105 lines
3.3 KiB
YAML
105 lines
3.3 KiB
YAML
|
# M8.8 Test Query Set for Accuracy Benchmarks
|
||
|
|
# 20 diverse queries with known-relevant document IDs
|
||
|
|
# Format: query_id, query_text, relevant_doc_ids (for NDCG/Recall calculation)
|
||
|
|
|
||
|
|
queries:
|
||
|
|
- id: q1
|
||
|
|
text: "kubernetes networking configuration"
|
||
|
|
relevant_docs: ["k8s-networking-1", "k8s-networking-2", "network-config"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q2
|
||
|
|
text: "how to troubleshoot pod failures"
|
||
|
|
relevant_docs: ["pod-debugging", "troubleshoot-failures", "k8s-errors"]
|
||
|
|
query_type: "procedural"
|
||
|
|
|
||
|
|
- id: q3
|
||
|
|
text: "database connection pooling best practices"
|
||
|
|
relevant_docs: ["db-pooling", "connection-management", "performance-tuning"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q4
|
||
|
|
text: "fix memory leak in golang application"
|
||
|
|
relevant_docs: ["golang-memory", "leak-detection", "profiling"]
|
||
|
|
query_type: "troubleshooting"
|
||
|
|
|
||
|
|
- id: q5
|
||
|
|
text: "compare kubernetes and docker swarm"
|
||
|
|
relevant_docs: ["k8s-vs-swarm", "container-orchestration", "architecture-comparison"]
|
||
|
|
query_type: "comparative"
|
||
|
|
|
||
|
|
- id: q6
|
||
|
|
text: "OpenSearch tuning for search performance"
|
||
|
|
relevant_docs: ["opensearch-config", "search-optimization", "performance"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q7
|
||
|
|
text: "SSL certificate renewal automation"
|
||
|
|
relevant_docs: ["ssl-certs", "cert-renewal", "automation"]
|
||
|
|
query_type: "procedural"
|
||
|
|
|
||
|
|
- id: q8
|
||
|
|
text: "PostgreSQL replication setup"
|
||
|
|
relevant_docs: ["pg-replication", "high-availability", "backup"]
|
||
|
|
query_type: "procedural"
|
||
|
|
|
||
|
|
- id: q9
|
||
|
|
text: "service mesh traffic routing"
|
||
|
|
relevant_docs: ["service-mesh", "istio", "networking"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q10
|
||
|
|
text: "k8s resource limits and requests"
|
||
|
|
relevant_docs: ["k8s-resources", "limits", "scheduling"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q11
|
||
|
|
text: "debugging distributed tracing issues"
|
||
|
|
relevant_docs: ["tracing", "jaeger", "observability"]
|
||
|
|
query_type: "troubleshooting"
|
||
|
|
|
||
|
|
- id: q12
|
||
|
|
text: "terraform state management best practices"
|
||
|
|
relevant_docs: ["terraform-state", "infrastructure-as-code", "best-practices"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q13
|
||
|
|
text: "rate limiting API endpoints"
|
||
|
|
relevant_docs: ["rate-limiting", "api-gateway", "performance"]
|
||
|
|
query_type: "procedural"
|
||
|
|
|
||
|
|
- id: q14
|
||
|
|
text: "monitoring and alerting setup"
|
||
|
|
relevant_docs: ["monitoring", "prometheus", "alerts"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q15
|
||
|
|
text: "optimize database query performance"
|
||
|
|
relevant_docs: ["query-optimization", "indexing", "execution-plan"]
|
||
|
|
query_type: "procedural"
|
||
|
|
|
||
|
|
- id: q16
|
||
|
|
text: "microservices design patterns"
|
||
|
|
relevant_docs: ["microservices", "architecture", "patterns"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q17
|
||
|
|
text: "handle concurrent requests in api"
|
||
|
|
relevant_docs: ["concurrency", "api-design", "threading"]
|
||
|
|
query_type: "procedural"
|
||
|
|
|
||
|
|
- id: q18
|
||
|
|
text: "security hardening checklist"
|
||
|
|
relevant_docs: ["security", "hardening", "compliance"]
|
||
|
|
query_type: "factual"
|
||
|
|
|
||
|
|
- id: q19
|
||
|
|
text: "restore from database backup"
|
||
|
|
relevant_docs: ["backup", "disaster-recovery", "restore"]
|
||
|
|
query_type: "procedural"
|
||
|
|
|
||
|
|
- id: q20
|
||
|
|
text: "error handling and retry logic"
|
||
|
|
relevant_docs: ["error-handling", "resilience", "retries"]
|
||
|
|
query_type: "factual"
|