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/search/search-how-to-integrated-vectorization.md
+9-9Lines changed: 9 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,7 +12,7 @@ ms.date: 04/29/2025
12
12
13
13
# Set up integrated vectorization in Azure AI Search using REST
14
14
15
-
In this article, you learn how to use a skillset to chunk and vectorize content from a [supported data source](#supported-data-sources). The skillset calls the [Text Split skill](cognitive-search-skill-textsplit.md) or [Document Layout skill](cognitive-search-skill-document-intelligence-layout.md) for chunking and an embedding skill that's attached to a [supported embedding model](#supported-embedding-models) for chunk vectorization.
15
+
In this article, you learn how to use a skillset to chunk and vectorize content from a [supported data source](#supported-data-sources). The skillset calls the [Text Split skill](cognitive-search-skill-textsplit.md) or [Document Layout skill](cognitive-search-skill-document-intelligence-layout.md) for chunking and an embedding skill that's attached to a [supported embedding model](#supported-embedding-models) for chunk vectorization. You also learn how to store the chunked and vectorized content in a [vector index](vector-search-how-to-create-index.md).
16
16
17
17
This article describes the end-to-end workflow for [integrated vectorization](vector-search-integrated-vectorization.md) using REST<!--or Python-->. For portal-based instructions, see [Quickstart: Vectorize text and images in the Azure portal](search-get-started-portal-import-vectors.md).
18
18
@@ -50,7 +50,7 @@ For integrated vectorization, you must use one of the following embedding models
50
50
|[Azure AI services multi-service resource](/azure/ai-services/multi-service-resource#azure-ai-services-resource-for-azure-ai-search-skills) <sup>3</sup> | For text and images: [Azure AI Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>4</sup></li> |
51
51
<!--| [Azure AI Foundry model catalog](/azure/ai-foundry/what-is-azure-ai-foundry) | For text:<br>Cohere-embed-v3-english<br>Cohere-embed-v3-multilingual<br><br>For images:<br>Facebook-DinoV2-Image-Embeddings-ViT-Base<br>Facebook-DinoV2-Image-Embeddings-ViT-Giant |-->
52
52
53
-
<sup>1</sup> The endpoint of your Azure OpenAI resource must have a [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains), such as `https://my-unique-name.cognitiveservices.azure.com`. If you created your resource in the [Azure portal](https://portal.azure.com/), this subdomain was automatically generated during resource setup.
53
+
<sup>1</sup> The endpoint of your Azure OpenAI resource must have a [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains), such as `https://my-unique-name.openai.azure.com`. If you created your resource in the [Azure portal](https://portal.azure.com/), this subdomain was automatically generated during resource setup.
54
54
55
55
<sup>2</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Azure AI Foundry portal](https://ai.azure.com/) aren't supported. Only Azure OpenAI resources created in the Azure portal are compatible with the [Azure OpenAI Embedding skill](cognitive-search-skill-azure-openai-embedding.md) integration.
56
56
@@ -514,7 +514,7 @@ For built-in data chunking, Azure AI Search offers the [Text Split skill](cognit
514
514
```
515
515
516
516
> [!NOTE]
517
-
> The Document Layout skill is in public preview. If you want to call this skill, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/skillsets/create?view=rest-searchservice-2025-03-01-preview).
517
+
> The Document Layout skill is in public preview. If you want to call this skill, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/skillsets/create?view=rest-searchservice-2025-03-01-preview&preserve-view=true).
518
518
519
519
<!--### [Python](#tab/built-in-skill-python)
520
520
@@ -572,7 +572,7 @@ or [Azure AI Vision skill](cognitive-search-skill-vision-vectorize.md)<!--[Azure
572
572
```
573
573
574
574
> [!NOTE]
575
-
> The Azure AI Vision skill is in public preview. If you want to call this skill, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/skillsets/create?view=rest-searchservice-2025-03-01-preview).
575
+
> The Azure AI Vision skill is in public preview. If you want to call this skill, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/skillsets/create?view=rest-searchservice-2025-03-01-preview&preserve-view=true).
576
576
577
577
1. If you're using the Azure OpenAI Embedding skill, set `dimensions` to the [number of embeddings generated by your embedding model](cognitive-search-skill-azure-openai-embedding.md#supported-dimensions-by-modelname).
578
578
@@ -608,7 +608,7 @@ or [Azure AI Vision skill](cognitive-search-skill-vision-vectorize.md)<!--[Azure
608
608
}
609
609
```
610
610
611
-
The Azure AI Vision skill and AML skill (for indexer connections to the Azure AI Foundry model catalog) are in public preview. If you want to call these skills, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/skillsets/create?view=rest-searchservice-2025-03-01-preview).
611
+
The Azure AI Vision skill and AML skill (for indexer connections to the Azure AI Foundry model catalog) are in public preview. If you want to call these skills, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/skillsets/create?view=rest-searchservice-2025-03-01-preview&preserve-view=true).
612
612
613
613
### [Python](#tab/embedding-skill-python)
614
614
@@ -764,7 +764,7 @@ In this section, you enable vectorization at query time by [defining a vectorize
764
764
```
765
765
766
766
> [!NOTE]
767
-
> The Azure AI Vision vectorizer is in public preview. If you want to call this vectorizer, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/indexes/create?view=rest-searchservice-2025-03-01-preview).
767
+
> The Azure AI Vision vectorizer is in public preview. If you want to call this vectorizer, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/indexes/create?view=rest-searchservice-2025-03-01-preview&preserve-view=true).
768
768
769
769
1. Specify your vectorizer in `vectorSearch.profiles`.
770
770
@@ -795,7 +795,7 @@ In this section, you enable vectorization at query time by [defining a vectorize
795
795
```
796
796
797
797
> [!NOTE]
798
-
> The Azure AI Vision vectorizer and Azure AI Foundry model catalog vectorizer are in public preview. If you want to call these vectorizers, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/indexes/create?view=rest-searchservice-2025-03-01-preview).
798
+
> The Azure AI Vision vectorizer and Azure AI Foundry model catalog vectorizer are in public preview. If you want to call these vectorizers, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/indexes/create?view=rest-searchservice-2025-03-01-preview&preserve-view=true).
799
799
800
800
<!--### [Python](#tab/vectorizer-python)
801
801
@@ -868,7 +868,7 @@ In this section, you verify that your content was successfully indexed by [creat
868
868
```
869
869
870
870
> [!NOTE]
871
-
> The Azure AI Vision vectorizer is in public preview. If you previously called this vectorizer, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-03-01-preview).
871
+
> The Azure AI Vision vectorizer is in public preview. If you previously called this vectorizer, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-03-01-preview&preserve-view=true).
872
872
873
873
For queries that invoke integrated vectorization, `kind` must be set to `text`, and `text` must specify a text string. This string is passed to the vectorizer assigned to the vector field. For more information, see [Query with integrated vectorization](vector-search-how-to-query.md#query-with-integrated-vectorization).
874
874
@@ -877,7 +877,7 @@ In this section, you verify that your content was successfully indexed by [creat
877
877
<!--
878
878
879
879
> [!NOTE]
880
-
> The Azure AI Vision vectorizer and Azure AI Foundry model catalog vectorizer are in public preview. If you previously called these vectorizers, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-03-01-preview).
880
+
> The Azure AI Vision vectorizer and Azure AI Foundry model catalog vectorizer are in public preview. If you previously called these vectorizers, use a preview API, such as [`2025-03-01-preview`](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-03-01-preview&preserve-view=true).
0 commit comments