Phase 1 of the AI architecture doc ("Improve Generation Quality") —
qwen3:4b and qwen3:8b were already pulled onto the Ollama PVC, and
apps/litellm/base/configmap.yaml already had the correct model_list
mapping every feature alias to them instead of gemma3:270m. Neither
was actually in effect:
1. apps/litellm was never included in
clusters/production/kustomization.yaml, so it was only ever
deployed by a one-off manual `kubectl apply` and has been
completely outside GitOps ever since (same root cause as the
ai-guard registry drift found earlier). Added it to the root
kustomization. Corrected its image reference from
registry.nxtgauge.com/litellm:latest (doesn't appear to exist) to
ghcr.io/berriai/litellm:latest, matching what's actually running
live — adopting this file without that fix would have broken a
working deployment the moment Flux started managing it.
2. apps/ollama/base/deployment.yaml's memory limit (1500Mi) was too
small to ever load qwen3:4b (~2.5GB) or qwen3:8b (~5.2GB) — every
model alias in the (also-never-applied) LiteLLM config was
therefore unusable regardless of what it was named. Raised to
4 CPU / 8Gi limit (node has 16GB total, was at ~26% memory use) and
added OLLAMA_KEEP_ALIVE=30m so a loaded model survives the gaps
between bursty feature requests instead of reloading from disk on
every first call after 5+ minutes idle.
- Add namespace, PVC, deployment, service, and kustomization for Ollama
- ClusterIP only (internal), no ingress
- 10Gi PVC mounted at /root/.ollama
- Resource limits: 700Mi-1500Mi memory, 500m-1000m CPU
- Add ArgoCD Application CR for ollama
- Update backend configmap with OLLAMA_BASE_URL and OLLAMA_CHAT_MODEL
