Merge pull request #94062 from amymsft/patch-1

jborsecnik · web-flow · commit ca4960546440 · 2022-06-08T13:14:55.000-07:00
Pass in "input" to the invoke method.
diff --git a/articles/machine-learning/how-to-use-batch-endpoint-sdk-v2.md b/articles/machine-learning/how-to-use-batch-endpoint-sdk-v2.md
@@ -204,7 +204,7 @@ Using the `MLClient` created earlier, we'll get a handle to the endpoint. The en
     # invoke the endpoint for batch scoring job
     job = ml_client.batch_endpoints.invoke(
         endpoint_name=batch_endpoint_name,
-        input_data=input,
+        input=input,
         deployment_name="non-mlflow-deployment",  # name is required as default deployment is not set
         params_override=[{"mini_batch_size": "20"}, {"compute.instance_count": "4"}],
     )

Original file line number	Diff line number	Diff line change
@@ -204,7 +204,7 @@ Using the `MLClient` created earlier, we'll get a handle to the endpoint. The en
`204`	`204`	`# invoke the endpoint for batch scoring job`
`205`	`205`	`job = ml_client.batch_endpoints.invoke(`
`206`	`206`	`endpoint_name=batch_endpoint_name,`
`207`		`- input_data=input,`
	`207`	`+ input=input,`
`208`	`208`	`deployment_name="non-mlflow-deployment", # name is required as default deployment is not set`
`209`	`209`	`params_override=[{"mini_batch_size": "20"}, {"compute.instance_count": "4"}],`
`210`	`210`	`)`