Files
gradio-ui/tts.yaml
2026-02-12 05:36:15 -05:00

97 lines
2.1 KiB
YAML

---
apiVersion: apps/v1
kind: Deployment
metadata:
name: tts-ui
namespace: ai-ml
labels:
app: tts-ui
component: demo-ui
spec:
replicas: 1
selector:
matchLabels:
app: tts-ui
template:
metadata:
labels:
app: tts-ui
component: demo-ui
spec:
containers:
- name: gradio
image: ghcr.io/billy-davies-2/llm-apps:v2-202602120535
imagePullPolicy: Always
command: ["python", "tts.py"]
ports:
- containerPort: 7860
name: http
protocol: TCP
env:
- name: TTS_URL
# Ray Serve endpoint - routes to /tts prefix
value: "http://ai-inference-serve-svc.ai-ml.svc.cluster.local:8000/tts"
- name: MLFLOW_TRACKING_URI
value: "http://mlflow.mlflow.svc.cluster.local:80"
resources:
requests:
cpu: "100m"
memory: "256Mi"
limits:
cpu: "500m"
memory: "512Mi"
livenessProbe:
httpGet:
path: /
port: 7860
initialDelaySeconds: 10
periodSeconds: 30
readinessProbe:
httpGet:
path: /
port: 7860
initialDelaySeconds: 5
periodSeconds: 10
imagePullSecrets:
- name: ghcr-registry
---
apiVersion: v1
kind: Service
metadata:
name: tts-ui
namespace: ai-ml
labels:
app: tts-ui
spec:
type: ClusterIP
ports:
- port: 80
targetPort: 7860
protocol: TCP
name: http
selector:
app: tts-ui
---
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
name: tts-ui
namespace: ai-ml
annotations:
external-dns.alpha.kubernetes.io/hostname: tts-ui.lab.daviestechlabs.io
spec:
parentRefs:
- name: envoy-internal
namespace: network
sectionName: https-lab
hostnames:
- tts-ui.lab.daviestechlabs.io
rules:
- matches:
- path:
type: PathPrefix
value: /
backendRefs:
- name: tts-ui
port: 80