Foundry Tools

Microsoft Azure provides a wide range of cloud services that you can use to develop, deploy, and manage an AI solution. The most obvious starting point for considering AI development on Azure is Foundry Tools; a set of out-of-the-box prebuilt APIs and models that you can integrate into your applications. The following table lists some commonly used Foundry Tools (for a full list of all available Foundry Tools, see Available Foundry Tools).

Service	Description
Azure OpenAI	Azure OpenAI in Foundry Models provides access to OpenAI generative AI models including the GPT family of large and small language models and DALL-E image-generation models within a scalable and securable cloud service on Azure.
Azure Vision	The Azure Vision service provides a set of models and APIs that you can use to implement common computer vision functionality in an application. With the AI Vision service, you can detect common objects in images, generate captions, descriptions, and tags based on image contents, and read text in images.
Azure Speech	The Azure Speech service provides APIs that you can use to implement text to speech and speech to text transformation, as well as specialized speech-based capabilities like speaker recognition and translation.
Azure Language	The Azure Language service provides models and APIs that you can use to analyze natural language text and perform tasks such as entity extraction, sentiment analysis, and summarization. The AI Language service also provides functionality to help you build conversational language models and question answering solutions.
Microsoft Foundry Content Safety	Microsoft Foundry Content Safety provides developers with access to advanced algorithms for processing images and text and flagging content that is potentially offensive, risky, or otherwise undesirable.
Azure Translator	The Azure Translator service uses state-of-the-art language models to translate text between a large number of languages.
Azure AI Face	The Azure AI Face service is a specialist computer vision implementation that can detect, analyze, and recognize human faces. Because of the potential risks associated with personal identification and misuse of this capability, access to some features of the AI Face service are restricted to approved customers.
Azure AI Custom Vision	The Azure AI Custom Vision service enables you to train and use custom computer vision models for image classification and object detection.
Azure Document Intelligence	With Azure Document Intelligence, you can use pre-built or custom models to extract fields from complex documents such as invoices, receipts, and forms.
Azure Content Understanding	The Azure Content Understanding service provides multi-modal content analysis capabilities that enable you to build models to extract data from forms and documents, images, videos, and audio streams.
Azure AI Search	The Azure AI Search service uses a pipeline of AI skills based on other Foundry Tools and custom code to extract information from content and create a searchable index. AI Search is commonly used to create vector indexes for data that can then be used to ground prompts submitted to generative AI language models, such as those provided in Azure OpenAI.

Considerations for Foundry Tools resources

To use Foundry Tools, you create one or more Azure AI resources in an Azure subscription and implement code in client applications to consume them. In some cases, AI services include web-based visual interfaces that you can use to configure and test your resources - for example to train a custom image classification model using the Custom Vision service you can use the visual interface to upload training images, manage training jobs, and deploy the resulting model.

Single service or Foundry Tools resource?

Most Foundry Tools, such as Azure Vision, Azure Language, and so on, can be provisioned as standalone resources, enabling you to create only the Azure resources you specifically need. Additionally, standalone Foundry Tools often include a free-tier SKU with limited functionality, enabling you to evaluate and develop with the service at no cost. Each standalone Azure AI resource provides an endpoint and authorization keys that you can use to access it securely from a client application.

Alternatively, you can provision a Foundry Tools resource that encapsulates multiple AI services in a single Azure resource. Using a Foundry Tools resource can make it easier to manage applications that use multiple AI capabilities. There are two Foundry resource types you can use:

Resource	Description
Foundry Tools	The Foundry Tools resource type includes the following services, making them available from a single endpoint: Azure Speech Azure Language Azure Translator Azure Vision Azure AI Face Azure AI Custom Vision Azure Document Intelligence
Microsoft Foundry	The Microsoft Foundry resource type includes the following services, and supports working with them through a Microsoft Foundry project*: Azure OpenAI Azure Speech Azure Language Microsoft Foundry Content Safety Azure Translator Azure Vision Azure AI Face Azure Document Intelligence Azure Content Understanding

* Microsoft Foundry is discussed in the next unit.

Regional availability

Some services and models are available in only a subset of Azure regions. Consider service availability and any regional quota restrictions for your subscription when provisioning Foundry Tools. Use the product availability table to check regional availability of Azure services. Use the model availability table in the Azure OpenAI documentation to determine regional availability for Azure OpenAI models.

Cost

Foundry Tools are charged based on usage, with different pricing schemes available depending on the specific services being used. As you plan an AI solution on Azure, use the Foundry Tools pricing documentation to understand pricing for the AI services you intend to incorporate into your application. You can use the Azure pricing calculator to estimate the costs your expected usage will incur.