Make all xeon tgi image version consistent (#851)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

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

@@ -247,7 +247,7 @@ spec:
       - envFrom:
         - configMapRef:
             name: audio-qna-config
-        image: ghcr.io/huggingface/text-generation-inference:2.2.0
+        image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
         name: llm-dependency-deploy-demo
         securityContext:
           capabilities:

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

@@ -233,7 +233,7 @@ For users in China who are unable to download models directly from Huggingface,
    export HF_TOKEN=${your_hf_token}
    export HF_ENDPOINT="https://hf-mirror.com"
    model_name="Intel/neural-chat-7b-v3-3"
-   docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.2.0 --model-id $model_name
+   docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --shm-size 1g ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu --model-id $model_name
    ```
 
 2. Offline
@@ -247,7 +247,7 @@ For users in China who are unable to download models directly from Huggingface,
      ```bash
      export HF_TOKEN=${your_hf_token}
      export model_path="/path/to/model"
-     docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.2.0 --model-id /data
+     docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu --model-id /data
      ```
 
 ### Setup Environment Variables

ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml

@@ -1474,7 +1474,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data
@@ -1554,7 +1554,7 @@ spec:
             runAsUser: 1000
             seccompProfile:
               type: RuntimeDefault
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

DocSum/kubernetes/intel/README_gmc.md

@@ -7,17 +7,17 @@ Install GMC in your Kubernetes cluster, if you have not already done so, by foll
 
 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.
 
-The DocSum pipeline uses  prebuilt images. The Xeon version uses the prebuilt image llm-docsum-tgi:latest which internally leverages the
-the image ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu. The service is called tgi-svc. Meanwhile, the Gaudi version launches the
-service tgi-gaudi-svc, which uses the image `ghcr.io/huggingface/tgi-gaudi:2.0.5`. Both TGI model services serve the model specified in the LLM_MODEL_ID variable that is exported by you. In the below example we use Intel/neural-chat-7b-v3-3.
+The DocSum pipeline uses  prebuilt images. The Xeon version uses the prebuilt image `llm-docsum-tgi:latest` which internally leverages the
+the image `ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu`. The service is called tgi-svc. Meanwhile, the Gaudi version launches the
+service tgi-gaudi-svc, which uses the image `ghcr.io/huggingface/tgi-gaudi:2.0.5`. Both TGI model services serve the model specified in the LLM_MODEL_ID variable that is exported by you. In the below example we use `Intel/neural-chat-7b-v3-3`.
 
 [NOTE]
 Refer to [Docker Xeon README](https://github.com/opea-project/GenAIExamples/blob/main/DocSum/docker_compose/intel/cpu/xeon/README.md) or
 [Docker Gaudi README](https://github.com/opea-project/GenAIExamples/blob/main/DocSum/docker_compose/intel/hpu/gaudi/README.md) to build the OPEA images. 
 These will be available on Docker Hub soon, simplifying installation.
 
 ## Deploy the RAG pipeline
-This involves deploying the application pipeline custom resource. You can use docsum_xeon.yaml if you have just a Xeon cluster or docsum_gaudi.yaml if you have a Gaudi cluster.
+This involves deploying the application pipeline custom resource. You can use `docsum_xeon.yaml` if you have just a Xeon cluster or `docsum_gaudi.yaml` if you have a Gaudi cluster.
 
 1. Setup Environment variables. These are specific to the user. Skip the proxy settings if you are not operating behind one.
 

ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml

@@ -993,7 +993,7 @@ spec:
                 name: chatqna-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.1.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml

@@ -229,7 +229,7 @@ spec:
                 name: codegen-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:1.4"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/docsum.yaml

@@ -229,7 +229,7 @@ spec:
                 name: docsum-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.1.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/faqgen.yaml

@@ -138,7 +138,7 @@ spec:
             - configMapRef:
                 name: faqgen-tgi-config
           securityContext: {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.1.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

VisualQnA/kubernetes/intel/cpu/xeon/manifest/visualqna.yaml

@@ -216,7 +216,7 @@ spec:
                 name: visualqna-tgi-config
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
+          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

VisualQnA/tests/test_compose_on_xeon.sh

@@ -21,7 +21,7 @@ function build_docker_images() {
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:2.2.0
+    docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
     docker images && sleep 1s
 }