f005922483
검색 실패 케이스를 자동 수집해 gold dataset 시드로 활용. wiggly-weaving-puppy 플랜 Phase 0.3 산출물. 자동 수집 트리거 (3가지): - result_count == 0 → no_result - confidence < 0.5 → low_confidence - 60초 내 동일 사용자 재쿼리 → user_reformulated (이전 쿼리 기록) confidence는 Phase 0.3 휴리스틱 (top score + match_reason). Phase 2 QueryAnalyzer 도입 후 LLM 기반으로 교체 예정. 구현: - migrations/015_search_failure_logs.sql: 테이블 + 3개 인덱스 - app/models/search_failure.py: ORM - app/services/search_telemetry.py: confidence 계산 + recent 트래커 + INSERT - app/api/search.py: BackgroundTasks로 dispatch (응답 latency 영향 X) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
29 lines
1.1 KiB
Python
29 lines
1.1 KiB
Python
"""search_failure_logs 테이블 ORM — 검색 실패 자동 수집 (Phase 0.3)"""
|
|
|
|
from datetime import datetime
|
|
from typing import Any
|
|
|
|
from sqlalchemy import BigInteger, Boolean, DateTime, Float, ForeignKey, Integer, String, Text
|
|
from sqlalchemy.dialects.postgresql import JSONB
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from core.database import Base
|
|
|
|
|
|
class SearchFailureLog(Base):
|
|
__tablename__ = "search_failure_logs"
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
|
|
query: Mapped[str] = mapped_column(Text, nullable=False)
|
|
user_id: Mapped[int | None] = mapped_column(
|
|
BigInteger, ForeignKey("users.id", ondelete="SET NULL")
|
|
)
|
|
created_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), default=datetime.now, nullable=False
|
|
)
|
|
result_count: Mapped[int] = mapped_column(Integer, nullable=False)
|
|
confidence: Mapped[float | None] = mapped_column(Float)
|
|
failure_reason: Mapped[str] = mapped_column(String(30), nullable=False)
|
|
context: Mapped[dict[str, Any] | None] = mapped_column(JSONB)
|
|
reviewed: Mapped[bool] = mapped_column(Boolean, default=False, nullable=False)
|