hyungi/hyungi_document_server
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(search): Phase 1.1a 모듈 분리 — services/search/ 디렉토리

Browse Source 
검색 로직을 services/search/* 모듈로 분리. trigram 도입은 Phase 1.2 인덱스와 함께.

신규:
- services/search/{__init__,retrieval_service,rerank_service,query_analyzer,evidence_service,synthesis_service}.py
- retrieval_service는 search_text/search_vector 이전 (ILIKE 동작 그대로)
- 나머지는 Phase 1.3/2/3 placeholder

이동:
- services/search_fusion.py → services/search/fusion_service.py (R100)

수정:
- api/search.py — thin orchestrator로 축소 (251줄 → 178줄)

동작 변경 없음 — 구조만 분리. 회귀 검증 후 Phase 1.2 진입.
This commit is contained in:
Hyungi Ahn
2026-04-07 13:46:04 +09:00
parent e0f45f9ce0
commit a4eb71d368
8 changed files with 153 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

93
app/api/search.py
View File

@@ -1,19 +1,22 @@
"""하이브리드 검색 API — FTS + ILIKE + 벡터 (필드별 가중치)"""
"""하이브리드 검색 API — orchestrator (Phase 1.1: thin endpoint).
retrieval / fusion / rerank 등 실제 로직은 services/search/* 모듈로 분리.
이 파일은 mode 분기, 응답 직렬화, debug 응답 구성, BackgroundTask dispatch만 담당.
"""
import time
from typing import Annotated
from fastapi import APIRouter, BackgroundTasks, Depends, Query
from pydantic import BaseModel
from sqlalchemy import text
from sqlalchemy.ext.asyncio import AsyncSession
from ai.client import AIClient
from core.auth import get_current_user
from core.database import get_session
from core.utils import setup_logger
from models.user import User
from services.search_fusion import DEFAULT_FUSION, get_strategy, normalize_display_scores
from services.search.fusion_service import DEFAULT_FUSION, get_strategy, normalize_display_scores
from services.search.retrieval_service import search_text, search_vector
from services.search_telemetry import (
compute_confidence,
compute_confidence_hybrid,
@@ -102,19 +105,19 @@ async def search(
if mode == "vector":
t0 = time.perf_counter()
vector_results = await _search_vector(session, q, limit)
vector_results = await search_vector(session, q, limit)
timing["vector_ms"] = (time.perf_counter() - t0) * 1000
if not vector_results:
notes.append("vector_search_returned_empty (AI client error or no embeddings)")
results = vector_results
else:
t0 = time.perf_counter()
text_results = await _search_text(session, q, limit)
text_results = await search_text(session, q, limit)
timing["text_ms"] = (time.perf_counter() - t0) * 1000
if mode == "hybrid":
t1 = time.perf_counter()
vector_results = await _search_vector(session, q, limit)
vector_results = await search_vector(session, q, limit)
timing["vector_ms"] = (time.perf_counter() - t1) * 1000
if not vector_results:
notes.append("vector_search_returned_empty — text-only fallback")
@@ -172,79 +175,3 @@ async def search(
mode=mode,
debug=debug_obj,
)
async def _search_text(session: AsyncSession, query: str, limit: int) -> list[SearchResult]:
"""FTS + ILIKE — 필드별 가중치 적용"""
result = await session.execute(
text("""
SELECT id, title, ai_domain, ai_summary, file_format,
left(extracted_text, 200) AS snippet,
(
-- title 매칭 (가중치 최고)
CASE WHEN coalesce(title, '') ILIKE '%%' || :q || '%%' THEN 3.0 ELSE 0 END
-- ai_tags 매칭 (가중치 높음)
+ CASE WHEN coalesce(ai_tags::text, '') ILIKE '%%' || :q || '%%' THEN 2.5 ELSE 0 END
-- user_note 매칭 (가중치 높음)
+ CASE WHEN coalesce(user_note, '') ILIKE '%%' || :q || '%%' THEN 2.0 ELSE 0 END
-- ai_summary 매칭 (가중치 중상)
+ CASE WHEN coalesce(ai_summary, '') ILIKE '%%' || :q || '%%' THEN 1.5 ELSE 0 END
-- extracted_text 매칭 (가중치 중간)
+ CASE WHEN coalesce(extracted_text, '') ILIKE '%%' || :q || '%%' THEN 1.0 ELSE 0 END
-- FTS 점수 (보너스)
+ coalesce(ts_rank(
to_tsvector('simple', coalesce(title, '') || ' ' || coalesce(extracted_text, '')),
plainto_tsquery('simple', :q)
), 0) * 2.0
) AS score,
-- match reason
CASE
WHEN coalesce(title, '') ILIKE '%%' || :q || '%%' THEN 'title'
WHEN coalesce(ai_tags::text, '') ILIKE '%%' || :q || '%%' THEN 'tags'
WHEN coalesce(user_note, '') ILIKE '%%' || :q || '%%' THEN 'note'
WHEN coalesce(ai_summary, '') ILIKE '%%' || :q || '%%' THEN 'summary'
WHEN coalesce(extracted_text, '') ILIKE '%%' || :q || '%%' THEN 'content'
ELSE 'fts'
END AS match_reason
FROM documents
WHERE deleted_at IS NULL
AND (coalesce(title, '') ILIKE '%%' || :q || '%%'
OR coalesce(ai_tags::text, '') ILIKE '%%' || :q || '%%'
OR coalesce(user_note, '') ILIKE '%%' || :q || '%%'
OR coalesce(ai_summary, '') ILIKE '%%' || :q || '%%'
OR coalesce(extracted_text, '') ILIKE '%%' || :q || '%%'
OR to_tsvector('simple', coalesce(title, '') || ' ' || coalesce(extracted_text, ''))
@@ plainto_tsquery('simple', :q))
ORDER BY score DESC
LIMIT :limit
"""),
{"q": query, "limit": limit},
)
return [SearchResult(**row._mapping) for row in result]
async def _search_vector(session: AsyncSession, query: str, limit: int) -> list[SearchResult]:
"""벡터 유사도 검색 (코사인 거리)"""
try:
client = AIClient()
query_embedding = await client.embed(query)
await client.close()
except Exception:
return []
result = await session.execute(
text("""
SELECT id, title, ai_domain, ai_summary, file_format,
(1 - (embedding <=> cast(:embedding AS vector))) AS score,
left(extracted_text, 200) AS snippet,
'vector' AS match_reason
FROM documents
WHERE embedding IS NOT NULL AND deleted_at IS NULL
ORDER BY embedding <=> cast(:embedding AS vector)
LIMIT :limit
"""),
{"embedding": str(query_embedding), "limit": limit},
)
return [SearchResult(**row._mapping) for row in result]