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
In this quickstart, build a console application by using the [**Azure.Search.Documents**](/dotnet/api/overview/azure/search.documents-readme) client library to add semantic ranking to an existing search index.
14
-
15
13
> [!TIP]
16
14
> You can [download the source code](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-semantic-search/SemanticSearchQuickstart) to start with a finished project or follow these steps to create your own.
17
15
18
16
## Set up the client
19
17
20
-
In this quickstart, you use an IDE and the [Azure.Search.Documents](TBD)library to configure and use a semantic ranker.
18
+
In this quickstart, you use an IDE and the [**Azure.Search.Documents**](/dotnet/api/overview/azure/search.documents-readme) client library to add semantic ranking to an existing search index.
21
19
22
-
We recommend [Visual Studio](TBD) for this quickstart.
20
+
We recommend [Visual Studio](https://visualstudio.microsoft.com/vs/community/) for this quickstart.
> You can [download and run a finished notebook](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Semantic-Search) to start with a finished project or follow these steps to create your own.
14
+
> You can [download a finished notebook](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Semantic-Search) to start with a finished project or follow these steps to create your own.
15
15
16
16
## Set up the client
17
17
18
18
In this quickstart, use a Jupyter notebook and the [**azure-search-documents**](/python/api/overview/azure/search-documents-readme) library in the Azure SDK for Python to learn about semantic ranking.
19
19
20
-
Use [Visual Studio Code with the Python extension](https://code.visualstudio.com/docs/languages/python), or equivalent IDE, with Python 3.10 or later.
20
+
We recommend [Visual Studio Code](https://code.visualstudio.com/download) with Python 3.10 or later and the [Python extension](https://code.visualstudio.com/docs/languages/python) for this quickstart.
21
21
22
22
We recommend a virtual environment for this quickstart:
Copy file name to clipboardExpand all lines: articles/search/includes/quickstarts/semantic-ranker-intro.md
+24-7Lines changed: 24 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,7 @@ author: haileytap
4
4
ms.author: haileytapia
5
5
ms.service: azure-ai-search
6
6
ms.topic: include
7
-
ms.date: 06/25/2025
7
+
ms.date: 06/27/2025
8
8
---
9
9
10
10
In this quickstart, you learn about the index and query modifications that invoke semantic ranker.
@@ -16,20 +16,38 @@ You can add a semantic configuration to an existing index with no rebuild requir
16
16
In this quickstart:
17
17
18
18
> [!div class="checklist"]
19
-
> - Add a *semantic configuration* to a search index
19
+
> - Add a semantic configuration to a search index
20
20
> - Add semantic parameters to a query
21
21
22
22
## Prerequisites
23
23
24
24
+ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/free/?WT.mc_id=A261C142F).
25
25
26
-
+ An [Azure AI Search service](../../search-create-service-portal.md), at Basic tier or higher, with [semantic ranker enabled](semantic-how-to-enable-disable.md).
26
+
+ An [Azure AI Search service](../../search-create-service-portal.md), at Basic tier or higher, with [semantic ranker enabled](../../semantic-how-to-enable-disable.md).
27
27
28
28
+ A [new or existing index](../../search-how-to-create-search-index.md) with descriptive or verbose text fields, attributed as retrievable in your index.
29
29
30
-
## Configure role-based access
30
+
## Configure access
31
31
32
-
TBD
32
+
You can connect to your Azure AI Search service [using API keys](../../search-security-api-keys.md) or Microsoft Entra ID with role assignments. Keys are easier to start with, but roles are more secure.
33
+
34
+
To configure the recommended role-based access:
35
+
36
+
1. Sign in to the [Azure portal](https://portal.azure.com/) and select your search service.
37
+
38
+
1. From the left pane, select **Settings** > **Keys**.
39
+
40
+
1. Under **API Access control**, select **Both**.
41
+
42
+
This option enables both key-based and keyless authentication. After you assign roles, you can return to this step and select **Role-based access control**.
43
+
44
+
1. From the left pane, select **Access control (IAM)**.
45
+
46
+
1. Select **Add** > **Add role assignment**.
47
+
48
+
1. Assign the **Search Service Contributor** and **Search Index Data Contributor** roles to your user account.
49
+
50
+
For more information, see [Connect to Azure AI Search using roles](../../search-security-rbac.md).
33
51
34
52
## Start with an index
35
53
@@ -39,7 +57,7 @@ If you don't have access to the Azure portal, you can create a hotels-quickstart
39
57
40
58
Both indexes have a "Description" field that's suitable for demonstrating the semantic ranker.
41
59
42
-
1. Sign in to the Azure portal and find your search service.
60
+
1. Sign in to the [Azure portal](https://portal.azure.com/) and find your search service.
43
61
44
62
1. Under **Search management** > **Indexes**, open the hotels index. Make sure the index doesn't have a semantic configuration.
45
63
@@ -106,7 +124,6 @@ Both indexes have a "Description" field that's suitable for demonstrating the se
106
124
"Description": "Oceanfront hotel overlooking the beach features rooms with a private balcony and 2 indoor and outdoor pools. Inspired by the natural beauty of the island, each room includes an original painting of local scenes by the owner. Rooms include a mini fridge, Keurig coffee maker, and flatscreen TV. Various shops and art entertainment are on the boardwalk, just steps away."
107
125
}
108
126
]
109
-
}
110
127
```
111
128
112
129
Later, you can try this query again after semantic ranking is configured to see how the response changes.
> You can [download the source code](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-semantic-search) to start with a finished project or follow these steps to create your own.
14
+
12
15
## Set up the client
13
16
14
17
In this quickstart, you use a REST client and the [Azure AI Search REST APIs](/rest/api/searchservice) to configure and use a semantic ranker.
0 commit comments