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

Use AbstractBatchingProcessor for InferenceProcessor #820

Merged
merged 2 commits into from
Jul 12, 2024

Conversation

chishui
Copy link
Contributor

@chishui chishui commented Jul 4, 2024

Description

Based on discussion, it's strongly recommended to move sub batching logic from _bulk API to each processor.

So for two batch supporting processors: text_embedding, sparse_encoding, based on discussion, we make them inherit from a newly introduced AbstractBatchingProcessing so that these two processors supports a new optional parameter batch_size and this parameter can control the cutting sub batches logic. The default of this parameter is 1 to be consistent with existing behavior.

Add more integration tests.

Issues Resolved

opensearch-project/OpenSearch#14283

Check List

  • New functionality includes testing.
    • All tests pass
  • New functionality has been documented.
    • New functionality has javadoc added
  • Commits are signed as per the DCO using --signoff

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

@zane-neo
Copy link
Collaborator

@chishui Please take a look on the conflict.

chishui added 2 commits July 10, 2024 13:25
Signed-off-by: Liyun Xiu <xiliyun@amazon.com>
Signed-off-by: Liyun Xiu <xiliyun@amazon.com>
@chishui chishui force-pushed the batch-processor-main branch from 93a28b2 to 7537831 Compare July 10, 2024 05:30
@chishui
Copy link
Contributor Author

chishui commented Jul 10, 2024

@chishui Please take a look on the conflict.

conflicts have been resolved

@zhichao-aws zhichao-aws merged commit bf2fd5a into opensearch-project:main Jul 12, 2024
81 checks passed
@zhichao-aws zhichao-aws added the backport 2.x Label will add auto workflow to backport PR to 2.x branch label Jul 12, 2024
opensearch-trigger-bot bot pushed a commit that referenced this pull request Jul 12, 2024
* Use AbstractBatchingProcessor for InferenceProcessor

Signed-off-by: Liyun Xiu <xiliyun@amazon.com>

* Add chagnelog

Signed-off-by: Liyun Xiu <xiliyun@amazon.com>

---------

Signed-off-by: Liyun Xiu <xiliyun@amazon.com>
(cherry picked from commit bf2fd5a)
zhichao-aws added a commit that referenced this pull request Jul 19, 2024
* Use AbstractBatchingProcessor for InferenceProcessor

Signed-off-by: Liyun Xiu <xiliyun@amazon.com>

* Add chagnelog

Signed-off-by: Liyun Xiu <xiliyun@amazon.com>

---------

Signed-off-by: Liyun Xiu <xiliyun@amazon.com>
(cherry picked from commit bf2fd5a)

Co-authored-by: Liyun Xiu <xiliyun@amazon.com>
Co-authored-by: zhichao-aws <zhichaog@amazon.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
backport 2.x Label will add auto workflow to backport PR to 2.x branch
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants