Update module

GoogleCloudPlatform · Jun 6, 2024 · e0a50f2 · e0a50f2
1 parent 29d3634
commit e0a50f2
Show file tree

Hide file tree

Showing 3 changed files with 78 additions and 53 deletions.
diff --git a/examples/genai-rag-multimodal/README.md b/examples/genai-rag-multimodal/README.md
@@ -59,6 +59,18 @@ Once all the requirements are set up, you can begin by running and adjusting the
 
 To run the notebook, open the Google Cloud Console on Vertex AI Workbench, open jupyterlab and upload the notebook (`multimodal_rag_langchain.ipynb`) to it.
 
+### Optional: Use `terraform output` and bash command to fill in fields in the notebook
+
+You can save some time adjusting the notebook by running the commands below:
+
+```bash
+sed -i "s/<INSERT_PRIVATE_IP_VALUE_HERE>/$(terraform output -raw private_endpoint_ip_address)/g" multimodal_rag_langchain.ipynb
+sed -i "s/<INSERT_HOST_VPC_PROJECT_ID>/$(terraform output -raw host_vpc_project_id)/g" multimodal_rag_langchain.ipynb
+sed -i "s/<INSERT_NOTEBOOK_PROJECT_ID>/$(terraform output -raw notebook_project_id)/g" multimodal_rag_langchain.ipynb
+sed -i "s/<INSERT_BUCKET_NAME>/$(terraform output -raw vector_search_bucket_name)/g" multimodal_rag_langchain.ipynb 
+sed -i "s:<INSERT_HOST_VPC_NETWORK>:$(terraform output -raw host_vpc_network):g" multimodal_rag_langchain.ipynb
+```
+
 ## Known Issues
 
 - `Error: Error creating Instance: googleapi: Error 400: value_to_check(https://compute.googleapis.com/compute/v1/projects/...) is not found`.

diff --git a/examples/genai-rag-multimodal/multimodal_rag_langchain.ipynb b/examples/genai-rag-multimodal/multimodal_rag_langchain.ipynb
@@ -179,11 +179,13 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "id": "R5Xep4W9lq-Z"
+   },
    "source": [
-    "### Create Private Endpoint IP Address\n",
+    "### Restart current runtime\n",
     "\n",
-    "Retrieve the IP address value created when setting up Private Service Connect for Vector Search."
+    "To use the newly installed packages in this Jupyter runtime, you must restart the runtime. You can do this by running the cell below, which will restart the current kernel."
    ]
   },
   {
@@ -192,20 +194,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "PRIVATE_ENDPOINT_IP_ADDRESS=<INSERT_VALUE_HERE>"
+    "# Restart kernel after installs so that your environment can access the new packages\n",
+    "import IPython\n",
+    "\n",
+    "app = IPython.Application.instance()\n",
+    "app.kernel.do_shutdown(True)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Update Project Allowlist\n",
-    "\n",
-    "Insert the values of the Host Shared VPC Project and the current notebook project on the cell below.\n",
-    "\n",
-    "For example: `PROJECT_ALLOWLIST=[\"prj-d-shared-restricted-83dn\",\"prj-d-ml-machine-learning-0v09\"]` \n",
+    "### Create Private Endpoint IP Address\n",
     "\n",
-    "Remember that these values will be different on your environment"
+    "Retrieve the IP address value created when setting up Private Service Connect for Vector Search. You can retrieve this value by running `terraform output` on the example."
    ]
   },
   {
@@ -214,48 +216,29 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "PROJECT_ALLOWLIST=[\"<INSERT_HOST_VPC_PROJECT_ID>\", \"<INSERT_NOTEBOOK_PROJECT_ID>\"]"
+    "PRIVATE_ENDPOINT_IP_ADDRESS=\"<INSERT_PRIVATE_IP_VALUE_HERE>\""
    ]
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "id": "R5Xep4W9lq-Z"
-   },
+   "metadata": {},
    "source": [
-    "### Restart current runtime\n",
+    "### Update Project Allowlist\n",
     "\n",
-    "To use the newly installed packages in this Jupyter runtime, you must restart the runtime. You can do this by running the cell below, which will restart the current kernel."
+    "Insert the values of the Host Shared VPC Project and the current notebook project on the cell below.\n",
+    "\n",
+    "For example: `PROJECT_ALLOWLIST=[\"prj-d-shared-restricted-83dn\",\"prj-d-ml-machine-learning-0v09\"]` \n",
+    "\n",
+    "Remember that these values will be different on your environment"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "executionInfo": {
-     "elapsed": 646,
-     "status": "ok",
-     "timestamp": 1707913872852,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -330
-    },
-    "id": "XRvKdaPDTznN",
-    "outputId": "759357fb-7531-4423-a75f-b896af19ce37",
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# Restart kernel after installs so that your environment can access the new packages\n",
-    "import IPython\n",
-    "\n",
-    "app = IPython.Application.instance()\n",
-    "app.kernel.do_shutdown(True)"
+    "PROJECT_ALLOWLIST=[\"<INSERT_HOST_VPC_PROJECT_ID>\", \"<INSERT_NOTEBOOK_PROJECT_ID>\"]"
    ]
   },
   {
@@ -302,7 +285,7 @@
    },
    "outputs": [],
    "source": [
-    "PROJECT_ID = \"<INSERT_PROJECT_ID_HERE>\"  # @param {type:\"string\"}\n",
+    "PROJECT_ID = \"<INSERT_NOTEBOOK_PROJECT_ID>\"  # @param {type:\"string\"}\n",
     "LOCATION = \"us-central1\"  # @param {type:\"string\"}\n",
     "\n",
     "# For Vector Search Staging\n",
@@ -716,27 +699,33 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "index_endpoint.deployed_indexes.private_endpoints.service_attachment"
+    "SERVICE_ATTACHMENT=index_endpoint.deployed_indexes.private_endpoints.service_attachment\n",
+    "\n",
+    "SERVICE_ATTACHMENT"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "* Retrieve the value of the service attachment and execute the command below on your local machine:\n",
-    "\n",
-    "```bash\n",
-    "NETWORK=<INSERT_HOST_VPC_NETWORK_NAME>\n",
-    "NETWORK_PROJECT_ID=<INSERT_HOST_VPC_NETWORK_PROJECT_ID>\n",
-    "SERVICE_ATTACHMENT=<INSERT_VALUE_FROM_CELL_ABOVE_HERE>\n",
+    "* Retrieve the value of the service attachment and execute the command below on your local machine:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "NETWORK=\"<INSERT_HOST_VPC_NETWORK>\"\n",
+    "NETWORK_PROJECT_ID=\"<INSERT_HOST_VPC_PROJECT_ID>\"\n",
     "\n",
-    "gcloud compute forwarding-rules create vector-search-endpoint \\\n",
-    "    --network=$NETWORK \\\n",
+    "!gcloud compute forwarding-rules create vector-search-endpoint \\\n",
+    "    --network={NETWORK} \\\n",
     "    --address=vector-search-endpoint \\\n",
-    "    --target-service-attachment=$SERVICE_ATTACHMENT \\\n",
-    "    --project=$NETWORK_PROJECT_ID \\\n",
-    "    --region=us-central1\n",
-    "```"
+    "    --target-service-attachment={SERVICE_ATTACHMENT} \\\n",
+    "    --project={NETWORK_PROJECT_ID} \\\n",
+    "    --region=us-central1"
    ]
   },
   {

diff --git a/examples/genai-rag-multimodal/outputs.tf b/examples/genai-rag-multimodal/outputs.tf
@@ -0,0 +1,24 @@
+output "private_endpoint_ip_address" {
+  description = "The private IP address of the vector search endpoint"
+  value       = google_compute_address.vector_search_static_ip.address
+}
+
+output "host_vpc_project_id" {
+  description = "This is the Project ID where the Host VPC network is located"
+  value       = var.vector_search_vpc_project
+}
+
+output "host_vpc_network" {
+  description = "This is the Self-link of the Host VPC network"
+  value       = var.network
+}
+
+output "notebook_project_id" {
+  description = "The Project ID where the notebook will be run on"
+  value       = var.machine_learning_project
+}
+
+output "vector_search_bucket_name" {
+  description = "The name of the bucket that Vector Search will use"
+  value       = google_storage_bucket.vector_search_bucket.name
+}