a2e3260bb1
Was defaulting to plain Ollama with gemma3:270m for every request - no LLM_PROVIDER or LITELLM_* env vars were set. LiteLLM is already deployed with purpose-built model aliases per task (apps/litellm/base/configmap.yaml); this wires ai-assistant to use it.
66 lines
2 KiB
YAML
66 lines
2 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: nxtgauge-ai-assistant
|
|
labels:
|
|
app: nxtgauge-ai-assistant
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: nxtgauge-ai-assistant
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: nxtgauge-ai-assistant
|
|
spec:
|
|
imagePullSecrets:
|
|
- name: ghcr-regcred
|
|
containers:
|
|
- name: ai-assistant
|
|
image: registry.nxtgauge.com/nxtgauge-ai-assistant:2f999dfe95a48ea4090a90519dc3950f1e729924
|
|
imagePullPolicy: Always
|
|
ports:
|
|
- containerPort: 8080
|
|
name: http
|
|
env:
|
|
- name: APP_HOST
|
|
value: "0.0.0.0"
|
|
- name: APP_PORT
|
|
value: "8080"
|
|
- name: OLLAMA_BASE_URL
|
|
value: "http://ollama.nxtgauge-ai.svc.cluster.local:11434"
|
|
- name: OLLAMA_CHAT_MODEL
|
|
value: "gemma3:270m"
|
|
- name: OLLAMA_EMBED_MODEL
|
|
value: "nomic-embed-text"
|
|
- name: LLM_PROVIDER
|
|
value: "litellm"
|
|
- name: LITELLM_BASE_URL
|
|
value: "http://litellm.nxtgauge-ai.svc.cluster.local:4000"
|
|
- name: LITELLM_MODEL
|
|
value: "askash-main"
|
|
- name: LITELLM_API_KEY
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: litellm-secrets
|
|
key: LITELLM_MASTER_KEY
|
|
- name: NXTGAUGE_USERS_URL
|
|
value: "http://nxtgauge-rust-users:9101"
|
|
- name: AI_SERVICE_KEY
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: nxtgauge-ai-assistant-secrets
|
|
key: ai-service-key
|
|
- name: JWT_SECRET
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: nxtgauge-ai-assistant-secrets
|
|
key: jwt-secret
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
limits:
|
|
cpu: 1000m
|
|
memory: 512Mi
|