radius-project/resource-types-contrib
Add Kubernetes models Recipe - Bicep
Aperta
#246 aperta il 20 lug 2026
good first issuetriaged
Metriche repository
- Star
- (7 stelle)
- Metriche merge PR
- (Merge medio 8g 5h) (16 PR mergiate in 30 g)
Descrizione
Overview of the Resource type and Recipe
Radius.AI/models only has an Azure recipe today (Azure OpenAI, via the AKS recipe pack). Create a Kubernetes Recipe in Bicep using an OpenAI-compatible in-cluster inference server.
Acceptance criteria
- A Kubernetes Bicep recipe at
AI/models/recipes/kubernetes/bicep/(e.g. LocalAI/Ollama: Deployment + Service) serving an open-weight model mapped frommodel. - Emits the Radius
resultobject with the resource type's outputs. - Recipe entry added to the default Kubernetes recipe pack (
recipepack/kubernetes/default-recipepack.bicep) and wired into thepublish-bicep-recipesworkflow matrix. - README; manual testing with
make test-recipe.
Additional context
Footprint: default to a small CPU model for testing; model pull at startup can be slow. Azure-style model values (e.g. gpt-5-mini) don't map 1:1 to open weights — pick an open-weight default. Example: Data/postgreSqlDatabases/recipes/kubernetes/bicep/; contribution guide docs/contributing/contributing-resource-types-recipes.md.