6dc03c9a55
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
1. k8s/argocd/awoooi-prod-app.yaml:
移除 Deployment image ignoreDifferences
- 原設計造成 CD 更新 kustomization.yaml 後 ArgoCD 不更新 image
- 修復後 GitOps 閉環恢復正常
2. scripts/cold_start_playbooks.py:
ADR-073 Phase 1 Step 8 — 生成 15 個基礎 Playbook (K8s/Docker/DB/Infra)
執行結果: Playbooks 0 → 15
3. scripts/batch_vectorize_km.py:
ADR-073 Phase 1 Step 9 — 批次向量化 KM
執行結果: 711/713 embedding IS NOT NULL
Phase 1 全部完成，飛輪已解封：
- Pod 運行 105998d（含 8be87b0 所有修復）
- debounce 30min + alertname NULL 修復 + _collect_mcp_context 啟用
- 15 Playbooks + 711 KM 向量化
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
88 lines
2.7 KiB
Python
88 lines
2.7 KiB
Python
"""
|
||
batch_vectorize_km.py — ADR-073 Phase 1 Step 9
|
||
|
||
批次向量化所有 embedding IS NULL 的 KnowledgeEntry。
|
||
|
||
執行方式（在 K8s Pod 內）：
|
||
# 透過 AWOOOI API embed-all endpoint
|
||
python3 scripts/batch_vectorize_km.py --via-api
|
||
|
||
# 直接呼叫 Service（需在 Pod 內）
|
||
python3 scripts/batch_vectorize_km.py
|
||
|
||
2026-04-12 Claude Sonnet 4.6 (ADR-073 Phase 1)
|
||
"""
|
||
import asyncio
|
||
import asyncpg
|
||
import os
|
||
import sys
|
||
import httpx
|
||
|
||
VIA_API = "--via-api" in sys.argv
|
||
DRY_RUN = "--dry-run" in sys.argv
|
||
DATABASE_URL = os.environ.get("DATABASE_URL", "").replace("postgresql+asyncpg://", "postgresql://")
|
||
API_BASE = os.environ.get("API_BASE", "http://localhost:8000")
|
||
|
||
|
||
async def check_status():
|
||
"""確認需要向量化的數量"""
|
||
conn = await asyncpg.connect(DATABASE_URL)
|
||
total = await conn.fetchval("SELECT count(*) FROM knowledge_entries")
|
||
null_emb = await conn.fetchval("SELECT count(*) FROM knowledge_entries WHERE embedding IS NULL")
|
||
await conn.close()
|
||
return total, null_emb
|
||
|
||
|
||
async def via_api():
|
||
"""呼叫 /api/v1/knowledge/embed-all endpoint"""
|
||
print(f"呼叫 {API_BASE}/api/v1/knowledge/embed-all ...")
|
||
async with httpx.AsyncClient(timeout=300.0) as client:
|
||
resp = await client.post(f"{API_BASE}/api/v1/knowledge/embed-all")
|
||
if resp.status_code == 200:
|
||
result = resp.json()
|
||
print(f"✅ API 回應: {result}")
|
||
else:
|
||
print(f"❌ API 錯誤 {resp.status_code}: {resp.text}")
|
||
|
||
|
||
async def via_service():
|
||
"""直接呼叫 KnowledgeService.embed_all_entries()"""
|
||
sys.path.insert(0, "/app")
|
||
from src.services.knowledge_service import get_knowledge_service
|
||
|
||
service = get_knowledge_service()
|
||
result = await service.embed_all_entries()
|
||
print(f"✅ 向量化結果: {result}")
|
||
|
||
|
||
async def main():
|
||
if not DATABASE_URL and not VIA_API:
|
||
print("ERROR: DATABASE_URL 未設定，請加 --via-api 使用 API 模式")
|
||
sys.exit(1)
|
||
|
||
if not VIA_API and DATABASE_URL:
|
||
total, null_emb = await check_status()
|
||
print(f"knowledge_entries: total={total}, embedding IS NULL={null_emb}")
|
||
if null_emb == 0:
|
||
print("✅ 所有條目已向量化，無需執行")
|
||
return
|
||
|
||
if DRY_RUN:
|
||
print(f"[DRY RUN] 將向量化 {null_emb} 筆 KM 條目")
|
||
print("使用 --via-api 透過 API 執行，或不加參數直接執行 Service")
|
||
return
|
||
|
||
if VIA_API:
|
||
await via_api()
|
||
else:
|
||
await via_service()
|
||
|
||
# 完成後確認
|
||
if DATABASE_URL:
|
||
total, null_emb = await check_status()
|
||
print(f"\n完成後狀態: total={total}, embedding IS NULL={null_emb}, vectorized={total - null_emb}")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
asyncio.run(main())
|