Generating a client based on the OpenAPI REST specification yields some pretty unusable clients, something that can go a long way is coming up with some half decent operationId
Tools and libraries MAY use the operationId to uniquely identify an operation, therefore, it is RECOMMENDED to follow common programming naming conventions.
Something like post-v2-models-$-MODEL_NAME-versions-$-MODEL_VERSION-infer certainly isn't a common naming convention in many languages I know of.
Generating a client based on the OpenAPI REST specification yields some pretty unusable clients, something that can go a long way is coming up with some half decent
operationIdThe OpenAPI spec suggests:
Something like
post-v2-models-$-MODEL_NAME-versions-$-MODEL_VERSION-infercertainly isn't a common naming convention in many languages I know of.https://github.com/kserve/open-inference-protocol/blob/eeb043e2c95c1dd35f8b9185f5dadf44c7f10c9f/specification/protocol/open_inference_rest.yaml#L119
I'm not sure if including the spec version in the operationId is a good idea or not, eg, is
infera better operationId thaninferv2orv2-infer?