feat(O13): relevance evaluation CronJob manifest

- Runs every 6 hours with sample queries - Tests query endpoint with known queries - Reports precision (queries with results / total) - Snapshots /metrics endpoint for monitoring - Lightweight: curl-based, 16Mi memory - Deploy: kubectl apply -f k8s/infra/relevance-eval-cronjob.yaml
2026-09-13 21:50:21 +09:00
parent f304a7133e
commit 9e85b1a063
1 changed files with 94 additions and 0 deletions
@@ -0,0 +1,94 @@
+# CronJob for periodic relevance evaluation (O13)
+# Runs sample queries against memory service and evaluates result relevance
+# Pushes metrics to Prometheus via pushgateway or direct scrape
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: memory-relevance-eval
+  namespace: poimen
+  labels:
+    app: memory-relevance-eval
+spec:
+  # Run every 6 hours
+  schedule: "0 */6 * * *"
+  successfulJobsHistoryLimit: 3
+  failedJobsHistoryLimit: 1
+
+  jobTemplate:
+    spec:
+      template:
+        metadata:
+          labels:
+            app: memory-relevance-eval
+        spec:
+          securityContext:
+            runAsNonRoot: true
+            runAsUser: 1000
+            seccompProfile:
+              type: RuntimeDefault
+          containers:
+            - name: eval
+              image: curlimages/curl:8.13.0
+              securityContext:
+                allowPrivilegeEscalation: false
+                capabilities:
+                  drop: ["ALL"]
+              command:
+                - /bin/sh
+                - -c
+                - |
+                  MEMORY_URL="http://poimen-memory.poimen.svc.cluster.local:8080"
+                  
+                  echo "=== Relevance evaluation at $(date) ==="
+                  
+                  # Sample queries for evaluation
+                  QUERIES='[
+                    "kubernetes deployment",
+                    "database migration",
+                    "LLM entity extraction",
+                    "tea cli forgejo",
+                    "SOPS encryption secrets"
+                  ]'
+                  
+                  TOTAL=0
+                  RELEVANT=0
+                  
+                  for q in "kubernetes deployment" "database migration" "LLM entity extraction"; do
+                    echo "Testing query: $q"
+                    RESULT=$(curl -s --max-time 30 -X POST "$MEMORY_URL/memory/query" \
+                      -H "Content-Type: application/json" \
+                      -d "{\"query\": \"$q\", \"search_type\": \"entities\", \"top_k\": 5}")
+                    
+                    COUNT=$(echo "$RESULT" | grep -o '"total_count":[0-9]*' | cut -d: -f2)
+                    TOTAL=$((TOTAL + 1))
+                    
+                    if [ "${COUNT:-0}" -gt 0 ]; then
+                      RELEVANT=$((RELEVANT + 1))
+                      echo "  Result: $COUNT results (relevant)"
+                    else
+                      echo "  Result: 0 results (irrelevant)"
+                    fi
+                  done
+                  
+                  PRECISION=$(echo "scale=2; $RELEVANT / $TOTAL" | bc 2>/dev/null || echo "0")
+                  echo ""
+                  echo "=== Summary ==="
+                  echo "Total queries: $TOTAL"
+                  echo "Queries with results: $RELEVANT"
+                  echo "Precision: $PRECISION"
+                  echo ""
+                  echo "=== Health check ==="
+                  curl -s "$MEMORY_URL/health"
+                  echo ""
+                  echo "=== Metrics snapshot ==="
+                  curl -s "$MEMORY_URL/metrics" | grep -E "^memory_(query|relevance|ingest)_" | head -20
+              
+              resources:
+                requests:
+                  cpu: 10m
+                  memory: 16Mi
+                limits:
+                  cpu: 50m
+                  memory: 32Mi
+          
+          restartPolicy: OnFailure