feat: Knowledge Base RAG 시스템 + 채팅 LLM 개선 (Phase 0~5 완료)

- KB RAG 전체 파이프라인: 업로드, 파싱(xlsx/pdf/docx/text), 임베딩, Qdrant 인덱싱
- KB 관리 UI(14번 탭): 로그인, 문서 목록, 업로드, 삭제, 재인덱스
- OllamaController: 한글 시스템 프롬프트, plant_context.md 외부 파일화, SSE tool_start/tool_result 이벤트
- 프론트: 툴 실행 카드, KB 인용 링크, 표 자동 렌더, 추천 질문 칩
- nl2sql_worker: history_table.recorded_at 사용, tag_metadata 응답 개선
- DB: KB 테이블 5개 DDL + 시드, pgcrypto 확장

mcp-server/worker/nl2sql_worker.py

@@ -238,15 +238,14 @@ async def _query_pv_history(tag_names: list[str], time_from: str, time_to: str,
     conn = _get_db_connection()
     try:
         with conn.cursor() as cur:
-            # TimescaleDB의 time_bucket 함수 사용
             cur.execute(
                 """
-                SELECT time_bucket('1 min', ts) AS time, tag_name, value
-                FROM realtime_table
-                WHERE tag_name = ANY(%s)
-                  AND ts >= %s
-                  AND ts <= %s
-                ORDER BY time DESC
+                SELECT recorded_at AS time, tagname AS tag_name, value
+                FROM history_table
+                WHERE tagname = ANY(%s)
+                  AND recorded_at >= %s
+                  AND recorded_at <= %s
+                ORDER BY recorded_at DESC, tagname
                 LIMIT %s
                 """,
                 (tag_names, time_from, time_to, limit),
@@ -272,17 +271,25 @@ async def _get_tag_metadata(query: str, limit: int = 10) -> str:
         with conn.cursor() as cur:
             cur.execute(
                 """
-                SELECT DISTINCT tag_name, unit, description
+                SELECT tagname, livevalue, timestamp, node_id
                 FROM realtime_table
-                WHERE tag_name ILIKE %s
-                ORDER BY tag_name
+                WHERE tagname ILIKE %s
+                ORDER BY tagname
                 LIMIT %s
                 """,
                 (f"%{query}%", limit),
             )
-            columns = ["tag_name", "unit", "description"]
+            columns = ["tag_name", "current_value", "last_updated", "node_id"]
             rows = cur.fetchall()
-            data = [dict(zip(columns, row)) for row in rows]
+            data = [
+                {
+                    "tag_name": r[0],
+                    "current_value": r[1],
+                    "last_updated": r[2].isoformat() if r[2] else None,
+                    "node_id": r[3],
+                }
+                for r in rows
+            ]
             return {
                 "success": True,
                 "query": query,