fix(search): text-leg 본문 스코어링 2000자 절단 + bge-m3 keep_alive 로 검색 latency 개선

코퍼스 ~52배 성장(코드 가정 765 → 실제 40k docs) 후 search_text ORDER BY 가
후보 행마다 extracted_text(평균 3.7KB·최대 1.6MB) 전체에 similarity() +
to_tsvector() 재토큰화를 재연산 → broad/영어 쿼리 text_ms 최대 4960ms.
scoring/match_reason 의 extracted_text 를 left(...,2000) 으로 절단(후보 CTE 의
FTS 매칭은 전체 본문 유지 → recall 불변). embed() 요청에 keep_alive:-1 추가로
ollama bge-m3 GPU 상주 → sparse 검색의 cold reload(~6s) 제거.

검증(snapshot freeze docs 43958/chunks 195671, 51 case, eval-version both):
- graded NDCG 0.575 → 0.575 (±0.000, 전 카테고리 byte-identical)
- Recall g>=2 0.691 / g>=3 0.739 불변, v0.1 NDCG/Recall/Top-3 불변
- latency p50 760→586ms (-23%) / p95 5230→832ms (-84%)
- EXPLAIN 단일쿼리: V0 4917ms → left(2000) 285ms (17x)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

app/ai/client.py

@@ -264,7 +264,7 @@ class AIClient:
         """벡터 임베딩 — GPU 서버 전용"""
         response = await self._http.post(
             self.ai.embedding.endpoint,
-            json={"model": self.ai.embedding.model, "prompt": text},
+            json={"model": self.ai.embedding.model, "prompt": text, "keep_alive": -1},  # bge-m3 GPU 상주(홈랩 sparse 검색 cold reload ~6s 방지)
         )
         response.raise_for_status()
         return response.json()["embedding"]

app/services/search/retrieval_service.py

@@ -361,7 +361,7 @@ async def search_text(
                        + similarity(coalesce(d.ai_tags::text, ''), :q) * 2.5
                        + similarity(coalesce(d.user_note, ''), :q) * 2.0
                        + similarity(coalesce(d.ai_summary, ''), :q) * 1.5
-                       + similarity(coalesce(d.extracted_text, ''), :q) * 1.0
+                       + similarity(left(coalesce(d.extracted_text, ''), 2000), :q) * 1.0
                        -- FTS 보너스 (idx_documents_fts_full 활용)
                        + coalesce(ts_rank(
                            to_tsvector('simple',
@@ -369,7 +369,7 @@ async def search_text(
                                coalesce(d.ai_tags::text, '') || ' ' ||
                                coalesce(d.ai_summary, '') || ' ' ||
                                coalesce(d.user_note, '') || ' ' ||
-                               coalesce(d.extracted_text, '')
+                               left(coalesce(d.extracted_text, ''), 2000)
                            ),
                            plainto_tsquery('simple', :q)
                        ), 0) * 2.0
@@ -380,7 +380,7 @@ async def search_text(
                        WHEN similarity(coalesce(d.ai_tags::text, ''), :q) >= 0.3 THEN 'tags'
                        WHEN similarity(coalesce(d.user_note, ''), :q) >= 0.3 THEN 'note'
                        WHEN similarity(coalesce(d.ai_summary, ''), :q) >= 0.3 THEN 'summary'
-                       WHEN similarity(coalesce(d.extracted_text, ''), :q) >= 0.3 THEN 'content'
+                       WHEN similarity(left(coalesce(d.extracted_text, ''), 2000), :q) >= 0.3 THEN 'content'
                        ELSE 'fts'
                    END AS match_reason,
                    d.material_type, d.jurisdiction, d.published_date