Skip to content

Conversation

@DonalEvans
Copy link
Contributor

  • Add method to allow services that implement SenderService to indicate whether they support chunked inference
  • Return immediately if the input list is empty for services that support chunked inference
  • Throw exception if the input list is empty for services that do not support chunked inference, to maintain existing behaviour
  • Add tests for all services that implement doChunkedInfer()
  • Update DeepSeekServiceTests for new error message

- Add method to allow services that implement SenderService to indicate
  whether they support chunked inference
- Return immediately if the input list is empty for services that
  support chunked inference
- Throw exception if the input list is empty for services that do not
  support chunked inference, to maintain existing behaviour
- Add tests for all services that implement doChunkedInfer()
- Update DeepSeekServiceTests for new error message
@DonalEvans DonalEvans added >bug :ml Machine learning Team:ML Meta label for the ML team v9.3.0 labels Nov 26, 2025
@elasticsearchmachine
Copy link
Collaborator

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

@elasticsearchmachine
Copy link
Collaborator

Hi @DonalEvans, I've created a changelog YAML for you.

Copy link
Contributor

@mromaios mromaios left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Copy link
Member

@dan-rubinstein dan-rubinstein left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@jimczi jimczi merged commit f70dbb8 into elastic:main Nov 28, 2025
34 checks passed
wwang500 pushed a commit that referenced this pull request Nov 28, 2025
- Add method to allow services that implement SenderService to indicate
  whether they support chunked inference
- Return immediately if the input list is empty for services that
  support chunked inference
- Throw exception if the input list is empty for services that do not
  support chunked inference, to maintain existing behaviour
- Add tests for all services that implement doChunkedInfer()
- Update DeepSeekServiceTests for new error message

(cherry picked from commit f70dbb8)
wwang500 added a commit that referenced this pull request Nov 28, 2025
* [ML] Correctly handle empty inputs in chunkedInfer() (#138632)

- Add method to allow services that implement SenderService to indicate
  whether they support chunked inference
- Return immediately if the input list is empty for services that
  support chunked inference
- Throw exception if the input list is empty for services that do not
  support chunked inference, to maintain existing behaviour
- Add tests for all services that implement doChunkedInfer()
- Update DeepSeekServiceTests for new error message

(cherry picked from commit f70dbb8)

* fix JinaAI tests due to the conflict

---------

Co-authored-by: Donal Evans <donal.evans@elastic.co>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants