Vertex AI not working

[o-lenczyk]

Hi
I was following this https://www.librechat.ai/docs/configuration/pre_configured_ai/google in order to configure Gemini over Vertex AI

I manually added secret with vertex service account to my deployment. I also added new env: GOOGLE_MODELS

apiVersion: apps/v1
kind: Deployment
metadata:
  annotations:
    deployment.kubernetes.io/revision: "3"
    meta.helm.sh/release-name: librechat
    meta.helm.sh/release-namespace: librechat
  creationTimestamp: "2025-04-21T21:38:37Z"
  generation: 3
  labels:
    app.kubernetes.io/instance: librechat
    app.kubernetes.io/managed-by: Helm
    app.kubernetes.io/name: librechat-librechat
    app.kubernetes.io/version: v0.7.7
    helm.sh/chart: librechat-1.8.9
  name: librechat-librechat
  namespace: librechat
  resourceVersion: "53488528"
  uid: c384947f-1b9a-430a-b92a-bd55b4d7786e
spec:
  progressDeadlineSeconds: 600
  replicas: 1
  revisionHistoryLimit: 10
  selector:
    matchLabels:
      app.kubernetes.io/instance: librechat
      app.kubernetes.io/name: librechat-librechat
  strategy:
    rollingUpdate:
      maxSurge: 25%
      maxUnavailable: 25%
    type: RollingUpdate
  template:
    metadata:
      annotations:
        checksum/configEnv: 111a33e7f8b2ca5b20b2675368d166474ab6c4a786b11e51069d7c5452fb05f1
      creationTimestamp: null
      labels:
        app.kubernetes.io/instance: librechat
        app.kubernetes.io/managed-by: Helm
        app.kubernetes.io/name: librechat-librechat
        app.kubernetes.io/version: v0.7.7
        helm.sh/chart: librechat-1.8.9
    spec:
      containers:
      - env:
        - name: GOOGLE_MODELS
          value: gemini-1.5-flash-preview-0514,gemini-1.5-pro-preview-0514,gemini-1.0-pro-vision-001,gemini-1.0-pro-002,gemini-1.0-pro-001,gemini-pro-vision,gemini-1.0-pro
        envFrom:
        - configMapRef:
            name: librechat-librechat-configenv
        - secretRef:
            name: librechat-credentials-env
            optional: true
        image: ghcr.io/danny-avila/librechat:v0.7.7
        imagePullPolicy: IfNotPresent
        lifecycle: {}
        name: librechat-librechat
        ports:
        - containerPort: 3080
          name: http
          protocol: TCP
        resources: {}
        securityContext:
          capabilities:
            drop:
            - ALL
          runAsNonRoot: true
          runAsUser: 1000
        terminationMessagePath: /dev/termination-log
        terminationMessagePolicy: File
        volumeMounts:
        - mountPath: /api/data
          name: auth-volume
          readOnly: true
        - mountPath: /app/client/public/images
          name: image-volume
      dnsPolicy: ClusterFirst
      restartPolicy: Always
      schedulerName: default-scheduler
      securityContext:
        fsGroup: 2000
      terminationGracePeriodSeconds: 30
      volumes:
      - name: auth-volume
        secret:
          defaultMode: 420
          secretName: auth-secret
      - name: image-volume
        persistentVolumeClaim:
          claimName: librechat-librechat-images

 kubectl exec -it librechat-librechat-6bf4c9f6-wpptz -- ls /api/data/auth.json                                                                                                                
/api/data/auth.json

Can you tell me what should I do to have the gemini model enabled in the LibreChat UI?

[hinewin]

Were you able to get it enabled in the UI through the helmchart?