feat: Monitoring & Observability (Prometheus + Grafana)

[maximilien]

Summary

Deploy comprehensive monitoring and observability for production RAG systems.

Scope

• Deploy Prometheus for metrics collection
• Deploy Grafana for dashboards
• Create Milvus health dashboard
• Create ingestion metrics dashboard
• Create query performance dashboard
• Add resource usage monitoring
• Configure alerting rules
• Test alerting on failures

Commands

weave stack monitor
weave stack metrics export metrics.json

Success Criteria

• Monitoring dashboards display metrics
• Alerts trigger on failures
• Monitoring setup guide complete

Priority: Phase 2 - Week 2

Estimated: 2-3 days
Assignee: TBD (DevOps/monitoring experience preferred)

Related

Production feature - critical for production operations.