[ML] InferenceService support aliases #128584
Conversation
"elser" is an alias for "elasticsearch", and "sagemaker" is an alias for "amazon_sagemaker". Users can continue to create and use providers by their alias. Elasticsearch will continue to support the alias when it reads the configuration from the internal index.
prwhelan
added
>enhancement
:ml
|
Hi @prwhelan, I've created a changelog YAML for you. |
|
Pinging @elastic/ml-core (Team:ML) |
jonathan-buttner
left a comment
jonathan-buttner
left a comment
There was a problem hiding this comment.
Looks great 🙌 I think there are a few places where we still use the name(). From what you've seen do you think it'll create confusion if a user did a PUT with amazon_bedrock but see amazonbedrock instead?
| testSupportedStream("streaming_completion_test_service_alias"); | ||
| } | ||
|
|
||
| public void testSupportedStream(String serviceName) throws Exception { |
There was a problem hiding this comment.
nit: Can we make this private and potentially static?
I don't think so, or at least I don't think I'd be confused by that. GET will return |
"elser" is an alias for "elasticsearch", and "sagemaker" is an alias for "amazon_sagemaker". Users can continue to create and use providers by their alias. Elasticsearch will continue to support the alias when it reads the configuration from the internal index.
💚 Backport successful
|
"elser" is an alias for "elasticsearch", and "sagemaker" is an alias for "amazon_sagemaker". Users can continue to create and use providers by their alias. Elasticsearch will continue to support the alias when it reads the configuration from the internal index.
"elser" is an alias for "elasticsearch", and "sagemaker" is an alias for "amazon_sagemaker". Users can continue to create and use providers by their alias. Elasticsearch will continue to support the alias when it reads the configuration from the internal index.
3 participants
"elser" is an alias for "elasticsearch", and "sagemaker" is an alias for "amazon_sagemaker".
Users can continue to create and use providers by their alias. Elasticsearch will continue to support the alias when it reads the configuration from the internal index.