fix

Author: santiagxf

articles/machine-learning/how-to-deploy-mlflow-models-online-progressive.md

@@ -79,6 +79,7 @@ The workspace is the top-level resource for Azure Machine Learning, providing a
     ```python
     import json
     import mlflow
+    import urllib.request
     from mlflow.deployments import get_deploy_client
     ```
 
@@ -339,6 +340,74 @@ So far, the endpoint is empty. There are no deployments on it. Let's create the
     )    
     ```
 
+1. Create a sample input to test the deployment
+
+    # [Azure CLI](#tab/cli)
+    
+    __sample.yml__
+
+    ```yml
+    {
+        "input_data": {
+            "columns": [
+                "age",
+                "sex",
+                "cp",
+                "trestbps",
+                "chol",
+                "fbs",
+                "restecg",
+                "thalach",
+                "exang",
+                "oldpeak",
+                "slope",
+                "ca",
+                "thal"
+            ],
+            "data": [
+                [ 48, 0, 3, 130, 275, 0, 0, 139, 0, 0.2, 1, 0, "normal" ]
+            ]
+        }
+    }
+    ```
+    
+    # [Python (Azure ML SDK)](#tab/sdk)
+    
+    The following code samples 5 observations from the training dataset, removes the `target` column (as the model will predict it), and creates a request in the file `sample.json` that can be used with the model deployment.
+
+    ```python
+    samples = (
+        pd.read_csv("data/heart.csv")
+        .sample(n=5)
+        .drop(columns=["target"])
+        .reset_index(drop=True)
+    )
+    
+    with open("sample.json", "w") as f:
+        f.write(
+            json.dumps(
+                {"input_data": json.loads(samples.to_json(orient="split", index=False))}
+            )
+        )
+    ```
+    
+    # [Python (MLflow SDK)](#tab/mlflow)
+
+    The following code samples 5 observations from the training dataset, removes the `target` column (as the model will predict it), and creates a request.
+
+    ```python
+    samples = (
+        pd.read_csv("data/heart.csv")
+        .sample(n=5)
+        .drop(columns=["target"])
+        .reset_index(drop=True)
+    )
+    
+    sample_request = json.dumps(
+                {"input_data": json.loads(samples.to_json(orient="split", index=False))}
+            )
+    ```
+
 1. Test the deployment
 
     # [Azure CLI](#tab/cli)
@@ -357,17 +426,31 @@ So far, the endpoint is empty. There are no deployments on it. Let's create the
     ```
     
     # [Python (MLflow SDK)](#tab/mlflow)
+
+    Get the scoring URI:
+
+    ```python
+    scoring_uri = deployment_client.get_endpoint(endpoint=endpoint_name)["properties"]["scoringUri"]
+    ```
     
-    Let's create the authentication header:
+    Let's create the headers:
 
     ```python
-    authentication_header = f"'Authorization: Bearer {endpoint_secret_key}'"
+    headers = {
+        'Content-Type':'application/json',
+        'Authorization':('Bearer '+ endpoint_secret_key),
+        'azureml-model-deployment': 'default'
+    }
     ```
 
     Call the endpoint and its default deployment:
 
     ```python
-    
+    req = urllib.request.Request(scoring_uri, sample_request, headers)
+    response = urllib.request.urlopen(req)
+
+    result = response.read()
+    print(result)
     ```
 
 ### Create a green deployment under the endpoint

articles/machine-learning/how-to-deploy-mlflow-models.md

@@ -53,7 +53,7 @@ Each workflow has different capabilities, particularly around which type of comp
 | Scenario | MLflow SDK | Azure ML CLI/SDK | Azure ML studio |
 | :- | :-: | :-: | :-: |
 | Deploy to managed online endpoints | [See example](how-to-deploy-mlflow-models-online-progressive.md)<sup>1</sup> | [See example](how-to-deploy-mlflow-models-online-endpoints.md)<sup>1</sup> | [See example](how-to-deploy-mlflow-models-online-endpoints.md?tabs=studio)<sup>1</sup> |
-| Deploy to managed online endpoints (with a scoring script) |  | [See example](how-to-deploy-mlflow-models-online-endpoints.md#customizing-mlflow-model-deployments) | Not supported  |
+| Deploy to managed online endpoints (with a scoring script) |  | [See example](how-to-deploy-mlflow-models-online-endpoints.md#customizing-mlflow-model-deployments) |  |
 | Deploy to batch endpoints |  | [See example](how-to-mlflow-batch.md) | [See example](how-to-mlflow-batch.md?tab=studio) |
 | Deploy to batch endpoints (with a scoring script) |  | [See example](how-to-mlflow-batch.md#customizing-mlflow-models-deployments-with-a-scoring-script) |   |
 | Deploy to web services (ACI/AKS) | Legacy support<sup>2</sup> | <sup>2</sup> | <sup>2</sup> |
@@ -224,11 +224,6 @@ If you want to customize how inference is executed for MLflow models (or opt-out
 
 To learn more, review these articles:
 
-- [Deploy models with REST](how-to-deploy-with-rest.md)
-- [Create and use online endpoints in the studio](how-to-use-managed-online-endpoint-studio.md)
-- [Safe rollout for online endpoints](how-to-safely-rollout-online-endpoints.md)
-- [How to autoscale managed online endpoints](how-to-autoscale-endpoints.md)
-- [Use batch endpoints for batch scoring](batch-inference/how-to-use-batch-endpoint.md)
-- [View costs for an Azure Machine Learning managed online endpoint](how-to-view-online-endpoints-costs.md)
-- [Access Azure resources with an online endpoint and managed identity](how-to-access-resources-from-endpoints-managed-identities.md)
-- [Troubleshoot online endpoint deployment](how-to-troubleshoot-managed-online-endpoints.md)
+- [Deploy MLflow models to online endpoints](how-to-deploy-mlflow-models-online-endpoints.md)
+- [Progressive rollout of MLflow models](how-to-deploy-mlflow-models-online-progressive.md)
+- [Deploy MLflow models to Batch Endpoints](how-to-mlflow-batch.md)