100 lines
2.9 KiB
YAML
100 lines
2.9 KiB
YAML
|
apiVersion: apps/v1
|
||
|
|
kind: Deployment
|
||
|
|
metadata:
|
||
|
|
name: model-catalog
|
||
|
|
namespace: agentgateway-system
|
||
|
|
labels:
|
||
|
|
app.kubernetes.io/name: model-catalog
|
||
|
|
app.kubernetes.io/instance: agentgateway
|
||
|
|
app.kubernetes.io/part-of: agentgateway
|
||
|
|
app.kubernetes.io/version: "0.1.1"
|
||
|
|
spec:
|
||
|
|
replicas: 2
|
||
|
|
strategy:
|
||
|
|
type: RollingUpdate
|
||
|
|
rollingUpdate:
|
||
|
|
maxSurge: 0
|
||
|
|
maxUnavailable: 1
|
||
|
|
selector:
|
||
|
|
matchLabels:
|
||
|
|
app.kubernetes.io/name: model-catalog
|
||
|
|
app.kubernetes.io/instance: agentgateway
|
||
|
|
template:
|
||
|
|
metadata:
|
||
|
|
labels:
|
||
|
|
app.kubernetes.io/name: model-catalog
|
||
|
|
app.kubernetes.io/instance: agentgateway
|
||
|
|
app.kubernetes.io/part-of: agentgateway
|
||
|
|
app.kubernetes.io/version: "0.1.1"
|
||
|
|
spec:
|
||
|
|
automountServiceAccountToken: true
|
||
|
|
serviceAccountName: model-catalog
|
||
|
|
securityContext:
|
||
|
|
runAsNonRoot: true
|
||
|
|
runAsUser: 65532
|
||
|
|
runAsGroup: 65532
|
||
|
|
seccompProfile:
|
||
|
|
type: RuntimeDefault
|
||
|
|
topologySpreadConstraints:
|
||
|
|
- maxSkew: 1
|
||
|
|
topologyKey: kubernetes.io/hostname
|
||
|
|
whenUnsatisfiable: DoNotSchedule
|
||
|
|
labelSelector:
|
||
|
|
matchLabels:
|
||
|
|
app.kubernetes.io/name: model-catalog
|
||
|
|
app.kubernetes.io/instance: agentgateway
|
||
|
|
containers:
|
||
|
|
- name: catalog
|
||
|
|
image: registry.quorate.internal/quorate/agentgateway-catalog:0.1.1@sha256:919e63ef02b9d6f40efa613570a5cb04af40764e9f377da4db4f58b4c3f23389
|
||
|
|
imagePullPolicy: IfNotPresent
|
||
|
|
args:
|
||
|
|
- run
|
||
|
|
env:
|
||
|
|
- name: POD_NAMESPACE
|
||
|
|
valueFrom:
|
||
|
|
fieldRef:
|
||
|
|
fieldPath: metadata.namespace
|
||
|
|
- name: ENABLED_PROVIDERS
|
||
|
|
value: google-vertex,novita
|
||
|
|
- name: NOVITA_API_KEY
|
||
|
|
valueFrom:
|
||
|
|
secretKeyRef:
|
||
|
|
name: agentgateway-novita
|
||
|
|
key: api_key
|
||
|
|
- name: SYNC_INTERVAL
|
||
|
|
value: 6h
|
||
|
|
- name: SYNC_RETRY_INTERVAL
|
||
|
|
value: 5m
|
||
|
|
ports:
|
||
|
|
- name: metrics
|
||
|
|
containerPort: 8080
|
||
|
|
protocol: TCP
|
||
|
|
readinessProbe:
|
||
|
|
httpGet:
|
||
|
|
path: /readyz
|
||
|
|
port: metrics
|
||
|
|
livenessProbe:
|
||
|
|
httpGet:
|
||
|
|
path: /healthz
|
||
|
|
port: metrics
|
||
|
|
resources:
|
||
|
|
requests:
|
||
|
|
cpu: 10m
|
||
|
|
memory: 16Mi
|
||
|
|
limits:
|
||
|
|
memory: 64Mi
|
||
|
|
securityContext:
|
||
|
|
allowPrivilegeEscalation: false
|
||
|
|
readOnlyRootFilesystem: true
|
||
|
|
capabilities:
|
||
|
|
drop:
|
||
|
|
- ALL
|
||
|
|
volumeMounts:
|
||
|
|
- name: catalog
|
||
|
|
mountPath: /catalog
|
||
|
|
readOnly: true
|
||
|
|
volumes:
|
||
|
|
- name: catalog
|
||
|
|
configMap:
|
||
|
|
name: agentgateway-model-costs
|
||
|
|
optional: true
|