feat: Add architecture diagram for stable diffusion blueprint

ai-ml/trainium-inferentia/examples/inference/ray-serve/stable-diffusion-inf2/gradio-ui/Dockerfile

@@ -0,0 +1,13 @@
+# Use Python base image
+FROM --platform=linux/amd64 python:3.9-slim
+
+# Set working directory in the container
+WORKDIR /app
+
+# Copy the Python script into the container
+COPY gradio-app-stablediffusion.py /app/gradio-app-stablediffusion.py
+
+RUN pip install --no-cache-dir gradio requests Pillow
+
+# Command to run the Python script
+ENTRYPOINT ["python", "gradio-app-stablediffusion.py"]

ai-ml/trainium-inferentia/examples/gradio-ui/gradio-app-stablediffusion.py → ai-ml/trainium-inferentia/examples/inference/ray-serve/stable-diffusion-inf2/gradio-ui/gradio-app-stablediffusion.py

@@ -1,14 +1,12 @@
 import gradio as gr
 import requests
-import json
+import os
 from PIL import Image
 from io import BytesIO
 
 # Constants for model endpoint and service name
-model_endpoint = "/imagine"
-# service_name = "http://<REPLACE_ME_WITH_ELB_DNS_NAME>/serve"
-service_name = "http://localhost:8000"  # Replace with your actual service name
-
+model_endpoint = os.environ.get("MODEL_ENDPOINT", "/imagine")
+service_name = os.environ.get("SERVICE_NAME", "http://localhost:8000")
 
 # Function to generate image based on prompt
 def generate_image(prompt):
@@ -25,9 +23,10 @@ def generate_image(prompt):
 
     except requests.exceptions.RequestException as e:
         # Handle any request exceptions (e.g., connection errors)
-        return f"AI: Error: {str(e)}"
+        # return f"AI: Error: {str(e)}"
+        return Image.new('RGB', (100, 100), color='red')
 
 # Define the Gradio PromptInterface
 demo = gr.Interface(fn=generate_image,
                     inputs = [gr.Textbox(label="Enter the Prompt")],
-                    outputs = gr.Image(type='pil')).launch(debug='True')
+                    outputs = gr.Image(type='pil')).launch(server_name="0.0.0.0")

ai-ml/trainium-inferentia/examples/inference/ray-serve/stable-diffusion-inf2/gradio-ui/gradio-deploy.yaml

@@ -0,0 +1,56 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gradio
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: gradio-deployment
+  namespace: gradio
+  labels:
+    app: gradio
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: gradio
+  template:
+    metadata:
+      labels:
+        app: gradio
+    spec:
+      containers:
+      - name: gradio
+        image: public.ecr.aws/data-on-eks/gradio-app:sd-v1.0
+        imagePullPolicy: IfNotPresent
+        ports:
+        - containerPort: 7860
+        resources:
+          requests:
+            cpu: "512m"
+            memory: "2048Mi"
+          limits:
+            cpu: "1"
+            memory: "4096Mi"
+        env:
+        - name: MODEL_ENDPOINT
+          value: "/imagine"
+        #Please note that the service name is currently hardcoded to match the Stable Diffusion service for this blueprint. If there are any updates or changes to the actual RayServe deployment, you'll need to update the service name in this code accordingly.
+        - name: SERVICE_NAME
+          value: "http://stablediffusion-service.stablediffusion.svc.cluster.local:8000"
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: gradio-service
+  namespace: gradio
+spec:
+  selector:
+    app: gradio
+  ports:
+  - name: http
+    protocol: TCP
+    port: 7860
+    targetPort: 7860
+  type: ClusterIP

analytics/terraform/datahub-on-eks/README.md

@@ -28,8 +28,7 @@ Checkout the [documentation website](https://awslabs.github.io/data-on-eks/docs/
 | <a name="module_eks"></a> [eks](#module\_eks) | terraform-aws-modules/eks/aws | ~> 19.15 |
 | <a name="module_eks_blueprints_addons"></a> [eks\_blueprints\_addons](#module\_eks\_blueprints\_addons) | aws-ia/eks-blueprints-addons/aws | ~> 1.2 |
 | <a name="module_vpc"></a> [vpc](#module\_vpc) | terraform-aws-modules/vpc/aws | ~> 5.0 |
-| <a name="module_vpc_endpoints"></a> [vpc\_endpoints](#module\_vpc\_endpoints) | terraform-aws-modules/vpc/aws//modules/vpc-endpoints | ~> 5.0 |
-| <a name="module_vpc_endpoints_sg"></a> [vpc\_endpoints\_sg](#module\_vpc\_endpoints\_sg) | terraform-aws-modules/security-group/aws | ~> 5.0 |
+| <a name="module_vpc_endpoints"></a> [vpc\_endpoints](#module\_vpc\_endpoints) | terraform-aws-modules/vpc/aws//modules/vpc-endpoints | ~> 5.1 |
 
 ## Resources
 
@@ -43,15 +42,17 @@ Checkout the [documentation website](https://awslabs.github.io/data-on-eks/docs/
 
 | Name | Description | Type | Default | Required |
 |------|-------------|------|---------|:--------:|
-| <a name="input_create_iam_service_linked_role_es"></a> [create\_iam\_service\_linked\_role\_es](#input\_create\_iam\_service\_linked\_role\_es) | Whether to create `AWSServiceRoleForAmazonOpensearchService` service-linked role. Set it to `false` if the role already exists | `bool` | `true` | no |
+| <a name="input_create_vpc"></a> [create\_vpc](#input\_create\_vpc) | Create VPC | `bool` | `true` | no |
 | <a name="input_eks_cluster_version"></a> [eks\_cluster\_version](#input\_eks\_cluster\_version) | EKS Cluster version | `string` | `"1.26"` | no |
 | <a name="input_enable_vpc_endpoints"></a> [enable\_vpc\_endpoints](#input\_enable\_vpc\_endpoints) | Enable VPC Endpoints | `bool` | `false` | no |
 | <a name="input_name"></a> [name](#input\_name) | Name of the VPC and EKS Cluster | `string` | `"datahub-on-eks"` | no |
+| <a name="input_private_subnet_ids"></a> [private\_subnet\_ids](#input\_private\_subnet\_ids) | Ids for existing private subnets - needed when create\_vpc set to false | `list(string)` | `[]` | no |
 | <a name="input_private_subnets"></a> [private\_subnets](#input\_private\_subnets) | Private Subnets CIDRs. 32766 Subnet1 and 16382 Subnet2 IPs per Subnet | `list(string)` | <pre>[<br>  "10.1.0.0/17",<br>  "10.1.128.0/18"<br>]</pre> | no |
 | <a name="input_public_subnets"></a> [public\_subnets](#input\_public\_subnets) | Public Subnets CIDRs. 62 IPs per Subnet | `list(string)` | <pre>[<br>  "10.1.255.128/26",<br>  "10.1.255.192/26"<br>]</pre> | no |
 | <a name="input_region"></a> [region](#input\_region) | Region | `string` | `"us-west-2"` | no |
 | <a name="input_tags"></a> [tags](#input\_tags) | Default tags | `map(string)` | `{}` | no |
-| <a name="input_vpc_cidr"></a> [vpc\_cidr](#input\_vpc\_cidr) | VPC CIDR | `string` | `"10.1.0.0/16"` | no |
+| <a name="input_vpc_cidr"></a> [vpc\_cidr](#input\_vpc\_cidr) | VPC CIDR - must change to match the cidr of the existing VPC if create\_vpc set to false | `string` | `"10.1.0.0/16"` | no |
+| <a name="input_vpc_id"></a> [vpc\_id](#input\_vpc\_id) | VPC Id for the existing vpc - needed when create\_vpc set to false | `string` | `""` | no |
 
 ## Outputs
 

analytics/terraform/datahub-on-eks/providers.tf

@@ -15,4 +15,3 @@ provider "helm" {
     token                  = data.aws_eks_cluster_auth.this.token
   }
 }
-