Skip to content

[IRD] Documentation for MLOps for multi-instance helm and removing model registry reference in docker-compose #1744

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sajeevrajput merged 5 commits into from
Feb 14, 2026
Merged

[IRD] Documentation for MLOps for multi-instance helm and removing model registry reference in docker-compose #1744

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b3e377a
updated payload.json code in all docs for helm/mlops
jessicaearayil Feb 13, 2026
902a598
included 30443 in curl command and renumbered mlops section
jessicaearayil Feb 13, 2026
4630088
removed variables in docker-compose file
jessicaearayil Feb 13, 2026
446e2df
updated all multi-instance-helm with mlops
jessicaearayil Feb 13, 2026
e8075d5
updated docs for multi-instance helm
jessicaearayil Feb 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions manufacturing-ai-suite/industrial-edge-insights-vision/docker-compose.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,10 +143,8 @@ services:
ports:
- '${MINIO_SERVER_PORT}:8000'
environment:
AppName: "ModelRegistry"
MINIO_ACCESS_KEY: ${MINIO_ACCESS_KEY}
MINIO_SECRET_KEY: ${MINIO_SECRET_KEY}
ENABLE_HTTPS_MODE: ${ENABLE_HTTPS_MODE}
MINIO_BROWSER_REDIRECT_URL: https://${HOST_IP}/minio/
command: server --address ":8000" --certs-dir /certs /data

Expand Down
138 changes: 131 additions & 7 deletions ...uide/pallet-defect-detection/get-started/deploy-multiple-instances-with-helm.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,7 @@
-------------------------------------------
Environment variables loaded from /home/intel/IRD/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/helm/temp_apps/pallet-defect-detection/pdd1/.env
Running sample app: pallet-defect-detection
Using Helm deployment - curl commands will use: 10.223.23.150:30443
Using Helm deployment - curl commands will use: <HOST_IP>:<NGINX_HTTPS_PORT>
Checking status of dlstreamer-pipeline-server...
Server reachable. HTTP Status Code: 200
Getting list of loaded pipelines...
Expand All @@ -150,7 +150,7 @@
-------------------------------------------
Environment variables loaded from /home/intel/IRD/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/helm/temp_apps/pallet-defect-detection/pdd2/.env
Running sample app: pallet-defect-detection
Using Helm deployment - curl commands will use: 10.223.23.150:30444
Using Helm deployment - curl commands will use: <HOST_IP>:<NGINX_HTTPS_PORT>
Checking status of dlstreamer-pipeline-server...
Server reachable. HTTP Status Code: 200
Getting list of loaded pipelines...
Expand All @@ -174,7 +174,7 @@
-------------------------------------------
Environment variables loaded from /home/intel/IRD/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/helm/temp_apps/weld-porosity/weld1/.env
Running sample app: weld-porosity
Using Helm deployment - curl commands will use: 10.223.23.150:30445
Using Helm deployment - curl commands will use: <HOST_IP>:<NGINX_HTTPS_PORT>
Checking status of dlstreamer-pipeline-server...
Server reachable. HTTP Status Code: 200
Getting list of loaded pipelines...
Expand Down Expand Up @@ -307,7 +307,7 @@
2. Start the pipeline for <INSTANCE_NAME>:

```bash
./sample_start.sh -i <INSTANCE_NAME> -p <PIPELINE_NAME>
./sample_start.sh helm -i <INSTANCE_NAME> -p <PIPELINE_NAME>
```

Output:
Expand Down Expand Up @@ -343,7 +343,7 @@
1. Fetch the list of pipeline for <INSTANCE_NAME>:

```bash
./sample_list.sh -i <INSTANCE_NAME>
./sample_list.sh helm -i <INSTANCE_NAME>
```

Example Output:
Expand Down Expand Up @@ -375,15 +375,15 @@

```text
Instance name set to: pdd1
Custom payload file set to: custom_payload_corrected.json
Custom payload file set to: custom_payload.json
Starting specified pipeline(s)...
Found SAMPLE_APP: pallet-defect-detection for INSTANCE_NAME: pdd1
Environment variables loaded from /home/intel/IRD/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/helm/temp_apps/pallet-defect-detection/pdd1/.env
Running sample app: pallet-defect-detection
Using Helm deployment - curl commands will use: <HOST_IP>:<NGINX_HTTPS_PORT>
Checking status of dlstreamer-pipeline-server...
Server reachable. HTTP Status Code: 200
Loading payload from custom_payload_corrected.json
Loading payload from custom_payload.json
Payload loaded successfully.
Starting pipeline: pallet_defect_detection_gpu
Launching pipeline: pallet_defect_detection_gpu
Expand Down Expand Up @@ -740,3 +740,127 @@ Applications can take advantage of S3 publish feature from DL Streamer Pipeline
```sh
./run.sh helm_uninstall
```

## MLOps using Model Download

1. Run all the steps mentioned in above [section](#setup-the-application) to setup the application.

2. Install the helm chart

```sh
./run.sh helm_install
```

3. Copy the resources such as video and model from local directory to the `dlstreamer-pipeline-server` pod to make them available for application while launching pipelines.

```sh
# Below is an example for Pallet Defect Detection. Please adjust the source path of models and videos appropriately for other sample applications.

POD_NAME=$(kubectl get pods -n <INSTANCE_NAME> -o jsonpath='{.items[*].metadata.name}' | tr ' ' '\n' | grep deployment-dlstreamer-pipeline-server | head -n 1)

kubectl cp resources/pallet-defect-detection/videos/warehouse.avi $POD_NAME:/home/pipeline-server/resources/videos/ -c dlstreamer-pipeline-server -n <INSTANCE_NAME>

kubectl cp resources/pallet-defect-detection/models/* $POD_NAME:/home/pipeline-server/resources/models/ -c dlstreamer-pipeline-server -n <INSTANCE_NAME>
```

4. Modify the payload in `helm/temp_apps/<SAMPLE_APP>/<INSTANCE_NAME>/payload.json` to launch an instance for the mlops pipeline.

Below is an example for pallet-defect-detection. Please modify the payload for other sample applications.

```json
[
{
"pipeline": "pallet_defect_detection_mlops",
"payload":{
"source": {
"uri": "file:///home/pipeline-server/resources/videos/warehouse.avi",
"type": "uri"
},
"destination": {
"frame": {
"type": "webrtc",
"peer-id": "pdd"
}
},
"parameters": {
"detection-properties": {
"model": "/home/pipeline-server/resources/models/pallet-defect-detection/deployment/Detection/model/model.xml",
"device": "CPU"
}
}
}
}
]
```

5. Start the pipeline with the above payload.

Below is an example for starting an instance for pallet-defect-detection:

```sh
./sample_start.sh helm -i <INSTANCE_NAME> -p pallet_defect_detection_mlops
```
Note the instance-id.

6. Download and prepare the model. Below is an example for downloading and preparing model for pallet-defect-detection. Please modify MODEL_URL for the other sample applications.
>NOTE- For sake of simplicity, we assume that the new model has already been downloaded by Model Download microservice. The following curl command is only a simulation that just downloads the model. In production, however, they will be downloaded by the Model Download service.

```sh
export MODEL_URL='https://github.com/open-edge-platform/edge-ai-resources/raw/a7c9522f5f936c47de8922046db7d7add13f93a0/models/INT8/pallet_defect_detection.zip'

curl -L "$MODEL_URL" -o "$(basename $MODEL_URL)"

unzip "$(basename $MODEL_URL)" -d new-model # downloaded model is now extracted to `new-model` directory.
```

7. Copy the new model to the `dlstreamer-pipeline-server` pod to make it available for application while launching pipeline.

```sh

POD_NAME=$(kubectl get pods -n <INSTANCE_NAME> -o jsonpath='{.items[*].metadata.name}' | tr ' ' '\n' | grep deployment-dlstreamer-pipeline-server | head -n 1)

kubectl cp new-model $POD_NAME:/home/pipeline-server/resources/models/ -c dlstreamer-pipeline-server -n <INSTANCE_NAME>
```
>NOTE- If there are multiple sample_apps in config.yml, repeat steps 6 and 7 for each sample app and instance.


8. Stop the existing pipeline before restarting it with a new model. Use the instance-id generated from step 5.
```sh
curl -k --location -X DELETE https://<HOST_IP>:<NGINX_HTTPS_PORT>/api/pipelines/{instance_id}
```

9. Modify the payload in `helm/temp_apps/<SAMPLE_APP>/<INSTANCE_NAME>/payload.json` to launch an instance for the mlops pipeline with this new model.

Below is an example for pallet-defect-detection. Please modify the payload for other sample applications.

```json
[
{
"pipeline": "pallet_defect_detection_mlops",
"payload":{
"source": {
"uri": "file:///home/pipeline-server/resources/videos/warehouse.avi",
"type": "uri"
},
"destination": {
"frame": {
"type": "webrtc",
"peer-id": "pdd"
}
},
"parameters": {
"detection-properties": {
"model": "/home/pipeline-server/resources/models/new-model/deployment/Detection/model/model.xml",
"device": "CPU"
}
}
}
}
]

10. View the WebRTC streaming on `https://<HOST_IP>:<NGINX_HTTPS_PORT>/mediamtx/<peer-str-id>/` by replacing `<peer-str-id>` with the value used in the original cURL command to start the pipeline.


## Troubleshooting

- [Troubleshooting Guide](../troubleshooting.md)
14 changes: 7 additions & 7 deletions ...-vision/docs/user-guide/pallet-defect-detection/get-started/deploy-with-helm.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -422,12 +422,12 @@ Applications can take advantage of S3 publish feature from DL Streamer Pipeline
kubectl cp new-model $POD_NAME:/home/pipeline-server/resources/models/ -c dlstreamer-pipeline-server -n apps
```

7. Stop the existing pipeline before restarting it with a new model. Use the instance-id generated from step 5.
8. Stop the existing pipeline before restarting it with a new model. Use the instance-id generated from step 5.
```sh
curl -k --location -X DELETE https://<HOST_IP>/api/pipelines/{instance_id}
curl -k --location -X DELETE https://<HOST_IP>:30443/api/pipelines/{instance_id}
```

8. Modify the payload in `helm/apps/pallet-defect-detection/payload.json` to launch an instance for the mlops pipeline with this new model
9. Modify the payload in `helm/apps/pallet-defect-detection/payload.json` to launch an instance for the mlops pipeline with this new model

```json
[
Expand All @@ -446,18 +446,18 @@ Applications can take advantage of S3 publish feature from DL Streamer Pipeline
},
"parameters": {
"detection-properties": {
"model": "/home/pipeline-server/resources/models/deployment/Detection/model/model.xml",
"model": "/home/pipeline-server/resources/models/new-model/deployment/Detection/model/model.xml",
"device": "CPU"
}
}
}
}
]

11. View the WebRTC streaming on `https://<HOST_IP>:30443/mediamtx/<peer-str-id>/` by replacing `<peer-str-id>` with the value used in the original cURL command to start the pipeline.

![WebRTC streaming](../_assets/webrtc-streaming.png)
10. View the WebRTC streaming on `https://<HOST_IP>:30443/mediamtx/<peer-str-id>/` by replacing `<peer-str-id>` with the value used in the original cURL command to start the pipeline.

![WebRTC streaming](../_assets/webrtc-streaming.png)

## Troubleshooting

- [Troubleshooting Guide](../troubleshooting.md)
Loading
Loading