Merge branch 'main' into feature/pooja/added_tests

Author: pooja-intel

health-and-life-sciences-ai-suite/multi_modal_patient_monitoring/helm/README.md

@@ -9,6 +9,35 @@ This Helm chart deploys the **Multi modal patient monitoring app** on Kubernetes
 - `kubectl`
 - `helm` (v3+)
 - A working PersistentVolume provisioner (required for PVC binding)
+- **NGINX Ingress Controller** (required when `ingress.enabled: true`, which is the default)
+
+### Ingress Controller prerequisite (required for default configuration)
+
+This chart creates Ingress resources that use `ingressClassName: nginx`. You must have the
+NGINX Ingress Controller running in your cluster before installing the chart with ingress enabled.
+
+```bash
+# Install NGINX Ingress Controller via Helm
+helm repo add ingress-nginx https://kubernetes.github.io/ingress-nginx
+helm repo update
+helm install ingress-nginx ingress-nginx/ingress-nginx \
+  --namespace ingress-nginx --create-namespace
+
+# Wait for the controller to be ready
+kubectl wait --namespace ingress-nginx \
+  --for=condition=ready pod \
+  --selector=app.kubernetes.io/component=controller \
+  --timeout=120s
+```
+
+For **Minikube**, enable the built-in ingress addon instead:
+```bash
+minikube addons enable ingress
+```
+
+If you do not have an ingress controller and do not wish to install one, set
+`ingress.enabled: false` in `values.yaml` and use port-forwarding to access the
+application (see [Access without Ingress](#access-without-ingress-controller) below).
 
 ### Storage prerequisite (required)
 
@@ -118,8 +147,30 @@ Healthy services will show:
 - No crash loops
 
 
+## Ingress Configuration
+
+The chart creates two Ingress resources when `ingress.enabled: true` (default):
+
+| Value | Default | Description |
+|---|---|---|
+| `ingress.enabled` | `true` | Create Ingress resources for external access |
+| `ingress.className` | `nginx` | IngressClass to use (requires a matching controller) |
+| `ingress.annotations` | *(nginx-specific)* | Annotations applied to the main ingress |
+| `ingress.hosts` | `multi-modal-patient-monitoring.local` | Hostname and path routing rules |
+
+To disable ingress (e.g., for environments without an ingress controller):
+
+```bash
+helm install multi-modal-patient-monitoring . \
+  --namespace multi-modal-patient-monitoring \
+  --create-namespace \
+  --set ingress.enabled=false
+```
+
 ## Access the Frontend UI
-### 1. Check the Ingress Resource
+
+### With Ingress (default)
+#### 1. Check the Ingress Resource
 
 Run the following command to view the ingress configuration:
 
@@ -133,15 +184,15 @@ Example output:
 NAME       HOSTS               PATHS   ADDRESS         PORTS
 multi-modal-patient-monitoring  multi-modal-patient-monitoring.local       /       xx.xx.xx.xx   80
 ```
-### 2. If an IP Address Appears in ADDRESS
+#### 2. If an IP Address Appears in ADDRESS
 
 Add the hostname mapping to your local machine:
 ```bash
 echo "<IP> multi-modal-patient-monitoring.local" | sudo tee -a /etc/hosts
 ```
 Replace <IP> with the value shown in the ADDRESS column.
 
-### 3. If the ADDRESS Field is Empty (Common in Minikube)
+#### 3. If the ADDRESS Field is Empty (Common in Minikube)
 Some local Kubernetes environments (such as Minikube) do not automatically populate the ingress IP.
 
 Retrieve the Minikube cluster IP:
@@ -153,13 +204,13 @@ Then map the hostname to the IP:
 echo "$(minikube ip) multi-modal-patient-monitoring.local" | sudo tee -a /etc/hosts
 ```
 
-### 4. Enable Ingress in Minikube (if not already enabled)
+#### 4. Enable Ingress in Minikube (if not already enabled)
 ```bash
 minikube addons enable ingress
 ```
 Wait a few moments for the ingress controller to start.
 
-### 5.Open the Application
+#### 5.Open the Application
 Open your browser and navigate to:
 ```bash
 http://<host-or-ip>/
@@ -183,6 +234,52 @@ From here you can access:
 
   - Metrics Dashboard
 
+### Access without Ingress Controller
+
+If you deployed with `ingress.enabled: false` or do not have an NGINX Ingress Controller,
+you can access the application using `kubectl port-forward`.
+
+#### Forward the UI service
+```bash
+kubectl port-forward -n multi-modal-patient-monitoring svc/ui 8080:80
+```
+Then open http://localhost:8080 in your browser.
+
+#### Forward the Aggregator API (video streams and API)
+```bash
+kubectl port-forward -n multi-modal-patient-monitoring svc/aggregator 8081:80
+```
+The aggregator API is then available at http://localhost:8081.
+
+#### Forward the Pose Estimation stream
+```bash
+kubectl port-forward -n multi-modal-patient-monitoring svc/pose 8085:8085
+```
+The pose video feed is then available at http://localhost:8085/video_feed and
+http://localhost:8085/pose-video.
+
+> **Tip:** You can run all three `port-forward` commands in separate terminal windows
+> to access the full application simultaneously.
+
+#### Alternative: NodePort access
+
+You can also switch the services to NodePort type by overriding the service type:
+
+```bash
+helm install multi-modal-patient-monitoring . \
+  --namespace multi-modal-patient-monitoring \
+  --create-namespace \
+  --set ingress.enabled=false \
+  --set service.type=NodePort
+```
+
+Then find the assigned node ports:
+```bash
+kubectl get svc -n multi-modal-patient-monitoring
+```
+
+Access the services at `http://<node-ip>:<node-port>`.
+
 
 ## Uninstall
 ```bash

health-and-life-sciences-ai-suite/multi_modal_patient_monitoring/helm/multi_modal_patient_monitoring/templates/pose-ingress.yaml

@@ -1,3 +1,4 @@
+{{- if .Values.ingress.enabled }}
 apiVersion: networking.k8s.io/v1
 kind: Ingress
 metadata:
@@ -31,4 +32,5 @@ spec:
               service:
                 name: pose
                 port:
-                  number: 8085
+                  number: 8085
+{{- end }}

metro-ai-suite/metro-sdk-manager/docs/user-guide/metro-gen-ai-sdk/get-started.md

@@ -35,22 +35,14 @@ curl https://raw.githubusercontent.com/open-edge-platform/edge-ai-suites/refs/he
 
 This section demonstrates a complete RAG (Retrieval-Augmented Generation) application workflow using the installed Gen AI components.
 
-### Step 1: Navigate to Sample Application
-
-Navigate to the pre-installed question-answering application directory:
-
-```bash
-cd $HOME/metro/edge-ai-libraries/sample-applications/chat-question-and-answer
-```
-
-### Step 2: Setup Model Download Service
+### Step 1: Setup Model Download Service
 
 Configure and start the Model Download service to manage LLM and embedding model downloads:
 
 ```bash
 cd $HOME/metro/edge-ai-libraries/microservices/model-download
 export REGISTRY="intel/"
-export TAG=latest
+export TAG=1.2.0
 export HUGGINGFACEHUB_API_TOKEN=<your-huggingface-token>
 source scripts/run_service.sh up --plugins openvino --model-path $HOME/metro/models/
 ```
@@ -59,7 +51,7 @@ source scripts/run_service.sh up --plugins openvino --model-path $HOME/metro/mod
 
 Update the `<your-huggingface-token>` to your Access Token from Hugging Face. To learn more, follow this [guide](https://huggingface.co/docs/hub/en/security-tokens).
 
-### Step 3: Configure Environment and Dependencies
+### Step 2: Configure Environment and Dependencies
 
 Set up the Python virtual environment and install required dependencies:
 
@@ -72,13 +64,13 @@ export EMBEDDING_MODEL_NAME=Alibaba-NLP/gte-large-en-v1.5
 export RERANKER_MODEL=BAAI/bge-reranker-base
 export DEVICE="CPU"
 export REGISTRY="intel/"
-export TAG=latest
+export TAG=2.1.0-rc2
 export MODEL_DOWNLOAD_HOST=localhost
 export MODEL_DOWNLOAD_PORT=8200
 source setup.sh llm=OVMS embed=OVMS
 ```
 
-### Step 4: Deploy the Application
+### Step 3: Deploy the Application
 
 Start the complete Gen AI application stack using Docker Compose:
 
@@ -87,15 +79,15 @@ export ALLOWED_HOSTS="*.intel.com,en.wikipedia.org,*.wikipedia.org,*.github.com"
 docker compose up
 ```
 
-### Step 5: Verify Deployment Status
+### Step 4: Verify Deployment Status
 
 Run below command in another terminal to check that all application components are running correctly:
 
 ```bash
 docker ps
 ```
 
-### Step 6: Access the Application Interface
+### Step 5: Access the Application Interface
 
 Open a web browser and navigate to the application dashboard:
 

metro-ai-suite/metro-sdk-manager/docs/user-guide/metro-vision-ai-sdk/tutorial-3.md

@@ -64,7 +64,7 @@ mkdir -p ~/metro/metro-vision-tutorial-3
 cd ~/metro/metro-vision-tutorial-3
 
 # Download sample city intersection video for object detection
-wget -O intersection.mp4 https://www.pexels.com/download/video/34505889/?fps=29.97&h=360&w=640
+wget -O intersection.mp4 https://www.pexels.com/download/video/34505889?fps=29.97&h=360&w=640
 
 ```
 
@@ -100,7 +100,7 @@ cat > inference.py << 'EOF'
 
 import cv2
 import numpy as np
-from openvino.runtime import Core
+from openvino import Core
 
 # --- Configuration ---
 model_path = "/home/openvino/public/yolov10s/FP16/yolov10s.xml"
@@ -128,6 +128,11 @@ class_names = [
 # --- Initialize OpenVINO Core and Load Model ---
 ie = Core()
 model = ie.read_model(model=model_path)
+
+# Reshape model to static input shape if dynamic (YOLOv10s expects 640x640)
+if model.inputs[0].partial_shape.is_dynamic:
+    model.reshape({model.inputs[0].any_name: [1, 3, 640, 640]})
+
 compiled_model = ie.compile_model(model=model, device_name="CPU")
 
 # Get model input and output information

metro-ai-suite/metro-sdk-manager/scripts/metro-gen-ai-sdk.sh

@@ -28,6 +28,9 @@ images=(
   "intel/multimodal-embedding-serving:1.3.2-rc1"
   "intel/vdms-dataprep:1.3.2-rc1"
   "intel/vlm-openvino-serving:1.3.2-rc1"
+  "intel/model-download:1.2.0"
+  "intel/chatqna:2.1.0-rc2"
+  "intel/chatqna-ui:2.1.0-rc2"
 )
 NAME="Metro Gen AI SDK"