Complete Azure ML Managed Endpoints Tutorial: Production Model Deployment

Azure ML Managed Endpoints provide a fully managed solution for deploying machine learning models at scale. They handle infrastructure, scaling, security, and monitoring automatically.

Why Managed Endpoints?

• Fully managed: No infrastructure to manage
• Auto-scaling: Scale based on traffic
• Blue-green deployments: Safe rollouts
• Built-in monitoring: Metrics and logging
• Security: Authentication and network isolation

• Online endpoints: Real-time inference
• Batch endpoints: Large-scale batch processing

Prerequisites

pip install azure-ai-ml azure-identity

Azure CLI
az login
az extension add -n ml

Online Endpoints

1. Create Online Endpoint

from azure.ai.ml import MLClient
from azure.ai.ml.entities import ManagedOnlineEndpoint
from azure.identity import DefaultAzureCredential

mlclient = MLClient(

    credential=DefaultAzureCredential(),
    subscriptionid="your-subscription-id",
    resourcegroupname="my-resource-group",
    workspacename="my-ml-workspace"

)

Create endpoint
endpoint = ManagedOnlineEndpoint(
    name="my-online-endpoint",
    description="Online endpoint for real-time inference",
    authmode="key",  # or "amltoken"

    tags={"environment": "production"}
)

mlclient.onlineendpoints.begincreateorupdate(endpoint).result()
print(f"Endpoint created: {endpoint.name}")

2. Create Deployment

from azure.ai.ml.entities import (
    ManagedOnlineDeployment,
    Model,
    Environment,
    CodeConfiguration
)

Create deployment
bluedeployment = ManagedOnlineDeployment(

    name="blue",
    endpointname="my-online-endpoint",
    model=Model(path="./model"),
    codeconfiguration=CodeConfiguration(

        code="./scoring",
        scoringscript="score.py"
    ),
    environment=Environment(
        condafile="./environment.yml",

        image="mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04:latest"
    ),
    instancetype="StandardDS3v2",
    instancecount=1

)

mlclient.onlinedeployments.begincreateorupdate(bluedeployment).result()

print("Deployment created")

# scoring/score.py
import json
import joblib
import numpy as np
import os
import logging

def init():
    """Initialize model on startup."""
    global model
    modelpath = os.path.join(os.getenv("AZUREMLMODELDIR"), "model.joblib")
    model = joblib.load(modelpath)

    logging.info("Model loaded successfully")

def run(rawdata):
    """Run inference on incoming data."""
    try:
        data = json.loads(rawdata)

        features = np.array(data["features"])

        # Run prediction
        predictions = model.predict(features)
        probabilities = model.predictproba(features)

        return {
            "predictions": predictions.tolist(),
            "probabilities": probabilities.tolist()
        }

    except Exception as e:
        logging.error(f"Error: {str(e)}")
        return {"error": str(e)}

4. Set Traffic

# Route all traffic to blue deployment
endpoint.traffic = {"blue": 100}
mlclient.onlineendpoints.begincreateorupdate(endpoint).result()


Get endpoint details
endpoint = mlclient.onlineendpoints.get("my-online-endpoint")

print(f"Scoring URI: {endpoint.scoringuri}")
print(f"Traffic: {endpoint.traffic}")

5. Test Endpoint

import json

Test data
testdata = {

    "features": [[5.1, 3.5, 1.4, 0.2], [6.2, 3.4, 5.4, 2.3]]
}

Invoke endpoint
response = mlclient.onlineendpoints.invoke(

    endpointname="my-online-endpoint",
    requestfile=json.dumps(testdata)
)