add predict functionality #318
Conversation
plzdoo
requested review from
dhrubo-os,
greaa-aws,
ylwu-amzn,
b4sjoo,
jngz-es and
rbhavna
as code owners
|
DCO is missing. Could you please take a look at this? |
| @@ -494,6 +494,34 @@ def generate_embedding(self, model_id: str, sentences: List[str]) -> object: | |||
| body=API_BODY, | |||
| ) | |||
|
|
|||
| def predict(self, model_id: str, algo_name: str, input_json): | |||
|
|
|||
| API_URL = f"{ML_BASE_URI}/_predict/{algo_name}/{model_id}/_deploy" | |||
There was a problem hiding this comment.
I don't think, this is the correct endpoint for the predict functionality.
There was a problem hiding this comment.
Thanks for pointing out. Already changed this
Signed-off-by: yimingl9 <[email protected]>
Modify request Signed-off-by: yimingl9 <[email protected]>
|
@plzdoo , can you take latest changes from main? You can reuse |
|
@plzdoo linting is failing. Can you check this? Please let me know if you are facing any blocker? |
|
@plzdoo , can you pull latest changes from dev? |
|
| @@ -237,6 +237,64 @@ def test_DEPRECATED_integration_pretrained_model_upload_unload_delete(): | |||
| raised = True | |||
| assert raised == False, "Raised Exception in deleting pretrained model" | |||
|
|
|||
| def test_predict(): | |||
| input_json = { | |||
There was a problem hiding this comment.
Can you consider taking iris_index as an argument here. Since, that is a fixture, you would have the iris data in the opensearch in an index. iris_index variable will have the actual name of the index here.. So, input_index can be iris_index
|
@plzdoo are you working on this? |
Description
[Describe what this change achieves]
Issues Resolved
[List any issues this PR will resolve]
Check List
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.