Story Crater Bot
6d5a0ba205
- Nginx ingress + TLS termination (homelab-ca) - Portainer container UI - CoreDNS internal DNS rewrites - DuckDNS DDNS updater - Ollama LLM inference - 8 project-usage guides (team reference)
93 lines
3.0 KiB
YAML
93 lines
3.0 KiB
YAML
{{- if .Values.preloadJob.enabled }}
|
|
apiVersion: batch/v1
|
|
kind: Job
|
|
metadata:
|
|
name: ollama-preload
|
|
namespace: llm
|
|
labels:
|
|
app.kubernetes.io/name: ollama-preload
|
|
spec:
|
|
backoffLimit: 3
|
|
template:
|
|
spec:
|
|
serviceAccountName: default
|
|
restartPolicy: Never
|
|
affinity:
|
|
nodeAffinity:
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
|
nodeSelectorTerms:
|
|
- matchExpressions:
|
|
- key: topology.kubernetes.io/zone
|
|
operator: In
|
|
values:
|
|
- az-a
|
|
tolerations:
|
|
- key: node-role.kubernetes.io/control-plane
|
|
operator: Equal
|
|
effect: NoSchedule
|
|
initContainers:
|
|
- name: model-cache-init
|
|
image: ollama/ollama:latest
|
|
imagePullPolicy: IfNotPresent
|
|
command:
|
|
- sh
|
|
- -c
|
|
- |
|
|
set -e
|
|
echo "Starting Ollama server to cache models..."
|
|
ollama serve &
|
|
OLLAMA_PID=$!
|
|
sleep 10
|
|
echo "Caching hot-tier models..."
|
|
{{- range .Values.preloadJob.hotModels }}
|
|
echo "Checking if {{ . }} is cached..."
|
|
if ollama ls | grep -q "{{ . }}"; then
|
|
echo "✓ {{ . }} already cached, skipping"
|
|
else
|
|
echo "Pulling {{ . }}..."
|
|
ollama pull {{ . }}
|
|
fi
|
|
{{- end }}
|
|
echo "Model cache initialization complete"
|
|
kill $OLLAMA_PID || true
|
|
wait $OLLAMA_PID 2>/dev/null || true
|
|
volumeMounts:
|
|
- name: models
|
|
mountPath: /root/.ollama
|
|
env:
|
|
- name: OLLAMA_HOST
|
|
value: "127.0.0.1:11434"
|
|
|
|
containers:
|
|
- name: cache-populate
|
|
image: curlimages/curl:latest
|
|
imagePullPolicy: IfNotPresent
|
|
command:
|
|
- sh
|
|
- -c
|
|
- |
|
|
set -e
|
|
echo "Waiting for Ollama pod to be ready..."
|
|
until curl -f http://ollama.llm.svc.cluster.local:11434/api/tags 2>/dev/null; do
|
|
echo "Ollama not ready, waiting..."
|
|
sleep 5
|
|
done
|
|
echo "Ollama is ready, populating local cache..."
|
|
{{- range .Values.preloadJob.hotModels }}
|
|
echo "Checking if {{ . }} is already cached..."
|
|
if curl -s http://ollama.llm.svc.cluster.local:11434/api/tags | grep -q "{{ . }}"; then
|
|
echo "✓ {{ . }} already cached, skipping"
|
|
else
|
|
echo "Caching {{ . }} locally..."
|
|
curl -X POST http://ollama.llm.svc.cluster.local:11434/api/pull \
|
|
-H "Content-Type: application/json" \
|
|
-d '{"name":"{{ . }}","stream":false}'
|
|
fi
|
|
{{- end }}
|
|
echo "Local cache population complete"
|
|
|
|
volumes:
|
|
- name: models
|
|
emptyDir: {}
|
|
{{- end }}
|