음성 재생과 운영 배포 정리

apps/api/app/routes/kb.py

@@ -22,7 +22,7 @@ from pydantic import BaseModel, Field
 
 from ..db import acquire, get_pool
 from ..deps import AIView, Principal, Role, require_role
-from ..services import rag
+from ..services import live_coach, rag
 
 router = APIRouter(prefix="/kb", tags=["kb"])
 
@@ -104,6 +104,24 @@ class IndexResponse(BaseModel):
     degraded: bool = False
 
 
+class LiveCoachSourcePackSyncItem(BaseModel):
+    source_id: str
+    doc_id: Optional[int]
+    chunks_indexed: int
+    skipped_unchanged: bool
+    embedded: bool
+    degraded: bool = False
+
+
+class LiveCoachSourcePackSyncResponse(BaseModel):
+    sources_upserted: int
+    chunks_indexed: int
+    skipped_unchanged: int
+    embedded: bool
+    degraded: bool = False
+    items: list[LiveCoachSourcePackSyncItem] = Field(default_factory=list)
+
+
 # ── 헬퍼: rag.NotConfigured → 503 ───────────────────────
 def _to_chunk_out(c: rag.RetrievedChunk) -> ChunkOut:
     return ChunkOut(
@@ -222,6 +240,7 @@ async def eval_grounding(body: KBSearchRequest) -> KBSearchResponse:
                 query=body.query,
                 k=body.k,
                 kinds=body.kb_kind,
+                source_ids=body.source_id,
                 rerank=body.rerank,
             )
             try:
@@ -319,3 +338,80 @@ async def index_document(
         embedded=result.embedded,
         degraded=result.degraded,
     )
+
+
+@router.post(
+    "/live-coach/source-packs/sync",
+    response_model=LiveCoachSourcePackSyncResponse,
+    status_code=status.HTTP_202_ACCEPTED,
+)
+async def sync_live_coach_source_packs(
+    principal: Annotated[Principal, Depends(require_role(Role.ADMIN))],
+) -> LiveCoachSourcePackSyncResponse:
+    """허가된 라이브 코칭 source pack을 kb.source/kb.chunk RAG 색인에 적재한다.
+
+    로컬 `data/kb/live_coaching_*.json`은 UI 즉시 코칭의 기본 근거이고, 이 경로는 같은 자료를
+    evaluator RAG 검색에도 올린다. source row를 먼저 upsert한 뒤 content_hash 기반 증분 색인을
+    수행한다. 임베딩 모델 미가용 시 BM25-only degraded 색인으로 이어진다.
+    """
+    source_rows = live_coach.build_rag_source_rows()
+    index_payloads = live_coach.build_rag_index_payloads()
+    if not source_rows or not index_payloads:
+        raise HTTPException(
+            status.HTTP_422_UNPROCESSABLE_ENTITY,
+            detail="live coach source packs are empty",
+        )
+
+    items: list[LiveCoachSourcePackSyncItem] = []
+    source_row_by_id = {row["source_id"]: row for row in source_rows}
+    try:
+        async with acquire() as conn:
+            for row in source_rows:
+                await conn.execute(
+                    """
+                    INSERT INTO kb.source
+                      (source_id, title, kb_kind, license_class, origin_path, citation, external_llm_ok)
+                    VALUES ($1, $2, $3, $4, $5, $6, $7)
+                    ON CONFLICT (source_id) DO UPDATE SET
+                      title = EXCLUDED.title,
+                      kb_kind = EXCLUDED.kb_kind,
+                      license_class = EXCLUDED.license_class,
+                      origin_path = EXCLUDED.origin_path,
+                      citation = EXCLUDED.citation,
+                      external_llm_ok = EXCLUDED.external_llm_ok
+                    """,
+                    row["source_id"],
+                    row["title"],
+                    row["kb_kind"],
+                    row["license_class"],
+                    row["origin_path"],
+                    row["citation"],
+                    row["external_llm_ok"],
+                )
+            for payload in index_payloads:
+                if payload["source_id"] not in source_row_by_id:
+                    continue
+                result = await rag.index_document(conn, rag.IndexRequest(**payload))
+                items.append(
+                    LiveCoachSourcePackSyncItem(
+                        source_id=payload["source_id"],
+                        doc_id=result.doc_id,
+                        chunks_indexed=result.chunks_indexed,
+                        skipped_unchanged=result.skipped_unchanged,
+                        embedded=result.embedded,
+                        degraded=result.degraded,
+                    )
+                )
+    except rag.NotConfigured as exc:
+        raise HTTPException(status.HTTP_503_SERVICE_UNAVAILABLE, detail=f"RAG not configured: {exc}") from exc
+    except RuntimeError as exc:
+        raise HTTPException(status.HTTP_503_SERVICE_UNAVAILABLE, detail=f"DB not ready: {exc}") from exc
+
+    return LiveCoachSourcePackSyncResponse(
+        sources_upserted=len(source_rows),
+        chunks_indexed=sum(item.chunks_indexed for item in items),
+        skipped_unchanged=sum(1 for item in items if item.skipped_unchanged),
+        embedded=all(item.embedded for item in items) if items else False,
+        degraded=any(item.degraded for item in items),
+        items=items,
+    )