feat: add litellm to new aitooling ArgoCD project (#94)
Deploys LiteLLM proxy with CNPG PostgreSQL (3-instance HA), PgBouncer pooler, and Redis cache. Introduces a dedicated aitooling AppProject and ApplicationSet to keep AI tooling services separate from platform infra. Reviewed-on: #94
This commit was merged in pull request #94.
This commit is contained in:
@@ -0,0 +1,67 @@
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: litellm
|
||||
namespace: litellm
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
app: litellm
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: litellm
|
||||
spec:
|
||||
containers:
|
||||
- name: litellm
|
||||
image: docker.litellm.ai/berriai/litellm-database:main-stable
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- --config
|
||||
- /app/config.yaml
|
||||
- --port
|
||||
- "4000"
|
||||
- --num_workers
|
||||
- "8"
|
||||
ports:
|
||||
- containerPort: 4000
|
||||
name: http
|
||||
protocol: TCP
|
||||
envFrom:
|
||||
- secretRef:
|
||||
name: litellm-credentials
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /health/liveliness
|
||||
port: 4000
|
||||
failureThreshold: 3
|
||||
initialDelaySeconds: 30
|
||||
periodSeconds: 30
|
||||
successThreshold: 1
|
||||
timeoutSeconds: 5
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /health/readiness
|
||||
port: 4000
|
||||
failureThreshold: 3
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 10
|
||||
successThreshold: 1
|
||||
timeoutSeconds: 5
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: 250m
|
||||
memory: 512Mi
|
||||
volumeMounts:
|
||||
- mountPath: /app/config.yaml
|
||||
name: config
|
||||
subPath: config.yaml
|
||||
restartPolicy: Always
|
||||
volumes:
|
||||
- name: config
|
||||
configMap:
|
||||
name: litellm-config
|
||||
Reference in New Issue
Block a user