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
Copy file name to clipboardExpand all lines: articles/ai-services/content-understanding/quickstart/use-ai-foundry.md
+32-29Lines changed: 32 additions & 29 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -11,9 +11,13 @@ ms.date: 05/19/2025
11
11
12
12
# Use Azure AI Content Understanding in the Azure AI Foundry
13
13
14
-
[The Azure AI Foundry](https://aka.ms/cu-landing) is a comprehensive platform for developing and deploying generative AI applications and APIs responsibly. Azure AI Content Understanding is a new generative [Azure AI Service](../../what-are-ai-services.md) that analyzes files from varied modalities and extracts structured output in a user-defined field format. Input sources include document, video, image, and audio data. This guide shows you how to build and test a Content Understanding analyzer in the AI Foundry. You can then utilize the extracted data in any app or process you build using a simple REST API call. Content Understanding analyzers are fully customizable. You can create an analyzer by building your own schema from scratch or by using a suggested analyzer template offered to address common scenarios across each data type.
14
+
In this quickstart, you learn how to create a custom task and build your first analyzer using the Azure AI Foundry. The Azure AI Foundry is a comprehensive platform for developing and deploying generative AI applications and APIs responsibly. You also learn how to share your project with other users.
15
15
16
-
:::image type="content" source="../media/quickstarts/ai-foundry-overview.png" alt-text="Screenshot of the Content Understanding workflow in the Azure AI Foundry.":::
16
+
[Azure AI Foundry](../../../ai-foundry/index.yml) is a comprehensive platform for developing and deploying generative AI applications and APIs responsibly. Azure AI Content Understanding is a new generative [Azure AI Service](../../what-are-ai-services.md) that analyzes files from varied modalities and extracts structured output in a user-defined field format.
17
+
18
+
Input sources include document, video, image, and audio data. This guide shows you how to build and test a Content Understanding analyzer in the AI Foundry. You can then utilize the extracted data in any app or process you build using a simple REST API call. Content Understanding analyzers are fully customizable. You can create an analyzer by building your own schema from scratch or by using a suggested analyzer template offered to address common scenarios across each data type.
19
+
20
+
:::image type="content" source="../media/quickstarts/ai-foundry-overview.png" alt-text="Screenshot of the Content Understanding workflow in the Azure AI Foundry.":::
17
21
18
22
## Prerequisites
19
23
@@ -23,42 +27,29 @@ To get started, make sure you have the following resources and permissions:
23
27
24
28
* An [Azure AI Foundry project](../../../ai-foundry/how-to/create-projects.md) created in one of the following supported regions: `westus`, `swedencentral`, or `australiaeast`. A project is used to organize your work and save state while building customized AI apps.
25
29
26
-
> [!IMPORTANT]
27
-
> If your organization requires you to customize the security of storage resources, refer to [Azure AI services API access keys](../../../ai-foundry/concepts/encryption-keys-portal.md) to create resources that meet your organizations requirements through the Azure portal. To learn how to utilize customer managed keys, refer to [Encrypt data using customer-managed keys](../../../ai-foundry/concepts/encryption-keys-portal.md).
30
+
[!INCLUDE [hub based project required](../../../ai-foundry/includes/uses-hub-only.md)]
28
31
29
-
## Create your first project in the AI Foundry portal
32
+
* If your organization requires you to customize the security of storage resources, refer to [Azure AI services API access keys](../../../ai-foundry/concepts/encryption-keys-portal.md) to create resources that meet your organizations requirements through the Azure portal. To learn how to utilize customer managed keys, refer to [Encrypt data using customer-managed keys](../../../ai-foundry/concepts/encryption-keys-portal.md).
30
33
31
-
In order to try out [the Content Understanding service in the AI Foundry](https://aka.ms/cu-landing), you have to create a project. You can create a project from the [AI Foundry home page](https://ai.azure.com/) or the [Content Understanding landing page](https://aka.ms/cu-landing)
34
+
## Create a custom task
32
35
33
-
To create a project in [Azure AI Foundry](https://ai.azure.com), follow these steps:
36
+
Follow these steps to create a custom task in the Azure AI Foundry. This task will be used to build your first analyzer.
34
37
35
38
1. Go to the **Home** page of [Azure AI Foundry](https://ai.azure.com).
36
-
1. Select **+ Create project**.
37
-
1. Enter a name for the project. Keep all the other settings as default.
38
-
1. Select **Customize** to specify properties of the hub.
39
-
1. For **Region**. You must choose `westus`, `swedencentral`, or `australiaeast`.
40
-
1. Select **Next**.
41
-
1. Select **Create project**.
42
-
43
-
## Sharing your project
44
-
45
-
In order to share and manage access to the project you created, navigate to the Management Center, found at the bottom of the navigation for your project:
46
-
47
-
:::image type="content" source="../media/quickstarts/cu-find-management-center.png" alt-text="Screenshot of where to find management center.":::
48
-
49
-
50
-
You can manage the users and their individual roles here:
51
-
52
-
:::image type="content" source="../media/quickstarts/cu-management-center.png" alt-text="Screenshot of Project users section of management center.":::
39
+
1. Select your hub based project. You might need to select **View all resources** to see your project.
40
+
1. Select **Content Understanding** from the left navigation pane.
41
+
1. Select **+ Create**.
42
+
1. Enter a name for your task. Optionally, enter a description and change other settings.
43
+
1. Select **Create**.
53
44
54
-
## Create your first task and analyzer
45
+
## Create your first task analyzer
55
46
56
47
Now that everything is configured to get started, we can walk through, step-by-step, how to create a task and build your first analyzer. The type of task that you create depends on what data you plan to bring in.
57
48
58
-
***Single-file task:** A single-file task utilizes Content Understanding Standard mode and allows you to bring in one file to create your analyzer.
59
-
***Multi-file task:** A multi-file task utilizes Content Understanding Pro mode and allows you to bring in multiple files to create your analyzer. You can also bring in a set of reference data that the service can use to perform multi-step reasoning and make conclusions about your data. To learn more about the difference between Content Understanding Standard and Pro mode, check out [Azure AI Content Understanding pro and standard modes](../concepts/standard-pro-modes.md).
49
+
*[Single-file task:](#single-file-task-standard-mode) A single-file task utilizes Content Understanding Standard mode and allows you to bring in one file to create your analyzer.
50
+
*[Multi-file task:](#multi-file-task-pro-mode) A multi-file task utilizes Content Understanding Pro mode and allows you to bring in multiple files to create your analyzer. You can also bring in a set of reference data that the service can use to perform multi-step reasoning and make conclusions about your data. To learn more about the difference between Content Understanding Standard and Pro mode, check out [Azure AI Content Understanding pro and standard modes](../concepts/standard-pro-modes.md).
To create a single-file Content Understanding task, start by building your field schema. The schema is the customizable framework that allows the analyzer to extract insights from your data. In this example, the schema is created to extract key data from an invoice document, but you can bring in any type of data and the steps remain the same. For a complete list of supported file types, see [input file limits](../service-limits.md#input-file-limits).
64
55
@@ -96,12 +87,24 @@ To create a single-file Content Understanding task, start by building your field
96
87
97
88
Now you successfully built your first Content Understanding analyzer, and are ready to start extracting insights from your data. Check out [Quickstart: Azure AI Content Understanding REST APIs](./use-rest-api.md) to utilize the REST API to call your analyzer.
98
89
99
-
#[Multi-file task (Pro mode)](#tab/pro)
90
+
### Multi-file task (Pro mode)
100
91
101
92
To create a multi-file Content Understanding task, start by building your field schema. The schema is the customizable framework that allows the analyzer to extract insights from your data. In this example, the schema is created to extract key data from an invoice document, but you can bring in any document based data and the steps remain the same. For a complete list of supported file types, see [input file limits](../service-limits.md#input-file-limits).
102
93
103
94
104
95
96
+
## Sharing your project
97
+
98
+
In order to share and manage access to the project you created, navigate to the Management Center, found at the bottom of the navigation for your project:
99
+
100
+
:::image type="content" source="../media/quickstarts/cu-find-management-center.png" alt-text="Screenshot of where to find management center.":::
101
+
102
+
103
+
You can manage the users and their individual roles here:
104
+
105
+
:::image type="content" source="../media/quickstarts/cu-management-center.png" alt-text="Screenshot of Project users section of management center.":::
106
+
107
+
105
108
## Next steps
106
109
107
110
* Learn more about creating and using [analyzer templates](../concepts/analyzer-templates.md) in the Azure AI Foundry.
Copy file name to clipboardExpand all lines: articles/ai-services/language-service/conversational-language-understanding/how-to/migrate-from-luis.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ author: jboback
6
6
manager: nitinme
7
7
ms.service: azure-ai-language
8
8
ms.topic: how-to
9
-
ms.date: 04/29/2025
9
+
ms.date: 05/23/2025
10
10
ms.author: jboback
11
11
ms.custom: language-service-clu
12
12
---
@@ -22,7 +22,7 @@ CLU offers the following advantages over LUIS:
22
22
- Ease of integration with different CLU and [custom question answering](../../question-answering/overview.md) projects using [orchestration workflow](../../orchestration-workflow/overview.md).
23
23
- The ability to add testing data within the experience using Language Studio and APIs for model performance evaluation prior to deployment.
24
24
25
-
To get started, you can [create a new project](../quickstart.md?pivots=language-studio#create-a-conversational-language-understanding-project) or [migrate your LUIS application](#migrate-your-luis-applications).
25
+
To get started, you can [use CLU directly](../quickstart.md) or [migrate your LUIS application](#migrate-your-luis-applications).
26
26
27
27
## Comparison between LUIS and CLU
28
28
@@ -33,7 +33,7 @@ The following table presents a side-by-side comparison between the features of L
33
33
|Machine-learned and Structured ML entities| Learned [entity components](#how-are-entities-different-in-clu)|Machine-learned entities without subentities are transferred as CLU entities. Structured ML entities only transfer leaf nodes (lowest level subentities that don't have their own subentities) as entities in CLU. The name of the entity in CLU is the name of the subentity concatenated with the parent. For example, _Order.Size_|
34
34
|List, regex, and prebuilt entities| List, regex, and prebuilt [entity components](#how-are-entities-different-in-clu)| List, regex, and prebuilt entities are transferred as entities in CLU with a populated entity component based on the entity type.|
35
35
|`Pattern.Any` entities| Not currently available |`Pattern.Any` entities are removed.|
36
-
|Single culture for each application|[Multilingual models](#how-is-conversational-language-understanding-multilingual) enable multiple languages for each project. |The primary language of your project are set as your LUIS application culture. Your project can be trained to extend to different languages.|
36
+
|Single culture for each application|[Multilingual models](#how-is-conversational-language-understanding-multilingual) enable multiple languages for each project. |The primary language of your project is set as your LUIS application culture. Your project can be trained to extend to different languages.|
37
37
|Entity roles |[Roles](#how-are-entity-roles-transferred-to-clu) are no longer needed. | Entity roles are transferred as entities.|
38
38
|Settings for: normalize punctuation, normalize diacritics, normalize word form, use all training data |[Settings](#how-is-the-accuracy-of-clu-better-than-luis) are no longer needed. |Settings aren't transferred. |
39
39
|Patterns and phrase list features|[Patterns and Phrase list features](#how-is-the-accuracy-of-clu-better-than-luis) are no longer needed. |Patterns and phrase list features aren't transferred. |
Copy file name to clipboardExpand all lines: articles/ai-services/language-service/conversational-language-understanding/includes/quickstarts/rest-api.md
+1-7Lines changed: 1 addition & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -3,7 +3,7 @@ author: jboback
3
3
manager: nitinme
4
4
ms.service: azure-ai-language
5
5
ms.topic: include
6
-
ms.date: 11/21/2024
6
+
ms.date: 05/23/2025
7
7
ms.author: jboback
8
8
---
9
9
@@ -24,12 +24,6 @@ ms.author: jboback
24
24
25
25
:::image type="content" source="../../../media/azure-portal-resource-credentials.png" alt-text="A screenshot showing the key and endpoint page in the Azure portal" lightbox="../../../media/azure-portal-resource-credentials.png":::
26
26
27
-
## Import a new CLU fine-tuning project
28
-
29
-
Once you have a Language resource or an Azure AI resource created, create a fine-tuning task and select Azure AI language and select Conversational language understanding as the task type. A task is a work area for building your custom models based on your data. Your task can only be accessed by you and others who have access to the resource being used.
30
-
31
-
For this quickstart, you can download [this sample](https://github.com/Azure-Samples/cognitive-services-sample-data-files/blob/master/language-service/CLU/EmailAppDemo.json) and import it. This task can predict the intended commands from user input, such as: reading emails, deleting emails, and attaching a document to an email.
32
-
33
27
## Import a new CLU sample project
34
28
35
29
Once you have a Language resource created, create a conversational language understanding project. A project is a work area for building your custom ML models based on your data. Your project can only be accessed by you and others who have access to the Language resource being used.
Copy file name to clipboardExpand all lines: articles/ai-services/language-service/conversational-language-understanding/overview.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -46,7 +46,7 @@ In a large corporation, an enterprise chat bot may handle various employee affai
46
46
47
47
### Agents
48
48
49
-
CLU is utilized by the [intent routing](https://aka.ms/intent-triage-agent-template) agent template, which detects user intent and provides exact answering. Perfect for deterministically intent routing and exact question answering with human control.
49
+
CLU is utilized by the [intent routing](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/agent-catalog/msft-agent-samples/foundry-agent-service-sdk/intent-routing-agent) agent template, which detects user intent and provides exact answering. Perfect for deterministically intent routing and exact question answering with human control.
# Quickstart: Conversational language understanding
16
16
17
17
Use this article to get started with Conversational Language understanding using Azure AI Foundry and the REST API. Follow these steps to try out an example.
18
18
19
-
::: zone pivot="azure-ai-foundry"
19
+
::: zone pivot="language-studio"
20
20
21
21
[!INCLUDE [Language Studio quickstart](includes/quickstarts/language-studio.md)]
0 commit comments