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-foundry/concepts/retrieval-augmented-generation.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,7 @@ ms.custom:
8
8
- ignite-2023
9
9
- build-2024
10
10
ms.topic: conceptual
11
-
ms.date: 12/12/2024
11
+
ms.date: 04/03/2025
12
12
ms.reviewer: sgilley
13
13
ms.author: sgilley
14
14
author: sdgilley
@@ -20,7 +20,7 @@ This article talks about the importance and need for Retrieval Augmented Generat
20
20
21
21
## What is RAG?
22
22
23
-
Some basics first. Large language models (LLMs) like ChatGPT are trained on public internet data that was available at the point in time when they were trained. They can answer questions related to the data they were trained on. This public data might not be sufficient to meet all your needs. You might want questions answered based on your private data. Or, the public data might simply have gotten out of date. The solution to this problem is Retrieval Augmented Generation (RAG), a pattern used in AI that uses an LLM to generate answers with your own data.
23
+
Some basics first. Large language models (LLMs) like ChatGPT are trained on public internet data that was available at the point in time when they were trained. They can answer questions related to the data they were trained on. This public data might not be sufficient to meet all your needs. You might want questions answered based on your private data. Or, the public data might simply be out of date. The solution to this problem is Retrieval Augmented Generation (RAG), a pattern used in AI that uses an LLM to generate answers with your own data.
| Model | Offer Availability Region | Hub/Project Region for Deployment | Hub/Project Region for Fine tuning |
76
76
|---------|---------|---------|---------|
77
-
Phi-4 <br> Phi-4-mini-instruct <br> Phi-4-multimodal-instruct | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 |
77
+
Phi-4 <br> Phi-4-mini-instruct <br> Phi-4-multimodal-instruct | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 <br> East US <br> North Central US <br> South Central US <br> West US <br> West US 3 |
78
78
Phi-3.5-vision-Instruct | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | Not available |
79
-
Phi-3.5-MoE-Instruct | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 |
80
-
Phi-3.5-Mini-Instruct | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 |
79
+
Phi-3.5-MoE-Instruct | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 <br> East US <br> North Central US <br> South Central US <br> West US <br> West US 3 |
80
+
Phi-3.5-Mini-Instruct | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 <br> East US <br> North Central US <br> South Central US <br> West US <br> West US 3 |
81
81
Phi-3-Mini-4k-Instruct <br> Phi-3-Mini-128K-Instruct | Not applicable | East US 2 <br> Sweden Central | East US 2 |
82
82
Phi-3-Small-8K-Instruct <br> Phi-3-Small-128K-Instruct | Not applicable | East US 2 <br> Sweden Central | Not available |
83
83
Phi-3-Medium-4K-Instruct <br> Phi-3-Medium-128K-Instruct | Not applicable | East US 2 <br> Sweden Central | East US 2 |
@@ -88,11 +88,11 @@ Phi-3-Medium-4K-Instruct <br> Phi-3-Medium-128K-Instruct | Not applicable | E
88
88
| Model | Offer Availability Region | Hub/Project Region for Deployment | Hub/Project Region for Fine tuning |
89
89
|---------|---------|---------|---------|
90
90
Codestral-2501 | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR <br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | Not available |
91
-
Mistral Nemo | [Microsoft Managed Countries/Regions/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR <br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 |
91
+
Mistral Nemo | [Microsoft Managed Countries/Regions/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR <br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 <br> East US <br> North Central US <br> South Central US <br> West US <br> West US 3 |
92
92
Mistral Small (2503) <br> Mistral Small | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR <br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | Not available |
93
-
Ministral-3B | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR<br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 |
93
+
Ministral-3B | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR<br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 <br> East US <br> North Central US <br> South Central US <br> West US <br> West US 3 |
94
94
Mistral Large (2407) <br> Mistral-Large | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR<br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | Not available |
95
-
Mistral-Large (2411) | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR<br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 |
95
+
Mistral-Large (2411) | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) <br> Brazil <br> Hong Kong SAR<br> Israel | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3 | East US 2 <br> East US <br> North Central US <br> South Central US <br> West US <br> West US 3 |
| Model | Offer Availability Region | Hub/Project Region for Deployment | Hub/Project Region for Fine tuning |
107
107
|---------|---------|---------|---------|
108
-
tsuzumi-7b | [Microsoft Managed Countries/Regions/regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) | East US 2 <br> South Central US <br> East US <br> West US 3 <br> West US <br> North Central US | East US 2 |
108
+
tsuzumi-7b | [Microsoft Managed Countries/Regions/regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions) | East US 2 <br> South Central US <br> East US <br> West US 3 <br> West US <br> North Central US | East US 2 <br> East US <br> North Central US <br> South Central US <br> West US <br> West US 3 |
Microsoft will use data you send to Grounding with Bing to improve Microsoft products and services. Where you send personal data to this service, you are responsible for obtaining sufficient consent from the data subjects. The Data Protection Terms in the Online Services Terms do not apply to Grounding with Bing.
105
-
106
-
Your use of Grounding with Bing Search will be governed by the Terms of Use. By using Grounding with Bing Search, you agree to be bound by and comply with these Terms of Use.
Copy file name to clipboardExpand all lines: articles/ai-services/agents/how-to/tools/fabric.md
-1Lines changed: 0 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,7 +37,6 @@ You need to first build and publish a Fabric data agent and then connect your Fa
37
37
## Setup
38
38
> [!NOTE]
39
39
> * The model you selected in Azure AI Agent setup is only used for agent orchestration and response generation. It doesn't impact which model Fabric data agent uses for NL2SQL operation.
40
-
> * Supported regions: `westus`, `japaneast`.
41
40
1. Create an Azure AI Agent by following the steps in the [quickstart](../../quickstart.md).
42
41
43
42
1. Create and publish a [Fabric data agent](https://go.microsoft.com/fwlink/?linkid=2312910)
Copy file name to clipboardExpand all lines: articles/ai-services/agents/includes/azure-search/setup.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
@@ -4,7 +4,7 @@ author: fosteramanda
4
4
ms.author: fosteramanda
5
5
ms.service: azure-ai-agent-service
6
6
ms.topic: include
7
-
ms.date: 12/10/2024
7
+
ms.date: 03/22/2025
8
8
---
9
9
10
10
## Setup: Create an agent that can use an existing Azure AI Search index
@@ -32,7 +32,7 @@ If you already connected the AI Search resource that contains the index you want
32
32
:::image type="content" source="../../media/tools/ai-search/azure-portal.png" alt-text="A screenshot of an AI Search resource Keys tab in the Azure portal." lightbox="../../media/tools/ai-search/azure-portal.png":::
33
33
34
34
##### Create an Azure AI Search project connection
35
-
If you use Microsoft Entra ID for the connection authentication type, you need to manually assign the project managed identity the roles Search Index Data Contributor and Search Service Contributor to the Azure AI Search resource.
35
+
If you use Microsoft Entra ID for the connection authentication type, you need to manually assign the project managed identity the roles Search Index Data Contributor and Search Service Contributor to the Azure AI Search resource. The connection **name** must be the AI Search **index** name.
36
36
37
37
# [Azure CLI](#tab/azurecli)
38
38
**Create the following connections.yml file**
@@ -101,7 +101,7 @@ Now that you have created a project connection to your Azure AI Search resource,
101
101
102
102
## Add the Azure AI Search tool to an agent
103
103
104
-
you can add the Azure AI Search tool to an agent programatically using the code examples listed at the top of this article, or the Azure AI Foundry portal. If you want to use the portal:
104
+
You can add the Azure AI Search tool to an agent programmatically using the code examples listed at the top of this article, or the Azure AI Foundry portal. If you want to use the portal:
105
105
106
106
1. In the **Create and debug** screen for your agent, scroll down the **Setup** pane on the right to **knowledge**. Then select **Add**.
Document Intelligence doesn't support containers for v4.0. Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models and `2023-07-31 (GA)` for Read, Layout, Invoice, Receipt, and ID Document models:
18
+
Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models and `2023-07-31 (GA)` for Read, Layout, Invoice, Receipt, and ID Document models, and `2024-11-30 (GA)` for Layout model:
19
19
20
20
*[REST API `2022-08-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.0%20(2022-08-31)&preserve-view=true&tabs=HTTP)
21
21
*[REST API `2023-07-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.1%20(2023-07-31)&tabs=HTTP&preserve-view=true)
22
+
*[REST API `v4.0: 2024-11-30 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v4.0%20(2024-11-30)&tabs=HTTP&preserve-view=true)
22
23
*[Client libraries targeting `REST API 2022-08-31 (GA)`](../sdk-overview-v3-0.md)
23
24
*[Client libraries targeting `REST API 2023-07-31 (GA)`](../sdk-overview-v3-1.md)
25
+
*[Client libraries targeting `REST API v4.0: 2024-11-30 (GA)`](../sdk-overview-v4-0.md)
24
26
25
-
✔️ See [**Document Intelligence v3.0 containers in disconnected environments**](?view=doc-intel-3.0.0&preserve-view=true) or [**Document Intelligence v3.1 containers in disconnected environments**](?view=doc-intel-3.1.0&preserve-view=true) for supported versions of container documentation.
27
+
✔️ See [**Document Intelligence v3.0 containers in disconnected environments**](?view=doc-intel-3.0.0&preserve-view=true) or [**Document Intelligence v3.1 containers in disconnected environments**](?view=doc-intel-3.1.0&preserve-view=true)or [**Document Intelligence v4.0 containers in disconnected environments**](?view=doc-intel-4.0.0&preserve-view=true)for supported versions of container documentation.
Document Intelligence doesn't support containers for v4.0. Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models and `2023-07-31 (GA)` for Read, Layout, Invoice, Receipt, and ID Document models:
19
+
Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models, `2023-07-31 (GA)` for Read, Layout, Invoice, Receipt, and ID Document models, and `2024-11-30 (GA)` for Layout model:
20
20
21
21
*[REST API `2022-08-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.0%20(2022-08-31)&preserve-view=true&tabs=HTTP)
22
22
*[REST API `2023-07-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.1%20(2023-07-31)&tabs=HTTP&preserve-view=true)
23
+
*[REST API `2024-11-30 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v4.0%20(2024-11-30)&tabs=HTTP&preserve-view=true)
23
24
*[Client libraries targeting `REST API 2022-08-31 (GA)`](../sdk-overview-v3-0.md)
24
25
*[Client libraries targeting `REST API 2023-07-31 (GA)`](../sdk-overview-v3-1.md)
26
+
*[Client libraries targeting `REST API 2024-11-30 (GA)`](../sdk-overview-v4-0.md)
25
27
26
-
✔️ See [**Document Intelligence v3.0 container image tags**](?view=doc-intel-3.0.0&preserve-view=true) or [**Document Intelligence v3.1 container image tags**](?view=doc-intel-3.1.0&preserve-view=true) for supported versions of container documentation.
28
+
✔️ See [**Document Intelligence v3.0 container image tags**](?view=doc-intel-3.0.0&preserve-view=true) or [**Document Intelligence v3.1 container image tags**](?view=doc-intel-3.1.0&preserve-view=true)or [**Document Intelligence v4.0 container image tags**](?view=doc-intel-4.0.0&preserve-view=true)for supported versions of container documentation.
27
29
28
30
:::moniker-end
29
31
@@ -72,11 +74,26 @@ The following containers support DocumentIntelligence v3.1 models and features:
Document Intelligence container images can be found within the [**Microsoft Artifact Registry** (also know as Microsoft Container Registry(MCR))](https://mcr.microsoft.com/catalog?search=document%20intelligence), the primary registry for all Microsoft published container images.
83
+
84
+
The following containers support DocumentIntelligence v3.1 models and features:
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/whats-new.md
+7Lines changed: 7 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,6 +27,13 @@ Document Intelligence service is updated on an ongoing basis. Bookmark this page
27
27
> [!IMPORTANT]
28
28
> Preview API versions are retired once the GA API is released. The 2023-02-28-preview API version is retiring. If you're still using the preview API or the associated SDK versions, update your code to target the latest API version `2024-11-30 (GA)`. </br>
29
29
30
+
## April 2025
31
+
**Document Intelligence v4.0 container is now available! Currently, Layout model is the only supported model for v4.0 release.**
32
+
<br>
33
+
For more information, *see:*
34
+
*[Install and run containers](containers/install-run.md?view=doc-intel-4.0.0&preserve-view=true)
**Document Intelligence v4.0 programming language SDKs are now generally available (GA)**! <br><br>The latest client libraries default to the [**2024-11-30 REST API (GA)**](/rest/api/aiservices/operation-groups?view=rest-aiservices-v4.0%20(2024-11-30)&preserve-view=true) version of the service.<br><br>
0 commit comments