Skip to content
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.

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

Adding endpoint creation validation to ElasticInferenceService #117642

Merged
merged 6 commits into from
Feb 19, 2025

Conversation

dan-rubinstein
Copy link
Member

@dan-rubinstein dan-rubinstein commented Nov 27, 2024

Description

This change introduces endpoint validation for EIS endpoints.

Question for the team before merging this change: Is there a reason we needed the updateModelWithEmbeddingDetails function? It seems that it just recreates the model with it's existing values so I have removed it in this change?

Testing

  • Unit tests
  • Ran EIS gateway+model-server locally and confirmed that creating an EIS endpoint successfully makes a validation call
  • Attempted to make an endpoint without EIS gateway+model-server running and confirmed that validation call fails and endpoint is not created.

@dan-rubinstein dan-rubinstein added :ml Machine learning Team:ML Meta label for the ML team v9.0.0 labels Nov 27, 2024
@elasticsearchmachine elasticsearchmachine added the external-contributor Pull request authored by a developer outside the Elasticsearch team label Nov 27, 2024
@dan-rubinstein dan-rubinstein removed the external-contributor Pull request authored by a developer outside the Elasticsearch team label Nov 27, 2024
@dan-rubinstein
Copy link
Member Author

@elasticmachine merge upstream

@dan-rubinstein dan-rubinstein marked this pull request as ready for review February 18, 2025 18:53
@elasticsearchmachine
Copy link
Collaborator

Pinging @elastic/ml-core (Team:ML)

@elasticsearchmachine
Copy link
Collaborator

Hi @dan-rubinstein, I've created a changelog YAML for you.

@dan-rubinstein dan-rubinstein added v8.19.0 auto-backport Automatically create backport pull requests when merged labels Feb 19, 2025
@jonathan-buttner
Copy link
Contributor

Is there a reason we needed the updateModelWithEmbeddingDetails function? It seems that it just recreates the model with it's existing values so I have removed it in this change?

I think that was a copy/paste issue. Although when EIS begins supporting text embedding we'll want to add it back so that we can get the accurate number of dimensions.

@dan-rubinstein
Copy link
Member Author

@elasticmachine merge upstream

@dan-rubinstein dan-rubinstein merged commit bea8df3 into elastic:main Feb 19, 2025
17 checks passed
@elasticsearchmachine
Copy link
Collaborator

💔 Backport failed

Status Branch Result
8.x Commit could not be cherrypicked due to conflicts

You can use sqren/backport to manually backport by running backport --upstream elastic/elasticsearch --pr 117642

dan-rubinstein added a commit to dan-rubinstein/elasticsearch that referenced this pull request Feb 19, 2025
…ic#117642)

* Adding endpoint creation validation to ElasticInferenceService

* Fix unit tests

* Update docs/changelog/117642.yaml

---------

Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>
dan-rubinstein added a commit that referenced this pull request Feb 20, 2025
…) (#122956)

* Adding endpoint creation validation to ElasticInferenceService

* Fix unit tests

* Update docs/changelog/117642.yaml

---------

Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>
@dan-rubinstein dan-rubinstein deleted the eis-validation branch February 20, 2025 19:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
auto-backport Automatically create backport pull requests when merged backport pending >enhancement :ml Machine learning Team:ML Meta label for the ML team v8.19.0 v9.1.0
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants