[ChatQnA] Deploy ChatQnA for benchmarking with different configurations. (#870)

.pre-commit-config.yaml

@@ -18,8 +18,6 @@ repos:
               SearchQnA/ui/svelte/tsconfig.json|
               DocSum/ui/svelte/tsconfig.json
           )$
-      - id: check-yaml
-        args: [--allow-multiple-documents]
       - id: debug-statements
       - id: requirements-txt-fixer
       - id: trailing-whitespace

ChatQnA/benchmark/performance/helm_charts/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

ChatQnA/benchmark/performance/helm_charts/Chart.yaml

@@ -0,0 +1,27 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v2
+name: chatqna-charts
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.16.0"

ChatQnA/benchmark/performance/helm_charts/README.md

@@ -0,0 +1,38 @@
+## ChatQnA Deployment
+
+This document guides you through deploying ChatQnA pipelines using Helm charts. Helm charts simplify managing Kubernetes applications by packaging configuration and resources.
+
+## Getting Started
+
+### Preparation
+
+```bash
+# on k8s-master node
+cd GenAIExamples/ChatQnA/benchmark/performance/helm_charts
+
+# Replace <your token> with your actual Hugging Face token and run the following command:
+HUGGINGFACE_TOKEN=<your token>
+find . -name '*.yaml' -type f -exec sed -i "s#\${HF_TOKEN}#${HUGGINGFACE_TOKEN}#g" {} \;
+
+# Replace the following placeholders with the desired model IDs:
+LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
+EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
+RERANK_MODEL_ID=BAAI/bge-reranker-base
+find . -name '*.yaml' -type f -exec sed -i "s#\$(LLM_MODEL_ID)#${LLM_MODEL_ID}#g" {} \;
+find . -name '*.yaml' -type f -exec sed -i "s#\$(EMBEDDING_MODEL_ID)#${EMBEDDING_MODEL_ID}#g" {} \;
+find . -name '*.yaml' -type f -exec sed -i "s#\$(RERANK_MODEL_ID)#${RERANK_MODEL_ID}#g" {} \;
+
+```
+
+### ChatQnA Installation
+
+```bash
+# Deploy a ChatQnA pipeline using the specified YAML configuration.
+# To deploy with different configurations, simply provide a different YAML file.
+helm install chatqna helm_charts/ -f helm_charts/oob_single_node.yaml
+
+# Tips: To display rendered manifests according to the given yaml.
+helm template chatqna helm_charts/ -f helm_charts/oob_single_node.yaml
+```
+
+Notes: The provided [BKC manifests](https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA/benchmark) for single, two, and four node Kubernetes clusters are generated using this tool.

ChatQnA/benchmark/performance/helm_charts/oob_single_node.yaml

@@ -0,0 +1,237 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+config:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVER_HOST_IP: embedding-dependency-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVER_HOST_IP: llm-dependency-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVER_HOST_IP: reranking-dependency-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  TEI_EMBEDDING_ENDPOINT: http://embedding-dependency-svc.default.svc.cluster.local:6006
+  TEI_ENDPOINT: http://embedding-dependency-svc.default.svc.cluster.local:6006
+  TEI_RERANKING_ENDPOINT: http://reranking-dependency-svc.default.svc.cluster.local:8808
+  TGI_LLM_ENDPOINT: http://llm-dependency-svc.default.svc.cluster.local:9009
+
+deployments:
+  - name: chatqna-backend-server-deploy
+    spec:
+      image_name: opea/chatqna-no-wrapper
+      image_tag: latest
+      replicas: 1
+      ports:
+        - containerPort: 8888
+
+  - name: dataprep-deploy
+    spec:
+      image_name: opea/dataprep-redis
+      image_tag: latest
+      replicas: 1
+      ports:
+        - containerPort: 6007
+
+  - name: vector-db
+    spec:
+      image_name: redis/redis-stack
+      image_tag: 7.2.0-v9
+      replicas: 1
+      ports:
+        - containerPort: 6379
+        - containerPort: 8001
+
+  - name: retriever-deploy
+    spec:
+      image_name: opea/retriever-redis
+      image_tag: latest
+      replicas: 1
+      ports:
+        - containerPort: 7000
+
+  - name: embedding-dependency-deploy
+    spec:
+      image_name: ghcr.io/huggingface/text-embeddings-inference
+      image_tag: cpu-1.5
+      replicas: 1
+      ports:
+        - containerPort: 80
+      args:
+        - name: "--model-id"
+          value: $(EMBEDDING_MODEL_ID)
+        - name: "--auto-truncate"
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+  - name: reranking-dependency-deploy
+    spec:
+      image_name: opea/tei-gaudi
+      image_tag: latest
+      replicas: 1
+      resources:
+        limits:
+          habana.ai/gaudi: 1
+      args:
+        - name: "--model-id"
+        - value: $(RERANK_MODEL_ID)
+        - name: "--auto-truncate"
+      env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: "true"
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+        - name: HF_TOKEN
+          value: ${HF_TOKEN}
+        - name: MAX_WARMUP_SEQUENCE_LENGTH
+          value: "512"
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+  - name: llm-dependency-deploy
+    spec:
+      image_name: ghcr.io/huggingface/tgi-gaudi
+      image_tag: 2.0.4
+      replicas: 7
+      ports:
+        - containerPort: 80
+      resources:
+        limits:
+          habana.ai/gaudi: 1
+      args:
+        - name: "--model-id"
+          value: $(LLM_MODEL_ID)
+        - name: "--max-input-length"
+          value: "2048"
+        - name: "--max-total-tokens"
+          value: "4096"
+      env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: "true"
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+        - name: HF_TOKEN
+          value: ${HF_TOKEN}
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+services:
+  - name: chatqna-backend-server-svc
+    spec:
+      ports:
+        - name: service
+          nodePort: 30888
+          port: 8888
+          targetPort: 8888
+      selector:
+        app: chatqna-backend-server-deploy
+      type: NodePort
+
+  - name: dataprep-svc
+    spec:
+      ports:
+        - name: port1
+          port: 6007
+          targetPort: 6007
+      selector:
+        app: dataprep-deploy
+      type: ClusterIP
+
+  - name: embedding-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 6006
+          targetPort: 80
+      selector:
+        app: embedding-dependency-deploy
+      type: ClusterIP
+
+  - name: llm-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 9009
+          targetPort: 80
+      selector:
+        app: llm-dependency-deploy
+      type: ClusterIP
+
+  - name: reranking-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 8808
+          targetPort: 80
+      selector:
+        app: reranking-dependency-deploy
+      type: ClusterIP
+
+  - name: retriever-svc
+    spec:
+      ports:
+        - name: service
+          port: 7000
+          targetPort: 7000
+      selector:
+        app: retriever-deploy
+      type: ClusterIP
+
+  - name: vector-db
+    spec:
+      ports:
+        - name: vector-db-service
+          port: 6379
+          targetPort: 6379
+        - name: vector-db-insight
+          port: 8001
+          targetPort: 8001
+      selector:
+        app: vector-db
+      type: ClusterIP

ChatQnA/benchmark/performance/helm_charts/templates/configmap.yaml

@@ -0,0 +1,25 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: qna-config
+  namespace: default
+data:
+  EMBEDDING_MODEL_ID: {{ .Values.config.EMBEDDING_MODEL_ID }}
+  EMBEDDING_SERVER_HOST_IP: {{ .Values.config.EMBEDDING_SERVER_HOST_IP }}
+  HUGGINGFACEHUB_API_TOKEN: {{ .Values.config.HUGGINGFACEHUB_API_TOKEN }}
+  INDEX_NAME: {{ .Values.config.INDEX_NAME }}
+  LLM_MODEL_ID: {{ .Values.config.LLM_MODEL_ID }}
+  LLM_SERVER_HOST_IP: {{ .Values.config.LLM_SERVER_HOST_IP }}
+  NODE_SELECTOR: {{ .Values.config.NODE_SELECTOR }}
+  REDIS_URL: {{ .Values.config.REDIS_URL }}
+  RERANK_MODEL_ID: {{ .Values.config.RERANK_MODEL_ID }}
+  RERANK_SERVER_HOST_IP: {{ .Values.config.RERANK_SERVER_HOST_IP }}
+  RETRIEVER_SERVICE_HOST_IP: {{ .Values.config.RETRIEVER_SERVICE_HOST_IP }}
+  TEI_EMBEDDING_ENDPOINT: {{ .Values.config.TEI_EMBEDDING_ENDPOINT }}
+  TEI_ENDPOINT: {{ .Values.config.TEI_ENDPOINT }}
+  TEI_RERANKING_ENDPOINT: {{ .Values.config.TEI_RERANKING_ENDPOINT }}
+  TGI_LLM_ENDPOINT: {{ .Values.config.TGI_LLM_ENDPOINT }}
+---

ChatQnA/benchmark/performance/helm_charts/templates/deployment.yaml

@@ -0,0 +1,108 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+{{- range $deployment := .Values.deployments }}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ $deployment.name }}
+  namespace: default
+spec:
+  replicas: {{ $deployment.spec.replicas }}
+  selector:
+    matchLabels:
+      app: {{ $deployment.name }}
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: {{ $deployment.name }}
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        {{- if $deployment.spec.args }}
+        args:
+        {{- range $arg := $deployment.spec.args }}
+          {{- if $arg.name }}
+          - {{ $arg.name }}
+          {{- end }}
+          {{- if $arg.value }}
+          - "{{ $arg.value }}"
+          {{- end }}
+        {{- end }}
+        {{- end }}
+
+        {{- if $deployment.spec.env }}
+        env:
+        {{- range $env := $deployment.spec.env }}
+          - name: {{ $env.name }}
+            value: "{{ $env.value }}"
+        {{- end }}
+        {{- end }}
+
+        image: {{ $deployment.spec.image_name }}:{{ $deployment.spec.image_tag }}
+        imagePullPolicy: IfNotPresent
+        name: {{ $deployment.name }}
+
+        {{- if $deployment.spec.ports }}
+        ports:
+        {{- range $port := $deployment.spec.ports }}
+          {{- range $port_name, $port_id := $port }}
+          - {{ $port_name }}: {{ $port_id }}
+          {{- end }}
+        {{- end }}
+        {{- end }}
+
+        {{- if $deployment.spec.resources }}
+        resources:
+        {{- range $resourceType, $resource := $deployment.spec.resources }}
+          {{ $resourceType }}:
+          {{- range $limitType, $limit := $resource }}
+            {{ $limitType }}: {{ $limit }}
+          {{- end }}
+        {{- end }}
+        {{- end }}
+
+        {{- if $deployment.spec.volumeMounts }}
+        volumeMounts:
+        {{- range $volumeMount := $deployment.spec.volumeMounts }}
+          - mountPath: {{ $volumeMount.mountPath }}
+            name: {{ $volumeMount.name }}
+        {{- end }}
+        {{- end }}
+
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: {{ $deployment.name }}
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+
+
+      {{- if $deployment.spec.volumes }}
+      volumes:
+      {{- range $index, $volume := $deployment.spec.volumes }}
+        - name: {{ $volume.name }}
+          {{- if $volume.hostPath }}
+          hostPath:
+            path: {{ $volume.hostPath.path }}
+            type: {{ $volume.hostPath.type }}
+          {{- else if $volume.emptyDir }}
+          emptyDir:
+            medium: {{ $volume.emptyDir.medium }}
+            sizeLimit: {{ $volume.emptyDir.sizeLimit }}
+          {{- end }}
+      {{- end }}
+      {{- end }}
+
+
+---
+{{- end }}

ChatQnA/benchmark/performance/helm_charts/templates/service.yaml

@@ -0,0 +1,24 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+{{- range $service := .Values.services }}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ $service.name }}
+  namespace: default
+spec:
+  ports:
+  {{- range $port := $service.spec.ports }}
+    - name: {{ $port.name }}
+    {{- range $port_name, $port_id := $port }}
+      {{- if ne $port_name "name"}}
+      {{ $port_name }}: {{ $port_id }}
+      {{- end }}
+    {{- end }}
+  {{- end }}
+  selector:
+    app: {{ $service.spec.selector.app }}
+  type: {{ $service.spec.type }}
+---
+{{- end }}

ChatQnA/benchmark/performance/helm_charts/tuned_single_node.yaml

@@ -0,0 +1,259 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+config:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVER_HOST_IP: embedding-dependency-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVER_HOST_IP: llm-dependency-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVER_HOST_IP: reranking-dependency-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  TEI_EMBEDDING_ENDPOINT: http://embedding-dependency-svc.default.svc.cluster.local:6006
+  TEI_ENDPOINT: http://embedding-dependency-svc.default.svc.cluster.local:6006
+  TEI_RERANKING_ENDPOINT: http://reranking-dependency-svc.default.svc.cluster.local:8808
+  TGI_LLM_ENDPOINT: http://llm-dependency-svc.default.svc.cluster.local:9009
+
+deployments:
+  - name: chatqna-backend-server-deploy
+    spec:
+      image_name: opea/chatqna-no-wrapper
+      image_tag: latest
+      replicas: 2
+      ports:
+        - containerPort: 8888
+      resources:
+        limits:
+          cpu: "8"
+          memory: "8000Mi"
+        requests:
+          cpu: "8"
+          memory: "8000Mi"
+
+  - name: dataprep-deploy
+    spec:
+      image_name: opea/dataprep-redis
+      image_tag: latest
+      replicas: 1
+      ports:
+        - containerPort: 6007
+
+  - name: vector-db
+    spec:
+      image_name: redis/redis-stack
+      image_tag: 7.2.0-v9
+      replicas: 1
+      ports:
+        - containerPort: 6379
+        - containerPort: 8001
+
+  - name: retriever-deploy
+    spec:
+      image_name: opea/retriever-redis
+      image_tag: latest
+      replicas: 2
+      ports:
+        - containerPort: 7000
+      resources:
+        requests:
+          cpu: "4"
+          memory: "4000Mi"
+
+  - name: embedding-dependency-deploy
+    spec:
+      image_name: ghcr.io/huggingface/text-embeddings-inference
+      image_tag: cpu-1.5
+      replicas: 1
+      ports:
+        - containerPort: 80
+      args:
+        - name: "--model-id"
+          value: $(EMBEDDING_MODEL_ID)
+        - name: "--auto-truncate"
+      resources:
+        limits:
+          cpu: "80"
+          memory: "20000Mi"
+        requests:
+          cpu: "80"
+          memory: "20000Mi"
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+  - name: reranking-dependency-deploy
+    spec:
+      image_name: opea/tei-gaudi
+      image_tag: latest
+      replicas: 1
+      resources:
+        limits:
+          habana.ai/gaudi: 1
+      args:
+        - name: "--model-id"
+        - value: $(RERANK_MODEL_ID)
+        - name: "--auto-truncate"
+      env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: "true"
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+        - name: HF_TOKEN
+          value: ${HF_TOKEN}
+        - name: MAX_WARMUP_SEQUENCE_LENGTH
+          value: "512"
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+  - name: llm-dependency-deploy
+    spec:
+      image_name: ghcr.io/huggingface/tgi-gaudi
+      image_tag: 2.0.4
+      replicas: 7
+      ports:
+        - containerPort: 80
+      resources:
+        limits:
+          habana.ai/gaudi: 1
+      args:
+        - name: "--model-id"
+          value: $(LLM_MODEL_ID)
+        - name: "--max-input-length"
+          value: "1280"
+        - name: "--max-total-tokens"
+          value: "2048"
+        - name: "--max-batch-total-tokens"
+          value: "65536"
+        - name: "--max-batch-prefill-tokens"
+          value: "4096"
+      env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: "true"
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+        - name: HF_TOKEN
+          value: ${HF_TOKEN}
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+services:
+  - name: chatqna-backend-server-svc
+    spec:
+      ports:
+        - name: service
+          nodePort: 30888
+          port: 8888
+          targetPort: 8888
+      selector:
+        app: chatqna-backend-server-deploy
+      type: NodePort
+
+  - name: dataprep-svc
+    spec:
+      ports:
+        - name: port1
+          port: 6007
+          targetPort: 6007
+      selector:
+        app: dataprep-deploy
+      type: ClusterIP
+
+  - name: embedding-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 6006
+          targetPort: 80
+      selector:
+        app: embedding-dependency-deploy
+      type: ClusterIP
+
+  - name: llm-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 9009
+          targetPort: 80
+      selector:
+        app: llm-dependency-deploy
+      type: ClusterIP
+
+  - name: reranking-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 8808
+          targetPort: 80
+      selector:
+        app: reranking-dependency-deploy
+      type: ClusterIP
+
+  - name: retriever-svc
+    spec:
+      ports:
+        - name: service
+          port: 7000
+          targetPort: 7000
+      selector:
+        app: retriever-deploy
+      type: ClusterIP
+
+  - name: vector-db
+    spec:
+      ports:
+        - name: vector-db-service
+          port: 6379
+          targetPort: 6379
+        - name: vector-db-insight
+          port: 8001
+          targetPort: 8001
+      selector:
+        app: vector-db
+      type: ClusterIP

ChatQnA/benchmark/performance/helm_charts/values.yaml

@@ -0,0 +1,237 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+config:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVER_HOST_IP: embedding-dependency-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVER_HOST_IP: llm-dependency-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVER_HOST_IP: reranking-dependency-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  TEI_EMBEDDING_ENDPOINT: http://embedding-dependency-svc.default.svc.cluster.local:6006
+  TEI_ENDPOINT: http://embedding-dependency-svc.default.svc.cluster.local:6006
+  TEI_RERANKING_ENDPOINT: http://reranking-dependency-svc.default.svc.cluster.local:8808
+  TGI_LLM_ENDPOINT: http://llm-dependency-svc.default.svc.cluster.local:9009
+
+deployments:
+  - name: chatqna-backend-server-deploy
+    spec:
+      image_name: opea/chatqna-no-wrapper
+      image_tag: latest
+      replicas: 1
+      ports:
+        - containerPort: 8888
+
+  - name: dataprep-deploy
+    spec:
+      image_name: opea/dataprep-redis
+      image_tag: latest
+      replicas: 1
+      ports:
+        - containerPort: 6007
+
+  - name: vector-db
+    spec:
+      image_name: redis/redis-stack
+      image_tag: 7.2.0-v9
+      replicas: 1
+      ports:
+        - containerPort: 6379
+        - containerPort: 8001
+
+  - name: retriever-deploy
+    spec:
+      image_name: opea/retriever-redis
+      image_tag: latest
+      replicas: 1
+      ports:
+        - containerPort: 7000
+
+  - name: embedding-dependency-deploy
+    spec:
+      image_name: ghcr.io/huggingface/text-embeddings-inference
+      image_tag: cpu-1.5
+      replicas: 1
+      ports:
+        - containerPort: 80
+      args:
+        - name: "--model-id"
+          value: $(EMBEDDING_MODEL_ID)
+        - name: "--auto-truncate"
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+  - name: reranking-dependency-deploy
+    spec:
+      image_name: opea/tei-gaudi
+      image_tag: latest
+      replicas: 1
+      resources:
+        limits:
+          habana.ai/gaudi: 1
+      args:
+        - name: "--model-id"
+        - value: $(RERANK_MODEL_ID)
+        - name: "--auto-truncate"
+      env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: "true"
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+        - name: HF_TOKEN
+          value: ${HF_TOKEN}
+        - name: MAX_WARMUP_SEQUENCE_LENGTH
+          value: "512"
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+  - name: llm-dependency-deploy
+    spec:
+      image_name: ghcr.io/huggingface/tgi-gaudi
+      image_tag: 2.0.4
+      replicas: 7
+      ports:
+        - containerPort: 80
+      resources:
+        limits:
+          habana.ai/gaudi: 1
+      args:
+        - name: "--model-id"
+          value: $(LLM_MODEL_ID)
+        - name: "--max-input-length"
+          value: "2048"
+        - name: "--max-total-tokens"
+          value: "4096"
+      env:
+        - name: OMPI_MCA_btl_vader_single_copy_mechanism
+          value: none
+        - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
+          value: "true"
+        - name: runtime
+          value: habana
+        - name: HABANA_VISIBLE_DEVICES
+          value: all
+        - name: HF_TOKEN
+          value: ${HF_TOKEN}
+      volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      volumes:
+        - hostPath:
+            path: /mnt/models
+            type: Directory
+          name: model-volume
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Gi
+          name: shm
+
+services:
+  - name: chatqna-backend-server-svc
+    spec:
+      ports:
+        - name: service
+          nodePort: 30888
+          port: 8888
+          targetPort: 8888
+      selector:
+        app: chatqna-backend-server-deploy
+      type: NodePort
+
+  - name: dataprep-svc
+    spec:
+      ports:
+        - name: port1
+          port: 6007
+          targetPort: 6007
+      selector:
+        app: dataprep-deploy
+      type: ClusterIP
+
+  - name: embedding-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 6006
+          targetPort: 80
+      selector:
+        app: embedding-dependency-deploy
+      type: ClusterIP
+
+  - name: llm-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 9009
+          targetPort: 80
+      selector:
+        app: llm-dependency-deploy
+      type: ClusterIP
+
+  - name: reranking-dependency-svc
+    spec:
+      ports:
+        - name: service
+          port: 8808
+          targetPort: 80
+      selector:
+        app: reranking-dependency-deploy
+      type: ClusterIP
+
+  - name: retriever-svc
+    spec:
+      ports:
+        - name: service
+          port: 7000
+          targetPort: 7000
+      selector:
+        app: retriever-deploy
+      type: ClusterIP
+
+  - name: vector-db
+    spec:
+      ports:
+        - name: vector-db-service
+          port: 6379
+          targetPort: 6379
+        - name: vector-db-insight
+          port: 8001
+          targetPort: 8001
+      selector:
+        app: vector-db
+      type: ClusterIP