Skip to content

Update ML.NET Azure Functions How-To Guide #32973

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 5 commits into from
Closed

Update ML.NET Azure Functions How-To Guide #32973

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7cf70f6
Initial updates
luisquintanilla Dec 9, 2022
61c0020
Fix md lint errors
luisquintanilla Dec 9, 2022
cf59fa1
Update code snippets
luisquintanilla Dec 13, 2022
87a83db
Merge branch 'dotnet:main' into mlnet-az-fn-update
luisquintanilla Dec 13, 2022
60aa9e6
Update date
luisquintanilla Dec 13, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
57 changes: 22 additions & 35 deletions ...machine-learning/how-to-guides/serve-model-serverless-azure-functions-ml-net.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
title: Deploy a model to Azure Functions
description: Serve ML.NET sentiment analysis machine learning model for prediction over the internet using Azure Functions
ms.date: 09/07/2021
ms.date: 12/14/2022
author: luisquintanilla
ms.author: luquinta
ms.custom: mvc, how-to
Expand All @@ -13,58 +13,45 @@ ms.topic: how-to

Learn how to deploy a pre-trained ML.NET machine learning model for predictions over HTTP through an Azure Functions serverless environment.

> [!NOTE]
> This sample runs a preview version of the `PredictionEnginePool` service.

## Prerequisites

- [Visual Studio 2019](https://visualstudio.microsoft.com/downloads/?utm_medium=microsoft&utm_source=learn.microsoft.com&utm_campaign=inline+link&utm_content=download+vs2019) or later or Visual Studio 2017 version 15.6 or later with the ".NET Core cross-platform development" and "Azure development" workloads installed.
- [Visual Studio 2022](https://visualstudio.microsoft.com/downloads/?utm_medium=microsoft&utm_source=learn.microsoft.com&utm_campaign=inline+link&utm_content=download+vs2019) with the **.NET desktop development** and **Azure development** workloads installed. The .NET 6 SDK is automatically installed when you select this workload.
- [Azure Functions Tools](/azure/azure-functions/functions-develop-vs#check-your-tools-version)
- PowerShell
- Pre-trained model. Use the [ML.NET Sentiment Analysis tutorial](../tutorials/sentiment-analysis.md) to build your own model or download this [pre-trained sentiment analysis machine learning model](https://github.com/dotnet/samples/blob/main/machine-learning/models/sentimentanalysis/sentiment_model.zip)
- Pre-trained model. Download this [pre-trained sentiment analysis machine learning model](https://github.com/dotnet/samples/blob/main/machine-learning/models/sentimentanalysis/sentiment_model.zip) or use the [ML.NET Sentiment Analysis tutorial](../tutorials/sentiment-analysis.md) to build your own model.

## Azure Functions sample overview

This sample is a **C# HTTP Trigger Azure Functions application** that uses a pretrained binary classification model to categorize the sentiment of text as positive or negative. Azure Functions provides an easy way to run small pieces of code at scale on a managed serverless environment in the cloud. The code for this sample can be found on the [dotnet/machinelearning-samples](https://github.com/dotnet/machinelearning-samples/tree/main/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction) repository on GitHub.

## Create Azure Functions project

1. Open Visual Studio 2017. Select **File** > **New** > **Project** from the menu bar. In the **New Project** dialog, select the **Visual C#** node followed by the **Cloud** node. Then select the **Azure Functions** project template. In the **Name** text box, type "SentimentAnalysisFunctionsApp" and then select the **OK** button.
1. In the **New Project** dialog, open the dropdown above the project options and select **Azure Functions v2 (.NET Core)**. Then, select the **Http trigger** project and then select the **OK** button.
1. Create a directory named *MLModels* in your project to save your model:

In **Solution Explorer**, right-click on your project and select **Add** > **New Folder**. Type "MLModels" and hit Enter.

1. Install the **Microsoft.ML NuGet Package** version **1.3.1**:
1. In Visual Studio 2022 open the **Create a new project** dialog.
1. In the "Create a new project" dialog, select the **Azure Functions** project template.
1. In the **Name** text box, type "SentimentAnalysisFunctionsApp" and select the **Next** button.
1. In the "Additional information dialog", leave all the defaults as is and select the **Create** button.
1. Install the **Microsoft.ML NuGet Package**

In Solution Explorer, right-click on your project and select **Manage NuGet Packages**. Choose "nuget.org" as the Package source, select the Browse tab, search for **Microsoft.ML**, select that package in the list, and select the **Install** button. Select the **OK** button on the **Preview Changes** dialog and then select the **I Accept** button on the **License Acceptance** dialog if you agree with the license terms for the packages listed.

1. Install the **Microsoft.Azure.Functions.Extensions NuGet Package**:

In Solution Explorer, right-click on your project and select **Manage NuGet Packages**. Choose "nuget.org" as the Package source, select the Browse tab, search for **Microsoft.Azure.Functions.Extensions**, select that package in the list, and select the **Install** button. Select the **OK** button on the **Preview Changes** dialog and then select the **I Accept** button on the **License Acceptance** dialog if you agree with the license terms for the packages listed.

1. Install the **Microsoft.Extensions.ML NuGet Package** version **0.15.1**:

In Solution Explorer, right-click on your project and select **Manage NuGet Packages**. Choose "nuget.org" as the Package source, select the Browse tab, search for **Microsoft.Extensions.ML**, select that package in the list, and select the **Install** button. Select the **OK** button on the **Preview Changes** dialog and then select the **I Accept** button on the **License Acceptance** dialog if you agree with the license terms for the packages listed.

1. Install the **Microsoft.NET.Sdk.Functions NuGet Package** version **1.0.31**:

In Solution Explorer, right-click on your project and select **Manage NuGet Packages**. Choose "nuget.org" as the Package source, select the Installed tab, search for **Microsoft.NET.Sdk.Functions**, select that package in the list, select **1.0.31** from the Version dropdown, and select the **Update** button. Select the **OK** button on the **Preview Changes** dialog and then select the **I Accept** button on the **License Acceptance** dialog if you agree with the license terms for the packages listed.
Follow the same steps to install the **Microsoft.Extensions.ML**, **Microsoft.Extensions.DependencyInjection**, and **Microsoft.Azure.Functions.Extensions** NuGet packages.

## Add pre-trained model to project

1. Create a directory named *MLModels* in your project to save your pre-build model:
In Solution Explorer, right-click on your project and select **Add > New Folder**. Type "MLModels" and hit Enter.
1. Copy your pre-built model to the *MLModels* folder.
1. In Solution Explorer, right-click your pre-built model file and select **Properties**. Under **Advanced**, change the value of **Copy to Output Directory** to **Copy if newer**.

## Create Azure Function to analyze sentiment

Create a class to predict sentiment. Add a new class to your project:

1. In **Solution Explorer**, right-click the project, and then select **Add** > **New Item**.
1. In **Solution Explorer**, right-click the project, and then select **Add** > **New Azure Function...**.

1. In the **Add New Item** dialog box, select **Azure Function** and change the **Name** field to *AnalyzeSentiment.cs*. Then, select the **Add** button.

1. In the **New Azure Function** dialog box, select **Http Trigger**. Then, select the **OK** button.
1. In the **New Azure Function** dialog box, select **Http Trigger** and choose **Anonymous** from the Authorization level dropdown. Then, select the **OK** button.

The *AnalyzeSentiment.cs* file opens in the code editor. Add the following `using` statement to the top of *AnalyzeSentiment.cs*:

Expand All @@ -85,7 +72,7 @@ You need to create some classes for your input data and predictions. Add a new c

1. Create a directory named *DataModels* in your project to save your data models:
In Solution Explorer, right-click on your project and select **Add > New Folder**. Type "DataModels" and hit Enter.
2. In Solution Explorer, right-click the *DataModels* directory, and then select **Add > New Item**.
2. In Solution Explorer, right-click the *DataModels* directory, and then select **Add > Class**.
3. In the **Add New Item** dialog box, select **Class** and change the **Name** field to *SentimentData.cs*. Then, select the **Add** button.

The *SentimentData.cs* file opens in the code editor. Add the following using statement to the top of *SentimentData.cs*:
Expand All @@ -96,7 +83,7 @@ You need to create some classes for your input data and predictions. Add a new c

[!code-csharp [SentimentData](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/DataModels/SentimentData.cs#L5-L13)]

4. In Solution Explorer, right-click the *DataModels* directory, and then select **Add > New Item**.
4. In Solution Explorer, right-click the *DataModels* directory, and then select **Add > Class**.
5. In the **Add New Item** dialog box, select **Class** and change the **Name** field to *SentimentPrediction.cs*. Then, select the **Add** button. The *SentimentPrediction.cs* file opens in the code editor. Add the following using statement to the top of *SentimentPrediction.cs*:

[!code-csharp [SentimentPredictionUsings](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/DataModels/SentimentPrediction.cs#L1)]
Expand All @@ -113,11 +100,11 @@ To make a single prediction, you have to create a [`PredictionEngine`](xref:Micr

The following link provides more information if you want to learn more about [dependency injection](https://en.wikipedia.org/wiki/Dependency_injection).

1. In **Solution Explorer**, right-click the project, and then select **Add** > **New Item**.
1. In **Solution Explorer**, right-click the project, and then select **Add** > **Class**.
1. In the **Add New Item** dialog box, select **Class** and change the **Name** field to *Startup.cs*. Then, select the **Add** button.
1. Add the following using statements to the top of *Startup.cs*:

[!code-csharp [StartupUsings](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/Startup.cs#L1-L6)]
[!code-csharp [StartupUsings](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/Startup.cs#L1-L7)]

1. Remove the existing code below the using statements and add the following code:

Expand All @@ -134,15 +121,15 @@ The following link provides more information if you want to learn more about [de

1. Define variables to store the environment the app is running in and the file path where the model is located inside the `Startup` class

[!code-csharp [DefineStartupVars](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/Startup.cs#L13-L14)]
[!code-csharp [DefineStartupVars](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/Startup.cs#L14-L15)]

1. Below that, create a constructor to set the values of the `_environment` and `_modelPath` variables. When the application is running locally, the default environment is *Development*.

[!code-csharp [StartupCtor](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/Startup.cs#L16-L29)]
[!code-csharp [StartupCtor](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/Startup.cs#L17-L30)]

1. Then, add a new method called `Configure` to register the `PredictionEnginePool` service below the constructor.

[!code-csharp [ConfigureServices](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/Startup.cs#L31-L35)]
[!code-csharp [ConfigureServices](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/Startup.cs#L32-L36)]

At a high level, this code initializes the objects and services automatically for later use when requested by the application instead of having to manually do it.

Expand All @@ -167,15 +154,15 @@ The model is identified by the `modelName` parameter so that more than one model

Insert the following code inside the *AnalyzeSentiment* class:

[!code-csharp [AnalyzeCtor](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/AnalyzeSentiment.cs#L18-L24)]
[!code-csharp [AnalyzeCtor](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/AnalyzeSentiment.cs#L20-L23)]

This code assigns the `PredictionEnginePool` by passing it to the function's constructor which you get via dependency injection.

## Use the model to make predictions

Replace the existing implementation of *Run* method in *AnalyzeSentiment* class with the following code:

[!code-csharp [AnalyzeRunMethod](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/AnalyzeSentiment.cs#L26-L45)]
[!code-csharp [AnalyzeRunMethod](~/machinelearning-samples/samples/csharp/end-to-end-apps/ScalableMLModelOnAzureFunction/SentimentAnalysisFunctionsApp/AnalyzeSentiment.cs#L26-L44)]

When the `Run` method executes, the incoming data from the HTTP request is deserialized and used as input for the `PredictionEnginePool`. The `Predict` method is then called to make predictions using the `SentimentAnalysisModel` registered in the `Startup` class and returns the results back to the user if successful.

Expand Down