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

[BUG] _predict API not working with asymmetric embedding models #2317

Closed
br3no opened this issue Apr 12, 2024 · 0 comments
Closed

[BUG] _predict API not working with asymmetric embedding models #2317

br3no opened this issue Apr 12, 2024 · 0 comments
Labels
bug Something isn't working untriaged

Comments

@br3no
Copy link
Contributor

br3no commented Apr 12, 2024

What is the bug?
Predict API not working with asymmetric models.

How can one reproduce the bug?
Steps to reproduce the behavior:

  1. create a model group
  2. register an asymmetric model (cf. asymmetric embeddings #2123 (comment))
  3. run inference with it, using the correct parameter
  4. an error states that the parameter was not passed.

What is the expected behavior?
The prediction should work.

What is your host/environment?

  • OS: MacOS
  • Version Sonoma
  • Plugins

Do you have any screenshots?

Do you have any additional context?
I have a fix already.

@br3no br3no added bug Something isn't working untriaged labels Apr 12, 2024
intrafindBreno pushed a commit to br3no/ml-commons that referenced this issue Apr 12, 2024
opensearch-trigger-bot bot pushed a commit that referenced this issue Apr 25, 2024
* Fixes #2317 predict api not working with asymmetric models

Signed-off-by: br3no <[email protected]>

* Adding unit test code path for the parsing of the parameter.

Signed-off-by: br3no <[email protected]>

* Removing involuntary import of guava

Signed-off-by: br3no <[email protected]>

* Refactor package of AsymmetricTextEmbeddingParameters

The MLCommonsClassLoader expects all MLAlgoParameters to be in the
"org.opensearch.ml.common.input.parameter" package.

Signed-off-by: br3no <[email protected]>

* fixing unit test after package refactoring

Signed-off-by: br3no <[email protected]>

---------

Signed-off-by: br3no <[email protected]>
(cherry picked from commit 8425a65)
ylwu-amzn pushed a commit that referenced this issue Apr 25, 2024
…2359)

* Fixes #2317 predict api not working with asymmetric models

Signed-off-by: br3no <[email protected]>

* Adding unit test code path for the parsing of the parameter.

Signed-off-by: br3no <[email protected]>

* Removing involuntary import of guava

Signed-off-by: br3no <[email protected]>

* Refactor package of AsymmetricTextEmbeddingParameters

The MLCommonsClassLoader expects all MLAlgoParameters to be in the
"org.opensearch.ml.common.input.parameter" package.

Signed-off-by: br3no <[email protected]>

* fixing unit test after package refactoring

Signed-off-by: br3no <[email protected]>

---------

Signed-off-by: br3no <[email protected]>
(cherry picked from commit 8425a65)

Co-authored-by: Breno Faria <[email protected]>
dhrubo-os pushed a commit to dhrubo-os/ml-commons that referenced this issue May 17, 2024
… models (opensearch-project#2318) (opensearch-project#2359)

* Fixes opensearch-project#2317 predict api not working with asymmetric models

Signed-off-by: br3no <[email protected]>

* Adding unit test code path for the parsing of the parameter.

Signed-off-by: br3no <[email protected]>

* Removing involuntary import of guava

Signed-off-by: br3no <[email protected]>

* Refactor package of AsymmetricTextEmbeddingParameters

The MLCommonsClassLoader expects all MLAlgoParameters to be in the
"org.opensearch.ml.common.input.parameter" package.

Signed-off-by: br3no <[email protected]>

* fixing unit test after package refactoring

Signed-off-by: br3no <[email protected]>

---------

Signed-off-by: br3no <[email protected]>
(cherry picked from commit 8425a65)

Co-authored-by: Breno Faria <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working untriaged
Projects
None yet
Development

No branches or pull requests

1 participant