add manifests wit wrapper

Signed-off-by: srinarayan-srikanthan <srinarayan.srikanthan@intel.com>

.github/workflows/manual-docker-publish.yml

@@ -11,23 +11,23 @@ on:
         required: true
         type: string
       examples:
-        default: "Translation"
-        description: 'List of examples to publish [AudioQnA,ChatQnA,CodeGen,CodeTrans,DocSum,FaqGen,SearchQnA,Translation]'
+        default: ""
+        description: 'List of examples to publish [AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,FaqGen,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA]'
         required: false
         type: string
       images:
-        default: "gmcmanager,gmcrouter"
-        description: 'List of images to publish [gmcmanager,gmcrouter, ...]'
+        default: ""
+        description: 'List of images to publish [gmcmanager,gmcrouter]'
         required: false
         type: string
       tag:
-        default: "v0.9"
-        description: "Tag to publish"
+        default: "rc"
+        description: "Tag to publish, like [1.0rc]"
         required: true
         type: string
       publish_tags:
-        default: "latest,v0.9"
-        description: 'Tag list apply to publish images'
+        default: "latest,1.x"
+        description: "Tag list apply to publish images, like [latest,1.0]"
         required: false
         type: string
 

.github/workflows/manual-docker-scan.yml

@@ -11,13 +11,13 @@ on:
         required: true
         type: string
       examples:
-        default: "ChatQnA"
-        description: 'List of examples to scan [AudioQnA,ChatQnA,CodeGen,CodeTrans,DocSum,FaqGen,SearchQnA,Translation]'
+        default: ""
+        description: 'List of examples to publish "AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,FaqGen,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA"'
         required: false
         type: string
       images:
-        default: "gmcmanager,gmcrouter"
-        description: 'List of images to scan [gmcmanager,gmcrouter, ...]'
+        default: ""
+        description: 'List of images to publish "gmcmanager,gmcrouter"'
         required: false
         type: string
       tag:

.github/workflows/pr-manifest-validate.yml

@@ -1,54 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Manifests Validate
-
-on:
-  pull_request:
-    branches: [main]
-    types: [opened, reopened, ready_for_review, synchronize] # added `ready_for_review` since draft is skipped
-    paths:
-      - "**/kubernetes/manifests/**"
-      - .github/workflows/manifest-validate.yml
-  workflow_dispatch:
-
-# If there is a new commit, the previous jobs will be canceled
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-env:
-  MANIFEST_DIR: "manifests"
-
-jobs:
-  manifests-validate:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout out Repo
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: changed files
-        id: changed_files
-        run: |
-          set -xe
-          changed_folder=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }} | \
-          grep "kubernetes/manifests" | grep -vE '.github|README.md|*.txt|*.sh' | cut -d'/' -f1 | sort -u )
-          echo "changed_folder: $changed_folder"
-          if [ -z "$changed_folder" ]; then
-              echo "No changes in manifests folder"
-              echo "SKIP=true" >> $GITHUB_OUTPUT
-              exit 0
-          fi
-          echo "SKIP=false" >> $GITHUB_OUTPUT
-          for folder in $changed_folder; do
-              folder_str="$folder_str $folder/kubernetes/manifests/"
-          done
-          echo "folder_str=$folder_str"
-          echo "folder_str=$folder_str" >> $GITHUB_ENV
-
-      - uses: docker://ghcr.io/yannh/kubeconform:latest
-        if: steps.changed_files.outputs.SKIP == 'false'
-        with:
-          args: "-summary -output json ${{env.folder_str}}"

.github/workflows/push-image-build.yml

@@ -9,7 +9,6 @@ on:
     paths:
       - "**.py"
       - "**Dockerfile"
-  workflow_dispatch:
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}-on-push

.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

AgentQnA/README.md

@@ -103,4 +103,4 @@ curl http://${ip_address}:9090/v1/chat/completions -X POST -H "Content-Type: app
 
 ## How to register your own tools with agent
 
-You can take a look at the tools yaml and python files in this example. For more details, please refer to the "Provide your own tools" section in the instructions [here](https://github.com/opea-project/GenAIComps/tree/main/comps/agent/langchain#5-customize-agent-strategy).
+You can take a look at the tools yaml and python files in this example. For more details, please refer to the "Provide your own tools" section in the instructions [here](https://github.com/opea-project/GenAIComps/tree/main/comps/agent/langchain/README.md#5-customize-agent-strategy).

AudioQnA/benchmark/accuracy/README.md

@@ -14,7 +14,7 @@ We evaluate the WER (Word Error Rate) metric of the ASR microservice.
 
 ### Launch ASR microservice
 
-Launch the ASR microserice with the following commands. For more details please refer to [doc](https://github.com/opea-project/GenAIComps/tree/main/comps/asr).
+Launch the ASR microserice with the following commands. For more details please refer to [doc](https://github.com/opea-project/GenAIComps/tree/main/comps/asr/whisper/README.md).
 
 ```bash
 git clone https://github.com/opea-project/GenAIComps

AudioQnA/kubernetes/intel/README_gmc.md

@@ -4,7 +4,7 @@ This document outlines the deployment process for a AudioQnA application utilizi
 
 The AudioQnA Service leverages a Kubernetes operator called genai-microservices-connector(GMC). GMC supports connecting microservices to create pipelines based on the specification in the pipeline yaml file in addition to allowing the user to dynamically control which model is used in a service such as an LLM or embedder. The underlying pipeline language also supports using external services that may be running in public or private cloud elsewhere.
 
-Install GMC  in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector). Soon as we publish images to Docker Hub, at which point no builds will be required, simplifying install.
+Install GMC  in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md). Soon as we publish images to Docker Hub, at which point no builds will be required, simplifying install.
 
 
 The AudioQnA application is defined as a Custom Resource (CR) file that the above GMC operator acts  upon. It first checks if the microservices listed in the CR yaml file are running, if not starts them and then proceeds to connect them. When the AudioQnA pipeline is ready, the service endpoint details are returned, letting you use the application. Should you use "kubectl get pods" commands you will see all the component microservices, in particular `asr`, `tts`, and `llm`.

ChatQnA/README.md

@@ -16,6 +16,8 @@ Quick Start Deployment Steps:
 2. Run Docker Compose.
 3. Consume the ChatQnA Service.
 
+Note: If you do not have docker installed you can run this script to install docker : `bash docker_compose/install_docker.sh`
+
 ### Quick Start: 1.Setup Environment Variable
 
 To set up environment variables for deploying ChatQnA services, follow these steps:
@@ -240,7 +242,7 @@ Refer to the [Kubernetes Guide](./kubernetes/intel/README.md) for instructions o
 
 Install Helm (version >= 3.15) first. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
 
-Refer to the [ChatQnA helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/chatqna) for instructions on deploying ChatQnA into Kubernetes on Xeon & Gaudi.
+Refer to the [ChatQnA helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/chatqna/README.md) for instructions on deploying ChatQnA into Kubernetes on Xeon & Gaudi.
 
 ### Deploy ChatQnA on AI PC
 
@@ -306,7 +308,7 @@ Two ways of consuming ChatQnA Service:
 
 ## Troubleshooting
 
-1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA/docker_compose/intel/cpu/xeon#validate-microservices) first. A simple example:
+1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA/docker_compose/intel/cpu/xeon/README.md#validate-microservices) first. A simple example:
 
    ```bash
    http_proxy="" curl ${host_ip}:6006/embed -X POST  -d '{"inputs":"What is Deep Learning?"}' -H 'Content-Type: application/json'

ChatQnA/benchmark/oob_with_wrapper/with_rerank/four_gaudi/oob_four_gaudi_with_rerank.yaml

@@ -275,10 +275,6 @@ spec:
         - '2048'
         - --max-total-tokens
         - '4096'
-        - --max-batch-total-tokens
-        - '65536'
-        - --max-batch-prefill-tokens
-        - '4096'
         env:
         - name: OMPI_MCA_btl_vader_single_copy_mechanism
           value: none
@@ -288,20 +284,12 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/oob_with_wrapper/with_rerank/single_gaudi/oob_single_gaudi_with_rerank.yaml

@@ -275,10 +275,6 @@ spec:
         - '2048'
         - --max-total-tokens
         - '4096'
-        - --max-batch-total-tokens
-        - '65536'
-        - --max-batch-prefill-tokens
-        - '4096'
         env:
         - name: OMPI_MCA_btl_vader_single_copy_mechanism
           value: none
@@ -288,20 +284,12 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/oob_with_wrapper/with_rerank/two_gaudi/oob_two_gaudi_with_rerank.yaml

@@ -275,10 +275,6 @@ spec:
         - '2048'
         - --max-total-tokens
         - '4096'
-        - --max-batch-total-tokens
-        - '65536'
-        - --max-batch-prefill-tokens
-        - '4096'
         env:
         - name: OMPI_MCA_btl_vader_single_copy_mechanism
           value: none
@@ -288,20 +284,12 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/oob_with_wrapper/without_rerank/four_gaudi/oob_four_gaudi_without_rerank.yaml

@@ -323,7 +323,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.1
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:
@@ -336,10 +336,6 @@ spec:
         - '2048'
         - --max-total-tokens
         - '4096'
-        - --max-batch-total-tokens
-        - '65536'
-        - --max-batch-prefill-tokens
-        - '4096'
         volumeMounts:
         - mountPath: /data
           name: model-volume
@@ -359,16 +355,8 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
       serviceAccountName: default
       volumes:
       - name: model-volume
@@ -491,7 +479,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tei-gaudi:latest
+        image: opea/tei-gaudi:latest
         name: reranking-dependency-deploy
         args:
         - --model-id

ChatQnA/benchmark/oob_with_wrapper/without_rerank/single_gaudi/oob_single_gaudi_without_rerank.yaml

@@ -323,7 +323,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.1
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:
@@ -336,10 +336,6 @@ spec:
         - '2048'
         - --max-total-tokens
         - '4096'
-        - --max-batch-total-tokens
-        - '65536'
-        - --max-batch-prefill-tokens
-        - '4096'
         volumeMounts:
         - mountPath: /data
           name: model-volume
@@ -359,16 +355,8 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
       serviceAccountName: default
       volumes:
       - name: model-volume

ChatQnA/benchmark/oob_with_wrapper/without_rerank/two_gaudi/oob_two_gaudi_without_rerank.yaml

@@ -323,7 +323,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.1
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:
@@ -336,10 +336,6 @@ spec:
         - '2048'
         - --max-total-tokens
         - '4096'
-        - --max-batch-total-tokens
-        - '65536'
-        - --max-batch-prefill-tokens
-        - '4096'
         volumeMounts:
         - mountPath: /data
           name: model-volume
@@ -359,16 +355,8 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
       serviceAccountName: default
       volumes:
       - name: model-volume

ChatQnA/benchmark/performance/README.md

@@ -90,7 +90,7 @@ find . -name '*.yaml' -type f -exec sed -i "s#\$(RERANK_MODEL_ID)#${RERANK_MODEL
 
 ### Benchmark tool preparation
 
-The test uses the [benchmark tool](https://github.com/opea-project/GenAIEval/tree/main/evals/benchmark) to do performance test. We need to set up benchmark tool at the master node of Kubernetes which is k8s-master.
+The test uses the [benchmark tool](https://github.com/opea-project/GenAIEval/tree/main/evals/benchmark/README.md) to do performance test. We need to set up benchmark tool at the master node of Kubernetes which is k8s-master.
 
 ```bash
 # on k8s-master node

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

ChatQnA/benchmark/performance/oob/with_rerank/eight_gaudi/no_wrapper_oob_eight_gaudi_with_rerank.yaml

@@ -237,7 +237,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/oob/with_rerank/four_gaudi/no_wrapper_oob_four_gaudi_with_rerank.yaml

@@ -237,7 +237,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/oob/with_rerank/single_gaudi/no_wrapper_oob_single_gaudi_with_rerank.yaml

@@ -237,7 +237,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/oob/with_rerank/two_gaudi/no_wrapper_oob_two_gaudi_with_rerank.yaml

@@ -237,7 +237,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/oob/without_rerank/eight_gaudi/no_wrapper_oob_eight_gaudi_without_rerank.yaml

@@ -237,7 +237,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/oob/without_rerank/four_gaudi/no_wrapper_oob_four_gaudi_without_rerank.yaml

@@ -237,7 +237,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/oob/without_rerank/single_gaudi/no_wrapper_oob_single_gaudi_without_rerank.yaml

@@ -237,7 +237,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/oob/without_rerank/two_gaudi/no_wrapper_oob_two_gaudi_without_rerank.yaml

@@ -237,7 +237,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/oob_with_wrapper/with_rerank/four_gaudi/oob_four_gaudi_with_rerank.yaml

@@ -0,0 +1,641 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+data:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVICE_HOST_IP: llm-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVICE_HOST_IP: reranking-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
+kind: ConfigMap
+metadata:
+  name: qna-config
+  namespace: default
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        ports:
+        - containerPort: 8888
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    nodePort: 30888
+    port: 8888
+    targetPort: 8888
+  selector:
+    app: chatqna-backend-server-deploy
+  type: NodePort
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        ports:
+        - containerPort: 6007
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  selector:
+    app: dataprep-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        imagePullPolicy: IfNotPresent
+        name: embedding-dependency-deploy
+        ports:
+        - containerPort: 80
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+  selector:
+    app: embedding-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        ports:
+        - containerPort: 6000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+  selector:
+    app: embedding-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 31
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '2048'
+        - --max-total-tokens
+        - '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}
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        imagePullPolicy: IfNotPresent
+        name: llm-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+  selector:
+    app: llm-dependency-deploy
+  type: ClusterIP
+---
+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:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        ports:
+        - containerPort: 9000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+  selector:
+    app: llm-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(RERANK_MODEL_ID)
+        - --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'
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/tei-gaudi:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8808
+    targetPort: 80
+  selector:
+    app: reranking-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/reranking-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-deploy
+        ports:
+        - containerPort: 8000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8000
+    targetPort: 8000
+  selector:
+    app: reranking-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        ports:
+        - containerPort: 7000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: retriever-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+  selector:
+    app: retriever-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: vector-db
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: redis/redis-stack:7.2.0-v9
+        imagePullPolicy: IfNotPresent
+        name: vector-db
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: vector-db
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+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/oob_with_wrapper/with_rerank/single_gaudi/oob_single_gaudi_with_rerank.yaml

@@ -0,0 +1,641 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+data:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVICE_HOST_IP: llm-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVICE_HOST_IP: reranking-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
+kind: ConfigMap
+metadata:
+  name: qna-config
+  namespace: default
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        ports:
+        - containerPort: 8888
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    nodePort: 30888
+    port: 8888
+    targetPort: 8888
+  selector:
+    app: chatqna-backend-server-deploy
+  type: NodePort
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        ports:
+        - containerPort: 6007
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  selector:
+    app: dataprep-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        imagePullPolicy: IfNotPresent
+        name: embedding-dependency-deploy
+        ports:
+        - containerPort: 80
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+  selector:
+    app: embedding-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        ports:
+        - containerPort: 6000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+  selector:
+    app: embedding-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 7
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '2048'
+        - --max-total-tokens
+        - '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}
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        imagePullPolicy: IfNotPresent
+        name: llm-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+  selector:
+    app: llm-dependency-deploy
+  type: ClusterIP
+---
+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:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        ports:
+        - containerPort: 9000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+  selector:
+    app: llm-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(RERANK_MODEL_ID)
+        - --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'
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/tei-gaudi:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8808
+    targetPort: 80
+  selector:
+    app: reranking-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/reranking-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-deploy
+        ports:
+        - containerPort: 8000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8000
+    targetPort: 8000
+  selector:
+    app: reranking-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        ports:
+        - containerPort: 7000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: retriever-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+  selector:
+    app: retriever-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: vector-db
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: redis/redis-stack:7.2.0-v9
+        imagePullPolicy: IfNotPresent
+        name: vector-db
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: vector-db
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+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/oob_with_wrapper/with_rerank/two_gaudi/oob_two_gaudi_with_rerank.yaml

@@ -0,0 +1,641 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+data:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVICE_HOST_IP: llm-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVICE_HOST_IP: reranking-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
+kind: ConfigMap
+metadata:
+  name: qna-config
+  namespace: default
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        ports:
+        - containerPort: 8888
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    nodePort: 30888
+    port: 8888
+    targetPort: 8888
+  selector:
+    app: chatqna-backend-server-deploy
+  type: NodePort
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        ports:
+        - containerPort: 6007
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  selector:
+    app: dataprep-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        imagePullPolicy: IfNotPresent
+        name: embedding-dependency-deploy
+        ports:
+        - containerPort: 80
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+  selector:
+    app: embedding-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        ports:
+        - containerPort: 6000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+  selector:
+    app: embedding-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 15
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '2048'
+        - --max-total-tokens
+        - '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}
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        imagePullPolicy: IfNotPresent
+        name: llm-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+  selector:
+    app: llm-dependency-deploy
+  type: ClusterIP
+---
+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:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        ports:
+        - containerPort: 9000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+  selector:
+    app: llm-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(RERANK_MODEL_ID)
+        - --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'
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/tei-gaudi:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8808
+    targetPort: 80
+  selector:
+    app: reranking-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/reranking-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-deploy
+        ports:
+        - containerPort: 8000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8000
+    targetPort: 8000
+  selector:
+    app: reranking-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        ports:
+        - containerPort: 7000
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: retriever-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+  selector:
+    app: retriever-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: vector-db
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: redis/redis-stack:7.2.0-v9
+        imagePullPolicy: IfNotPresent
+        name: vector-db
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: vector-db
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+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/oob_with_wrapper/without_rerank/four_gaudi/oob_four_gaudi_without_rerank.yaml

@@ -0,0 +1,730 @@
+# 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: BAAI/bge-base-en-v1.5
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  TEI_EMBEDDING_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
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  INDEX_NAME: rag-redis
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  RERANK_SERVICE_HOST_IP: reranking-svc
+  NODE_SELECTOR: chatqna-opea
+  LLM_SERVICE_HOST_IP: llm-svc
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna-without-rerank:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        args: null
+        ports:
+        - containerPort: 8888
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  type: NodePort
+  selector:
+    app: chatqna-backend-server-deploy
+  ports:
+  - name: service
+    port: 8888
+    targetPort: 8888
+    nodePort: 30888
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        args: null
+        ports:
+        - containerPort: 6007
+        - containerPort: 6008
+        - containerPort: 6009
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: dataprep-deploy
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  - name: port2
+    port: 6008
+    targetPort: 6008
+  - name: port3
+    port: 6009
+    targetPort: 6009
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        name: embedding-dependency-deploy
+        args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-dependency-deploy
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: embedding-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        args: null
+        ports:
+        - containerPort: 6000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-deploy
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 32
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.1
+        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
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        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}
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-dependency-deploy
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+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:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: llm-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: 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
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-deploy
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: reranking-dependency-deploy
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/tei-gaudi:latest
+        name: reranking-dependency-deploy
+        args:
+        - --model-id
+        - $(RERANK_MODEL_ID)
+        - --auto-truncate
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        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'
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: reranking-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: reranking-dependency-deploy
+  ports:
+  - name: service
+    port: 8808
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: reranking-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/reranking-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-deploy
+        args: null
+        ports:
+        - containerPort: 8000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: reranking-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: reranking-deploy
+  ports:
+  - name: service
+    port: 8000
+    targetPort: 8000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: retriever-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_EMBEDDING_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: HUGGINGFACEHUB_API_TOKEN
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: HUGGINGFACEHUB_API_TOKEN
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        args: null
+        ports:
+        - containerPort: 7000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: retriever-deploy
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      labels:
+        app: vector-db
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: vector-db
+      containers:
+      - name: vector-db
+        image: redis/redis-stack:7.2.0-v9
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: vector-db
+  ports:
+  - name: vector-db-service
+    port: 6379
+    targetPort: 6379
+  - name: vector-db-insight
+    port: 8001
+    targetPort: 8001
+
+
+---

ChatQnA/benchmark/performance/oob_with_wrapper/without_rerank/single_gaudi/oob_single_gaudi_without_rerank.yaml

@@ -0,0 +1,579 @@
+# 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: BAAI/bge-base-en-v1.5
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  TEI_EMBEDDING_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
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  INDEX_NAME: rag-redis
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  RERANK_SERVICE_HOST_IP: reranking-svc
+  NODE_SELECTOR: chatqna-opea
+  LLM_SERVICE_HOST_IP: llm-svc
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna-without-rerank:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        args: null
+        ports:
+        - containerPort: 8888
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  type: NodePort
+  selector:
+    app: chatqna-backend-server-deploy
+  ports:
+  - name: service
+    port: 8888
+    targetPort: 8888
+    nodePort: 30888
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        args: null
+        ports:
+        - containerPort: 6007
+        - containerPort: 6008
+        - containerPort: 6009
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: dataprep-deploy
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  - name: port2
+    port: 6008
+    targetPort: 6008
+  - name: port3
+    port: 6009
+    targetPort: 6009
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        name: embedding-dependency-deploy
+        args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-dependency-deploy
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: embedding-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        args: null
+        ports:
+        - containerPort: 6000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-deploy
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 8
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.1
+        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
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        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}
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-dependency-deploy
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+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:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: llm-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: 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
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-deploy
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: retriever-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_EMBEDDING_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: HUGGINGFACEHUB_API_TOKEN
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: HUGGINGFACEHUB_API_TOKEN
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        args: null
+        ports:
+        - containerPort: 7000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: retriever-deploy
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      labels:
+        app: vector-db
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: vector-db
+      containers:
+      - name: vector-db
+        image: redis/redis-stack:7.2.0-v9
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: vector-db
+  ports:
+  - name: vector-db-service
+    port: 6379
+    targetPort: 6379
+  - name: vector-db-insight
+    port: 8001
+    targetPort: 8001
+
+
+---

ChatQnA/benchmark/performance/oob_with_wrapper/without_rerank/two_gaudi/oob_two_gaudi_without_rerank.yaml

@@ -0,0 +1,579 @@
+# 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: BAAI/bge-base-en-v1.5
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  TEI_EMBEDDING_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
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  INDEX_NAME: rag-redis
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  RERANK_SERVICE_HOST_IP: reranking-svc
+  NODE_SELECTOR: chatqna-opea
+  LLM_SERVICE_HOST_IP: llm-svc
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna-without-rerank:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        args: null
+        ports:
+        - containerPort: 8888
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  type: NodePort
+  selector:
+    app: chatqna-backend-server-deploy
+  ports:
+  - name: service
+    port: 8888
+    targetPort: 8888
+    nodePort: 30888
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        args: null
+        ports:
+        - containerPort: 6007
+        - containerPort: 6008
+        - containerPort: 6009
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: dataprep-deploy
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  - name: port2
+    port: 6008
+    targetPort: 6008
+  - name: port3
+    port: 6009
+    targetPort: 6009
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        name: embedding-dependency-deploy
+        args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-dependency-deploy
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: embedding-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        args: null
+        ports:
+        - containerPort: 6000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-deploy
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 16
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.1
+        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
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        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}
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-dependency-deploy
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+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:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: llm-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: 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
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-deploy
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: retriever-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_EMBEDDING_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: HUGGINGFACEHUB_API_TOKEN
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: HUGGINGFACEHUB_API_TOKEN
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        args: null
+        ports:
+        - containerPort: 7000
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: retriever-deploy
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      labels:
+        app: vector-db
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: vector-db
+      containers:
+      - name: vector-db
+        image: redis/redis-stack:7.2.0-v9
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: vector-db
+  ports:
+  - name: vector-db-service
+    port: 6379
+    targetPort: 6379
+  - name: vector-db-insight
+    port: 8001
+    targetPort: 8001
+
+
+---

ChatQnA/benchmark/performance/tuned/with_rerank/eight_gaudi/no_wrapper_tuned_eight_gaudi_with_rerank.yaml

@@ -255,7 +255,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned/with_rerank/four_gaudi/no_wrapper_tuned_four_gaudi_with_rerank.yaml

@@ -255,7 +255,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned/with_rerank/single_gaudi/no_wrapper_tuned_single_gaudi_with_rerank.yaml

@@ -255,7 +255,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned/with_rerank/two_gaudi/no_wrapper_tuned_two_gaudi_with_rerank.yaml

@@ -255,7 +255,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned/without_rerank/eight_gaudi/no_wrapper_tuned_eight_gaudi_without_rerank.yaml

@@ -255,7 +255,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned/without_rerank/four_gaudi/no_wrapper_tuned_four_gaudi_without_rerank.yaml

@@ -255,7 +255,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned/without_rerank/single_gaudi/no_wrapper_tuned_single_gaudi_without_rerank.yaml

@@ -255,7 +255,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned/without_rerank/two_gaudi/no_wrapper_tuned_two_gaudi_without_rerank.yaml

@@ -255,7 +255,7 @@ spec:
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned_with_wrapper/with_rerank/four_gaudi/tuned_four_gaudi_with_rerank.yaml

@@ -306,20 +306,12 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned_with_wrapper/with_rerank/single_gaudi/tuned_single_gaudi_with_rerank.yaml

@@ -306,20 +306,12 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned_with_wrapper/with_rerank/two_gaudi/tuned_two_gaudi_with_rerank.yaml

@@ -306,20 +306,12 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
         envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         imagePullPolicy: IfNotPresent
         name: llm-dependency-deploy
         ports:

ChatQnA/benchmark/performance/tuned_with_wrapper/without_rerank/four_gaudi/tuned_four_gaudi_without_rerank.yaml

@@ -342,7 +342,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:
@@ -378,16 +378,8 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
       serviceAccountName: default
       volumes:
       - name: model-volume

ChatQnA/benchmark/performance/tuned_with_wrapper/without_rerank/single_gaudi/tuned_single_gaudi_without_rerank.yaml

@@ -342,7 +342,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:
@@ -378,16 +378,8 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
       serviceAccountName: default
       volumes:
       - name: model-volume

ChatQnA/benchmark/performance/tuned_with_wrapper/without_rerank/two_gaudi/tuned_two_gaudi_without_rerank.yaml

@@ -342,7 +342,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: qna-config
-        image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:
@@ -378,16 +378,8 @@ spec:
           value: habana
         - name: HABANA_VISIBLE_DEVICES
           value: all
-        - name: HUGGING_FACE_HUB_TOKEN
+        - name: HF_TOKEN
           value: ${HF_TOKEN}
-        - name: ENABLE_HPU_GRAPH
-          value: 'true'
-        - name: LIMIT_HPU_GRAPH
-          value: 'true'
-        - name: USE_FLASH_ATTENTION
-          value: 'true'
-        - name: FLASH_ATTENTION_RECOMPUTE
-          value: 'true'
       serviceAccountName: default
       volumes:
       - name: model-volume

ChatQnA/benchmark/tuned_with_wrapper/with_rerank/four_gaudi/tuned_four_gaudi_with_rerank.yaml

@@ -0,0 +1,675 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+data:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVICE_HOST_IP: llm-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVICE_HOST_IP: reranking-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
+kind: ConfigMap
+metadata:
+  name: qna-config
+  namespace: default
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        ports:
+        - containerPort: 8888
+        resources:
+          limits:
+            cpu: 8
+            memory: 8000Mi
+          requests:
+            cpu: 8
+            memory: 8000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    nodePort: 30888
+    port: 8888
+    targetPort: 8888
+  selector:
+    app: chatqna-backend-server-deploy
+  type: NodePort
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        ports:
+        - containerPort: 6007
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  selector:
+    app: dataprep-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        imagePullPolicy: IfNotPresent
+        name: embedding-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            cpu: 76
+            memory: 20000Mi
+          requests:
+            cpu: 76
+            memory: 20000Mi
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+  selector:
+    app: embedding-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        ports:
+        - containerPort: 6000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+  selector:
+    app: embedding-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 31
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '1024'
+        - --max-total-tokens
+        - '2048'
+        - --max-batch-total-tokens
+        - '65536'
+        - --max-batch-prefill-tokens
+        - '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}
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        imagePullPolicy: IfNotPresent
+        name: llm-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+  selector:
+    app: llm-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: llm-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        ports:
+        - containerPort: 9000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+  selector:
+    app: llm-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(RERANK_MODEL_ID)
+        - --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'
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/tei-gaudi:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8808
+    targetPort: 80
+  selector:
+    app: reranking-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: reranking-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/reranking-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-deploy
+        ports:
+        - containerPort: 8000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8000
+    targetPort: 8000
+  selector:
+    app: reranking-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        ports:
+        - containerPort: 7000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: retriever-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+  selector:
+    app: retriever-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: vector-db
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: redis/redis-stack:7.2.0-v9
+        imagePullPolicy: IfNotPresent
+        name: vector-db
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: vector-db
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+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/tuned_with_wrapper/with_rerank/single_gaudi/tuned_single_gaudi_with_rerank.yaml

@@ -0,0 +1,675 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+data:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVICE_HOST_IP: llm-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVICE_HOST_IP: reranking-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
+kind: ConfigMap
+metadata:
+  name: qna-config
+  namespace: default
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        ports:
+        - containerPort: 8888
+        resources:
+          limits:
+            cpu: 8
+            memory: 8000Mi
+          requests:
+            cpu: 8
+            memory: 8000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    nodePort: 30888
+    port: 8888
+    targetPort: 8888
+  selector:
+    app: chatqna-backend-server-deploy
+  type: NodePort
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        ports:
+        - containerPort: 6007
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  selector:
+    app: dataprep-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        imagePullPolicy: IfNotPresent
+        name: embedding-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            cpu: 76
+            memory: 20000Mi
+          requests:
+            cpu: 76
+            memory: 20000Mi
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+  selector:
+    app: embedding-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        ports:
+        - containerPort: 6000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+  selector:
+    app: embedding-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 7
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '1024'
+        - --max-total-tokens
+        - '2048'
+        - --max-batch-total-tokens
+        - '65536'
+        - --max-batch-prefill-tokens
+        - '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}
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        imagePullPolicy: IfNotPresent
+        name: llm-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+  selector:
+    app: llm-dependency-deploy
+  type: ClusterIP
+---
+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:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        ports:
+        - containerPort: 9000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+  selector:
+    app: llm-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(RERANK_MODEL_ID)
+        - --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'
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/tei-gaudi:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8808
+    targetPort: 80
+  selector:
+    app: reranking-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/reranking-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-deploy
+        ports:
+        - containerPort: 8000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8000
+    targetPort: 8000
+  selector:
+    app: reranking-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        ports:
+        - containerPort: 7000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: retriever-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+  selector:
+    app: retriever-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: vector-db
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: redis/redis-stack:7.2.0-v9
+        imagePullPolicy: IfNotPresent
+        name: vector-db
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: vector-db
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+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/tuned_with_wrapper/with_rerank/two_gaudi/tuned_two_gaudi_with_rerank.yaml

@@ -0,0 +1,675 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+data:
+  EMBEDDING_MODEL_ID: BAAI/bge-base-en-v1.5
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  INDEX_NAME: rag-redis
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  LLM_SERVICE_HOST_IP: llm-svc
+  NODE_SELECTOR: chatqna-opea
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  RERANK_SERVICE_HOST_IP: reranking-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
+kind: ConfigMap
+metadata:
+  name: qna-config
+  namespace: default
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        ports:
+        - containerPort: 8888
+        resources:
+          limits:
+            cpu: 8
+            memory: 8000Mi
+          requests:
+            cpu: 8
+            memory: 8000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    nodePort: 30888
+    port: 8888
+    targetPort: 8888
+  selector:
+    app: chatqna-backend-server-deploy
+  type: NodePort
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        ports:
+        - containerPort: 6007
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  selector:
+    app: dataprep-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        imagePullPolicy: IfNotPresent
+        name: embedding-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            cpu: 76
+            memory: 20000Mi
+          requests:
+            cpu: 76
+            memory: 20000Mi
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+  selector:
+    app: embedding-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        ports:
+        - containerPort: 6000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: embedding-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+  selector:
+    app: embedding-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 15
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '1024'
+        - --max-total-tokens
+        - '2048'
+        - --max-batch-total-tokens
+        - '65536'
+        - --max-batch-prefill-tokens
+        - '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}
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        imagePullPolicy: IfNotPresent
+        name: llm-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+  selector:
+    app: llm-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: llm-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        ports:
+        - containerPort: 9000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: llm-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+  selector:
+    app: llm-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: reranking-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-dependency-deploy
+    spec:
+      containers:
+      - args:
+        - --model-id
+        - $(RERANK_MODEL_ID)
+        - --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'
+        envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/tei-gaudi:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-dependency-deploy
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-dependency-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+      volumes:
+      - hostPath:
+          path: /mnt/models
+          type: Directory
+        name: model-volume
+      - emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+        name: shm
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-dependency-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8808
+    targetPort: 80
+  selector:
+    app: reranking-dependency-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: reranking-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: reranking-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: reranking-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/reranking-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: reranking-deploy
+        ports:
+        - containerPort: 8000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: reranking-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: reranking-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 8000
+    targetPort: 8000
+  selector:
+    app: reranking-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        ports:
+        - containerPort: 7000
+        resources:
+          requests:
+            cpu: 4
+            memory: 4000Mi
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: retriever-deploy
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+  selector:
+    app: retriever-deploy
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: vector-db
+    spec:
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: redis/redis-stack:7.2.0-v9
+        imagePullPolicy: IfNotPresent
+        name: vector-db
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+      hostIPC: true
+      nodeSelector:
+        node-type: chatqna-opea
+      serviceAccountName: default
+      topologySpreadConstraints:
+      - labelSelector:
+          matchLabels:
+            app: vector-db
+        maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+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/tuned_with_wrapper/without_rerank/four_gaudi/tuned_four_gaudi_without_rerank.yaml

@@ -0,0 +1,614 @@
+# 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: BAAI/bge-base-en-v1.5
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  TEI_EMBEDDING_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
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  INDEX_NAME: rag-redis
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  RERANK_SERVICE_HOST_IP: reranking-svc
+  NODE_SELECTOR: chatqna-opea
+  LLM_SERVICE_HOST_IP: llm-svc
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna-without-rerank:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        args: null
+        ports:
+        - containerPort: 8888
+        resources:
+          limits:
+            cpu: 8
+            memory: 4000Mi
+          requests:
+            cpu: 8
+            memory: 4000Mi
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  type: NodePort
+  selector:
+    app: chatqna-backend-server-deploy
+  ports:
+  - name: service
+    port: 8888
+    targetPort: 8888
+    nodePort: 30888
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        args: null
+        ports:
+        - containerPort: 6007
+        - containerPort: 6008
+        - containerPort: 6009
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: dataprep-deploy
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  - name: port2
+    port: 6008
+    targetPort: 6008
+  - name: port3
+    port: 6009
+    targetPort: 6009
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        name: embedding-dependency-deploy
+        args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            cpu: 76
+            memory: 20000Mi
+          requests:
+            cpu: 76
+            memory: 20000Mi
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-dependency-deploy
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: embedding-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        args: null
+        ports:
+        - containerPort: 6000
+        resources:
+          limits:
+            cpu: 4
+          requests:
+            cpu: 4
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-deploy
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 32
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        name: llm-dependency-deploy-demo
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '1024'
+        - --max-total-tokens
+        - '2048'
+        - --max-batch-total-tokens
+        - '65536'
+        - --max-batch-prefill-tokens
+        - '4096'
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        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}
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-dependency-deploy
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: llm-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: llm-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        args: null
+        ports:
+        - containerPort: 9000
+        resources:
+          limits:
+            cpu: 4
+          requests:
+            cpu: 4
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-deploy
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 4
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: retriever-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_EMBEDDING_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: HUGGINGFACEHUB_API_TOKEN
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: HUGGINGFACEHUB_API_TOKEN
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        args: null
+        ports:
+        - containerPort: 7000
+        resources:
+          limits:
+            cpu: 8
+            memory: 2500Mi
+          requests:
+            cpu: 8
+            memory: 2500Mi
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: retriever-deploy
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      labels:
+        app: vector-db
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: vector-db
+      containers:
+      - name: vector-db
+        image: redis/redis-stack:7.2.0-v9
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: vector-db
+  ports:
+  - name: vector-db-service
+    port: 6379
+    targetPort: 6379
+  - name: vector-db-insight
+    port: 8001
+    targetPort: 8001
+
+
+---

ChatQnA/benchmark/tuned_with_wrapper/without_rerank/single_gaudi/tuned_single_gaudi_without_rerank.yaml

@@ -0,0 +1,614 @@
+# 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: BAAI/bge-base-en-v1.5
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  TEI_EMBEDDING_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
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  INDEX_NAME: rag-redis
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  RERANK_SERVICE_HOST_IP: reranking-svc
+  NODE_SELECTOR: chatqna-opea
+  LLM_SERVICE_HOST_IP: llm-svc
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna-without-rerank:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        args: null
+        ports:
+        - containerPort: 8888
+        resources:
+          limits:
+            cpu: 8
+            memory: 4000Mi
+          requests:
+            cpu: 8
+            memory: 4000Mi
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  type: NodePort
+  selector:
+    app: chatqna-backend-server-deploy
+  ports:
+  - name: service
+    port: 8888
+    targetPort: 8888
+    nodePort: 30888
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        args: null
+        ports:
+        - containerPort: 6007
+        - containerPort: 6008
+        - containerPort: 6009
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: dataprep-deploy
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  - name: port2
+    port: 6008
+    targetPort: 6008
+  - name: port3
+    port: 6009
+    targetPort: 6009
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        name: embedding-dependency-deploy
+        args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            cpu: 76
+            memory: 20000Mi
+          requests:
+            cpu: 76
+            memory: 20000Mi
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-dependency-deploy
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: embedding-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        args: null
+        ports:
+        - containerPort: 6000
+        resources:
+          limits:
+            cpu: 4
+          requests:
+            cpu: 4
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-deploy
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 8
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        name: llm-dependency-deploy-demo
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '1024'
+        - --max-total-tokens
+        - '2048'
+        - --max-batch-total-tokens
+        - '65536'
+        - --max-batch-prefill-tokens
+        - '4096'
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        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}
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-dependency-deploy
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+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:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: llm-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        args: null
+        ports:
+        - containerPort: 9000
+        resources:
+          limits:
+            cpu: 4
+          requests:
+            cpu: 4
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-deploy
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: retriever-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_EMBEDDING_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: HUGGINGFACEHUB_API_TOKEN
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: HUGGINGFACEHUB_API_TOKEN
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        args: null
+        ports:
+        - containerPort: 7000
+        resources:
+          limits:
+            cpu: 8
+            memory: 2500Mi
+          requests:
+            cpu: 8
+            memory: 2500Mi
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: retriever-deploy
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      labels:
+        app: vector-db
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: vector-db
+      containers:
+      - name: vector-db
+        image: redis/redis-stack:7.2.0-v9
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: vector-db
+  ports:
+  - name: vector-db-service
+    port: 6379
+    targetPort: 6379
+  - name: vector-db-insight
+    port: 8001
+    targetPort: 8001
+
+
+---

ChatQnA/benchmark/tuned_with_wrapper/without_rerank/two_gaudi/tuned_two_gaudi_without_rerank.yaml

@@ -0,0 +1,614 @@
+# 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: BAAI/bge-base-en-v1.5
+  RERANK_MODEL_ID: BAAI/bge-reranker-base
+  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
+  TEI_EMBEDDING_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
+  REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
+  INDEX_NAME: rag-redis
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+  EMBEDDING_SERVICE_HOST_IP: embedding-svc
+  RETRIEVER_SERVICE_HOST_IP: retriever-svc
+  RERANK_SERVICE_HOST_IP: reranking-svc
+  NODE_SELECTOR: chatqna-opea
+  LLM_SERVICE_HOST_IP: llm-svc
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: chatqna-backend-server-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: chatqna-backend-server-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: chatqna-backend-server-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: chatqna-backend-server-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/chatqna-without-rerank:latest
+        imagePullPolicy: IfNotPresent
+        name: chatqna-backend-server-deploy
+        args: null
+        ports:
+        - containerPort: 8888
+        resources:
+          limits:
+            cpu: 8
+            memory: 4000Mi
+          requests:
+            cpu: 8
+            memory: 4000Mi
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: chatqna-backend-server-svc
+  namespace: default
+spec:
+  type: NodePort
+  selector:
+    app: chatqna-backend-server-deploy
+  ports:
+  - name: service
+    port: 8888
+    targetPort: 8888
+    nodePort: 30888
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dataprep-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: dataprep-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: dataprep-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: dataprep-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/dataprep-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: dataprep-deploy
+        args: null
+        ports:
+        - containerPort: 6007
+        - containerPort: 6008
+        - containerPort: 6009
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: dataprep-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: dataprep-deploy
+  ports:
+  - name: port1
+    port: 6007
+    targetPort: 6007
+  - name: port2
+    port: 6008
+    targetPort: 6008
+  - name: port3
+    port: 6009
+    targetPort: 6009
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-dependency-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: embedding-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+        name: embedding-dependency-deploy
+        args:
+        - --model-id
+        - $(EMBEDDING_MODEL_ID)
+        - --auto-truncate
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            cpu: 76
+            memory: 20000Mi
+          requests:
+            cpu: 76
+            memory: 20000Mi
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-dependency-deploy
+  ports:
+  - name: service
+    port: 6006
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: embedding-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: embedding-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: embedding-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: embedding-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/embedding-tei:latest
+        imagePullPolicy: IfNotPresent
+        name: embedding-deploy
+        args: null
+        ports:
+        - containerPort: 6000
+        resources:
+          limits:
+            cpu: 4
+          requests:
+            cpu: 4
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: embedding-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: embedding-deploy
+  ports:
+  - name: service
+    port: 6000
+    targetPort: 6000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-dependency-deploy
+  namespace: default
+spec:
+  replicas: 16
+  selector:
+    matchLabels:
+      app: llm-dependency-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-dependency-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+        name: llm-dependency-deploy-demo
+        securityContext:
+          capabilities:
+            add:
+            - SYS_NICE
+        args:
+        - --model-id
+        - $(LLM_MODEL_ID)
+        - --max-input-length
+        - '1024'
+        - --max-total-tokens
+        - '2048'
+        - --max-batch-total-tokens
+        - '65536'
+        - --max-batch-prefill-tokens
+        - '4096'
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+        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}
+      serviceAccountName: default
+      volumes:
+      - name: model-volume
+        hostPath:
+          path: /mnt/models
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-dependency-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-dependency-deploy
+  ports:
+  - name: service
+    port: 9009
+    targetPort: 80
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llm-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: llm-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: llm-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: llm-deploy
+      hostIPC: true
+      containers:
+      - envFrom:
+        - configMapRef:
+            name: qna-config
+        image: opea/llm-tgi:latest
+        imagePullPolicy: IfNotPresent
+        name: llm-deploy
+        args: null
+        ports:
+        - containerPort: 9000
+        resources:
+          limits:
+            cpu: 4
+          requests:
+            cpu: 4
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: llm-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: llm-deploy
+  ports:
+  - name: service
+    port: 9000
+    targetPort: 9000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: retriever-deploy
+  namespace: default
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: retriever-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: retriever-deploy
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: retriever-deploy
+      hostIPC: true
+      containers:
+      - env:
+        - name: REDIS_URL
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: REDIS_URL
+        - name: TEI_EMBEDDING_ENDPOINT
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: TEI_EMBEDDING_ENDPOINT
+        - name: HUGGINGFACEHUB_API_TOKEN
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: HUGGINGFACEHUB_API_TOKEN
+        - name: INDEX_NAME
+          valueFrom:
+            configMapKeyRef:
+              name: qna-config
+              key: INDEX_NAME
+        image: opea/retriever-redis:latest
+        imagePullPolicy: IfNotPresent
+        name: retriever-deploy
+        args: null
+        ports:
+        - containerPort: 7000
+        resources:
+          limits:
+            cpu: 8
+            memory: 2500Mi
+          requests:
+            cpu: 8
+            memory: 2500Mi
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: retriever-svc
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: retriever-deploy
+  ports:
+  - name: service
+    port: 7000
+    targetPort: 7000
+
+
+---
+
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: vector-db
+  template:
+    metadata:
+      labels:
+        app: vector-db
+    spec:
+      nodeSelector:
+        node-type: chatqna-opea
+      topologySpreadConstraints:
+      - maxSkew: 1
+        topologyKey: kubernetes.io/hostname
+        whenUnsatisfiable: ScheduleAnyway
+        labelSelector:
+          matchLabels:
+            app: vector-db
+      containers:
+      - name: vector-db
+        image: redis/redis-stack:7.2.0-v9
+        ports:
+        - containerPort: 6379
+        - containerPort: 8001
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vector-db
+  namespace: default
+spec:
+  type: ClusterIP
+  selector:
+    app: vector-db
+  ports:
+  - name: vector-db-service
+    port: 6379
+    targetPort: 6379
+  - name: vector-db-insight
+    port: 8001
+    targetPort: 8001
+
+
+---

ChatQnA/docker_compose/install_docker.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Update the package index
+sudo apt-get -y update
+
+# Install prerequisites
+sudo apt-get -y install ca-certificates curl
+
+# Create the directory for the Docker GPG key
+sudo install -m 0755 -d /etc/apt/keyrings
+
+# Add Docker's official GPG key
+sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
+
+# Set permissions for the GPG key
+sudo chmod a+r /etc/apt/keyrings/docker.asc
+
+# Add Docker repository to the sources list
+echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
+  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
+
+# Update the package index with Docker packages
+sudo apt-get -y update
+
+# Install Docker packages
+sudo apt-get -y install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
+
+# add existing user
+sudo usermod -aG docker $USER
+
+# Optional: Verify that Docker is installed correctly
+sudo docker --version

ChatQnA/docker_compose/intel/cpu/aipc/README.md

@@ -11,36 +11,84 @@ git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
 ```
 
+If you are in a proxy environment, set the proxy-related environment variables:
+
+export http_proxy="Your_HTTP_Proxy"
+export https_proxy="Your_HTTPs_Proxy"
+
 ### 1. Build Embedding Image
 
 ```bash
-docker build --no-cache -t opea/embedding-tei:latest -f comps/embeddings/tei/langchain/Dockerfile .
+docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/tei/langchain/Dockerfile .
 ```
 
 ### 2. Build Retriever Image
 
 ```bash
-docker build --no-cache -t opea/retriever-redis:latest -f comps/retrievers/redis/langchain/Dockerfile .
+docker build --no-cache -t opea/retriever-redis:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/redis/langchain/Dockerfile .
 ```
 
 ### 3. Build Rerank Image
 
 ```bash
-docker build --no-cache -t opea/reranking-tei:latest -f comps/reranks/tei/Dockerfile .
+docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/tei/Dockerfile .
 ```
 
-### 4. Build LLM Image
+### 4. Set up Ollama Service and Build LLM Image
 
-We use [Ollama](https://ollama.com/) as our LLM service for AIPC. Please pre-download Ollama on your PC.
+We use [Ollama](https://ollama.com/) as our LLM service for AIPC.
+
+Please set up Ollama on your PC follow the instructions. This will set the entrypoint needed for the Ollama to suit the ChatQnA examples.
+
+#### 4.1 Set Up Ollama LLM Service
+
+Install Ollama service with one command
+
+curl -fsSL https://ollama.com/install.sh | sh
+
+##### Set Ollama Service Configuration
+
+Ollama Service Configuration file is /etc/systemd/system/ollama.service. Edit the file to set OLLAMA_HOST environment (Replace **${host_ip}** with your host IPV4).
+
+```
+Environment="OLLAMA_HOST=${host_ip}:11434"
+```
+
+##### Set https_proxy environment for Ollama
+
+if your system access network through proxy, add https_proxy in Ollama Service Configuration file
+
+```
+Environment="https_proxy="Your_HTTPS_Proxy"
+```
+
+##### Restart Ollam services
+
+```
+$ sudo systemctl daemon-reload
+$ sudo systemctl restart ollama.service
+```
+
+##### Pull LLM model
+
+```
+#export OLLAMA_HOST=http://${host_ip}:11434
+#ollama pull llam3
+#ollama lists
+NAME            ID              SIZE    MODIFIED
+llama3:latest   365c0bd3c000    4.7 GB  5 days ago
+```
+
+#### 4.2 Build LLM Image
 
 ```bash
-docker build --no-cache -t opea/llm-ollama:latest -f comps/llms/text-generation/ollama/langchain/Dockerfile .
+docker build --no-cache -t opea/llm-ollama:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/ollama/langchain/Dockerfile .
 ```
 
 ### 5. Build Dataprep Image
 
 ```bash
-docker build --no-cache -t opea/dataprep-redis:latest -f comps/dataprep/redis/langchain/Dockerfile .
+docker build --no-cache -t opea/dataprep-redis:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/redis/langchain/Dockerfile .
 cd ..
 ```
 
@@ -61,7 +109,7 @@ Build frontend Docker image via below command:
 
 ```bash
 cd GenAIExamples/ChatQnA/ui
-docker build --no-cache -t opea/chatqna-ui:latest -f ./docker/Dockerfile .
+docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
 cd ../../../..
 ```
 

ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh

@@ -10,6 +10,7 @@ export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
 export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
 export TGI_LLM_ENDPOINT="http://${host_ip}:9009"
+export vLLM_LLM_ENDPOINT="http://${host_ip}:9009"
 export REDIS_URL="redis://${host_ip}:6379"
 export INDEX_NAME="rag-redis"
 export REDIS_HOST=${host_ip}

ChatQnA/kubernetes/intel/README.md

@@ -13,7 +13,7 @@
 ## Deploy On Xeon
 
 ```
-cd GenAIExamples/ChatQnA/kubernetes/intel/cpu/xeon/manifests
+cd GenAIExamples/ChatQnA/kubernetes/intel/cpu/xeon/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" chatqna.yaml
 kubectl apply -f chatqna.yaml
@@ -33,7 +33,7 @@ kubectl apply -f chatqna_bf16.yaml
 ## Deploy On Gaudi
 
 ```
-cd GenAIExamples/ChatQnA/kubernetes/intel/hpu/gaudi/manifests
+cd GenAIExamples/ChatQnA/kubernetes/intel/hpu/gaudi/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" chatqna.yaml
 kubectl apply -f chatqna.yaml

ChatQnA/kubernetes/intel/README_gmc.md

@@ -2,9 +2,9 @@
 
 This document outlines the deployment process for a ChatQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline components on Intel Xeon server and Gaudi machines.
 
-The ChatQnA Service leverages a Kubernetes operator called genai-microservices-connector(GMC). GMC supports connecting microservices to create pipelines based on the specification in the pipeline yaml file in addition to allowing the user to dynamically control which model is used in a service such as an LLM or embedder. The underlying pipeline language also supports using external services that may be running in public or private cloud elsewhere.
+The ChatQnA Service leverages a Kubernetes operator called genai-microservices-connector (GMC). GMC supports connecting microservices to create pipelines based on the specification in the pipeline yaml file in addition to allowing the user to dynamically control which model is used in a service such as an LLM or embedder. The underlying pipeline language also supports using external services that may be running in public or private cloud elsewhere.
 
-Install GMC  in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector). Soon as we publish images to Docker Hub, at which point no builds will be required, simplifying install.
+Install GMC  in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md). Soon as we publish images to Docker Hub, at which point no builds will be required, simplifying install.
 
 
 The ChatQnA application is defined as a Custom Resource (CR) file that the above GMC operator acts  upon. It first checks if the microservices listed in the CR yaml file are running, if not starts them and then proceeds to connect them. When the ChatQnA RAG pipeline is ready, the service endpoint details are returned, letting you use the application. Should you use "kubectl get pods" commands you will see all the component microservices, in particular `embedding`, `retriever`, `rerank`, and `llm`.

ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml

@@ -1294,7 +1294,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/tei-gaudi:synapse_1.16"
+          image: "ghcr.io/huggingface/tei-gaudi:latest"
           imagePullPolicy: IfNotPresent
           args:
             - "--auto-truncate"

ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml

@@ -1115,7 +1115,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/tei-gaudi:synapse_1.16"
+          image: "ghcr.io/huggingface/tei-gaudi:latest"
           imagePullPolicy: IfNotPresent
           args:
             - "--auto-truncate"

CodeGen/README.md

@@ -106,7 +106,7 @@ Refer to the [Kubernetes Guide](./kubernetes/intel/README.md) for instructions o
 
 Install Helm (version >= 3.15) first. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
 
-Refer to the [CodeGen helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codegen) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi.
+Refer to the [CodeGen helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codegen/README.md) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi.
 
 ## Consume CodeGen Service
 
@@ -128,7 +128,7 @@ Two ways of consuming CodeGen Service:
 
 ## Troubleshooting
 
-1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/CodeGen/docker_compose/intel/cpu/xeon#validate-microservices) first. A simple example:
+1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/CodeGen/docker_compose/intel/cpu/xeon/README.md#validate-microservices) first. A simple example:
 
    ```bash
    http_proxy=""

CodeGen/benchmark/accuracy/README.md

@@ -8,7 +8,7 @@ We evaluate accuracy by [bigcode-evaluation-harness](https://github.com/bigcode-
 
 ### Launch CodeGen microservice
 
-Please refer to [CodeGen Examples](https://github.com/opea-project/GenAIExamples/tree/main/CodeGen), follow the guide to deploy CodeGen megeservice.
+Please refer to [CodeGen Examples](https://github.com/opea-project/GenAIExamples/tree/main/CodeGen/README.md), follow the guide to deploy CodeGen megeservice.
 
 Use `curl` command to test codegen service and ensure that it has started properly
 

CodeGen/kubernetes/intel/README_gmc.md

@@ -2,7 +2,7 @@
 
 This document outlines the deployment process for a Code Generation (CodeGen) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
 
-Install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
+Install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
 
 If you have only Intel Xeon machines you could use the codegen_xeon.yaml file or if you have a Gaudi cluster you could use codegen_gaudi.yaml
 In the below example we illustrate on Xeon.

CodeTrans/README.md

@@ -99,7 +99,7 @@ Refer to the [Code Translation Kubernetes Guide](./kubernetes/intel/README.md)
 
 Install Helm (version >= 3.15) first. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
 
-Refer to the [CodeTrans helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codetrans) for instructions on deploying CodeTrans into Kubernetes on Xeon & Gaudi.
+Refer to the [CodeTrans helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codetrans/README.md) for instructions on deploying CodeTrans into Kubernetes on Xeon & Gaudi.
 
 ## Consume Code Translation Service
 
@@ -121,7 +121,7 @@ By default, the UI runs on port 5173 internally.
 
 ## Troubleshooting
 
-1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/CodeTrans/docker_compose/intel/cpu/xeon#validate-microservices) first. A simple example:
+1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/CodeTrans/docker_compose/intel/cpu/xeon/README.md#validate-microservices) first. A simple example:
 
    ```bash
    http_proxy=""

CodeTrans/kubernetes/intel/README_gmc.md

@@ -2,7 +2,7 @@
 
 This document outlines the deployment process for a Code Translation (CodeTran) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
 
-Please install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
+Please install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
 
 If you have only Intel Xeon machines you could use the codetrans_xeon.yaml file or if you have a Gaudi cluster you could use codetrans_gaudi.yaml
 In the below example we illustrate on Xeon.

DocIndexRetriever/README.md

@@ -1,8 +1,22 @@
 # DocRetriever Application
 
-DocRetriever are the most widely adopted use case for leveraging the different methodologies to match user query against a set of free-text records. DocRetriever is essential to RAG system, which bridges the knowledge gap by dynamically fetching relevant information from external sources, ensuring that responses generated remain factual and current. The core of this architecture are vector databases, which are instrumental in enabling efficient and semantic retrieval of information. These databases store data as vectors, allowing RAG to swiftly access the most pertinent documents or data points based on semantic similarity.
+DocRetriever is the most widely adopted use case for leveraging the different methodologies to match user query against a set of free-text records. DocRetriever is essential to RAG system, which bridges the knowledge gap by dynamically fetching relevant information from external sources, ensuring that responses generated remain factual and current. The core of this architecture are vector databases, which are instrumental in enabling efficient and semantic retrieval of information. These databases store data as vectors, allowing RAG to swiftly access the most pertinent documents or data points based on semantic similarity.
 
 ## We provided DocRetriever with different deployment infra
 
-- [docker xeon version](docker_compose/intel/cpu/xeon/) => minimum endpoints, easy to setup
-- [docker gaudi version](docker_compose/intel/hpu/gaudi/) => with extra tei_gaudi endpoint, faster
+- [docker xeon version](docker_compose/intel/cpu/xeon/README.md) => minimum endpoints, easy to setup
+- [docker gaudi version](docker_compose/intel/hpu/gaudi/README.md) => with extra tei_gaudi endpoint, faster
+
+## We allow users to set retriever/reranker hyperparams via requests
+
+Example usage:
+
+```python
+url = "http://{host_ip}:{port}/v1/retrievaltool".format(host_ip=host_ip, port=port)
+payload = {
+    "messages": query,
+    "k": 5,  # retriever top k
+    "top_n": 2,  # reranker top n
+}
+response = requests.post(url, json=payload)
+```

DocIndexRetriever/docker_compose/intel/cpu/xeon/README.md

@@ -79,13 +79,26 @@ Retrieval from KnowledgeBase
 
 ```bash
 curl http://${host_ip}:8889/v1/retrievaltool -X POST -H "Content-Type: application/json" -d '{
-     "text": "Explain the OPEA project?"
+     "messages": "Explain the OPEA project?"
      }'
 
 # expected output
 {"id":"354e62c703caac8c547b3061433ec5e8","reranked_docs":[{"id":"06d5a5cefc06cf9a9e0b5fa74a9f233c","text":"Close SearchsearchMenu WikiNewsCommunity Daysx-twitter linkedin github searchStreamlining implementation of enterprise-grade Generative AIEfficiently integrate secure, performant, and cost-effective Generative AI workflows into business value.TODAYOPEA..."}],"initial_query":"Explain the OPEA project?"}
 ```
 
+**Note**: `messages` is the required field. You can also pass in parameters for the retriever and reranker in the request. The parameters that can changed are listed below.
+
+    1. retriever
+    * search_type: str = "similarity"
+    * k: int = 4
+    * distance_threshold: Optional[float] = None
+    * fetch_k: int = 20
+    * lambda_mult: float = 0.5
+    * score_threshold: float = 0.2
+
+    2. reranker
+    * top_n: int = 1
+
 ## 5. Trouble shooting
 
 1. check all containers are alive

DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml

@@ -74,13 +74,30 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
     restart: unless-stopped
+  tei-reranking-service:
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    container_name: tei-reranking-server
+    ports:
+      - "8808:80"
+    volumes:
+      - "./data:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
   reranking:
     image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
     container_name: reranking-tei-xeon-server
+    depends_on:
+      - tei-reranking-service
     ports:
       - "8000:8000"
     ipc: host
-    entrypoint: python local_reranking.py
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

DocIndexRetriever/docker_compose/intel/hpu/gaudi/README.md

@@ -80,13 +80,26 @@ Retrieval from KnowledgeBase
 
 ```bash
 curl http://${host_ip}:8889/v1/retrievaltool -X POST -H "Content-Type: application/json" -d '{
-     "text": "Explain the OPEA project?"
+     "messages": "Explain the OPEA project?"
      }'
 
 # expected output
 {"id":"354e62c703caac8c547b3061433ec5e8","reranked_docs":[{"id":"06d5a5cefc06cf9a9e0b5fa74a9f233c","text":"Close SearchsearchMenu WikiNewsCommunity Daysx-twitter linkedin github searchStreamlining implementation of enterprise-grade Generative AIEfficiently integrate secure, performant, and cost-effective Generative AI workflows into business value.TODAYOPEA..."}],"initial_query":"Explain the OPEA project?"}
 ```
 
+**Note**: `messages` is the required field. You can also pass in parameters for the retriever and reranker in the request. The parameters that can changed are listed below.
+
+    1. retriever
+    * search_type: str = "similarity"
+    * k: int = 4
+    * distance_threshold: Optional[float] = None
+    * fetch_k: int = 20
+    * lambda_mult: float = 0.5
+    * score_threshold: float = 0.2
+
+    2. reranker
+    * top_n: int = 1
+
 ## 5. Trouble shooting
 
 1. check all containers are alive

DocIndexRetriever/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -77,13 +77,30 @@ services:
       REDIS_URL: ${REDIS_URL}
       INDEX_NAME: ${INDEX_NAME}
     restart: unless-stopped
+  tei-reranking-service:
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    container_name: tei-reranking-gaudi-server
+    ports:
+      - "8808:80"
+    volumes:
+      - "./data:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
   reranking:
     image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
     container_name: reranking-tei-gaudi-server
+    depends_on:
+      - tei-reranking-service
     ports:
       - "8000:8000"
     ipc: host
-    entrypoint: python local_reranking.py
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

DocIndexRetriever/tests/test.py

@@ -0,0 +1,71 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import argparse
+
+import requests
+
+
+def search_knowledge_base(query: str, url: str, request_type="chat_completion") -> str:
+    """Search the knowledge base for a specific query."""
+    print(url)
+    proxies = {"http": ""}
+    if request_type == "chat_completion":
+        print("Sending chat completion request")
+        payload = {
+            "messages": query,
+            "k": 5,
+            "top_n": 2,
+        }
+    else:
+        print("Sending text request")
+        payload = {
+            "text": query,
+        }
+    response = requests.post(url, json=payload, proxies=proxies)
+    print(response)
+    if "documents" in response.json():
+        docs = response.json()["documents"]
+        context = ""
+        for i, doc in enumerate(docs):
+            if i == 0:
+                context = str(i) + ": " + doc
+            else:
+                context += "\n" + str(i) + ": " + doc
+        # print(context)
+        return context
+    elif "text" in response.json():
+        return response.json()["text"]
+    elif "reranked_docs" in response.json():
+        docs = response.json()["reranked_docs"]
+        context = ""
+        for i, doc in enumerate(docs):
+            if i == 0:
+                context = doc["text"]
+            else:
+                context += "\n" + doc["text"]
+        # print(context)
+        return context
+    else:
+        return "Error parsing response from the knowledge base."
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Index data")
+    parser.add_argument("--host_ip", type=str, default="localhost", help="Host IP")
+    parser.add_argument("--port", type=int, default=8889, help="Port")
+    parser.add_argument("--request_type", type=str, default="chat_completion", help="Test type")
+    args = parser.parse_args()
+    print(args)
+
+    host_ip = args.host_ip
+    port = args.port
+    url = "http://{host_ip}:{port}/v1/retrievaltool".format(host_ip=host_ip, port=port)
+
+    response = search_knowledge_base("OPEA", url, request_type=args.request_type)
+
+    print(response)
+
+
+if __name__ == "__main__":
+    main()

DocIndexRetriever/tests/test_compose_on_gaudi.sh

@@ -64,7 +64,7 @@ function validate() {
 }
 
 function validate_megaservice() {
-    echo "Testing DataPrep Service"
+    echo "=========Ingest data=================="
     local CONTENT=$(curl -X POST "http://${ip_address}:6007/v1/dataprep" \
      -H "Content-Type: multipart/form-data" \
      -F 'link_list=["https://opea.dev"]')
@@ -78,7 +78,7 @@ function validate_megaservice() {
     fi
 
     # Curl the Mega Service
-    echo "Testing retriever service"
+    echo "==============Testing retriever service: Text Request================="
     local CONTENT=$(curl http://${ip_address}:8889/v1/retrievaltool -X POST -H "Content-Type: application/json" -d '{
      "text": "Explain the OPEA project?"
     }')
@@ -93,6 +93,21 @@ function validate_megaservice() {
         docker logs doc-index-retriever-server | tee -a ${LOG_PATH}/doc-index-retriever-service-gaudi.log
         exit 1
     fi
+
+    echo "==============Testing retriever service: ChatCompletion Request================"
+    cd $WORKPATH/tests
+    local CONTENT=$(python test.py --host_ip ${ip_address} --request_type chat_completion)
+    local EXIT_CODE=$(validate "$CONTENT" "OPEA" "doc-index-retriever-service-gaudi")
+    echo "$EXIT_CODE"
+    local EXIT_CODE="${EXIT_CODE:0-1}"
+    echo "return value is $EXIT_CODE"
+    if [ "$EXIT_CODE" == "1" ]; then
+        docker logs tei-embedding-gaudi-server | tee -a ${LOG_PATH}/doc-index-retriever-service-gaudi.log
+        docker logs retriever-redis-server | tee -a ${LOG_PATH}/doc-index-retriever-service-gaudi.log
+        docker logs reranking-tei-server | tee -a ${LOG_PATH}/doc-index-retriever-service-gaudi.log
+        docker logs doc-index-retriever-server | tee -a ${LOG_PATH}/doc-index-retriever-service-gaudi.log
+        exit 1
+    fi
 }
 
 function stop_docker() {

DocIndexRetriever/tests/test_compose_on_xeon.sh

@@ -63,8 +63,8 @@ function validate() {
 }
 
 function validate_megaservice() {
-    echo "Testing DataPrep Service"
-    local CONTENT=$(curl -X POST "http://${ip_address}:6007/v1/dataprep" \
+    echo "===========Ingest data=================="
+    local CONTENT=$(http_proxy="" curl -X POST "http://${ip_address}:6007/v1/dataprep" \
      -H "Content-Type: multipart/form-data" \
      -F 'link_list=["https://opea.dev"]')
     local EXIT_CODE=$(validate "$CONTENT" "Data preparation succeeded" "dataprep-redis-service-xeon")
@@ -77,16 +77,32 @@ function validate_megaservice() {
     fi
 
     # Curl the Mega Service
-    echo "Testing retriever service"
+    echo "================Testing retriever service: Default params================"
+
     local CONTENT=$(curl http://${ip_address}:8889/v1/retrievaltool -X POST -H "Content-Type: application/json" -d '{
-     "text": "Explain the OPEA project?"
+     "messages": "Explain the OPEA project?"
     }')
     local EXIT_CODE=$(validate "$CONTENT" "OPEA" "doc-index-retriever-service-xeon")
     echo "$EXIT_CODE"
     local EXIT_CODE="${EXIT_CODE:0-1}"
     echo "return value is $EXIT_CODE"
     if [ "$EXIT_CODE" == "1" ]; then
-        docker logs tei-embedding-xeon-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        docker logs tei-embedding-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        docker logs retriever-redis-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        docker logs reranking-tei-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        docker logs doc-index-retriever-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        exit 1
+    fi
+
+    echo "================Testing retriever service: ChatCompletion Request================"
+    cd $WORKPATH/tests
+    local CONTENT=$(python test.py --host_ip ${ip_address} --request_type chat_completion)
+    local EXIT_CODE=$(validate "$CONTENT" "OPEA" "doc-index-retriever-service-xeon")
+    echo "$EXIT_CODE"
+    local EXIT_CODE="${EXIT_CODE:0-1}"
+    echo "return value is $EXIT_CODE"
+    if [ "$EXIT_CODE" == "1" ]; then
+        docker logs tei-embedding-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
         docker logs retriever-redis-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
         docker logs reranking-tei-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
         docker logs doc-index-retriever-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log

DocSum/README.md

@@ -21,7 +21,7 @@ Currently we support two ways of deploying Document Summarization services with
    docker pull opea/docsum:latest
    ```
 
-2. Start services using the docker images `built from source`: [Guide](./docker_compose)
+2. Start services using the docker images `built from source`: [Guide](https://github.com/opea-project/GenAIExamples/tree/main/DocSum/docker_compose)
 
 ### Required Models
 
@@ -98,7 +98,7 @@ Refer to [Kubernetes deployment](./kubernetes/intel/README.md)
 
 Install Helm (version >= 3.15) first. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
 
-Refer to the [DocSum helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/docsum) for instructions on deploying DocSum into Kubernetes on Xeon & Gaudi.
+Refer to the [DocSum helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/docsum/README.md) for instructions on deploying DocSum into Kubernetes on Xeon & Gaudi.
 
 ### Workflow of the deployed Document Summarization Service
 
@@ -143,7 +143,7 @@ Two ways of consuming Document Summarization Service:
 
 ## Troubleshooting
 
-1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/DocSum/docker_compose/intel/cpu/xeon#validate-microservices) first. A simple example:
+1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/DocSum/docker_compose/intel/cpu/xeon/README.md#validate-microservices) first. A simple example:
 
    ```bash
    http_proxy=""

DocSum/kubernetes/intel/README_gmc.md

@@ -3,7 +3,7 @@
 This document outlines the deployment process for a Document Summary (DocSum) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
 The DocSum Service leverages a Kubernetes operator called genai-microservices-connector(GMC). GMC supports connecting microservices to create pipelines based on the specification in the pipeline yaml file, in addition it allows the user to dynamically control which model is used in a service such as an LLM or embedder. The underlying pipeline language also supports using external services that may be running in public or private clouds elsewhere.
 
-Install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
+Install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
 
 The DocSum application is defined as a Custom Resource (CR) file that the above GMC operator acts upon. It first checks if the microservices listed in the CR yaml file are running, if not it starts them and then proceeds to connect them. When the DocSum RAG pipeline is ready, the service endpoint details are returned, letting you use the application. Should you use "kubectl get pods" commands you will see all the component microservices, in particular embedding, retriever, rerank, and llm.
 

FaqGen/benchmark/accuracy/README.md

@@ -16,7 +16,7 @@ python get_context.py
 
 ### Launch FaQGen microservice
 
-Please refer to [FaQGen microservice](https://github.com/opea-project/GenAIComps/tree/main/comps/llms/faq-generation/tgi), set up an microservice endpoint.
+Please refer to [FaQGen microservice](https://github.com/opea-project/GenAIComps/tree/main/comps/llms/faq-generation/tgi/langchain/README.md), set up an microservice endpoint.
 
 ```
 export FAQ_ENDPOINT = "http://${your_ip}:9000/v1/faqgen"

FaqGen/benchmark/accuracy/launch_tgi.sh

@@ -20,7 +20,7 @@ docker run -it --rm \
     --ipc=host \
     -e HTTPS_PROXY=$https_proxy \
     -e HTTP_PROXY=$https_proxy \
-    ghcr.io/huggingface/tgi-gaudi:2.0.1 \
+    ghcr.io/huggingface/tgi-gaudi:2.0.5 \
     --model-id $model_name \
     --max-input-tokens $max_input_tokens \
     --max-total-tokens $max_total_tokens \

LEGAL_INFORMATION.md

@@ -9,9 +9,9 @@ Generative AI Examples is licensed under [Apache License Version 2.0](http://www
 This software includes components that have separate copyright notices and licensing terms.
 Your use of the source code for these components is subject to the terms and conditions of the following licenses.
 
-- [Third Party Programs](/third-party-programs.txt)
+- [Third Party Programs](third-party-programs.txt)
 
-See the accompanying [license](/LICENSE) file for full license text and copyright notices.
+See the accompanying [license](LICENSE) file for full license text and copyright notices.
 
 ## Citation
 

MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md

@@ -6,7 +6,7 @@ This document outlines the deployment process for a MultimodalQnA application ut
 
 Since the `compose.yaml` will consume some environment variables, you need to setup them in advance as below.
 
-**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable**
+**Export the value of the public IP address of your Gaudi server to the `host_ip` environment variable**
 
 > Change the External_Public_IP below with the actual IPV4 value
 

MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -68,7 +68,7 @@ services:
       INDEX_NAME: ${INDEX_NAME}
     restart: unless-stopped
   tgi-gaudi:
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+    image: ghcr.io/huggingface/tgi-gaudi:2.0.5
     container_name: tgi-llava-gaudi-server
     ports:
       - "8399:80"

MultimodalQnA/tests/test_compose_on_gaudi.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-multimodal retriever-multimodal-redis lvm-tgi dataprep-multimodal-redis"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/tgi-gaudi:2.0.4
+    docker pull ghcr.io/huggingface/tgi-gaudi:2.0.5
 
     docker images && sleep 1s
 }

README.md

@@ -30,8 +30,8 @@ Deployment are based on released docker images by default, check [docker image l
 #### Prerequisite
 
 - For Docker Compose based deployment, you should have docker compose installed. Refer to [docker compose install](https://docs.docker.com/compose/install/).
-- For Kubernetes based deployment, we provide 3 ways from the easiest manifests to powerful [GMC](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector) based deployment.
-  - You should have a kubernetes cluster ready for use. If not, you can refer to [k8s install](https://github.com/opea-project/docs/tree/main/guide/installation/k8s_install) to deploy one.
+- For Kubernetes based deployment, we provide 3 ways from the easiest manifests to powerful [GMC](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md) based deployment.
+  - You should have a kubernetes cluster ready for use. If not, you can refer to [k8s install](https://github.com/opea-project/docs/tree/main/guide/installation/k8s_install/README.md) to deploy one.
   - (Optional) You should have GMC installed to your kubernetes cluster if you want to try with GMC. Refer to [GMC install](https://github.com/opea-project/docs/blob/main/guide/installation/gmc_install/gmc_install.md) for more information.
   - (Optional) You should have Helm (version >= 3.15) installed if you want to deploy with Helm Charts. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
 
@@ -68,4 +68,4 @@ Thank you for being a part of this journey. We can't wait to see what we can ach
 
 - [Code of Conduct](https://github.com/opea-project/docs/tree/main/community/CODE_OF_CONDUCT.md)
 - [Security Policy](https://github.com/opea-project/docs/tree/main/community/SECURITY.md)
-- [Legal Information](/LEGAL_INFORMATION.md)
+- [Legal Information](LEGAL_INFORMATION.md)

SearchQnA/README.md

@@ -32,7 +32,7 @@ Currently we support two ways of deploying SearchQnA services with docker compos
    docker pull opea/searchqna:latest
    ```
 
-2. Start services using the docker images `built from source`: [Guide](./docker_compose)
+2. Start services using the docker images `built from source`: [Guide](https://github.com/opea-project/GenAIExamples/tree/main/SearchQnA/docker_compose/)
 
 ### Setup Environment Variable
 
@@ -110,7 +110,7 @@ Two ways of consuming SearchQnA Service:
 
 ## Troubleshooting
 
-1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA/docker_compose/intel/cpu/xeon#validate-microservices) first. A simple example:
+1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA/docker_compose/intel/cpu/xeon/README.md#validate-microservices) first. A simple example:
 
    ```bash
    http_proxy=""

SearchQnA/kubernetes/intel/README_gmc.md

@@ -2,7 +2,7 @@
 
 This document outlines the deployment process for a Code Generation (SearchQnA) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
 
-Install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
+Install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
 
 If you have only Intel Xeon machines you could use the searchQnA_xeon.yaml file or if you have a Gaudi cluster you could use searchQnA_gaudi.yaml
 In the below example we illustrate on Xeon.

Translation/kubernetes/intel/README_gmc.md

@@ -2,7 +2,7 @@
 
 This document outlines the deployment process for a Code Generation (Translation) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
 
-Please install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
+Please install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
 
 If you have only Intel Xeon machines you could use the translation_xeon.yaml file or if you have a Gaudi cluster you could use translation_gaudi.yaml
 In the below example we illustrate on Xeon.

Translation/kubernetes/intel/hpu/gaudi/manifest/translation.yaml

@@ -362,7 +362,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/tgi-gaudi:2.0.1"
+          image: "ghcr.io/huggingface/tgi-gaudi:2.0.5"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

VisualQnA/kubernetes/intel/README_gmc.md

@@ -2,7 +2,7 @@
 
 This document outlines the deployment process for a Visual Question Answering (VisualQnA) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
 
-Please install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
+Please install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector/README.md). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
 
 If you have only Intel Xeon machines you could use the visualqna_xeon.yaml file or if you have a Gaudi cluster you could use visualqna_gaudi.yaml
 In the below example we illustrate on Xeon.

docker_images_list.md

@@ -16,7 +16,6 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/chatqna-without-rerank](https://hub.docker.com/r/opea/chatqna-without-rerank)             |                                                                                                    |                                                                                                                                                                                                                                                                                        |
 | [opea/chat-conversation-service](https://hub.docker.com/r/opea/chat-conversation-service)       |                                                                                                    |                                                                                                                                                                                                                                                                                        |
 | [opea/chat-conversation-ui-service](https://hub.docker.com/r/opea/chat-conversation-ui-service) |                                                                                                    |                                                                                                                                                                                                                                                                                        |
-| [opea/chat-history-service](https://hub.docker.com/r/opea/chat-history-service)                 |                                                                                                    |                                                                                                                                                                                                                                                                                        |
 | [opea/codegen](https://hub.docker.com/r/opea/codegen)                                           | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/Dockerfile)                 | The docker image served as the codegen gateway to provide service of the automatic creation of source code from a higher-level representation                                                                                                                                          |
 | [opea/codegen-ui](https://hub.docker.com/r/opea/codegen-ui)                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/docker/Dockerfile)       | The docker image acted as the codegen UI entry for facilitating interaction with users for automatically generating code from user's description                                                                                                                                       |
 | [opea/codegen-react-ui](https://hub.docker.com/r/opea/codegen-react-ui)                         | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/docker/Dockerfile.react) | The purpose of the docker image is to provide a user interface for Codegen using React. It allows generating the appropriate code based on the current user input.                                                                                                                     |
@@ -48,7 +47,6 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/guardrails-tgi](https://hub.docker.com/r/opea/guardrails-tgi)                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/llama_guard/langchain/Dockerfile)                         | The docker image exposed the OPEA guardrail microservice to provide content review for GenAI application use                                                                                                           |
 | [opea/guardrails-pii-detection](https://hub.docker.com/r/opea/guardrails-pii-detection) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/pii_detection/Dockerfile)                                 | The docker image exposed the OPEA guardrail microservice to provide PII detection for GenAI application use                                                                                                            |
 | [opea/habanalabs](https://hub.docker.com/r/opea/habanalabs)                             |                                                                                                                                        |                                                                                                                                                                                                                        |
-| [opea/knowledge_graphs](https://hub.docker.com/r/opea/knowledge_graphs)                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/knowledgegraphs/langchain/Dockerfile)                                | The docker image served as knowledge graph gateway to enhance question answering with graph knowledge searching.                                                                                                       |
 | [opea/llm-docsum-tgi](https://hub.docker.com/r/opea/llm-docsum-tgi)                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/summarization/tgi/langchain/Dockerfile)                         | This docker image is designed to build a document summarization microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a document summary. |
 | [opea/llm-faqgen-tgi](https://hub.docker.com/r/opea/llm-faqgen-tgi)                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/faq-generation/tgi/langchain/Dockerfile)                        | This docker image is designed to build a frequently asked questions microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a FAQ.          |
 | [opea/llm-ollama](https://hub.docker.com/r/opea/llm-ollama)                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/text-generation/ollama/langchain/Dockerfile)                    | The docker image exposed the OPEA LLM microservice based on ollama for GenAI application use                                                                                                                           |
@@ -57,7 +55,8 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/llm-vllm-hpu](https://hub.docker.com/r/opea/llm-vllm-hpu)                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/text-generation/vllm/langchain/dependency/Dockerfile.intel_hpu) | The docker image exposed the OPEA LLM microservice upon vLLM docker image for use by GenAI apps on the Gaudi                                                                                                           |
 | [opea/llm-vllm-ray](https://hub.docker.com/r/opea/llm-vllm-ray)                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/text-generation/vllm/ray/Dockerfile)                            | The docker image exposes the OPEA LLM microservices Ray-based upon the vLLM Docker image for GenAI application use                                                                                                     |
 | [opea/llm-vllm-ray-hpu](https://hub.docker.com/r/opea/llm-vllm-ray-hpu)                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/text-generation/vllm/ray/dependency/Dockerfile)                 | The docker image exposes Ray-based OPEA LLM microservices upon the vLLM Docker image for use by GenAI applications on the Gaudi                                                                                        |
-| [opea/prompt-registry-service](https://hub.docker.com/r/opea/prompt-registry-service)   |                                                                                                                                        |                                                                                                                                                                                                                        |
+| [opea/chat-history-service](https://hub.docker.com/r/opea/chat-history-service)         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/chathistory/mongo/Dockerfile)                                        | The docker image exposes OPEA Chat History microservice which based on MongoDB database, designed to allow user to store, retrieve and manage chat conversations                                                       |
+| [opea/prompt-registry-service](https://hub.docker.com/r/opea/prompt-registry-service)   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/prompt_registry/mongo/Dockerfile)                                    | The docker image exposes the OPEA Prompt Registry microservices which based on MongoDB database, designed to store and retrieve user's preferred prompts                                                               |
 | [opea/reranking-tei](https://hub.docker.com/r/opea/reranking-tei)                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/reranks/tei/Dockerfile)                                              | The docker image exposed the OPEA reranking microservice based on tei docker image for GenAI application use                                                                                                           |
 | [opea/retriever-qdrant](https://hub.docker.com/r/opea/retriever-qdrant)                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/qdrant/haystack/Dockerfile)                               | The docker image exposed the OPEA retrieval microservice based on qdrant vectordb for GenAI application use                                                                                                            |
 | [opea/retriever-redis](https://hub.docker.com/r/opea/retriever-redis)                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/redis/langchain/Dockerfile)                               | The docker image exposed the OPEA retrieval microservice based on redis vectordb for GenAI application use                                                                                                             |