GenAIExamples/AudioQnA/kubernetes/intel/cpu/xeon/manifest/audioqna.yaml

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

apiVersion: v1
kind: ConfigMap
metadata:
  name: audio-qna-config
  namespace: default
data:
  ASR_ENDPOINT: http://whisper-svc.default.svc.cluster.local:7066
  TTS_ENDPOINT: http://speecht5-svc.default.svc.cluster.local:7055
  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
  HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
  TGI_LLM_ENDPOINT: http://llm-dependency-svc.default.svc.cluster.local:3006
  MEGA_SERVICE_HOST_IP: audioqna-backend-server-svc
  ASR_SERVICE_HOST_IP: asr-svc
  ASR_SERVICE_PORT: "3001"
  LLM_SERVICE_HOST_IP: llm-svc
  LLM_SERVICE_PORT: "3007"
  TTS_SERVICE_HOST_IP: tts-svc
  TTS_SERVICE_PORT: "3002"

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: asr-deploy
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: asr-deploy
  template:
    metadata:
      annotations:
        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
      labels:
        app: asr-deploy
    spec:
      topologySpreadConstraints:
      - maxSkew: 1
        topologyKey: kubernetes.io/hostname
        whenUnsatisfiable: ScheduleAnyway
        labelSelector:
          matchLabels:
            app: asr-deploy
      hostIPC: true
      containers:
      - envFrom:
        - configMapRef:
            name: audio-qna-config
        image: opea/asr:latest
        imagePullPolicy: IfNotPresent
        name: asr-deploy
        args: null
        ports:
        - containerPort: 9099
      serviceAccountName: default
---
kind: Service
apiVersion: v1
metadata:
  name: asr-svc
spec:
  type: ClusterIP
  selector:
    app: asr-deploy
  ports:
  - name: service
    port: 3001
    targetPort: 9099
---

apiVersion: apps/v1
kind: Deployment
metadata:
  name: whisper-deploy
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: whisper-deploy
  template:
    metadata:
      annotations:
        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
      labels:
        app: whisper-deploy
    spec:
      topologySpreadConstraints:
      - maxSkew: 1
        topologyKey: kubernetes.io/hostname
        whenUnsatisfiable: ScheduleAnyway
        labelSelector:
          matchLabels:
            app: whisper-deploy
      hostIPC: true
      containers:
      - envFrom:
        - configMapRef:
            name: audio-qna-config
        image: opea/whisper:latest
        imagePullPolicy: IfNotPresent
        name: whisper-deploy
        args: null
        ports:
        - containerPort: 7066
      serviceAccountName: default
---
kind: Service
apiVersion: v1
metadata:
  name: whisper-svc
spec:
  type: ClusterIP
  selector:
    app: whisper-deploy
  ports:
  - name: service
    port: 7066
    targetPort: 7066

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: tts-deploy
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: tts-deploy
  template:
    metadata:
      annotations:
        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
      labels:
        app: tts-deploy
    spec:
      topologySpreadConstraints:
      - maxSkew: 1
        topologyKey: kubernetes.io/hostname
        whenUnsatisfiable: ScheduleAnyway
        labelSelector:
          matchLabels:
            app: tts-deploy
      hostIPC: true
      containers:
      - envFrom:
        - configMapRef:
            name: audio-qna-config
        image: opea/tts:latest
        imagePullPolicy: IfNotPresent
        name: tts-deploy
        args: null
        ports:
        - containerPort: 9088
      serviceAccountName: default
---
kind: Service
apiVersion: v1
metadata:
  name: tts-svc
spec:
  type: ClusterIP
  selector:
    app: tts-deploy
  ports:
  - name: service
    port: 3002
    targetPort: 9088

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: speecht5-deploy
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: speecht5-deploy
  template:
    metadata:
      annotations:
        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
      labels:
        app: speecht5-deploy
    spec:
      topologySpreadConstraints:
      - maxSkew: 1
        topologyKey: kubernetes.io/hostname
        whenUnsatisfiable: ScheduleAnyway
        labelSelector:
          matchLabels:
            app: speecht5-deploy
      hostIPC: true
      containers:
      - envFrom:
        - configMapRef:
            name: audio-qna-config
        image: opea/speecht5:latest
        imagePullPolicy: IfNotPresent
        name: speecht5-deploy
        args: null
        ports:
        - containerPort: 7055
      serviceAccountName: default
---
kind: Service
apiVersion: v1
metadata:
  name: speecht5-svc
spec:
  type: ClusterIP
  selector:
    app: speecht5-deploy
  ports:
  - name: service
    port: 7055
    targetPort: 7055

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: llm-dependency-deploy
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: llm-dependency-deploy
  template:
    metadata:
      annotations:
        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
      labels:
        app: llm-dependency-deploy
    spec:
      hostIPC: true
      containers:
      - envFrom:
        - configMapRef:
            name: audio-qna-config
        image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
        name: llm-dependency-deploy-demo
        securityContext:
          capabilities:
            add:
            - SYS_NICE
        args:
        - --model-id
        - $(LLM_MODEL_ID)
        - --max-input-length
        - '2048'
        - --max-total-tokens
        - '4096'
        volumeMounts:
        - mountPath: /data
          name: model-volume
        - mountPath: /dev/shm
          name: shm
        ports:
        - containerPort: 80
      serviceAccountName: default
      volumes:
      - name: model-volume
        hostPath:
          path: /home/sdp/cesg
          type: Directory
      - name: shm
        emptyDir:
          medium: Memory
          sizeLimit: 1Gi
---
kind: Service
apiVersion: v1
metadata:
  name: llm-dependency-svc
spec:
  type: ClusterIP
  selector:
    app: llm-dependency-deploy
  ports:
  - name: service
    port: 3006
    targetPort: 80

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: llm-deploy
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: llm-deploy
  template:
    metadata:
      annotations:
        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
      labels:
        app: llm-deploy
    spec:
      topologySpreadConstraints:
      - maxSkew: 1
        topologyKey: kubernetes.io/hostname
        whenUnsatisfiable: ScheduleAnyway
        labelSelector:
          matchLabels:
            app: llm-deploy
      hostIPC: true
      containers:
      - envFrom:
        - configMapRef:
            name: audio-qna-config
        image: opea/llm-tgi:latest
        imagePullPolicy: IfNotPresent
        name: llm-deploy
        args: null
        ports:
        - containerPort: 9000
      serviceAccountName: default
---
kind: Service
apiVersion: v1
metadata:
  name: llm-svc
spec:
  type: ClusterIP
  selector:
    app: llm-deploy
  ports:
  - name: service
    port: 3007
    targetPort: 9000

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: audioqna-backend-server-deploy
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: audioqna-backend-server-deploy
  template:
    metadata:
      annotations:
        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
      labels:
        app: audioqna-backend-server-deploy
    spec:
      topologySpreadConstraints:
      - maxSkew: 1
        topologyKey: kubernetes.io/hostname
        whenUnsatisfiable: ScheduleAnyway
        labelSelector:
          matchLabels:
            app: audioqna-backend-server-deploy
      hostIPC: true
      containers:
      - envFrom:
        - configMapRef:
            name: audio-qna-config
        image: opea/audioqna:latest
        imagePullPolicy: IfNotPresent
        name: audioqna-backend-server-deploy
        args: null
        ports:
        - containerPort: 8888
      serviceAccountName: default
---
kind: Service
apiVersion: v1
metadata:
  name: audioqna-backend-server-svc
spec:
  type: NodePort
  selector:
    app: audioqna-backend-server-deploy
  ports:
  - name: service
    port: 3008
    targetPort: 8888
    nodePort: 30666