3c6f6dfe2e
Set OPENAI_API_BASE_URL (config.py default) to our local vLLM endpoint. Open WebUI was using hardcoded 'https://api.openai.com/v1' for model discovery.
95 lines
2.7 KiB
YAML
95 lines
2.7 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: open-webui
|
|
namespace: open-webui
|
|
labels:
|
|
app.kubernetes.io/name: open-webui
|
|
app.kubernetes.io/part-of: open-webui
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
type: RollingUpdate
|
|
rollingUpdate:
|
|
maxSurge: 1
|
|
maxUnavailable: 0
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: open-webui
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: open-webui
|
|
app.kubernetes.io/part-of: open-webui
|
|
spec:
|
|
serviceAccountName: open-webui
|
|
containers:
|
|
- name: open-webui
|
|
image: ghcr.io/open-webui/open-webui:latest
|
|
imagePullPolicy: IfNotPresent
|
|
ports:
|
|
- name: http
|
|
containerPort: 8080
|
|
protocol: TCP
|
|
env:
|
|
# OpenWebUI configuration
|
|
- name: WEBUI_SECRET_KEY
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: body-wars-secret
|
|
key: vllm-api-key
|
|
optional: false
|
|
# Backend configuration for vLLM (OpenAI-compatible, NOT Ollama)
|
|
# OLLAMA_BASE_URLS removed: astro-orbiter runs vLLM, not Ollama
|
|
- name: OPENAI_BASE_URL
|
|
value: "http://astro-orbiter:8000/v1"
|
|
- name: OPENAI_API_BASE_URL
|
|
value: "http://astro-orbiter:8000/v1"
|
|
- name: OPENAI_API_KEY
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: body-wars-secret
|
|
key: vllm-api-key
|
|
optional: false
|
|
- name: OPENAI_MODEL_FALLBACK
|
|
value: "Gemma-4-26B-A4B-it-AWQ"
|
|
# Disable OpenAI API key validation (we're using vLLM, not OpenAI)
|
|
- name: OPENAI_VALIDATE_ENDPOINT
|
|
value: "false"
|
|
# Allow access from ingress
|
|
- name: WEBUI_URL
|
|
value: "https://body-wars.local.mk-labs.cloud"
|
|
# Observability settings
|
|
- name: ENABLE_API_KEY
|
|
value: "true"
|
|
- name: ENABLE_MODEL_FILTER
|
|
value: "false"
|
|
# Disable Ollama model detection (we use vLLM/OpenAI-compatible only)
|
|
- name: ENABLE_OLLAMA_API
|
|
value: "false"
|
|
# Storage
|
|
- name: DATA_DIR
|
|
value: "/app/backend/data"
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 256Mi
|
|
limits:
|
|
cpu: 1000m
|
|
memory: 1Gi
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /health
|
|
port: http
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 10
|
|
timeoutSeconds: 5
|
|
failureThreshold: 3
|
|
volumeMounts:
|
|
- name: data
|
|
mountPath: /app/backend/data
|
|
volumes:
|
|
- name: data
|
|
persistentVolumeClaim:
|
|
claimName: open-webui-data
|