checks or {}
|
|
|
|
def require_token(authorization: Annotated[str, Header()] = "") -> None:
|
|
scheme, _, token = authorization.partition(" ")
|
|
expected = settings.internal_token
|
|
if scheme != "Bearer" or not expected or not hmac.compare_digest(token, expected):
|
|
raise HTTPException(status.HTTP_401_UNAUTHORIZED, detail="auth.invalid_internal_token")
|
|
|
|
@app.get("/healthz")
|
|
async def healthz() -> dict[str, str]:
|
|
return {"status": "ok"}
|
|
|
|
async def run_check(name: str, check: Check) -> str:
|
|
try:
|
|
await asyncio.wait_for(check(), CHECK_TIMEOUT_S)
|
|
except Exception as exc:
|
|
log.warning("readiness check %s failed: %r", name, exc)
|
|
return "fail"
|
|
return "ok"
|
|
|
|
@app.get("/readyz")
|
|
async def readyz() -> JSONResponse:
|
|
# Проверки параллельные, каждая ограничена таймаутом; причину ошибки пишем только в лог.
|
|
names = list(checks)
|
|
outcomes = await asyncio.gather(*(run_check(n, checks[n]) for n in names))
|
|
results = dict(zip(names, outcomes, strict=True))
|
|
healthy = all(v == "ok" for v in results.values())
|
|
return JSONResponse(
|
|
{"status": "ok" if healthy else "degraded", "checks": results},
|
|
status_code=status.HTTP_200_OK if healthy else status.HTTP_503_SERVICE_UNAVAILABLE,
|
|
)
|
|
|
|
@app.get("/internal/status", dependencies=[Depends(require_token)])
|
|
async def internal_status() -> dict[str, object]:
|
|
return {"version": settings.version, "models": [], "ranker": MODEL_VER}
|
|
|
|
@app.post("/internal/wave/batch", dependencies=[Depends(require_token)])
|
|
async def wave_batch(req: BatchRequest) -> BatchResponse:
|
|
if wave is None:
|
|
raise HTTPException(status.HTTP_503_SERVICE_UNAVAILABLE, detail="wave.unavailable")
|
|
# Сборка — numpy и синхронные запросы к БД: в пуле потоков, чтобы не блокировать цикл событий.
|
|
return await asyncio.to_thread(wave.batch, req)
|
|
|
|
return app
|