azure-ai-services.pdf

Tell us about your PDF experience. Azure AI services documentation Build cutting-edge, market-ready, responsible applications for your organization with AI. OVERVIEW OVER...

Tell us about your PDF experience. Azure AI services documentation Build cutting-edge, market-ready, responsible applications for your organization with AI. OVERVIEW OVERVIEW What are Azure AI services? What is Azure AI Studio? QUICKSTART CONCEPT Chat with Azure OpenAI models Responsible use of AI using your own data Azure OpenAI Azure AI Search Perform a wide variety of natural language tasks. Bring AI-powered cloud search to your mobile and web applications. Content Safety Speech An AI service that detects unwanted contents Speech to text, text to speech, translation, and speaker recognition Document Intelligence Vision Turn documents into intelligent data-driven Analyze content in images and videos. solutions.  Custom Vision Face Customize image recognition for your business. Detect and identify people and emotions in images. Translator Language Use AI-powered translation technology to translate Build apps with industry-leading natural language more than 100 in-use, at-risk, and endangered understanding capabilities. languages and dialects. Video Indexer Immersive Reader Extract actionable insights from your videos. Help users read and comprehend text. Further resources Demo & customization studios Explore more AI resources Azure AI Studio Azure AI Studio Azure OpenAI Studio Azure Machine Learning Content Safety Semantic Kernel Speech AI Builder Document Intelligence Windows AI Vision GitHub Copilot Custom Vision Custom Translator Language Training & certification Deprecated Azure AI services AI learning and community hub Content Moderator Identify principles and practices for responsible AI Language Understanding (LUIS) AI Learning paths and modules QnA Maker AI Engineer career path Metrics Advisor Anomaly Detector Personalizer What are Azure AI services? Article 08/28/2024 Azure AI services help developers and organizations rapidly create intelligent, cutting- edge, market-ready, and responsible applications with out-of-the-box and prebuilt and customizable APIs and models. Example applications include natural language processing for conversations, search, monitoring, translation, speech, vision, and decision-making.  Tip Try Azure AI services including Azure OpenAI, Content Safety, Speech, Vision, and more in Azure AI Studio. For more information, see What is Azure AI Studio?. Most Azure AI services are available through REST APIs and client library SDKs in popular development languages. For more information, see each service's documentation. Available Azure AI services When building AI applications, use the following Azure AI services: ﾉ Expand table Service Description Azure AI Search Bring AI-powered cloud search to your mobile and web apps. Azure OpenAI Perform a wide variety of natural language tasks. Bot Service Create bots and connect them across channels. Content Safety An AI service that detects unwanted contents. Custom Vision Customize image recognition for your business. Document Turn documents into intelligent data-driven solutions. Intelligence Face Detect and identify people and emotions in images. Immersive Help users read and comprehend text. Reader  Service Description Language Build apps with industry-leading natural language understanding capabilities. Speech Speech to text, text to speech, translation, and speaker recognition. Translator Use AI-powered translation technology to translate more than 100 in-use, at-risk, and endangered languages and dialects. Video Indexer Extract actionable insights from your videos. Vision Analyze content in images and videos. The following Azure AI services are scheduled for retirement. These services are still available for existing applications but don't use them for new AI applications: ﾉ Expand table Service Description Anomaly Detector (retired) Identify potential problems early on. Content Moderator (retired) Detect potentially offensive or unwanted content. Language understanding Understand natural language in your apps. (retired) Metrics Advisor (retired) An AI service that detects unwanted contents. Personalizer (retired) Create rich, personalized experiences for each user. QnA maker (retired) Distill information into easy-to-navigate questions and answers. Pricing tiers and billing Pricing tiers (and the amount you get billed) are based on the number of transactions you send using your authentication information. Each pricing tier specifies the: Maximum number of allowed transactions per second (TPS). Service features enabled within the pricing tier. Cost for a predefined number of transactions. Going above this number causes an extra charge as specified in the pricing details for your service. ７ Note  Many of the Azure AI services have a free tier you can use to try the service. To use the free tier, use F0 as the SKU for your resource. Development options The tools that you can use to customize and configure models are different from tools that you use to call the Azure AI services. Out of the box, most Azure AI services allow you to send data and receive insights without any customization. For example: You can send an image to the Azure AI Vision service to detect words and phrases or count the number of people in the frame You can send an audio file to the Speech service and get transcriptions and translate the speech to text at the same time Azure offers a wide range of tools that are designed for different types of users, many of which can be used with Azure AI services. Designer-driven tools are the easiest to use, and are quick to set up and automate, but might have limitations when it comes to customization. Our REST APIs and client libraries provide users with more control and flexibility, but require more effort, time, and expertise to build a solution. If you use REST APIs and client libraries, there's an expectation that you're comfortable working with modern programming languages like C#, Java, Python, JavaScript, or another popular programming language. Let's take a look at the different ways that you can work with the Azure AI services. Client libraries and REST APIs Azure AI services client libraries and REST APIs provide direct access to your service. These tools provide programmatic access to the Azure AI services, their baseline models, and in many cases allow you to programmatically customize your models and solutions. Target user(s): Developers and data scientists Benefits: Provides the greatest flexibility to call the services from any language and environment UI: N/A - Code only Subscription(s): Azure account + Azure AI services resources If you want to learn more about available client libraries and REST APIs, use our Azure AI services overview to pick a service and get started with one of our quickstarts. Continuous integration and deployment You can use Azure DevOps and GitHub Actions to manage your deployments. In the following section, we have two examples of CI/CD integrations to train and deploy custom models for Speech and the Language Understanding (LUIS) service. Target user(s): Developers, data scientists, and data engineers Benefits: Allows you to continuously adjust, update, and deploy applications and models programmatically. There's significant benefit when regularly using your data to improve and update models for Speech, Vision, Language, and Decision UI tools: N/A - Code only Subscription(s): Azure account + Azure AI services resource + GitHub account Continuous integration and delivery with DevOps and GitHub Actions Language Understanding and the Speech service offer continuous integration and continuous deployment solutions that are powered by Azure DevOps and GitHub Actions. These tools are used for automated training, testing, and release management of custom models. CI/CD for Custom Speech CI/CD for LUIS On-premises containers Many of the Azure AI services can be deployed in containers for on-premises access and use. Using these containers gives you the flexibility to bring Azure AI services closer to your data for compliance, security, or other operational reasons. For a complete list of Azure AI containers, see On-premises containers for Azure AI services. Training models Some services allow you to bring your own data, then train a model. Trained custom models allow you to extend the model using the service's data and algorithm with your own data. The output matches your needs. When you bring your own data, you might need to tag the data in a way specific to the service. For example, if you're training a model to identify flowers, you can provide a catalog of flower images along with the location of the flower in each image to train the model. Azure AI services in the ecosystem With Azure and Azure AI services, you have access to a broad ecosystem, such as: Automation and integration tools like Logic Apps and Power Automate. Deployment options such as Azure Functions and the App Service. Azure AI services Docker containers for secure access. Tools like Apache Spark, Azure Databricks, Azure Synapse Analytics, and Azure Kubernetes Service for big data scenarios. To learn more, see Azure AI services ecosystem. Regional availability The APIs in Azure AI services are hosted on a growing network of Microsoft-managed data centers. You can find the regional availability for each API in Azure region list. Looking for a region we don't support yet? Let us know by filing a feature request on our UserVoice forum. Language support Azure AI services support a wide range of cultural languages at the service level. You can find the language availability for each API in the supported languages list. Security Azure AI services provide a layered security model, including authentication with Microsoft Entra credentials, a valid resource key, and Azure Virtual Networks. Certifications and compliance Azure AI services awarded certifications include Cloud Security Alliance STAR Certification, FedRAMP Moderate, and HIPAA BAA. To understand privacy and data management, go to the Trust Center. Help and support Azure AI services provide several support options to help you move forward with creating intelligent applications. Azure AI services also have a strong community of developers that can help answer your specific questions. For a full list of support options available to you, see Azure AI services support and help options. Next steps Learn how to get started with Azure Try Azure AI services and more in Azure AI Studio Plan and manage costs for Azure AI services Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Natural language support for Azure AI services Article 08/28/2024 Azure AI services enable you to build applications that see, hear, articulate, and understand users. Our language support capabilities enable users to communicate with your applications in natural ways and empower global outreach. Use the links in the tables to view language support and availability by service. Language supported services The following table provides links to language support reference articles by supported service. ﾉ Expand table Azure AI Language support Description Detect potentially offensive or unwanted content. Content Moderator (retired) Turn documents into intelligent data-driven solutions. Document Intelligence Help users read and comprehend text. Immersive Reader Build apps with industry-leading natural language Language service understanding capabilities. Understand natural language in your apps. Language Understanding (LUIS) (retired) Distill information into easy-to-navigate questions and answers. QnA Maker (retired) Configure speech-to-text, text-to-speech, translation, and Speech Service speaker recognition applications. Translate more than 100 in-use, at-risk, and endangered Translator languages and dialects. Extract actionable insights from your videos.  Azure AI Language support Description Video Indexer Analyze content in images and videos. Vision Language independent services These Azure AI services are language agnostic and don't have limitations based on human language. ﾉ Expand table Azure AI service Description Identify potential problems early on. Anomaly Detector Customize image recognition for your business. Custom Vision Detect and identify people and emotions in images. Face Create rich, personalized experiences for users. Personalizer See also What are Azure AI services? How to create an Azure AI services resource Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Quickstart: Create an Azure AI services resource Article 08/28/2024 Learn how to create and manage an Azure AI services resource. An Azure AI services resource allows you to access multiple Azure AI services with a single set of credentials. You can access Azure AI services through two different resource kinds: Azure AI services multi-service resource: Access multiple Azure AI services with a single set of credentials. Consolidates billing from the services you use. Single-service resource such as Face and Vision: Access a single Azure AI service with a unique set of credentials for each service created. Most Azure AI services offer a free tier to try it out. Azure AI services are Azure resources that you create under your Azure subscription. After you create a resource, you can use the keys and endpoint generated to authenticate your applications. Supported services with a multi-service resource The multi-service resource enables access to the following Azure AI services with a single set of credentials. Some services are available via the multi-service resource and single-service resource.  Tip We recommend whenever possible to use the Azure AI services resource (where the API kind is AIServices ) to access multiple Azure AI services with a single set of credentials. For services not available via the multi-service resource (such as Face and Custom Vision), you can create a single-service resource. ﾉ Expand table  Service Description Kind (via API) Azure Perform a wide variety of natural language AIServices OpenAI tasks. OpenAI Content An AI service that detects unwanted contents. AIServices Safety ContentSafety Custom Customize image recognition for your CustomVision.Prediction Vision business. (Prediction only) CustomVision.Training (Training only) Document Turn documents into intelligent data-driven AIServices Intelligence solutions. FormRecognizer Face Detect and identify people and emotions in Face images. Language Build apps with industry-leading natural AIServices language understanding capabilities. TextAnalytics Speech Speech to text, text to speech, translation, and AIServices speaker recognition. Speech Translator Use AI-powered translation technology to AIServices translate more than 100 in-use, at-risk, and TextTranslation endangered languages and dialects. Vision Analyze content in images and videos. AIServices (Training and Prediction) ComputerVision Prerequisites A valid Azure subscription - Create one for free. Create a new Azure AI services resource The Azure AI services multi-service resource is listed under Azure AI services > Azure AI services in the portal. Look for the logo as shown here:   ） Important Azure provides more than one resource kinds named Azure AI services. Be sure to select the one that is listed under Azure AI services > Azure AI services with the logo as shown previously. To create an Azure AI services resource follow these instructions: 1. Select this link to create an Azure AI services resource: https://portal.azure.com/#create/Microsoft.CognitiveServicesAIServices 2. On the Create page, provide the following information: ﾉ Expand table Project Description details Subscription Select one of your available Azure subscriptions. Resource The Azure resource group that will contain your Azure AI services resource. group You can create a new group or add it to a pre-existing group. Region The location of your Azure AI service instance. Different locations may introduce latency, but have no impact on the runtime availability of your resource. Name A descriptive name for your Azure AI services resource. For example, MyAIServicesResource. Pricing tier The cost of your Azure AI services account depends on the options you choose and your usage. For more information, see the API pricing  Project Description details details. 3. Configure other settings for your resource as needed, read and accept the conditions (as applicable), and then select Review + create.  Tip If your subscription doesn't allow you to create an Azure AI services resource, you may need to enable the privilege of that Azure resource provider using the Azure portal, PowerShell command or an Azure CLI command. If you are not the subscription owner, ask someone with the role of Owner or Admin to complete the registration for you or ask for the /register/action privileges to be granted to your account. Clean up resources If you want to clean up and remove an Azure AI services subscription, you can delete the resource or resource group. Deleting the resource group also deletes any other resources contained in the group. 1. In the Azure portal, expand the menu on the left side to open the menu of services, and choose Resource Groups to display the list of your resource groups. 2. Locate the resource group containing the resource to be deleted. 3. If you want to delete the entire resource group, select the resource group name. On the next page, Select Delete resource group, and confirm. 4. If you want to delete only the Azure AI services resource, select the resource group to see all the resources within it. On the next page, select the resource that you want to delete, select the ellipsis menu for that row, and select Delete. Pricing Pricing tiers (and the amount you're billed) are based on the number of transactions that you send by using your authentication information. Each pricing tier specifies the: Maximum number of allowed transactions per second (TPS). Service features enabled within the pricing tier. Cost for a predefined number of transactions. Going above this number will cause an extra charge, as specified in the pricing details for your service. Related content Go to the Azure AI services hub. Try AI services in the Azure AI Studio. Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Create an Azure AI services resource using Bicep Article 08/28/2024 Follow this quickstart to create Azure AI services resource using Bicep. Azure AI services help developers and organizations rapidly create intelligent, cutting- edge, market-ready, and responsible applications with out-of-the-box and prebuilt and customizable APIs and models. Example applications include natural language processing for conversations, search, monitoring, translation, speech, vision, and decision-making.  Tip Try Azure AI services including Azure OpenAI, Content Safety, Speech, Vision, and more in Azure AI Studio. For more information, see What is Azure AI Studio?. Most Azure AI services are available through REST APIs and client library SDKs in popular development languages. For more information, see each service's documentation. Bicep is a domain-specific language (DSL) that uses declarative syntax to deploy Azure resources. It provides concise syntax, reliable type safety, and support for code reuse. Bicep offers the best authoring experience for your infrastructure-as-code solutions in Azure. Things to consider Using Bicep to create an Azure AI services resource lets you create a multi-service resource. This enables you to: Access multiple Azure AI services with a single key and endpoint. Consolidate billing from the services you use. Prerequisites If you don't have an Azure subscription, create one for free. Review the Bicep file The Bicep file used in this quickstart is from Azure Quickstart Templates. Bicep @description('That name is the name of our application. It has to be unique.Type a name followed by your resource group name. (- )') param aiServicesName string = 'aiServices-${uniqueString(resourceGroup().id)}' @description('Location for all resources.') param location string = resourceGroup().location @allowed([ 'S0' ]) param sku string = 'S0' resource account 'Microsoft.CognitiveServices/accounts@2023-05-01' = { name: aiServicesName location: location identity: { type: 'SystemAssigned' } sku: { name: sku } kind: 'AIServices' properties: { publicNetworkAccess: 'Disabled' networkAcls: { defaultAction: 'Deny' } disableLocalAuth: true } } One Azure resource is defined in the Bicep file. The kind field in the Bicep file defines the type of resource. As needed, change the sku parameter value to the pricing instance you want. The sku depends on the resource kind that you use. For example, use TextAnalytics for the Azure AI Language service. The TextAnalytics kind uses S instead of S0 for the sku value. Deploy the Bicep file  1. Save the Bicep file as main.bicep to your local computer. 2. Deploy the Bicep file using either Azure CLI or Azure PowerShell. CLI Azure CLI az group create --name exampleRG --location eastus az deployment group create --resource-group exampleRG --template- file main.bicep When the deployment finishes, you should see a message indicating the deployment succeeded. Review deployed resources Use the Azure portal, Azure CLI, or Azure PowerShell to list the deployed resources in the resource group. CLI Azure CLI az resource list --resource-group exampleRG Clean up resources When no longer needed, use the Azure portal, Azure CLI, or Azure PowerShell to delete the resource group and its resources. CLI Azure CLI az group delete --name exampleRG Related content  Authenticate requests to Azure AI services. What are Azure AI services? Natural language support Use Azure AI services as containers. Plan and manage costs for Azure AI services. Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Quickstart: Create an Azure AI services resource by using an ARM template Article 08/28/2024 This quickstart shows you how to use an Azure Resource Manager template (ARM template) to create a resource in Azure AI services. Azure AI services help developers and organizations rapidly create intelligent, cutting- edge, market-ready, and responsible applications with out-of-the-box and prebuilt and customizable APIs and models. Example applications include natural language processing for conversations, search, monitoring, translation, speech, vision, and decision-making.  Tip Try Azure AI services including Azure OpenAI, Content Safety, Speech, Vision, and more in Azure AI Studio. For more information, see What is Azure AI Studio?. Most Azure AI services are available through REST APIs and client library SDKs in popular development languages. For more information, see each service's documentation. An Azure Resource Manager template is a JavaScript Object Notation (JSON) file that defines the infrastructure and configuration for your project. The template uses declarative syntax. You describe your intended deployment without writing the sequence of programming commands to create the deployment. Prerequisites If you don't have an Azure subscription, create one for free. Review the template The template that you use in this quickstart is from Azure Quickstart Templates. JSON { "$schema": "https://schema.management.azure.com/schemas/2019-04- 01/deploymentTemplate.json#",  "contentVersion": "1.0.0.0", "metadata": { "_generator": { "name": "bicep", "version": "0.29.47.4906", "templateHash": "6912458133303539897" } }, "parameters": { "aiServicesName": { "type": "string", "defaultValue": "[format('aiServices-{0}', uniqueString(resourceGroup().id))]", "metadata": { "description": "That name is the name of our application. It has to be unique.Type a name followed by your resource group name. (- )" } }, "location": { "type": "string", "defaultValue": "[resourceGroup().location]", "metadata": { "description": "Location for all resources." } }, "sku": { "type": "string", "defaultValue": "S0", "allowedValues": [ "S0" ] } }, "resources": [ { "type": "Microsoft.CognitiveServices/accounts", "apiVersion": "2023-05-01", "name": "[parameters('aiServicesName')]", "location": "[parameters('location')]", "identity": { "type": "SystemAssigned" }, "sku": { "name": "[parameters('sku')]" }, "kind": "AIServices", "properties": { "publicNetworkAccess": "Disabled", "networkAcls": { "defaultAction": "Deny" }, "disableLocalAuth": true } }  ] } One Azure resource is defined in the Bicep file. The kind field in the Bicep file defines the type of resource. As needed, change the sku parameter value to the pricing instance you want. The sku depends on the resource kind that you use. For example, use TextAnalytics for the Azure AI Language service. The TextAnalytics kind uses S instead of S0 for the sku value. Deploy the template Azure portal 1. Select the Deploy to Azure button. 2. Enter the following values. ﾉ Expand table Value Description Subscription Select an Azure subscription. Resource Select Create new, enter a unique name for the resource group, and group then select OK. Region Select a region (for example, East US). AI service Replace the value with a unique name for your Azure AI services Name resource. You'll need the name in the next section when you validate the deployment. Location Replace with the region that you selected. Sku Select the pricing tier for your resource.  3. Select Review + Create, and then select Create. When deployment is successful, the Go to resource button is available.  Tip If your subscription doesn't allow you to create an Azure AI services resource, you might need to enable the privilege of that Azure resource provider by using the Azure portal, a PowerShell command or an Azure CLI command. If you're not the subscription owner, ask the subscription owner or someone with an admin role to complete the registration for you. Or ask for the /register/action privileges to be granted to your account. Review deployed resources Azure portal  When your deployment finishes, you can select the Go to resource button to see your new resource. You can also find the resource group by: 1. Selecting Resource groups from the left pane. 2. Selecting the resource group name. Clean up resources If you want to clean up and remove an Azure AI services subscription, you can delete the resource or the resource group. Deleting the resource group also deletes any other resources that the group contains. Azure portal 1. On the left pane, select Resource groups to display the list of your resource groups. 2. Locate the resource group that contains the resource to be deleted. 3. Right-click the resource group, select Delete resource group, and then confirm. Related content For more information on how to securely work with Azure AI services, see Authenticate requests to Azure AI services. For a list of Azure AI services, see What are Azure AI services?. For a list of natural languages that Azure AI services support, see Natural language support in Azure AI services. To understand how to use Azure AI services on-premises, see What are Azure AI containers?. To estimate the cost of using Azure AI services, see Plan and manage costs for Azure AI Studio. Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Quickstart: Create an Azure AI services resource using Terraform Article 08/28/2024 This article shows how to use Terraform to create an Azure AI services multi-service resource using Terraform. Azure AI services help developers and organizations rapidly create intelligent, cutting- edge, market-ready, and responsible applications with out-of-the-box and prebuilt and customizable APIs and models. Example applications include natural language processing for conversations, search, monitoring, translation, speech, vision, and decision-making.  Tip Try Azure AI services including Azure OpenAI, Content Safety, Speech, Vision, and more in Azure AI Studio. For more information, see What is Azure AI Studio?. Most Azure AI services are available through REST APIs and client library SDKs in popular development languages. For more information, see each service's documentation. Terraform enables the definition, preview, and deployment of cloud infrastructure. Using Terraform, you create configuration files using HCL syntax. The HCL syntax allows you to specify the cloud provider - such as Azure - and the elements that make up your cloud infrastructure. After you create your configuration files, you create an execution plan that allows you to preview your infrastructure changes before they're deployed. Once you verify the changes, you apply the execution plan to deploy the infrastructure. In this article, you learn how to: ＂ Create a random pet name for the Azure resource group name using random_pet ＂ Create an Azure resource group using azurerm_resource_group ＂ Create a random string using random_string ＂ Create an Azure AI services multi-service resource using azurerm_cognitive_account Prerequisites Install and configure Terraform Implement the Terraform code ７ Note The sample code for this article is located in the Azure Terraform GitHub repo. You can view the log file containing the test results from current and previous versions of Terraform. See more articles and sample code showing how to use Terraform to manage Azure resources 1. Create a directory in which to test and run the sample Terraform code and make it the current directory. 2. Create a file named main.tf and insert the following code: Terraform resource "random_pet" "rg_name" { prefix = var.resource_group_name_prefix } resource "azurerm_resource_group" "rg" { name = random_pet.rg_name.id location = var.resource_group_location } resource "random_string" "azurerm_cognitive_account_name" { length = 13 lower = true numeric = false special = false upper = false } resource "azurerm_cognitive_account" "cognitive_service" { name = "CognitiveService-${random_string.azurerm_cognitive_account_name.result }" location = azurerm_resource_group.rg.location resource_group_name = azurerm_resource_group.rg.name sku_name = var.sku kind = "CognitiveServices" } 3. Create a file named outputs.tf and insert the following code: Terraform  output "resource_group_name" { value = azurerm_resource_group.rg.name } output "azurerm_cognitive_account_name" { value = azurerm_cognitive_account.cognitive_service.name } 4. Create a file named providers.tf and insert the following code: Terraform terraform { required_version = ">=1.0" required_providers { azurerm = { source = "hashicorp/azurerm" version = "~>3.0" } random = { source = "hashicorp/random" version = "~>3.0" } } } provider "azurerm" { features {} } 5. Create a file named variables.tf and insert the following code: Terraform variable "resource_group_location" { type = string description = "Location for all resources." default = "eastus" } variable "resource_group_name_prefix" { type = string description = "Prefix of the resource group name that's combined with a random ID so name is unique in your Azure subscription." default = "rg" } variable "sku" { type = string description = "The sku name of the Azure Analysis Services server to create. Choose from: B1, B2, D1, S0, S1, S2, S3, S4, S8, S9. Some skus  are region specific. See https://docs.microsoft.com/en- us/azure/analysis-services/analysis-services-overview#availability-by- region" default = "S0" } Initialize Terraform Run terraform init to initialize the Terraform deployment. This command downloads the Azure provider required to manage your Azure resources. Console terraform init -upgrade Key points: The -upgrade parameter upgrades the necessary provider plugins to the newest version that complies with the configuration's version constraints. Create a Terraform execution plan Run terraform plan to create an execution plan. Console terraform plan -out main.tfplan Key points: The terraform plan command creates an execution plan, but doesn't execute it. Instead, it determines what actions are necessary to create the configuration specified in your configuration files. This pattern allows you to verify whether the execution plan matches your expectations before making any changes to actual resources. The optional -out parameter allows you to specify an output file for the plan. Using the -out parameter ensures that the plan you reviewed is exactly what is applied. Apply a Terraform execution plan Run terraform apply to apply the execution plan to your cloud infrastructure. Console terraform apply main.tfplan Key points: The example terraform apply command assumes you previously ran terraform plan -out main.tfplan. If you specified a different filename for the -out parameter, use that same filename in the call to terraform apply. If you didn't use the -out parameter, call terraform apply without any parameters. Verify the results Azure CLI 1. Get the Azure resource name in which the Azure AI services multi-service resource was created. Console resource_group_name=$(terraform output -raw resource_group_name) 2. Get the Azure AI services multi-service resource name. Console azurerm_aiservices_account_name=$(terraform output -raw azurerm_aiservices_account_name) 3. Run az cognitiveservices account show to show the Azure AI services account you created in this article. Azure CLI az cognitiveservices account show --name $azurerm_aiservices_account_name \  --resource-group $resource_group_name Clean up resources When you no longer need the resources created via Terraform, do the following steps: 1. Run terraform plan and specify the destroy flag. Console terraform plan -destroy -out main.destroy.tfplan Key points: The terraform plan command creates an execution plan, but doesn't execute it. Instead, it determines what actions are necessary to create the configuration specified in your configuration files. This pattern allows you to verify whether the execution plan matches your expectations before making any changes to actual resources. The optional -out parameter allows you to specify an output file for the plan. Using the -out parameter ensures that the plan you reviewed is exactly what is applied. 2. Run terraform apply to apply the execution plan. Console terraform apply main.destroy.tfplan Troubleshoot Terraform on Azure Troubleshoot common problems when using Terraform on Azure Related content Learn more about Azure AI services resources ） Note: The author created this article with assistance from AI. Learn more Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Azure AI services and the AI ecosystem Article 08/28/2024 Azure AI services provides capabilities to solve general problems such as analyzing text for emotional sentiment or analyzing images to recognize objects or faces. You don't need special machine learning or data science knowledge to use these services. Azure Machine Learning Azure AI services and Azure Machine Learning both have the end-goal of applying artificial intelligence (AI) to enhance business operations, though how each provides this in the respective offerings is different. Generally, the audiences are different: Azure AI services are for developers without machine-learning experience. Azure Machine Learning is tailored for data scientists. Azure AI services for big data With Azure AI services for big data you can embed continuously improving, intelligent models directly into Apache Spark™ and SQL computations. These tools liberate developers from low-level networking details, so that they can focus on creating smart, distributed applications. Azure AI services for big data support the following platforms and connectors: Azure Databricks, Azure Synapse, Azure Kubernetes Service, and Data Connectors. Target user(s): Data scientists and data engineers Benefits: the Azure AI services for big data let users channel terabytes of data through Azure AI services using Apache Spark™. It's easy to create large-scale intelligent applications with any datastore. UI: N/A - Code only Subscription(s): Azure account + Azure AI services resources To learn more about big data for Azure AI services, see Azure AI services in Azure Synapse Analytics. Azure Functions and Azure Service Web Jobs Azure Functions and Azure App Service Web Jobs both provide code-first integration services designed for developers and are built on Azure App Services. These products provide serverless infrastructure for writing code. Within that code you can make calls to our services using our client libraries and REST APIs. Target user(s): Developers and data scientists Benefits: Serverless compute service that lets you run event-triggered code. UI: Yes Subscription(s): Azure account + Azure AI services resource + Azure Functions subscription Azure Logic Apps Azure Logic Apps share the same workflow designer and connectors as Power Automate but provide more advanced control, including integrations with Visual Studio and DevOps. Power Automate makes it easy to integrate with your Azure AI services resources through service-specific connectors that provide a proxy or wrapper around the APIs. These are the same connectors as those available in Power Automate. Target user(s): Developers, integrators, IT pros, DevOps Benefits: Designer-first (declarative) development model providing advanced options and integration in a low-code solution UI: Yes Subscription(s): Azure account + Azure AI services resource + Logic Apps deployment Power Automate Power Automate is a service in the Power Platform that helps you create automated workflows between apps and services without writing code. We offer several connectors to make it easy to interact with your Azure AI services resource in a Power Automate solution. Power Automate is built on top of Logic Apps. Target user(s): Business users (analysts) and SharePoint administrators Benefits: Automate repetitive manual tasks simply by recording mouse clicks, keystrokes and copy paste steps from your desktop! UI tools: Yes - UI only Subscription(s): Azure account + Azure AI services resource + Power Automate Subscription + Office 365 Subscription AI Builder AI Builder is a Microsoft Power Platform capability you can use to improve business performance by automating processes and predicting outcomes. AI Builder brings the power of AI to your solutions through a point-and-click experience. Many Azure AI services such as the Language service, and Azure AI Vision have been directly integrated here and you don't need to create your own Azure AI services. Target user(s): Business users (analysts) and SharePoint administrators Benefits: A turnkey solution that brings the power of AI through a point-and-click experience. No coding or data science skills required. UI tools: Yes - UI only Subscription(s): AI Builder Next steps Learn how you can build generative AI applications in the Azure AI Studio. Get answers to frequently asked questions in the Azure AI FAQ article Create your Azure AI services resource in the Azure portal or with Azure CLI. Keep up to date with service updates. Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Custom subdomain names for Azure AI services Article 08/28/2024 Starting in July 2019, Azure AI services use custom subdomain names for each resource created through the Azure portal , Azure Cloud Shell , or Azure CLI. Unlike regional endpoints, which were common for all customers in a specific Azure region, custom subdomain names are unique to the resource. Custom subdomain names are required to enable features like Microsoft Entra ID for authentication. How does this impact existing resources? Azure AI services resources created before July 1, 2019 use the regional endpoints for the associated service. These endpoints work with existing and new resources. If you'd like to migrate an existing resource to use custom subdomain names to enable features like Microsoft Entra ID, follow these instructions: 1. Sign in to the Azure portal and locate the Azure AI services resource that you'd like to add a custom subdomain name to. 2. In the Overview blade, locate and select Generate Custom Domain Name. 3. This opens a panel with instructions to create a unique custom subdomain for your resource. ２ Warning After you've created a custom subdomain name it cannot be changed. Do I need to update my existing resources? No. The regional endpoint will continue to work for new and existing Azure AI services and the custom subdomain name is optional. Even if a custom subdomain name is added the regional endpoint will continue to work with the resource. What if an SDK asks me for the region for a resource?  ２ Warning Speech Services use custom subdomains with private endpoints only. In all other cases, use regional endpoints with Speech Services and associated SDKs. Regional endpoints and custom subdomain names are both supported and can be used interchangeably. However, the full endpoint is required. Region information is available in the Overview blade for your resource in the Azure portal. For the full list of regional endpoints, see Is there a list of regional endpoints? Are custom subdomain names regional? Yes. Using a custom subdomain name doesn't change any of the regional aspects of your Azure AI services resource. What are the requirements for a custom subdomain name? A custom subdomain name is unique to your resource. The name can only include alphanumeric characters and the - character; it must be between 2 and 64 characters in length and cannot end with a -. Can I change a custom domain name? No. After a custom subdomain name is created and associated with a resource it cannot be changed. Can I reuse a custom domain name? Each custom subdomain name is unique, so in order to reuse a custom subdomain name that you've assigned to an Azure AI services resource, you'll need to delete the existing resource. After the resource has been deleted, you can reuse the custom subdomain name. Is there a list of regional endpoints? Yes. This is a list of regional endpoints that you can use with Azure AI services resources.  ７ Note The Translator service and Bing Search APIs use global endpoints. ﾉ Expand table Endpoint Region Endpoint type Public Global (Translator & https://api.cognitive.microsoft.com Bing) Australia East https://australiaeast.api.cognitive.microsoft.com Brazil South https://brazilsouth.api.cognitive.microsoft.com Canada Central https://canadacentral.api.cognitive.microsoft.com Central US https://centralus.api.cognitive.microsoft.com East Asia https://eastasia.api.cognitive.microsoft.com East US https://eastus.api.cognitive.microsoft.com East US 2 https://eastus2.api.cognitive.microsoft.com France Central https://francecentral.api.cognitive.microsoft.com India Central https://centralindia.api.cognitive.microsoft.com Japan East https://japaneast.api.cognitive.microsoft.com Korea Central https://koreacentral.api.cognitive.microsoft.com North Central US https://northcentralus.api.cognitive.microsoft.com North Europe https://northeurope.api.cognitive.microsoft.com South Africa North https://southafricanorth.api.cognitive.microsoft.com South Central US https://southcentralus.api.cognitive.microsoft.com Southeast Asia https://southeastasia.api.cognitive.microsoft.com UK South https://uksouth.api.cognitive.microsoft.com West Central US https://westcentralus.api.cognitive.microsoft.com West Europe https://westeurope.api.cognitive.microsoft.com  Endpoint Region Endpoint type West US https://westus.api.cognitive.microsoft.com West US 2 https://westus2.api.cognitive.microsoft.com US Gov US Gov Virginia https://virginia.api.cognitive.microsoft.us China China East 2 https://chinaeast2.api.cognitive.azure.cn China North https://chinanorth.api.cognitive.azure.cn See also What are Azure AI services? Authentication Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Plan and manage costs for Azure AI Studio Article 08/29/2024 ） Important Some of the features described in this article might only be available in preview. This preview is provided without a service-level agreement, and we don't recommend it for production workloads. Certain features might not be supported or might have constrained capabilities. For more information, see Supplemental Terms of Use for Microsoft Azure Previews. This article describes how you plan for and manage costs for Azure AI Studio. First, you use the Azure pricing calculator to help plan for Azure AI Studio costs before you add any resources for the service to estimate costs. Next, as you add Azure resources, review the estimated costs.  Tip Azure AI Studio does not have a specific page in the Azure pricing calculator. Azure AI Studio is composed of several other Azure services, some of which are optional. This article provides information on using the pricing calculator to estimate costs for these services. You use Azure AI services in Azure AI Studio. Costs for Azure AI services are only a portion of the monthly costs in your Azure bill. You're billed for all Azure services and resources used in your Azure subscription, including the third-party services. Prerequisites Cost analysis in Microsoft Cost Management supports most Azure account types, but not all of them. To view the full list of supported account types, see Understand Cost Management data. To view cost data, you need at least read access for an Azure account. For information about assigning access to Microsoft Cost Management data, see Assign access to data. Estimate costs before using Azure AI services Use the Azure pricing calculator to estimate costs before you add Azure AI services. 1. Select a product such as Azure OpenAI in the Azure pricing calculator.  2. Enter the number of units you plan to use. For example, enter the number of tokens for prompts and completions.  3. You can select more than one product to estimate costs for multiple products. For example, select Virtual Machines to add potential costs for compute resources.  As you add new resources to your project, return to this calculator and add the same resource here to update your cost estimates. Costs that typically accrue with Azure AI Studio When you create resources for a hub, resources for other Azure services are also created. They are: ﾉ Expand table Service pricing Description with example use cases page Azure AI services You pay to use services such as Azure OpenAI, Speech, Content Safety, Vision, Document Intelligence, and Language. Costs vary for each service and for some features within each service. For more information about provisioning of Azure AI services, see Azure AI Studio hubs. Azure AI Search An example use case is to store data in a vector search index. Azure Machine Compute instances are needed to run Visual Studio Code (Web or Desktop) Learning and prompt flow via Azure AI Studio. When you create a compute instance, the virtual machine (VM) stays on so it's available for your work. Enable idle shutdown to save on cost when the VM is idle for a specified time period. Or set up a schedule to automatically start and stop the compute instance to save cost when you aren't planning to use it. Azure Virtual Azure Virtual Machines gives you the flexibility of virtualization for a wide Machine range of computing solutions with support for Linux, Windows Server, SQL Server, Oracle, IBM, SAP, and more. Azure Container Provides storage of private Docker container images, enabling fast, scalable Registry Basic retrieval, and network-close deployment of container workloads on Azure. account Azure Blob Can be used to store Azure AI Studio project files. Storage Key Vault A key vault for storing secrets. Azure Private Link Azure Private Link enables you to access Azure PaaS Services (for example, Azure Storage and SQL Database) over a private endpoint in your virtual network. Costs might accrue before resource deletion Before you delete a hub in the Azure portal or with Azure CLI, the following sub resources are common costs that accumulate even when you aren't actively working in the workspace. If you're planning on returning to your hub at a later time, these resources might continue to accrue costs: Azure AI Search (for the data) Virtual machines Load Balancer Azure Virtual Network Bandwidth Each VM is billed per hour it's running. Cost depends on VM specifications. VMs that are running but not actively working on a dataset are still charged via the load balancer. For each compute instance, one load balancer is billed per day. Every 50 nodes of a compute cluster have one standard load balancer billed. Each load balancer is billed around $0.33/day. To avoid load balancer costs on stopped compute instances and compute clusters, delete the compute resource. Compute instances also incur P10 disk costs even in stopped state. This cost is because any user content saved to disk is persisted across the stopped state similar to Azure VMs. We're working on making the OS disk size/ type configurable to better control costs. For Azure Virtual Networks, one virtual network is billed per subscription and per region. Virtual networks can't span regions or subscriptions. Setting up private endpoints in virtual network setups might also incur charges. If your virtual network uses an Azure Firewall, the firewall might also incur charges. Bandwidth usage is charged; the more data transferred, the more you're charged.  Tip Using a managed virtual network is free. However some features of the managed network rely on Azure Private Link (for private endpoints) and Azure Firewall (for FQDN rules) and will incur charges. For more information, see Managed virtual network isolation. Costs might accrue after resource deletion After you delete a hub in the Azure portal or with Azure CLI, the following resources continue to exist. They continue to accrue costs until you delete them.  Azure Container Registry Azure Blob Storage Key Vault Application Insights (if you enabled it for your hub) Monitor costs As you use Azure AI Studio with hubs, you incur costs. Azure resource usage unit costs vary by time intervals (seconds, minutes, hours, and days) or by unit usage (bytes, megabytes, and so on). You can see the incurred costs in cost analysis. When you use cost analysis, you view hub costs in graphs and tables for different time intervals. Some examples are by day, current and prior month, and year. You also view costs against budgets and forecasted costs. Switching to longer views over time can help you identify spending trends. And you see where overspending might occur. If you create budgets, you can also easily see where they're exceeded. Monitor Azure AI Studio project costs You can get to cost analysis from the Azure portal. You can also get to cost analysis from the Azure AI Studio. ） Important Your AI Studio project costs are only a subset of your overall application or solution costs. You need to monitor costs for all Azure resources used in your application or solution. For more information, see Azure AI Studio hubs. For the examples in this section, assume that all Azure AI Studio resources are in the same resource group. But you can have resources in different resource groups. For example, your Azure AI Search resource might be in a different resource group than your project. Here's an example of how to monitor costs for a project. The costs are used as an example only. Your costs vary depending on the services that you use and the amount of usage. 1. Sign in to Azure AI Studio. 2. Select your project and select Settings from the left navigation section. Select View cost for resources from the Total cost section. The Azure portal opens to the  resource group for your project.  3. Expand the Resource column to see the costs for each service that's underlying your project. But this view doesn't include costs for all resources that you use in a project.  4. Select Costs by resource > Resources.   5. On the Cost analysis page where you're taken to, make sure the scope is set to your resource group.  In this example: The resource group name is rg-contosoairesource. The total cost for all resources and services in the resource group is $222.97. In this example, $222.97 is the total cost for your application or solution that you're building with Azure AI Studio. Again, this example assumes that all Azure AI Studio resources are in the same resource group. But you can have resources in different resource groups. The project name is contoso-outdoor-proj. The costs that are limited to resources and services in the project total $212.06. 6. Expand contoso-outdoor-proj to see the costs for services underlying the project resource.   7. Expand contoso_ai_resource to see the costs for services underlying the hub resource. You can also apply a filter to focus on other costs in your resource group. You can also view resource group costs directly from the Azure portal. To do so: 1. Sign in to Azure portal. 2. Select Resource groups. 3. Find and select the resource group that contains your Azure AI Studio resources. 4. From the left navigation menu, select Cost analysis.  For more information, see the Azure pricing calculator. Monitor costs for models offered through the Azure Marketplace Models deployed as a service using pay-as-you-go are offered through the Azure Marketplace. The model publishers might apply different costs depending on the offering. Each project in Azure AI Studio has its own subscription with the offering, which allows you to monitor the costs and the consumption happening on that project. Use Microsoft Cost Management to monitor the costs: 1. Sign in to Azure portal. 2. On the left navigation area, select Cost Management + Billing and then, on the same menu, select Cost Management. 3. On the left navigation area, under the section Cost Management, select now Cost Analysis. 4. Select a view such as Resources. The cost associated with each resource is displayed.  5. On the Type column, select the filter icon to filter all the resources of type microsoft.saas/resources. This type corresponds to resources created from offers from the Azure Marketplace. For convenience, you can filter by resource types containing the string SaaS.  6. One resource is displayed for each model offer per project. Naming of those resources is [Model offer name]-[GUID]. 7. Select to expand the resource details to get access to each of the costs meters associated with the resource. Tier represents the offering. Product is the specific product inside the offering. Some model providers might use the same name for both.   Tip Remember that one resource is created per each project, per each plan your project subscribes to. 8. When you expand the details, costs are reported per each of the meters associated with the offering. Each meter might track different sources of costs like inferencing, or fine tuning. The following meters are displayed (when some cost is associated with them): ﾉ Expand table Meter Group Description paygo-inference- Base Costs associated with the tokens used as input for input-tokens model inference of a base model. paygo-inference- Base Costs associated with the tokens generated as output output-tokens model for the inference of base model. paygo-finetuned- Fine- Costs associated with the hosting of an inference model-inference- tuned endpoint for a fine-tuned model. This value isn't the hosting model cost of hosting the model, but the cost of having an endpoint serving it.  Meter Group Description paygo-finetuned- Fine- Costs associated with the tokens used as input for model-inference- tuned inference of a fine tuned model. input-tokens model paygo-finetuned- Fine- Costs associated with the tokens generated as output model-inference- tuned for the inference of a fine tuned model. output-tokens model Create budgets You can create budgets to manage costs and create alerts that automatically notify stakeholders of spending anomalies and overspending risks. Alerts are based on spending compared to budget and cost thresholds. Budgets and alerts are created for Azure subscriptions and resource groups, so they're useful as part of an overall cost monitoring strategy. Budgets can be created with filters for specific resources or services in Azure if you want more granularity present in your monitoring. Filters help ensure that you don't accidentally create new resources that cost you more money. For more about the filter options when you create a budget, see Group and filter options. Export cost data You can also export your cost data to a storage account. Exporting data is helpful when you or others need to do more data analysis for costs. For example, finance teams can analyze the data using Excel or Power BI. You can export your costs on a daily, weekly, or monthly schedule and set a custom date range. Exporting cost data is the recommended way to retrieve cost datasets. Understand the full billing model for Azure AI services Azure AI services run on Azure infrastructure that accrues costs along with Azure AI when you deploy the new resource. It's important to understand that extra infrastructure might accrue cost. You need to manage that cost when you make changes to deployed resources. When you create or use Azure AI services resources, you might get charged based on the services that you use. There are two billing models available for Azure AI services:  Pay-as-you-go: Pay-as-you-go pricing, you're billed according to the Azure AI services offering that you use, based on its billing information. Commitment tiers: With commitment tier pricing, you commit to using several service features for a fixed fee, enabling you to have a predictable total cost based on the needs of your workload. You're billed according to the plan you choose. See Quickstart: purchase commitment tier pricing for information on available services, how to sign up, and considerations when purchasing a plan. ７ Note If you use the resource above the quota provided by the commitment plan, you will be charged for the additional usage as per the overage amount mentioned in the Azure portal when you purchase a commitment plan. You can pay for Azure AI services charges with your Azure Prepayment (previously called monetary commitment) credit. However, you can't use Azure Prepayment credit to pay for charges for third-party products and services including ones from the Azure Marketplace. For more information, see the Azure pricing calculator. Next steps Learn how to optimize your cloud investment with Microsoft Cost Management. Learn more about managing costs with cost analysis. Learn about how to prevent unexpected costs. Take the Cost Management guided learning course. Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Autoscale AI services limits Article 08/28/2024 This article provides guidance for how customers can access higher rate limits on their Azure AI services resources. Overview Each Azure AI services resource has a pre-configured static call rate (transactions per second) which limits the number of concurrent calls that customers can make to the backend service in a given time frame. The autoscale feature will automatically increase/decrease a customer's resource's rate limits based on near-real-time resource usage metrics and backend service capacity metrics. Get started with the autoscale feature This feature is disabled by default for every new resource. Follow these instructions to enable it. Azure portal Go to your resource's page in the Azure portal, and select the Overview tab on the left pane. Under the Essentials section, find the Autoscale line and select the link to view the Autoscale Settings pane and enable the feature.  Frequently asked questions Does enabling the autoscale feature mean my resource will never be throttled again? No, you may still get 429 errors for rate limit excess. If your application triggers a spike, and your resource reports a 429 response, autoscale checks the available capacity projection section to see whether the current capacity can accommodate a rate limit increase and respond within five minutes. If the available capacity is enough for an increase, autoscale gradually increases the rate limit cap of your resource. If you continue to call your resource at a high rate that results in more 429 throttling, your TPS rate will continue to increase over time. If this action continues for one hour or more, you should reach the maximum rate (up to 1000 TPS) currently available at that time for that resource. If the available capacity isn't enough for an increase, the autoscale feature waits five minutes and checks again. What if I need a higher default rate limit? By default, Azure AI services resources have a default rate limit of 10 TPS. If you need a higher default TPS, submit a ticket by following the New Support Request link on your resource's page in the Azure portal. Remember to include a business justification in the request. Will this feature increase my Azure spend? Azure AI services pricing hasn't changed and can be accessed here. We'll only bill for successful calls made to Azure AI services APIs. However, increased call rate limits mean more transactions are completed, and you may receive a higher bill. Be aware of potential errors and their consequences. If a bug in your client application causes it to call the service hundreds of times per second, that would likely lead to a much higher bill, whereas the cost would be much more limited under a fixed rate limit. Errors of this kind are your responsibility. We highly recommend that you perform development and client update tests against a resource with a fixed rate limit prior to using the autoscale feature. Can I disable this feature if I'd rather limit the rate than have unpredictable spending? Yes, you can disable the autoscale feature through Azure portal or CLI and return to your default call rate limit setting. If your resource was previously approved for a higher default TPS, it goes back to that rate. It can take up to five minutes for the changes to go into effect. Which services support the autoscale feature? Autoscale feature is available for the following services: Azure AI Vision Language (only available for sentiment analysis, key phrase extraction, named entity recognition, and text analytics for health) Anomaly Detector Content Moderator Custom Vision (Prediction) Immersive Reader LUIS Metrics Advisor Personalizer QnAMaker Document Intelligence Can I test this feature using a free subscription? No, the autoscale feature isn't available to free tier subscriptions. Next steps Plan and Manage costs for Azure AI services. Optimize your cloud investment with Azure Cost Management. Learn about how to prevent unexpected costs. Take the Cost Management guided learning course. Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Purchase commitment tier pricing Article 08/28/2024 Azure AI offers commitment tier pricing, allowing discounted rates compared to the pay-as-you-go pricing model. With commitment tier pricing, you can commit to using the following Azure AI services features for a fixed fee, enabling you to have a predictable total cost based on the needs of your workload: Speech to text (Standard) Text to speech (Neural) Text Translation (Standard) Language Understanding standard (Text Requests) Azure AI Language Sentiment Analysis Key Phrase Extraction Language Detection Named Entity Recognition (NER) Azure AI Vision - OCR Document Intelligence – Custom/Invoice For more information, see Azure AI services pricing. Create a new resource 1. Sign in to the Azure portal and select Create a new resource for one of the applicable Azure AI services or Azure AI services listed. 2. Enter the applicable information to create your resource. Be sure to select the standard pricing tier. ７ Note If you intend to purchase a commitment tier for disconnected container usage, you will need to request separate access and select the Commitment tier disconnected containers pricing tier. For more information, see disconnected containers.   3. Once your resource is created, you can change your pricing from pay-as-you-go, to a commitment plan. Purchase a commitment plan by updating your Azure resource 1. Sign in to the Azure portal with your Azure subscription. 2. In your Azure resource for one of the applicable features listed, select Commitment tier pricing. 3. Select Change to view the available commitments for hosted API and container usage. Choose a commitment plan for one or more of the following offerings: Web: web-based APIs, where you send data to Azure for processing. Connected container: Docker containers that enable you to deploy Azure AI services on premises, and maintain an internet connection for billing and metering.   4. In the window that appears, select both a Tier and Auto-renewal option. Commitment tier - The commitment tier for the feature. The commitment tier is enabled immediately when you select Purchase and you're charged the commitment amount on a pro-rated basis. Auto-renewal - Choose how you want to renew, change, or cancel the current commitment plan starting with the next billing cycle. If you decide to autorenew, the Auto-renewal date is the date (in your local timezone) when you'll be charged for the next billing cycle. This date coincides with the start of the calendar month. Ｕ Caution Once you select Purchase you will be charged for the tier you select. Once purchased, the commitment plan is non-refundable. Commitment plans are charged monthly, except the first month upon purchase which is pro-rated (cost and quota) based on the number of days remaining in that month. For the subsequent months, the charge is incurred on the first day of the month.   Overage pricing If you use the resource above the quota provided, you're charged for the additional usage as per the overage amount mentioned in the commitment tier. Purchase a different commitment plan The commitment plans have a calendar month commitment period. You can purchase a commitment plan at any time from the default pay-as-you-go pricing model. When you purchase a plan, you're charged a pro-rated price for the remaining month. During the commitment period, you can't change the commitment plan for the current month. However, you can choose a different commitment plan for the next calendar month. The billing for the next month would happen on the first day of the next month. If you need a larger commitment plan than any of the ones offered, contact [email protected]. End a commitment plan If you decide that you don't want to continue purchasing a commitment plan, you can set your resource's autorenewal to Do not auto-renew. Your commitment plan expires on the displayed commitment end date. After this date, you won't be charged for the commitment plan. You're able to continue using the Azure resource to make API calls, charged at pay-as-you-go pricing. You have until midnight (UTC) on the last day of each month to end a commitment plan, and not be charged for the following month. Purchase a commitment tier pricing plan for disconnected containers Commitment plans for disconnected containers have a calendar year commitment period. These are different plans than web and connected container commitment plans. When you purchase a commitment plan, you'll be charged the full price immediately. During the commitment period, you can't change your commitment plan, however you can purchase additional unit(s) at a pro-rated price for the remaining days in the year. You have until midnight (UTC) on the last day of your commitment, to end a commitment plan. You can choose a different commitment plan in the Commitment Tier pricing settings of your resource. Overage pricing for disconnected containers To use a disconnected container beyond the quota initially purchased with your disconnected container commitment plan, you can purchase additional quota by updating your commitment plan at any time. To purchase additional quota, go to your resource in Azure portal and adjust the "unit count" of your disconnected container commitment plan using the slider. This will add additional monthly quota and you will be charged a pro-rated price based on the remaining days left in the current billing cycle. See also Azure AI services pricing. Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Enable diagnostic logging for Azure AI services Article 08/28/2024 This guide provides step-by-step instructions to enable diagnostic logging for an Azure AI service. These logs provide rich, frequent data about the operation of a resource that are used for issue identification and debugging. Before you continue, you must have an Azure account with a subscription to at least one Azure AI service, such as Speech Services. Prerequisites To enable diagnostic logging, you'll need somewhere to store your log data. This tutorial uses Azure Storage and Log Analytics. Azure storage - Retains diagnostic logs for policy audit, static analysis, or backup. The storage account does not have to be in the same subscription as the resource emitting logs as long as the user who configures the setting has appropriate Azure RBAC access to both subscriptions. Log Analytics - A flexible log search and analytics tool that allows for analysis of raw logs generated by an Azure resource. ７ Note Additional configuration options are available. To learn more, see Collect and consume log data from your Azure resources. "Trace" in diagnostic logging is only available for Custom question answering. Enable diagnostic log collection Let's start by enabling diagnostic logging using the Azure portal. ７ Note To enable this feature using PowerShell or the Azure CLI, use the instructions provided in Collect and consume log data from your Azure resources.  1. Navigate to the Azure portal. Then locate and select an Azure AI services resource. For example, your subscription to Speech Services. 2. Next, from the left-hand navigation menu, locate Monitoring and select Diagnostic settings. This screen contains all previously created diagnostic settings for this resource. 3. If there is a previously created resource that you'd like to use, you can select it now. Otherwise, select + Add diagnostic setting. 4. Enter a name for the setting. Then select Archive to a storage account and Send to log Analytics. 5. When prompted to configure, select the storage account and OMS workspace that you'd like to use to store you diagnostic logs. Note: If you don't have a storage account or OMS workspace, follow the prompts to create one. 6. Select Audit, RequestResponse, and AllMetrics. Then set the retention period for your diagnostic log data. If a retention policy is set to zero, events for that log category are stored indefinitely. 7. Select Save. It can take up to two hours before logging data is available to query and analyze. So don't worry if you don't see anything right away. View and export diagnostic data from Azure Storage Azure Storage is a robust object storage solution that is optimized for storing large amounts of unstructured data. In this section, you'll learn to query your storage account for total transactions over a 30-day timeframe and export the data to excel. 1. From the Azure portal, locate the Azure Storage resource that you created in the last section. 2. From the left-hand navigation menu, locate Monitoring and select Metrics. 3. Use the available drop-downs to configure your query. For this example, let's set the time range to Last 30 days and the metric to Transaction. 4. When the query is complete, you'll see a visualization of transaction over the last 30 days. To export this data, use the Export to Excel button located at the top of the page. Learn more about what you can do with diagnostic data in Azure Storage. View logs in Log Analytics Follow these instructions to explore log analytics data for your resource.  1. From the Azure portal, locate and select Log Analytics from the left-hand navigation menu. 2. Locate and select the resource you created when enabling diagnostics. 3. Under General, locate and select Logs. From this page, you can run queries against your logs. Sample queries Here are a few basic Kusto queries you can use to explore your log data. Run this query for all diagnostic logs from Azure AI services for a specified time period: Kusto AzureDiagnostics | where ResourceProvider == "MICROSOFT.COGNITIVESERVICES" Run this query to see the 10 most recent logs: Kusto AzureDiagnostics | where ResourceProvider == "MICROSOFT.COGNITIVESERVICES" | take 10 Run this query to group operations by Resource: Kusto AzureDiagnostics | where ResourceProvider == "MICROSOFT.COGNITIVESERVICES" | summarize count() by Resource Run this query to find the average time it takes to perform an operation: Kusto AzureDiagnostics | where ResourceProvider == "MICROSOFT.COGNITIVESERVICES" | summarize avg(DurationMs) by OperationName Run this query to view the volume of operations over time split by OperationName with counts binned for every 10s.  Kusto AzureDiagnostics | where ResourceProvider == "MICROSOFT.COGNITIVESERVICES" | summarize count() by bin(TimeGenerated, 10s), OperationName | render areachart kind=unstacked Next steps To understand how to enable logging, as well as the metrics and log categories that are supported by the various Azure services, read the Overview of metrics in Microsoft Azure and the Overview of Azure Diagnostic Logs. Read these articles to learn about event hubs: What is Azure Event Hubs? Get started with Event Hubs Read Understand log searches in Azure Monitor logs. Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A Recover or purge deleted Azure AI services resources Article 09/12/2024 This article provides instructions on how to recover or purge an Azure AI services resource that is already deleted. Once you delete a resource, you won't be able to create another one with the same name for 48 hours. To create a resource with the same name, you need to purge the deleted resource. ７ Note The instructions in this article are applicable to both a multi-service resource and a single-service resource. A multi-service resource enables access to multiple Azure AI services using a single key and endpoint. On the other hand, a single-service resource enables access to just that specific Azure AI service for which the resource was created. Charges for provisioned deployments on a deleted resource will continue until the resource is purged. To prevent this, delete a resource's deployment before deleting the resource. Recover a deleted resource The following prerequisites must be met before you can recover a deleted resource: The resource to be recovered must have been deleted within the past 48 hours. The resource to be recovered must not have been purged already. A purged resource can't be recovered. Before you attempt to recover a deleted resource, make sure that the resource group for that account exists. If the resource group was deleted, you must recreate it. Recovering a resource group isn't possible. For more information, see Manage resource groups. If the deleted resource used customer-managed keys with Azure Key Vault and the key vault have also been deleted, then you must restore the key vault before you restore the Azure AI services resource. For more information, see Azure Key Vault recovery management.  If the deleted resource used a customer-managed storage and storage account has also been deleted, you must restore the storage account before you restore the Azure AI services resource. For instructions, see Recover a deleted storage account. To recover a deleted Azure AI services resource, use the following commands. Where applicable, replace: {subscriptionID} with your Azure subscription ID {resourceGroup} with your resource group {resourceName} with your resource name {location} with the location of your resource Azure portal If you need to recover a deleted resource, navigate to the hub of the Azure AI services API type and select "Manage deleted resources" from the menu. For example, if you would like to recover an "Anomaly detector" resource, search for "Anomaly detector" in the search bar and select the service. Then select Manage deleted resources. Select the subscription in the dropdown list to locate the deleted resource you would like to recover. Select one or more of the deleted resources and select Recover.  ７ Note It can take a couple of minutes for your deleted resource(s) to recover and show up in the list of the resources. Select the Refresh button in the menu to  update the list of resources. Purge a deleted resource Your subscription must have Microsoft.CognitiveServices/locations/resourceGroups/deletedAccounts/delete permissions to purge resources, such as Cognitive Services Contributor or Contributor. When using Contributor to purge a resource the role must be assigned at the subscription level. If the role assignment is only present at the resource or resource group level, you can't access the purge functionality. To purge a deleted Azure AI services resource, use the following commands. Where applicable, replace: {subscriptionID} with your Azure subscription ID {resourceGroup} with your resource group {resourceName} with your resource name {location} with the location of your resource ７ Note Once a resource is purged, it is permanently deleted and cannot be restored. You will lose all data and keys associated with the resource. Azure portal If you need to purge a deleted resource, the steps are similar to recovering a deleted resource. 1. Navigate to the hub of the Azure AI services API type of your deleted resource. For example, if you would like to purge an "Anomaly detector" resource, search for "Anomaly detector" in the search bar and select the service. Then select Manage deleted resources from the menu. 2. Select the subscription in the dropdown list to locate the deleted resource you would like to purge. 3. Select one or more deleted resources and select Purge. Purging permanently deletes an Azure AI services resource.   Related content Create an Azure AI services resource Create an Azure AI services resource using an ARM template Feedback Was this page helpful?  Yes  No Provide product feedback | Get help at Microsoft Q&A What are Azure AI containers? Article 08/28/2024 Azure AI services provides several Docker containers that let you use the same APIs that are available in Azure, on-premises. Using these containers gives you the flexibility to bring Azure AI services closer to your data for compliance, security or other operational reasons. Container support is currently available for a subset of Azure AI services. https://www.youtube-nocookie.com/embed/hdfbn4Q8jbo Containerization is an approach to software distribution in which an application or service, including its dependencies & configuration, is packaged together as a container image. With little or no modification, a container image can be deployed on a container host. Containers are isolated from each other and the underlying operating system, with a smaller footprint than a virtual machine. Containers can be instantiated from container images for short-term tasks, and removed when no longer needed. Features and benefits Immutable infrastructure: Enable DevOps teams to leverage a consistent and reliable set of known system parameters, while being able to adapt to change. Containers provide the flexibility to pivot within a predictable ecosystem and avoid configuration drift. Control over data: Choose where your data gets processed by Azure AI services. This can be essential if you can't send data to the cloud but need access to Azure AI services APIs. Support consistency in hybrid environments – across data, management, identity, and security. Control over model updates: Flexibility in versioning and updating of models deployed in their solutions. Portable architecture: Enables the creation of a portable application architecture that can be deployed on Azure, on-premises and the edge. Containers can be deployed directly to Azure Kubernetes Service, Azure Container Instances, or to a Kubernetes cluster deployed to Azure Stack. For more information, see Deploy Kubernetes to Azure Stack. High throughput / low latency: Provide customers the ability to scale for high throughput and low latency requirements by enabling Azure AI services to run physically close to their application logic and data. Containers don't cap transactions per second (TPS) and can be made to scale both up and out to handle demand if you provide the necessary hardware resources.  Scalability: With the ever growing popularity of containerization and container orchestration software, such as Kubernetes; scalability is at the forefront of technological advancements. Building on a scalable cluster foundation, application development caters to high availability. Containers in Azure AI services Azure AI containers provide the following set of Docker containers, each of which contains a subset of functionality from services in Azure AI services. You can find instructions and image locations in the tables below. ７ Note See Install and run Document Intelligence containers for Azure AI Document Intelligence container instructions and image locations. Decision containers ﾉ Expand table Service Container Description Availability Anomaly Anomaly The Anomaly Detector API enables you to Generally detector Detector monitor and detect abnormalities in your time available (image ) series data with machine learning. Language containers ﾉ Expand table Service Container Description Availability LUIS LUIS (image ) Loads a trained or published Language Generally Understanding model, also known as a available. LUIS app, into a docker container and This container can provides access to the query predictions also run in from the container's API endpoints. You disconnected can collect query logs from the container environments. and upload these back to the LUIS portal to improve the app's prediction accuracy. Service Container Description Availability Language Key Phrase Extracts key phrases to identify the main Generally service Extraction points. For example, for the input text "The available. (image ) food was delicious and there were This container can wonderful staff", the API returns the main also run in talking points: "food" and "wonderful disconnected staff". environments. Language Text Language For up to 120 languages, detects which Generally service Detection language the input text is written in and available. (image ) report a single language code for every This container can document submitted on the request. The also run in language code is paired with a score disconnected indicating the strength of the score. environments. Language Sentiment Analyzes raw text for clues about positive Generally service Analysis or negative sentiment. This version of available. (image ) sentiment analysis returns sentiment labels This container can (for example positive or negative) for each also run in document and sentence within it. disconnected environments. Language Text Analytics for Extract and label medical information from Generally service health (image ) unstructured clinical text. available Language Named Entity Extract named entities from text. Generally service Recognition available. (image ) This container can also run in disconnected environments. Language Custom Named Extract named entities from text, using a Generally service Entity custom model you create using your data. available Recognition (image ) Language Summarization Summarize text from various sources. Public preview. service (image ) This container can also run in disconnected environments. Translator Translator Translate text in several languages and Generally (image ) dialects. available. Gated - request access. This container can also run in Service Container Description Availability disconnected environments. Speech containers ﾉ Expand table Service Container Description Availability Speech Speech to text Transcribes continuous real-time Generally available. Service (image ) speech into text. This container can also API run in disconnected environments. Speech Custom Speech to Transcribes continuous real-time Generally available Service text (image ) speech into text using a custom This container can also API model. run in disconnected environments. Speech Neural Text to Converts text to natural-sounding Gene