You can build this locally with any model format supported by openvino:
$ aws s3 cp --recursive s3://rhoai-edge/example-models/fraud-detection/ /tmp/fraud-detection
$ podman build --build-arg MODEL_NAME=fraud-detection -f pipelines/containerfiles/Containerfile.openvino.mlserver.mlflow --tag openvino-fraud-detection /tmp/fraud-detection/1/
$ podman run -d --rm -p 8080:8080 localhost/openvino-fraud-detection:latest
$ curl localhost:8080/metrics
# HELP ovms_requests_success Number of successful requests to a model or a DAG.
# TYPE ovms_requests_success counter
ovms_requests_success{api="KServe",interface="REST",method="ModelReady",name="fraud-detection"} 0
ovms_requests_success{api="KServe",interface="gRPC",method="ModelReady",name="fraud-detection"} 0
ovms_requests_success{api="KServe",interface="gRPC",method="ModelInfer",name="fraud-detection",version="1"} 0
Merge criteria:
Model builds successfully locally and in the pipelines with metrics enabled
[ ] The commits are squashed in a cohesive manner and have meaningful messages.
[ ] Testing instructions have been added in the PR body (for PRs involving changes that are not immediately obvious).
[ ] The developer has manually tested the changes and verified that the changes work
Needs approval from an approver in each of these files:
- ~~[OWNERS](https://github.com/opendatahub-io/ai-edge/blob/main/OWNERS)~~ [grdryn]
Approvers can indicate their approval by writing `/approve` in a comment
Approvers can cancel approval by writing `/approve cancel` in a comment
Description
Removes the
METRICS_PORT
argument from the openvino containerfile since it is not referenced anywhere in the build process and the openvino metrics endpoint is served on the rest api portHow Has This Been Tested?
You can build this locally with any model format supported by openvino:
Merge criteria:
Model builds successfully locally and in the pipelines with metrics enabled