Add served-model support to serving endpoint query#1044
Conversation
Signed-off-by: Aidin Tavvafi <at.aidin@gmail.com>
|
Please ensure that the NEXT_CHANGELOG.md file is updated with any relevant changes. |
|
If integration tests don't run automatically, an authorized user can run them manually by following the instructions below: Trigger: Inputs:
Checks will be approved automatically on success. |
|
@hectorcast-db can you please help me with this PR? |
|
@rauchy can you please review this pull request? |
|
Hi @aidint |
What changes are proposed in this pull request?
This PR adds support for querying an individual model in the serving endpoints as documented here.
It adds served-models to the url used for the query requests if
served_model_nameis provided.While querying an individual model behind a serving endpoint is supported by rest api, it is not supported by the sdk. This limits users flexibility in serving multiple models in one endpoint. I raised this problem in this issue.
How is this tested?
I tested this with an endpoint in a private databricks workspace.
Describe any tests you have done; especially if test tests are not part of
the unit tests (e.g. local tests).
I couldn't find any test case for the query methods, therefore the answer is N/A.