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
@@ -21,23 +21,26 @@ This quickstart is based on the [Quickstart-Agentic-Retrieval](https://github.co
21
21
22
22
+ An [Azure AI Search service](../../search-create-service-portal.md) on the Basic tier or higher with [semantic ranker enabled](../../semantic-how-to-enable-disable.md).
23
23
24
-
+ An [Azure AI Foundry project](/azure/ai-foundry/how-to/create-projects).
24
+
+ An [Azure AI Foundry project](/azure/ai-foundry/how-to/create-projects). You get an Azure AI Foundry resource (that's needed for model deployments) when you create an Azure AI Foundry project.
25
25
26
26
+[Visual Studio Code](https://code.visualstudio.com/download) with the [Python extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python) and [Jupyter package](https://pypi.org/project/jupyter/).
27
27
28
-
+Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
28
+
+The [Azure CLI](/cli/azure/install-azure-cli) for keyless authentication with Microsoft Entra ID.
29
29
30
30
[!INCLUDE [Setup](./agentic-retrieval-setup.md)]
31
31
32
32
## Connect from your local system
33
33
34
34
You configured role-based access to interact with Azure AI Search and Azure OpenAI.
35
35
36
-
Run the following Azure CLI command and sign in with your Azure account. If you have multiple subscriptions, select the one that contains your Azure AI Search service and Azure AI Foundry project.
36
+
To connect from your local system:
37
37
38
-
```azurecli
39
-
az login
40
-
```
38
+
1. Open a new terminal in Visual Studio Code and change to the directory where you want to save your files.
39
+
1. Run the following Azure CLI command and sign in with your Azure account. If you have multiple subscriptions, select the one that contains your Azure AI Search service and Azure AI Foundry project.
40
+
41
+
```azurecli
42
+
az login
43
+
```
41
44
42
45
For more information, see [Quickstart: Connect without keys](../../search-get-started-rbac.md).
43
46
@@ -47,7 +50,7 @@ Before you run any code, install Python packages and define credentials, endpoin
47
50
48
51
To install the packages and load the connections:
49
52
50
-
1.Open Visual Studio Code and create a `.ipynb` file. For example, you can name the file `quickstart-agentic-retrieval.ipynb`.
53
+
1. In Visual Studio Code, create a `.ipynb` file. For example, you can name the file `quickstart-agentic-retrieval.ipynb`.
51
54
52
55
1. In the first code cell, paste the following code to install the required packages.
53
56
@@ -83,7 +86,7 @@ To install the packages and load the connections:
83
86
api_version = "2025-05-01-Preview"
84
87
```
85
88
86
-
1. Replace `endpoint`and`azure_openai_endpoint`with the values you obtained in [Get endpoints](#get-endpoints). Set `endpoint` to your Azure AI Search service endpoint, which looks like `https://<your-search-service-name>.search.windows.net`, and `azure_openai_endpoint` to your Azure AI Foundry endpoint, which looks like `https://<your-foundry-resource-name>.openai.azure.com`.
89
+
1. Set `endpoint` to your Azure AI Search endpoint, which looks like `https://<your-search-service-name>.search.windows.net.` Set `azure_openai_endpoint` to your Azure AI Foundry endpoint, which looks like `https://<your-foundry-resource-name>.openai.azure.com.` You obtained both values in the [Get endpoints](#get-endpoints) section.
@@ -22,11 +22,11 @@ Although you can provide your own data, this quickstart uses [sample JSON docume
22
22
23
23
+ An [Azure AI Search service](../../search-create-service-portal.md) on the Basic tier or higher with [semantic ranker enabled](../../semantic-how-to-enable-disable.md).
24
24
25
-
+ An [Azure AI Foundry project](/azure/ai-foundry/how-to/create-projects).
25
+
+ An [Azure AI Foundry project](/azure/ai-foundry/how-to/create-projects). You get an Azure AI Foundry resource (that's needed for model deployments) when you create an Azure AI Foundry project.
26
26
27
27
+[Visual Studio Code](https://code.visualstudio.com/download) with a [REST client](https://marketplace.visualstudio.com/items?itemName=humao.rest-client).
28
28
29
-
+Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
29
+
+The [Azure CLI](/cli/azure/install-azure-cli) for keyless authentication with Microsoft Entra ID.
30
30
31
31
[!INCLUDE [Setup](./agentic-retrieval-setup.md)]
32
32
@@ -36,6 +36,8 @@ You configured role-based access to interact with Azure AI Search and Azure Open
36
36
37
37
To connect from your local system:
38
38
39
+
1. Open a new terminal in Visual Studio Code and change to the directory where you want to save your files.
40
+
39
41
1. Run the following command and sign in with your Azure account. If you have multiple subscriptions, select the one that contains your Azure AI Search service and Azure AI Foundry project.
40
42
41
43
```azurecli
@@ -54,7 +56,8 @@ Before you send any requests, define credentials, endpoints, and deployment deta
54
56
55
57
To load the connections:
56
58
57
-
1. In Visual Studio Code, paste the following placeholders into a `.rest` or `.http` file. For example, you can create a file named `agentic-retrieval.rest`.
59
+
1. In Visual Studio Code create a `.rest` or `.http` file. For example, you can name the file `agentic-retrieval.rest`.
60
+
1. Paste these placeholders into the new file:
58
61
59
62
```HTTP
60
63
@baseUrl = PUT-YOUR-SEARCH-SERVICE-URL-HERE
@@ -69,7 +72,7 @@ To load the connections:
69
72
@api-version = 2025-05-01-Preview
70
73
```
71
74
72
-
1. Replace `@baseUrl` and `@aoaiBaseUrl` with the values you obtained in [Get endpoints](#get-endpoints).
75
+
1. Set `@baseUrl` to your Azure AI Search endpoint, which looks like `https://<your-search-service-name>.search.windows.net.` Set `@aoaiBaseUrl` to your Azure AI Foundry endpoint, which looks like `https://<your-foundry-resource-name>.openai.azure.com.` You obtained both values in the [Get endpoints](#get-endpoints) section.
73
76
74
77
1. Replace `@token` with the Microsoft Entra token you obtained in [Connect from your local system](#connect-from-your-local-system).
Copy file name to clipboardExpand all lines: articles/search/includes/quickstarts/agentic-retrieval-setup.md
+17-15Lines changed: 17 additions & 15 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,27 +4,19 @@ author: haileytap
4
4
ms.author: haileytapia
5
5
ms.service: azure-ai-search
6
6
ms.topic: include
7
-
ms.date: 6/13/2025
7
+
ms.date: 6/15/2025
8
8
---
9
9
10
10
## Configure role-based access
11
11
12
-
Azure AI Search needs access to your Azure OpenAI models. For this task, you can use API keys or Microsoft Entra ID with role assignments. Keys are easier to start with, but roles are more secure. This quickstart assumes roles.
12
+
You can use search service API keys or Microsoft Entra ID with role assignments. Keys are easier to start with, but roles are more secure. This quickstart assumes roles.
13
13
14
14
To configure the recommended role-based access:
15
15
16
16
1. Sign in to the [Azure portal](https://portal.azure.com/).
17
17
18
18
1.[Enable role-based access](../../search-security-enable-roles.md) on your Azure AI Search service.
19
19
20
-
1.[Create a system-assigned managed identity](../../search-howto-managed-identities-data-sources.md#create-a-system-managed-identity) on your Azure AI Search service. Here's how to do it using the Azure CLI:
21
-
22
-
```azurecli
23
-
az search service update --name YOUR-SEARCH-SERVICE-NAME --resource-group YOUR-RESOURCE-GROUP-NAME --identity-type SystemAssigned
24
-
```
25
-
26
-
If you already have a managed identity, you can skip this step.
27
-
28
20
1. On your Azure AI Search service, [assign the following roles](../../search-security-rbac.md#how-to-assign-roles-in-the-azure-portal) to yourself.
29
21
30
22
+**Search Service Contributor**
@@ -33,7 +25,17 @@ To configure the recommended role-based access:
33
25
34
26
+**Search Index Data Reader**
35
27
36
-
1. On your Azure AI Foundry resource, assign **Cognitive Services User** to the managed identity that you created for your search service.
28
+
For agentic retrieval, Azure AI Search also needs access to your Azure OpenAI Foundry resource.
29
+
30
+
1.[Create a system-assigned managed identity](../../search-howto-managed-identities-data-sources.md#create-a-system-managed-identity) on your Azure AI Search service. Here's how to do it using the Azure CLI:
31
+
32
+
```azurecli
33
+
az search service update --name YOUR-SEARCH-SERVICE-NAME --resource-group YOUR-RESOURCE-GROUP-NAME --identity-type SystemAssigned
34
+
```
35
+
36
+
If you already have a managed identity, you can skip this step.
37
+
38
+
1. On your Azure AI Foundry resource, assign **Cognitive Services User** to the managed identity that you created for your search service.
37
39
38
40
## Deploy models
39
41
@@ -57,11 +59,11 @@ To deploy the Azure OpenAI models:
57
59
58
60
1. Select **Deploy**.
59
61
60
-
Repeat the previous steps via the model catalog to deploy the **text-embedding-3-large** embedding model.
62
+
1.Repeat the previous steps, but this time deploy the **text-embedding-3-large** embedding model.
61
63
62
64
## Get endpoints
63
65
64
-
In your code, you specify the following endpoints to establish connections with Azure AI Search and Azure OpenAI. These steps assume that you configured role-based access in the previous section.
66
+
In your code, you specify the following endpoints to establish connections with you Azure AI Search service and Azure AI Foundry resource. These steps assume that you [configured role-based access as described previously](#configure-role-based-access).
65
67
66
68
To obtain your service endpoints:
67
69
@@ -75,6 +77,6 @@ To obtain your service endpoints:
75
77
76
78
1. On your Azure AI Foundry resource:
77
79
78
-
1. From the left pane, select **Resource Management** > **Keys and Endpoint**.
80
+
1. From the left pane, select **Resource Management** > **Keys and Endpoint**.
79
81
80
-
1.Copy the URL, which should be similar to `https://my-resource.openai.azure.com`.
82
+
1.Select the **OpenAI** tab and copy the URL that looks similar to `https://my-resource.openai.azure.com`.
0 commit comments