You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
# Quickstart: Create your first AI Foundry resource
20
+
# Quickstart: Set up your first AI Foundry resource
21
21
22
-
Learn how to create and manage an AI Foundry resource. It is the primary resource type for designing, deploying, and managing generative AI applications and agents. It provides access to agent service, models that are hosted using a serverless hosting model, evaluations and Azure OpenAI service. This is the recommended resource type for most applications built in Azure AI Foundry.
22
+
Learn how to create and manage an Azure AI Foundry resource. It is the [primary Azure resource type](../ai-foundry/concepts/resource-types.md) for building, deploying, and managing generative AI models and applications including agents in Azure.
23
23
24
-
Azure AI Foundry is the next version and renaming of former 'Azure AI Services'. All its previous capabilities are supported including Azure AI Services models for Speech, Vision, Language capabilities. New capabilities include AI Foundry API which lets you access Agent service and Evaluations, [projects](../ai-foundry/how-to/create-projects.md) as folders to organize your work, and [connections](../ai-foundry/how-to/connections-add.md) to integrate with other Azure services.
24
+
An Azure resource is required to use and manage services in Azure. It defines the scope for configuring access, security such as networking, billing, and monitoring.
25
25
26
-
Looking to use AI Foundry with advanced security settings? See [advanced AI Foundry creation options](../ai-foundry/how-to/create-resource-template.md)
26
+
Azure AI Foundry resource is the next version and renaming of former "Azure AI Services". It provides the application environment for hosting your agents, model deployments, evaluations, and more.
27
+
28
+
Looking to configure AI Foundry with advanced security settings? See [advanced AI Foundry creation options](../ai-foundry/how-to/create-resource-template.md)
27
29
28
30
Looking to use [Azure AI Search skills?](../search/tutorial-skillset.md) See classic [Azure AI multi-services resource](#azure-ai-multi-services-resource-for-azure-ai-search-skills).
29
31
32
+
## Create your first resource
33
+
34
+
An Azure AI Foundry resource can organize the work for multiple use cases, and is [typically shared](../ai-foundry/concepts/planning.md) between a team of developers that work on use cases in a similar business or data domain. Projects acts as folders to group related work.
35
+
36
+
:::image type="content" source="../foundry/media/how-to/projects/projects-multi-setup.png" alt-text="Screenshot of the Azure AI services multi-service account in the Azure portal.":::
37
+
38
+
To create your first resource, with basic Azure settings, follow the below steps using either Azure Portal, Azure CLI or Azure Powershell.
@@ -45,36 +55,42 @@ Looking to use [Azure AI Search skills?](../search/tutorial-skillset.md) See cla
45
55
46
56
::: zone-end
47
57
48
-
## Default project
58
+
#Access your resource
49
59
50
-
In AI Foundry, projects provide access to developer APIs, and act as folders to organize your work. A default project is created for you when you create your resource in Azure portal or Azure AI Foundry Portal. The default project has a special notion - it provides backwards compatibility with developer APIs that are supported on the parent resource level. Typically these are AI Services and Azure OpenAI APIs for model customization. Newer APIs including Agents and Evaluations are accessible from any project. For more information, see [Types of projects](../ai-foundry/what-is-azure-ai-foundry.md#project-types).
60
+
Now you've created your first resource, you can access it via [Foundry Portal for UX prototyping](https://ai.azure.com/), [Foundry SDK for development](), or via [Azure Portal for administrative management](https://portal.azure.com).
51
61
52
-
Your AI Foundry resource might or might not be associated with an AI Foundry project:
53
-
- If your AI Foundry resources was created using Azure CLI, PowerShell, Bicep template, Terraform, or SDKs. In those cases, the AI Foundry resource by default isn't associated with a project. You can create a project later as a child resource.
54
-
- If your AI Foundry resource was created as a connection. For example, when you try to deploy a model that is not available in the region of your current AI Foundry resource.
55
-
- A [project can be created in the Azure AI Foundry portal](../ai-foundry/how-to/create-projects.md) and automatically associated as a dependent of a new AI Foundry resource.
56
-
- An AI Foundry resource might have been created in the AI Foundry portal, but as a dependent resource of an [Azure AI Foundry hub](../ai-foundry/concepts/ai-resources.md). In this case, the resource is automatically associated with the project you create in the hub.
62
+
## Grant or obtain developer permissions
57
63
58
-
## Supported services with an AI Foundry resource
64
+
[Azure Role Based Access Control](/azure/role-based-access-control/resource-provider-operations.md) (RBAC) differentiates permissions between management and development actions. To build with Foundry, your user account must be assigned developer permissions ("data actions"). You can either use one of the built-in RBAC roles, or use a custom RBAC role.
59
65
60
-
The AI Foundry resource enables access to the following Azure AI services with a single set of credentials. Some services are available via the AI Foundry resource and single-service resource.
66
+
Built-in Azure RBAC developer roles for Foundry include:
61
67
62
-
> [!TIP]
63
-
> We recommend whenever possible to use the **AI Foundry** 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 AI Foundry resource (such as Face and Custom Vision), you can alternatively create a single-service resource.
64
-
65
-
| Service | Description | Kind (via API) |
66
-
| --- | --- | --- |
67
-
|[Azure AI Foundry Agent Service](./agents/index.yml)| Combine the power of generative AI models with tools that allow agents to access and interact with real-world data sources. |`AIServices`|
68
-
|[Azure AI Model Inference](../ai-foundry/model-inference/index.yml)| Performs model inference for flagship models in the Azure AI Foundry model catalog. |`AIServices`|
69
-
|[Azure OpenAI](../ai-foundry/openai/index.yml)| Perform a wide variety of natural language tasks. |`AIServices`<br/>`OpenAI`|
70
-
|[Content Safety](./content-safety/index.yml)| An AI service that detects unwanted contents. |`AIServices`<br/>`ContentSafety`|
71
-
|[Custom Vision](./custom-vision-service/index.yml)| Customize image recognition for your business. |`CustomVision.Prediction` (Prediction only)<br/>`CustomVision.Training` (Training only) |
|[Face](./computer-vision/overview-identity.md)| Detect and identify people and emotions in images. |`Face`|
74
-
|[Language](./language-service/index.yml)| Build apps with industry-leading natural language understanding capabilities. |`AIServices`<br/>`TextAnalytics`|
75
-
|[Speech](./speech-service/index.yml)| Speech to text, text to speech, translation, and speaker recognition. |`AIServices`<br/>`Speech`|
76
-
|[Translator](./translator/index.yml)| Use AI-powered translation technology to translate more than 100 in-use, at-risk, and endangered languages and dialects. |`AIServices`<br/>`TextTranslation`|
77
-
|[Vision](./computer-vision/index.yml)| Analyze content in images and videos. |`AIServices` (Training and Prediction)<br/>`ComputerVision`|
68
+
|Role|Description|
69
+
|---|---|
70
+
|Azure AI project manager|Grants development permissions, and project management permissions. Invite other users to collaborate on project as 'Azure AI user'.|
71
+
|Azure AI user|Grants development permissions.|
72
+
73
+
Only authorized users, typically the Azure subscription or resource group owner, can assign a role via either [Azure Portal]() or [AI Foundry Portal via management center](). [Learn more about role-based access control](../ai-foundry/concepts/rbac-azure-ai-foundry.md).
74
+
75
+
> [!IMPORTANT]
76
+
> Azure Owner and Contributor roles do only include only management permissions, and not development permissions. Development permissions are required to build with all capabilites in Foundry.
77
+
78
+
## Start building in your first project
79
+
80
+
With permissions set up, you are now ready to start building Foundry. In [Azure AI Foundry Portal](https://ai.azure.com/) open or [create your first project](../ai-foundry/how-to/create-projects.md). Projects organize your agent and model customization work in Foundry, and you can create multiple under the same resource.
81
+
82
+
Explore some of the services that come bundled with your resource:
83
+
84
+
| Service | Description |
85
+
| --- | --- |
86
+
|[Azure AI Foundry Agent Service](./agents/index.yml)| Combine the power of generative AI models with tools that allow agents to access and interact with real-world data sources. |
87
+
|[Azure AI Model Inference](../ai-foundry/model-inference/index.yml)| Performs model inference for flagship models in the Azure AI Foundry model catalog. |
88
+
|[Azure OpenAI](../ai-foundry/openai/index.yml)| Perform a wide variety of natural language tasks. |
89
+
|[Content Safety](./content-safety/index.yml)| An AI service that detects unwanted contents. |
|[Language](./language-service/index.yml)| Build apps with industry-leading natural language understanding capabilities. |
92
+
|[Speech](./speech-service/index.yml)| Speech to text, text to speech, translation, and speaker recognition. |
93
+
|[Translator](./translator/index.yml)| Use AI-powered translation technology to translate more than 100 in-use, at-risk, and endangered languages and dialects. |
78
94
79
95
## Azure AI multi-services resource for Azure AI Search skills
80
96
@@ -102,11 +118,10 @@ To create a multi-service resource for Azure AI Search skills follow these instr
102
118
> [!TIP]
103
119
> If your subscription doesn't allow you to create an AI Foundry resource, you might need to enable the privilege of that [Azure resource provider](/azure/azure-resource-manager/management/resource-providers-and-types#register-resource-provider) using the [Azure portal](/azure/azure-resource-manager/management/resource-providers-and-types#azure-portal), [PowerShell command](/azure/azure-resource-manager/management/resource-providers-and-types#azure-powershell) or an [Azure CLI command](/azure/azure-resource-manager/management/resource-providers-and-types#azure-cli). 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.
104
120
105
-
## Pricing
106
-
107
-
[!INCLUDE [SKUs and pricing](./includes/quickstarts/sku-pricing.md)]
108
-
109
-
## Related content
121
+
## Next steps
110
122
111
-
- Go to the [Azure AI services hub page](../ai-services/index.yml).
123
+
-[Create a project](../ai-foundry/how-to/create-projects.md) to organize your work.
124
+
-[Connect tools](../ai-foundry/how-to/connections-add.md) to build more rich applications.
125
+
- Learn about [access control in AI Foundry](../ai-foundry/concepts/rbac-azure-ai-foundry.md) to invite others to your working environment.
126
+
-[Secure your resource using private networking](../ai-foundry/how-to/configure-private-link.md)
112
127
- Try AI services in the [Azure AI Foundry portal](../ai-services/connect-services-ai-foundry-portal.md).
0 commit comments