forked from janhq/jan
-
Notifications
You must be signed in to change notification settings - Fork 0
/
values.yaml
256 lines (212 loc) · 6.34 KB
/
values.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
common:
imageTag: v0.4.6-cpu
# DO NOT CHANGE THE LINE ABOVE. MAKE ALL CHANGES BELOW
# Global pvc for all workload
pvc:
enabled: false
name: 'janroot'
accessModes: 'ReadWriteOnce'
storageClassName: ''
capacity: '50Gi'
# Global image pull secret
imagePullSecrets: []
externalSecret:
create: false
name: ''
annotations: {}
nameOverride: 'jan-server'
fullnameOverride: 'jan-server'
serviceAccount:
create: true
annotations: {}
name: 'jan-server-service-account'
podDisruptionBudget:
create: false
minAvailable: 1
workloads:
- name: server
image:
repository: ghcr.io/janhq/jan-server
pullPolicy: Always
command: ['/bin/sh', '-c']
args: ['cd server && node build/main.js']
replicaCount: 1
ports:
containerPort: 1337
strategy:
canary:
steps:
- setWeight: 50
- pause: { duration: 1m }
ingress:
enabled: true
className: 'nginx'
annotations:
nginx.ingress.kubernetes.io/proxy-body-size: '100m'
nginx.ingress.kubernetes.io/proxy-read-timeout: '1800'
nginx.ingress.kubernetes.io/proxy-send-timeout: '1800'
# cert-manager.io/cluster-issuer: 'jan-ai-dns01-cluster-issuer'
# nginx.ingress.kubernetes.io/force-ssl-redirect: 'true'
nginx.ingress.kubernetes.io/backend-protocol: HTTP
hosts:
- host: server.local
paths:
- path: /
pathType: Prefix
tls:
[]
# - hosts:
# - server-dev.jan.ai
# secretName: jan-server-prod-tls-v2
instrumentation:
enabled: false
podAnnotations: {}
podSecurityContext: {}
securityContext: {}
service:
extenalLabel: {}
type: ClusterIP
port: 1337
targetPort: 1337
# If you want to use GPU, please uncomment the following lines and change imageTag to the one with GPU support
resources:
# limits:
# nvidia.com/gpu: 1
requests:
cpu: 2000m
memory: 8192M
# If you want to use pv, please uncomment the following lines and enable pvc.enabled
volumes:
[]
# - name: janroot
# persistentVolumeClaim:
# claimName: janroot
volumeMounts:
[]
# - name: janroot
# mountPath: /app/server/build/jan
# AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, S3_BUCKET_NAME, AWS_ENDPOINT, AWS_REGION should mount as a secret env instead of plain text here
# Change API_BASE_URL to your server's public domain
env:
- name: API_BASE_URL
value: 'http://server.local'
lifecycle: {}
autoscaling:
enabled: false
minReplicas: 2
maxReplicas: 3
targetCPUUtilizationPercentage: 95
targetMemoryUtilizationPercentage: 95
kedaScaling:
enabled: false # ignore if autoscaling.enable = true
cooldownPeriod: 30
pollingInterval: 2
minReplicas: 1
maxReplicas: 5
metricName: celery_queue_length
query: celery_queue_length{queue_name="myqueue"} # change queue_name here
serverAddress: http://prometheus-prod-kube-prome-prometheus.monitoring.svc:9090
threshold: '3'
nodeSelector: {}
tolerations: []
podSecurityGroup:
enabled: false
securitygroupid: []
# Reloader Option
reloader: 'false'
vpa:
enabled: false
- name: web
image:
repository: ghcr.io/janhq/jan-server
pullPolicy: Always
command: ['/bin/sh', '-c']
args:
[
'export NODE_ENV=production && yarn workspace jan-web build && cd web && npx serve out',
]
replicaCount: 1
ports:
containerPort: 3000
strategy:
canary:
steps:
- setWeight: 50
- pause: { duration: 1m }
ingress:
enabled: true
className: 'nginx'
annotations:
nginx.ingress.kubernetes.io/proxy-body-size: '100m'
nginx.ingress.kubernetes.io/proxy-read-timeout: '1800'
nginx.ingress.kubernetes.io/proxy-send-timeout: '1800'
# cert-manager.io/cluster-issuer: 'jan-ai-dns01-cluster-issuer'
# nginx.ingress.kubernetes.io/force-ssl-redirect: 'true'
nginx.ingress.kubernetes.io/backend-protocol: HTTP
hosts:
- host: web.local
paths:
- path: /
pathType: Prefix
tls:
[]
# - hosts:
# - server-dev.jan.ai
# secretName: jan-server-prod-tls-v2
instrumentation:
enabled: false
podAnnotations: {}
podSecurityContext: {}
securityContext: {}
service:
extenalLabel: {}
type: ClusterIP
port: 3000
targetPort: 3000
resources:
limits:
cpu: 1000m
memory: 2048M
requests:
cpu: 50m
memory: 500M
volumes:
[]
# - name: janroot
# persistentVolumeClaim:
# claimName: janroot
volumeMounts:
[]
# - name: janroot
# mountPath: /app/server/build/jan
# AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, S3_BUCKET_NAME, AWS_ENDPOINT, AWS_REGION should mount as a secret env instead of plain text here
# Change API_BASE_URL to your server's public domain
env:
- name: API_BASE_URL
value: 'http://server.local'
lifecycle: {}
autoscaling:
enabled: true
minReplicas: 1
maxReplicas: 3
targetCPUUtilizationPercentage: 95
targetMemoryUtilizationPercentage: 95
kedaScaling:
enabled: false # ignore if autoscaling.enable = true
cooldownPeriod: 30
pollingInterval: 2
minReplicas: 1
maxReplicas: 5
metricName: celery_queue_length
query: celery_queue_length{queue_name="myqueue"} # change queue_name here
serverAddress: http://prometheus-prod-kube-prome-prometheus.monitoring.svc:9090
threshold: '3'
nodeSelector: {}
tolerations: []
podSecurityGroup:
enabled: false
securitygroupid: []
# Reloader Option
reloader: 'false'
vpa:
enabled: false