fix: linkback

Added matching engine CLIP notebook

notebooks/community/prediction/feature_store_integration/prediction_feature_store_integration.ipynb

@@ -1445,7 +1445,7 @@
       "source": [
         "We have provided a Identity model server, built using [CPR](https://cloud.google.com/vertex-ai/docs/predictions/custom-prediction-routines) to help with debugging your feature fetch config. The CPR built Identity model server simply returns the request body as the response. This will allow you to explore how the Feature Store/Prediction integration formats the prediction request to the model server.\n",
         "\n",
-        "The server has been published here - `us-docker.pkg.dev/vertex-prediction-samples/model-servers/cpr-identity`, and uses the following `Predictor`.\n",
+        "The server has been published here - `us-docker.pkg.dev/vertex-ai/sample-model-servers/cpr-identity-server:latest`, and uses the following `Predictor`.\n",
         "```\n",
         "from google.cloud.aiplatform.prediction.predictor import Predictor\n",
         "\n",
@@ -1470,7 +1470,79 @@
         "id": "46c332abbe7a"
       },
       "source": [
-        "Using the same feature fetch config file as in the previous example, let's now use it with the Identity model server to debug it."
+        "Using the same feature fetch config file as in the previous example, deploy it with the Identity model server to debug.\n",
+        "\n",
+        "First copy the image to Artifacts Registry."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "962c1cfe1588"
+      },
+      "outputs": [],
+      "source": [
+        "!gcloud services enable artifactregistry.googleapis.com"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "639b2d067827"
+      },
+      "outputs": [],
+      "source": [
+        "REPOSITORY = \"feature-store-prediction-sample\"\n",
+        "IMAGE = \"cpr-identity-server\"\n",
+        "CONTAINER_URI = f\"{REGION}-docker.pkg.dev/{PROJECT_ID}/{REPOSITORY}/{IMAGE}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6523af67c1ab"
+      },
+      "outputs": [],
+      "source": [
+        "!gcloud artifacts repositories create {REPOSITORY} \\\n",
+        "    --repository-format=docker \\\n",
+        "    --location=$REGION"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b3b939dc0b25"
+      },
+      "outputs": [],
+      "source": [
+        "!gcloud auth configure-docker {REGION}-docker.pkg.dev --quiet"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "34c1cec95124"
+      },
+      "outputs": [],
+      "source": [
+        "!docker pull us-docker.pkg.dev/vertex-ai/sample-model-servers/cpr-identity-server:latest\n",
+        "!docker tag us-docker.pkg.dev/vertex-ai/sample-model-servers/cpr-identity-server:latest $CONTAINER_URI\n",
+        "!docker push $CONTAINER_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d4c81e1eb726"
+      },
+      "source": [
+        "Now upload and deploy the identity model to Vertex Prediction for debugging."
       ]
     },
     {
@@ -1486,7 +1558,7 @@
         "identity_model = aiplatform.Model.upload(\n",
         "    display_name=IDENTITY_MODEL_DISPLAY_NAME,\n",
         "    artifact_uri=ARTIFACT_URI,\n",
-        "    serving_container_image_uri=\"us-docker.pkg.dev/vertex-prediction-samples/model-servers/cpr-identity\",\n",
+        "    serving_container_image_uri=CONTAINER_URI,\n",
         "    sync=False,\n",
         ")\n",
         "\n",

notebooks/official/custom/get_started_with_vertex_endpoint_and_shared_vm.ipynb

@@ -62,21 +62,9 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers: get started with Endpoints and shared VM for co-hosting models."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:flowers,icn"
-      },
-      "source": [
-        "### Pre-trained Models\n",
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers: get started with Endpoints and shared VM for co-hosting models.\n",
         "\n",
-        "The pre-trained models used for this tutorial are from the [TensorFlow Hub](https://tfhub.dev/) repository:\n",
-        "\n",
-        "- [image classification](https://tfhub.dev/google/imagenet/inception_v3/classification/5): trained with ImageNet.\n",
-        "- [text sentence encoder](https://tfhub.dev/google/universal-sentence-encoder/4): Google's universal sentence encoder"
+        "Learn more about [Shared resources across deployments](https://cloud.google.com/vertex-ai/docs/predictions/model-co-hosting)."
       ]
     },
     {
@@ -110,6 +98,20 @@
         "- Make a prediction request with second deployed model (model B)."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:flowers,icn"
+      },
+      "source": [
+        "### Model\n",
+        "\n",
+        "The pre-trained models used for this tutorial are from the [TensorFlow Hub](https://tfhub.dev/) repository:\n",
+        "\n",
+        "- [image classification](https://tfhub.dev/google/imagenet/inception_v3/classification/5): trained with ImageNet.\n",
+        "- [text sentence encoder](https://tfhub.dev/google/universal-sentence-encoder/4): Google's universal sentence encoder"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {