add status code to model tensor

[ylwu-amzn]

Description

Add http status code to model tensor, so client can know if the remote model returns correctly.

For example, if Cohere text embeding model exceed quota limit, it will return 429 status code.

Issues Resolved

[List any issues this PR will resolve]

Check List

• New functionality includes testing.
  • All tests pass
• New functionality has been documented.
  • New functionality has javadoc added
• Commits are signed 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.

[codecov]

Codecov Report

Merging #1443 (520bda3) into 2.9 (1b33d6d) will decrease coverage by 0.07%.
Report is 4 commits behind head on 2.9.
The diff coverage is 58.10%.

@@             Coverage Diff              @@
##                2.9    #1443      +/-   ##
============================================
- Coverage     78.76%   78.69%   -0.07%     
- Complexity     2161     2162       +1     
============================================
  Files           168      168              
  Lines          8775     8784       +9     
  Branches        878      879       +1     
============================================
+ Hits           6912     6913       +1     
- Misses         1462     1473      +11     
+ Partials        401      398       -3     

Flag	Coverage Δ
ml-commons	78.69% <58.10%> (-0.07%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files	Coverage Δ
...ain/java/org/opensearch/ml/engine/ModelHelper.java	89.92% <ø> (-0.08%)	⬇️
...engine/algorithms/remote/AwsConnectorExecutor.java	83.01% <100.00%> (+0.66%)	⬆️
...e/algorithms/remote/HttpJsonConnectorExecutor.java	66.66% <100.00%> (+2.08%)	⬆️
...va/org/opensearch/ml/engine/utils/ScriptUtils.java	90.00% <100.00%> (+13.52%)	⬆️
...ine/algorithms/remote/RemoteConnectorExecutor.java	88.46% <66.66%> (+1.79%)	⬆️
...va/org/opensearch/ml/task/MLPredictTaskRunner.java	82.63% <66.66%> (+1.81%)	⬆️
...ch/ml/engine/algorithms/remote/ConnectorUtils.java	59.78% <52.45%> (-11.84%)	⬇️

... and 2 files with indirect coverage changes

[vibrantvarun]

Can you post the api request and response here?

[opensearch-trigger-bot]

The backport to 2.x failed:

The process '/usr/bin/git' failed with exit code 1

To backport manually, run these commands in your terminal:

# Fetch latest updates from GitHub
git fetch
# Create a new working tree
git worktree add .worktrees/backport-2.x 2.x
# Navigate to the new working tree
cd .worktrees/backport-2.x
# Create a new branch
git switch --create backport/backport-1443-to-2.x
# Cherry-pick the merged commit of this pull request and resolve the conflicts
git cherry-pick -x --mainline 1 5fc555d78ac919dde73b413cd470d1cc33e97725
# Push it to GitHub
git push --set-upstream origin backport/backport-1443-to-2.x
# Go back to the original working tree
cd ../..
# Delete the working tree
git worktree remove .worktrees/backport-2.x

Then, create a pull request where the base branch is 2.x and the compare/head branch is backport/backport-1443-to-2.x.

[navneet1v]

status code are great. But, we need some more details on how client should respond to the status code. Like what are the retryable status code, which are permanent failures?

Another thing, this status code is exact status code from remote model, which is inconvenient from client like neural search. Either we should have ML commons also provide a status code around what it thinks of the error. Because different models can give different status code and then neural search cannot understand each of the model as it doesn't know what it really means and what response should be sent to customer.