Merge branch 'main' into test-ml-sdk-version-ml-1.11.1

cli/endpoints/online/deploy-with-packages/custom-model/deploy.sh

@@ -0,0 +1,45 @@
+#<register_model>
+MODEL_NAME='sklearn-regression'
+MODEL_PATH='model'
+az ml model create --name $MODEL_NAME --path $MODEL_PATH --type custom_model
+#</register_model>
+
+#<base_environment>
+az ml environment create -f environment/sklearn-regression-env.yml
+#</base_environment>
+
+#<build_package>
+az ml model package -n $MODEL_NAME -l latest --file package-moe.yml
+#</build_package>
+
+#<endpoint_name>
+ENDPOINT_NAME = "sklearn-regression-online"
+#</endpoint_name>
+
+# The following code ensures the created deployment has a unique name
+ENDPOINT_SUFIX=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w ${1:-5} | head -n 1)
+ENDPOINT_NAME="$ENDPOINT_NAME-$ENDPOINT_SUFIX"
+
+#<create_endpoint>
+az ml online-endpoint create -n $ENDPOINT_NAME
+#</create_endpoint>
+
+#<create_deployment>
+az ml online-deployment create -f deployment.yml
+#</create_deployment>
+
+#<test_deployment>
+az ml online-endpoint invoke -n $ENDPOINT_NAME -d with-package -f sample-request.json
+#</test_deployment>
+
+#<create_deployment_with_package>
+az ml online-deployment create -f model-deployment.yml --with-package
+#</create_deployment_with_package>
+
+#<delete_resources>
+az ml online-endpoint delete -n $ENDPOINT_NAME --yes
+#</delete_resources>
+
+#<build_package_copy>
+az ml model package -n $MODEL_NAME -l latest --file package-external.yml
+#</build_package_copy>

cli/endpoints/online/deploy-with-packages/custom-model/deployment.yml

@@ -0,0 +1,6 @@
+$schema: https://azuremlschemas.azureedge.net/latest/managedOnlineDeployment.schema.json
+name: with-package
+endpoint_name: hello-packages
+environment: azureml:sklearn-regression-online-pkg@latest
+instance_type: Standard_DS3_v2
+instance_count: 1

cli/endpoints/online/deploy-with-packages/custom-model/endpoint.yml

@@ -0,0 +1,3 @@
+$schema: https://azuremlschemas.azureedge.net/latest/managedOnlineEndpoint.schema.json
+name: hello-packages
+auth_mode: key

cli/endpoints/online/deploy-with-packages/custom-model/environment/conda.yaml

@@ -0,0 +1,10 @@
+name: model-env
+channels:
+  - conda-forge
+dependencies:
+  - python=3.9
+  - numpy=1.23.5
+  - pip=23.0.1
+  - scikit-learn=1.2.2
+  - scipy=1.10.1
+  - xgboost==1.3.3

cli/endpoints/online/deploy-with-packages/custom-model/environment/sklearn-regression-env.yml

@@ -0,0 +1,5 @@
+$schema: https://azuremlschemas.azureedge.net/latest/environment.schema.json
+name: sklearn-regression-env
+image: mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu22.04
+conda_file: conda.yaml
+description: An environment for models built with XGBoost and Scikit-learn.

cli/endpoints/online/deploy-with-packages/custom-model/model-deployment.yml

@@ -0,0 +1,10 @@
+$schema: https://azuremlschemas.azureedge.net/latest/managedOnlineDeployment.schema.json
+name: with-package
+endpoint_name: hello-packages
+model: azureml:sklearn-regression@latest
+environment: azureml:sklearn-regression-env@latest
+code_configuration:
+  code: src
+  scoring_script: score.py
+instance_type: Standard_DS3_v2
+instance_count: 1

cli/endpoints/online/deploy-with-packages/custom-model/package-external.yml

@@ -0,0 +1,12 @@
+$schema: http://azureml/sdk-2-0/ModelVersionPackage.json
+base_environment_source:
+    type: environment_asset
+    resource_id: azureml:sklearn-regression-env@latest
+target_environment_name: sklearn-regression-docker-pkg
+inferencing_server: 
+    type: azureml_online
+    code_configuration:
+      code: src
+      entry_script: score.py
+model_configuration:
+  mode: copy

cli/endpoints/online/deploy-with-packages/custom-model/package-moe.yml

@@ -0,0 +1,10 @@
+$schema: http://azureml/sdk-2-0/ModelVersionPackage.json
+base_environment_source:
+    type: environment_asset
+    resource_id: azureml:sklearn-regression-env@latest
+target_environment_name: sklearn-regression-online-pkg
+inferencing_server: 
+    type: azureml_online
+    code_configuration:
+      code: src
+      entry_script: score.py

cli/endpoints/online/deploy-with-packages/custom-model/sample-request.json

@@ -0,0 +1,6 @@
+{
+    "data": [
+        [1,2,3,4,5,6,7,8,9,10], 
+        [10,9,8,7,6,5,4,3,2,1]
+    ]
+}

cli/endpoints/online/deploy-with-packages/custom-model/src/score.py

@@ -0,0 +1,36 @@
+import os
+import logging
+import json
+import numpy
+import joblib
+
+
+def init():
+    """
+    This function is called when the container is initialized/started, typically after create/update of the deployment.
+    You can write the logic here to perform init operations like caching the model in memory
+    """
+    global model
+    # AZUREML_MODEL_DIR is an environment variable created during deployment.
+    # It is the path to the model folder (./azureml-models/$MODEL_NAME/$VERSION)
+    # Please provide your model's folder name if there is one
+    model_path = os.path.join(
+        os.getenv("AZUREML_MODEL_DIR"), "model/sklearn_regression_model.pkl"
+    )
+    # deserialize the model file back into a sklearn model
+    model = joblib.load(model_path)
+    logging.info("Init complete")
+
+
+def run(raw_data):
+    """
+    This function is called for every invocation of the endpoint to perform the actual scoring/prediction.
+    In the example we extract the data from the json input and call the scikit-learn model's predict()
+    method and return the result back
+    """
+    logging.info("model 1: request received")
+    data = json.loads(raw_data)["data"]
+    data = numpy.array(data)
+    result = model.predict(data)
+    logging.info("Request processed")
+    return result.tolist()

cli/endpoints/online/deploy-with-packages/mlflow-model/deploy.sh

@@ -0,0 +1,41 @@
+#<register_model>
+MODEL_NAME='heart-classifier-mlflow'
+MODEL_PATH='model'
+az ml model create --name $MODEL_NAME --path $MODEL_PATH --type mlflow_model
+#</register_model>
+
+#<build_package>
+az ml model package -n $MODEL_NAME -l latest --file package.yml
+#</build_package>
+
+#<endpoint_name>
+ENDPOINT_NAME = "heart-classifier"
+#</endpoint_name>
+
+# The following code ensures the created deployment has a unique name
+ENDPOINT_SUFIX=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w ${1:-5} | head -n 1)
+ENDPOINT_NAME="$ENDPOINT_NAME-$ENDPOINT_SUFIX"
+
+#<create_endpoint>
+az ml online-endpoint create -n $ENDPOINT_NAME
+#</create_endpoint>
+
+#<create_deployment>
+az ml online-deployment create -f deployment.yml -e $ENDPOINT_NAME
+#</create_deployment>
+
+#<test_deployment>
+az ml online-endpoint invoke -n $ENDPOINT_NAME -d with-package -f sample-request.json
+#</test_deployment>
+
+#<create_deployment_inline>
+az ml online-deployment create -f model-deployment.yml -e $ENDPOINT_NAME
+#</create_deployment_inline>
+
+#<delete_resources>
+az ml online-endpoint delete -n $ENDPOINT_NAME --yes
+#</delete_resources>
+
+#<build_package_copy>
+az ml model package -n $MODEL_NAME -l latest --file package-external.yml
+#</build_package_copy>

cli/endpoints/online/deploy-with-packages/mlflow-model/deployment.yml

@@ -0,0 +1,6 @@
+$schema: https://azuremlschemas.azureedge.net/latest/managedOnlineDeployment.schema.json
+name: with-package
+endpoint_name: heart-classifier
+environment: azureml:heart-classifier-mlflow-pkg@latest
+instance_type: Standard_DS3_v2
+instance_count: 1

cli/endpoints/online/deploy-with-packages/mlflow-model/endpoint.yml

@@ -0,0 +1,3 @@
+$schema: https://azuremlschemas.azureedge.net/latest/managedOnlineEndpoint.schema.json
+name: heart-classifier
+auth_mode: key

cli/endpoints/online/deploy-with-packages/mlflow-model/model-deployment.yml

@@ -0,0 +1,6 @@
+$schema: https://azuremlschemas.azureedge.net/latest/managedOnlineDeployment.schema.json
+name: with-package-inline
+endpoint_name: heart-classifier-mlflow
+model: azureml:heart-classifier-mlflow@latest
+instance_type: Standard_DS3_v2
+instance_count: 1

cli/endpoints/online/deploy-with-packages/mlflow-model/model/MLmodel

@@ -0,0 +1,22 @@
+artifact_path: pipeline
+flavors:
+  python_function:
+    env: conda.yaml
+    loader_module: mlflow.sklearn
+    model_path: model.pkl
+    python_version: 3.8.5
+  sklearn:
+    pickled_model: model.pkl
+    serialization_format: cloudpickle
+    sklearn_version: 1.1.2
+model_uuid: 04bd660a1b8b4b1e84b9198c46cfd117
+run_id: 22874b7e-b069-43f0-b90c-1c57793c7854
+signature:
+  inputs: '[{"name": "age", "type": "long"}, {"name": "sex", "type": "long"},
+    {"name": "cp", "type": "long"}, {"name": "trestbps", "type": "long"}, {"name":
+    "chol", "type": "long"}, {"name": "fbs", "type": "long"}, {"name": "restecg",
+    "type": "long"}, {"name": "thalach", "type": "long"}, {"name": "exang", "type":
+    "long"}, {"name": "oldpeak", "type": "double"}, {"name": "slope", "type": "long"},
+    {"name": "ca", "type": "long"}, {"name": "thal", "type": "string"}]'
+  outputs: '[{"type": "long"}]'
+utc_time_created: '2022-10-13 00:55:57.543663'

cli/endpoints/online/deploy-with-packages/mlflow-model/model/conda.yaml

@@ -0,0 +1,11 @@
+channels:
+- conda-forge
+dependencies:
+- python=3.8.5
+- pip
+- pip:
+  - mlflow
+  - cloudpickle==1.6.0
+  - scikit-learn==1.1.2
+  - xgboost==1.3.3
+name: mlflow-env

cli/endpoints/online/deploy-with-packages/mlflow-model/model/requirements.txt

@@ -0,0 +1,15 @@
+mlflow
+cloudpickle==1.6.0
+colorama==0.4.4
+dask==2.30.0
+dataclasses==0.6
+lz4==4.0.0
+psutil==5.9.0
+scikit-learn==1.1.2
+sparse==0.13.0
+tblib==1.7.0
+toolz==0.11.2
+typing-extensions==4.1.1
+uuid==1.30
+xgboost==1.4.2
+xxhash==3.0.0

cli/endpoints/online/deploy-with-packages/mlflow-model/package-external.yml

@@ -0,0 +1,6 @@
+$schema: http://azureml/sdk-2-0/ModelVersionPackage.json
+target_environment_name: heart-classifier-mlflow-pkg
+inferencing_server: 
+    type: azureml_online
+model_configuration:
+    mode: copy

cli/endpoints/online/deploy-with-packages/mlflow-model/package.yml

@@ -0,0 +1,4 @@
+$schema: http://azureml/sdk-2-0/ModelVersionPackage.json
+target_environment_name: heart-classifier-mlflow-pkg
+inferencing_server: 
+    type: azureml_online

cli/endpoints/online/deploy-with-packages/mlflow-model/sample-request.json

@@ -0,0 +1,11 @@
+{
+    "input_data": {
+        "columns": [
+            "age", "sex", "cp", "trestbps", "chol", "fbs", "restecg", "thalach", "exang", "oldpeak", "slope", "ca", "thal"
+        ],
+        "index": [1],
+        "data": [
+            [1, 1, 4, 145, 233, 1, 2, 150, 0, 2.3, 3, 0, 2]
+        ]
+    }
+}

cli/endpoints/online/deploy-with-packages/registry-model/deploy.sh

@@ -0,0 +1,11 @@
+#<get_model>
+MODEL_NAME="t5-base"
+MODEL_VERSION=$(az ml model show --name $MODEL_NAME --label latest --registry-name azureml | jq .version -r)
+#</get_model>
+
+#<build_package>
+az ml model package --name $MODEL_NAME \
+                    --version $MODEL_VERSION \
+                    --registry-name azureml \
+                    --file package.yml
+#</build_package>

cli/endpoints/online/deploy-with-packages/registry-model/package.yml

@@ -0,0 +1,4 @@
+$schema: http://azureml/sdk-2-0/ModelVersionPackage.json
+target_environment_name: pkg-t5-base-online
+inferencing_server: 
+    type: azureml_online

sdk/python/endpoints/online/deploy-with-packages/custom-model/environment/conda.yml

@@ -0,0 +1,10 @@
+name: model-env
+channels:
+  - conda-forge
+dependencies:
+  - python=3.9
+  - numpy=1.23.5
+  - pip=23.0.1
+  - scikit-learn=1.2.2
+  - scipy=1.10.1
+  - xgboost==1.3.3

sdk/python/endpoints/online/deploy-with-packages/custom-model/environment/sklearn-regression-env.yml

@@ -0,0 +1,5 @@
+$schema: https://azuremlschemas.azureedge.net/latest/environment.schema.json
+name: sklearn-regression-env
+image: mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu22.04
+conda_file: conda.yaml
+description: An environment for models built with XGBoost and Scikit-learn.

sdk/python/endpoints/online/deploy-with-packages/custom-model/sample-request.json

@@ -0,0 +1,6 @@
+{
+    "data": [
+        [1,2,3,4,5,6,7,8,9,10], 
+        [10,9,8,7,6,5,4,3,2,1]
+    ]
+}