Skip to content

RHDHBUGS-2501: openshift-ai connector allow for 'rhdh.modelcatalog.io/model-name' override #1683

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

Open
gabemontero wants to merge 4 commits into
base: main
Choose a base branch
from
+12 −9
Open

RHDHBUGS-2501: openshift-ai connector allow for 'rhdh.modelcatalog.io/model-name' override #1683

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e57723c
RHDHBUGS-2501: openshift-ai connector allow for 'rhdh.modelcatalog.io…
gabemontero Jan 16, 2026
9c9f6e5
Update modules/openshift-ai-connector-for-rhdh/proc-setting-up-opensh…
gabemontero Jan 19, 2026
c97729f
Update modules/openshift-ai-connector-for-rhdh/proc-setting-up-opensh…
gabemontero Jan 19, 2026
a114e43
Update modules/openshift-ai-connector-for-rhdh/ref-enrich-ai-model-me…
gabemontero Jan 19, 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
13 changes: 5 additions & 8 deletions ...nector-for-rhdh/proc-setting-up-openshift-ai-connector-for-rhdh-with-rhoai.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,8 +156,7 @@ type: kubernetes.io/service-account-token
----

. Update your {product-very-short} dynamic plugin configuration.
The {product-very-short} Pod requires two dynamic plugins.
.. In your {product-very-short} dynamic plugins ConfigMap, add the following code:
The {product-very-short} Pod requires two dynamic plugins. In your {product-very-short} dynamic plugins ConfigMap, add the following code:
+
[source,yaml]
----
Expand All @@ -172,9 +171,7 @@ plugins:
** If {product-very-short} was installed using the Operator, modify your {product-very-short} custom resource (CR) instance.
** If {product-very-short} was installed using the Helm charts, modify the *Deployment* specification.

. The system relies on three sidecar containers ({openshift-ai-connector-name}) running alongside the `backstage-backend` container.

Add these sidecar containers to your configuration referencing the `rhdh-rhoai-connector-token` Secret:
. The system relies on three sidecar containers ({openshift-ai-connector-name}) running alongside the `backstage-backend` container. Add these sidecar containers to your configuration referencing the `rhdh-rhoai-connector-token` Secret:
** `location`: Provides the REST API for {product-very-short} plugins to fetch model metadata.
** `storage-rest`: Maintains a cache of AI Model metadata in a ConfigMap called `bac-import-model`.
** `rhoai-normalizer`: Acts as a Kubernetes controller and {rhoai-short} client, normalizing {rhoai-short} metadata for the connector. The following code block is an example:
Expand All @@ -199,7 +196,7 @@ spec:
envFrom:
- secretRef:
name: rhdh-rhoai-connector-token
image: quay.io/redhat-ai-dev/model-catalog-location-service@sha256:763311530fb842a1366447e661ca22563e6ef22505d993716aea350bbbfae9a0
image: quay.io/redhat-ai-dev/model-catalog-location-service@sha256:c4471e07be6e0dbe821613053e6264a552cacda7f8604dbf306e6ac9e81e8ab9
imagePullPolicy: Always
name: location
ports:
Expand Down Expand Up @@ -249,7 +246,7 @@ spec:
envFrom:
- secretRef:
name: rhdh-rhoai-connector-token
image: quay.io/redhat-ai-dev/model-catalog-rhoai-normalizer@sha256:fe6c05d57495d6217c4d584940ec552c3727847ff60f39f5d04f94be024576d8
image: quay.io/redhat-ai-dev/model-catalog-rhoai-normalizer@sha256:9f19742450a3a9c6d9c01d8341a20db7eb5a52a39348f488ae06b6aa49754a26
imagePullPolicy: Always
name: rhoai-normalizer
volumeMounts:
Expand All @@ -275,4 +272,4 @@ where:

`modelCatalog`:: Specifies the name of the provider.
`development`:: Defines future connector capability beyond a single `baseUrl`.
`baseUrl`:: For Developer Preview, this value is the only one supported. Future releases might support external routes.
`baseUrl`:: For Developer Preview, this value is the only one supported. Future releases might support external routes.
8 changes: 7 additions & 1 deletion modules/openshift-ai-connector-for-rhdh/ref-enrich-ai-model-metadata.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,4 +39,10 @@ While {rhoai-short} provides essential data, an AI platform engineer using {rhoa
|`License`
|Links
|A URL to the license file of the model.
|===

|`rhdh.modelcatalog.io/model-name`
|Annotations
|A name of the model used when communicating with the model server's REST API. {openshift-ai-connector-name} stores this name in the `rhdh.modelcatalog.io/model-name` annotation on the `Resource` entity, and defaults this annotation's value to the combined names of the `ResourceModel` and `ModelVersion` in the model registry.

If the model registry is not used, the `KServe InferenceService` name becomes the default value instead, as it often is the same as the model name used when communicating with the model server's REST API. However, the names are not guaranteed to match. If the names do not match, provide the correct model name for model REST API invocations.
|===