Skip to content

Commit 83070d7

Browse files
jessicaearayiljessicaearayil
authored
[IRD] Documentation for MLOps for multi-instance helm and removing model registry reference in docker-compose (open-edge-platform#1744)
1 parent b936274 commit 83070d7

File tree

9 files changed

+1505
-999
lines changed

9 files changed

+1505
-999
lines changed

‎manufacturing-ai-suite/industrial-edge-insights-vision/docker-compose.yml‎

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -143,10 +143,8 @@ services:
143143
ports:
144144
- '${MINIO_SERVER_PORT}:8000'
145145
environment:
146-
AppName: "ModelRegistry"
147146
MINIO_ACCESS_KEY: ${MINIO_ACCESS_KEY}
148147
MINIO_SECRET_KEY: ${MINIO_SECRET_KEY}
149-
ENABLE_HTTPS_MODE: ${ENABLE_HTTPS_MODE}
150148
MINIO_BROWSER_REDIRECT_URL: https://${HOST_IP}/minio/
151149
command: server --address ":8000" --certs-dir /certs /data
152150

‎manufacturing-ai-suite/industrial-edge-insights-vision/docs/user-guide/pallet-defect-detection/get-started/deploy-multiple-instances-with-helm.md‎

Lines changed: 131 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -126,7 +126,7 @@
126126
-------------------------------------------
127127
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
128128
Running sample app: pallet-defect-detection
129-
Using Helm deployment - curl commands will use: 10.223.23.150:30443
129+
Using Helm deployment - curl commands will use: <HOST_IP>:<NGINX_HTTPS_PORT>
130130
Checking status of dlstreamer-pipeline-server...
131131
Server reachable. HTTP Status Code: 200
132132
Getting list of loaded pipelines...
@@ -150,7 +150,7 @@
150150
-------------------------------------------
151151
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
152152
Running sample app: pallet-defect-detection
153-
Using Helm deployment - curl commands will use: 10.223.23.150:30444
153+
Using Helm deployment - curl commands will use: <HOST_IP>:<NGINX_HTTPS_PORT>
154154
Checking status of dlstreamer-pipeline-server...
155155
Server reachable. HTTP Status Code: 200
156156
Getting list of loaded pipelines...
@@ -174,7 +174,7 @@
174174
-------------------------------------------
175175
Environment variables loaded from /home/intel/IRD/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/helm/temp_apps/weld-porosity/weld1/.env
176176
Running sample app: weld-porosity
177-
Using Helm deployment - curl commands will use: 10.223.23.150:30445
177+
Using Helm deployment - curl commands will use: <HOST_IP>:<NGINX_HTTPS_PORT>
178178
Checking status of dlstreamer-pipeline-server...
179179
Server reachable. HTTP Status Code: 200
180180
Getting list of loaded pipelines...
@@ -307,7 +307,7 @@
307307
2. Start the pipeline for <INSTANCE_NAME>:
308308
309309
```bash
310-
./sample_start.sh -i <INSTANCE_NAME> -p <PIPELINE_NAME>
310+
./sample_start.sh helm -i <INSTANCE_NAME> -p <PIPELINE_NAME>
311311
```
312312
313313
Output:
@@ -343,7 +343,7 @@
343343
1. Fetch the list of pipeline for <INSTANCE_NAME>:
344344
345345
```bash
346-
./sample_list.sh -i <INSTANCE_NAME>
346+
./sample_list.sh helm -i <INSTANCE_NAME>
347347
```
348348
349349
Example Output:
@@ -375,15 +375,15 @@
375375
376376
```text
377377
Instance name set to: pdd1
378-
Custom payload file set to: custom_payload_corrected.json
378+
Custom payload file set to: custom_payload.json
379379
Starting specified pipeline(s)...
380380
Found SAMPLE_APP: pallet-defect-detection for INSTANCE_NAME: pdd1
381381
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
382382
Running sample app: pallet-defect-detection
383383
Using Helm deployment - curl commands will use: <HOST_IP>:<NGINX_HTTPS_PORT>
384384
Checking status of dlstreamer-pipeline-server...
385385
Server reachable. HTTP Status Code: 200
386-
Loading payload from custom_payload_corrected.json
386+
Loading payload from custom_payload.json
387387
Payload loaded successfully.
388388
Starting pipeline: pallet_defect_detection_gpu
389389
Launching pipeline: pallet_defect_detection_gpu
@@ -740,3 +740,127 @@ Applications can take advantage of S3 publish feature from DL Streamer Pipeline
740740
```sh
741741
./run.sh helm_uninstall
742742
```
743+
744+
## MLOps using Model Download
745+
746+
1. Run all the steps mentioned in above [section](#setup-the-application) to setup the application.
747+
748+
2. Install the helm chart
749+
750+
```sh
751+
./run.sh helm_install
752+
```
753+
754+
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.
755+
756+
```sh
757+
# Below is an example for Pallet Defect Detection. Please adjust the source path of models and videos appropriately for other sample applications.
758+
759+
POD_NAME=$(kubectl get pods -n <INSTANCE_NAME> -o jsonpath='{.items[*].metadata.name}' | tr ' ' '\n' | grep deployment-dlstreamer-pipeline-server | head -n 1)
760+
761+
kubectl cp resources/pallet-defect-detection/videos/warehouse.avi $POD_NAME:/home/pipeline-server/resources/videos/ -c dlstreamer-pipeline-server -n <INSTANCE_NAME>
762+
763+
kubectl cp resources/pallet-defect-detection/models/* $POD_NAME:/home/pipeline-server/resources/models/ -c dlstreamer-pipeline-server -n <INSTANCE_NAME>
764+
```
765+
766+
4. Modify the payload in `helm/temp_apps/<SAMPLE_APP>/<INSTANCE_NAME>/payload.json` to launch an instance for the mlops pipeline.
767+
768+
Below is an example for pallet-defect-detection. Please modify the payload for other sample applications.
769+
770+
```json
771+
[
772+
{
773+
"pipeline": "pallet_defect_detection_mlops",
774+
"payload":{
775+
"source": {
776+
"uri": "file:///home/pipeline-server/resources/videos/warehouse.avi",
777+
"type": "uri"
778+
},
779+
"destination": {
780+
"frame": {
781+
"type": "webrtc",
782+
"peer-id": "pdd"
783+
}
784+
},
785+
"parameters": {
786+
"detection-properties": {
787+
"model": "/home/pipeline-server/resources/models/pallet-defect-detection/deployment/Detection/model/model.xml",
788+
"device": "CPU"
789+
}
790+
}
791+
}
792+
}
793+
]
794+
```
795+
796+
5. Start the pipeline with the above payload.
797+
798+
Below is an example for starting an instance for pallet-defect-detection:
799+
800+
```sh
801+
./sample_start.sh helm -i <INSTANCE_NAME> -p pallet_defect_detection_mlops
802+
```
803+
Note the instance-id.
804+
805+
6. Download and prepare the model. Below is an example for downloading and preparing model for pallet-defect-detection. Please modify MODEL_URL for the other sample applications.
806+
>NOTE- For sake of simplicity, we assume that the new model has already been downloaded by Model Download microservice. The following curl command is only a simulation that just downloads the model. In production, however, they will be downloaded by the Model Download service.
807+
808+
```sh
809+
export MODEL_URL='https://github.com/open-edge-platform/edge-ai-resources/raw/a7c9522f5f936c47de8922046db7d7add13f93a0/models/INT8/pallet_defect_detection.zip'
810+
811+
curl -L "$MODEL_URL" -o "$(basename $MODEL_URL)"
812+
813+
unzip "$(basename $MODEL_URL)" -d new-model # downloaded model is now extracted to `new-model` directory.
814+
```
815+
816+
7. Copy the new model to the `dlstreamer-pipeline-server` pod to make it available for application while launching pipeline.
817+
818+
```sh
819+
820+
POD_NAME=$(kubectl get pods -n <INSTANCE_NAME> -o jsonpath='{.items[*].metadata.name}' | tr ' ' '\n' | grep deployment-dlstreamer-pipeline-server | head -n 1)
821+
822+
kubectl cp new-model $POD_NAME:/home/pipeline-server/resources/models/ -c dlstreamer-pipeline-server -n <INSTANCE_NAME>
823+
```
824+
>NOTE- If there are multiple sample_apps in config.yml, repeat steps 6 and 7 for each sample app and instance.
825+
826+
827+
8. Stop the existing pipeline before restarting it with a new model. Use the instance-id generated from step 5.
828+
```sh
829+
curl -k --location -X DELETE https://<HOST_IP>:<NGINX_HTTPS_PORT>/api/pipelines/{instance_id}
830+
```
831+
832+
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.
833+
834+
Below is an example for pallet-defect-detection. Please modify the payload for other sample applications.
835+
836+
```json
837+
[
838+
{
839+
"pipeline": "pallet_defect_detection_mlops",
840+
"payload":{
841+
"source": {
842+
"uri": "file:///home/pipeline-server/resources/videos/warehouse.avi",
843+
"type": "uri"
844+
},
845+
"destination": {
846+
"frame": {
847+
"type": "webrtc",
848+
"peer-id": "pdd"
849+
}
850+
},
851+
"parameters": {
852+
"detection-properties": {
853+
"model": "/home/pipeline-server/resources/models/new-model/deployment/Detection/model/model.xml",
854+
"device": "CPU"
855+
}
856+
}
857+
}
858+
}
859+
]
860+
861+
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.
862+
863+
864+
## Troubleshooting
865+
866+
- [Troubleshooting Guide](../troubleshooting.md)

‎manufacturing-ai-suite/industrial-edge-insights-vision/docs/user-guide/pallet-defect-detection/get-started/deploy-with-helm.md‎

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -422,12 +422,12 @@ Applications can take advantage of S3 publish feature from DL Streamer Pipeline
422422
kubectl cp new-model $POD_NAME:/home/pipeline-server/resources/models/ -c dlstreamer-pipeline-server -n apps
423423
```
424424
425-
7. Stop the existing pipeline before restarting it with a new model. Use the instance-id generated from step 5.
425+
8. Stop the existing pipeline before restarting it with a new model. Use the instance-id generated from step 5.
426426
```sh
427-
curl -k --location -X DELETE https://<HOST_IP>/api/pipelines/{instance_id}
427+
curl -k --location -X DELETE https://<HOST_IP>:30443/api/pipelines/{instance_id}
428428
```
429429
430-
8. Modify the payload in `helm/apps/pallet-defect-detection/payload.json` to launch an instance for the mlops pipeline with this new model
430+
9. Modify the payload in `helm/apps/pallet-defect-detection/payload.json` to launch an instance for the mlops pipeline with this new model
431431
432432
```json
433433
[
@@ -446,18 +446,18 @@ Applications can take advantage of S3 publish feature from DL Streamer Pipeline
446446
},
447447
"parameters": {
448448
"detection-properties": {
449-
"model": "/home/pipeline-server/resources/models/deployment/Detection/model/model.xml",
449+
"model": "/home/pipeline-server/resources/models/new-model/deployment/Detection/model/model.xml",
450450
"device": "CPU"
451451
}
452452
}
453453
}
454454
}
455455
]
456456
457-
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.
458-
459-
![WebRTC streaming](../_assets/webrtc-streaming.png)
457+
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.
460458
459+
![WebRTC streaming](../_assets/webrtc-streaming.png)
460+
461461
## Troubleshooting
462462
463463
- [Troubleshooting Guide](../troubleshooting.md)

0 commit comments

Comments
 (0)