OCR and image analysis data sources, standalone files and PDFs

Author: HeidiSteen

articles/search/.openpublishing.redirection.search.json

@@ -1,5 +1,10 @@
 {
     "redirections": [
+        {
+            "source_path_from_root": "/articles/search/cognitive-search-quickstart-blob.md",
+            "redirect_url": "/azure/search/search-get-started-skillset",
+            "redirect_document_id": true
+        },
         {
             "source_path_from_root": "/articles/search/search-howto-connecting-azure-sql-database-to-azure-search-using-indexers.md",
             "redirect_url": "/azure/search/search-how-to-index-sql-database",

articles/search/cognitive-search-skill-image-analysis.md

@@ -23,11 +23,13 @@ This skill uses the machine learning models provided by [Azure AI Vision](/azure
 + The file size of the image must be less than 4 megabytes (MB)
 + The dimensions of the image must be greater than 50 x 50 pixels
 
+Supported data sources for OCR and image analysis are blobs in Azure Blob Storage and Azure Data Lake Storage (ADLS) Gen2, and image content in OneLake. Images can be standalone files or embedded images in a PDF or other files.
+
 This skill is implemented using the [AI Image Analysis API](/azure/ai-services/computer-vision/overview-image-analysis) version 3.2. If your solution requires calling a newer version of that service API (such as version 4.0), consider implementing through [Web API custom skill](cognitive-search-custom-skill-web-api.md).
 
 > [!NOTE]
 > This skill is bound to Azure AI services and requires [a billable resource](cognitive-search-attach-cognitive-services.md) for transactions that exceed 20 documents per indexer per day. Execution of built-in skills is charged at the existing [Azure AI services pay-as-you go price](https://azure.microsoft.com/pricing/details/cognitive-services/).
-> 
+>
 > In addition, image extraction is [billable by Azure AI Search](https://azure.microsoft.com/pricing/details/search/).
 >
 

articles/search/cognitive-search-skill-ocr.md

@@ -22,14 +22,16 @@ An OCR skill uses the machine learning models provided by [Azure AI Vision](/azu
 
 + For Greek and Serbian Cyrillic, the legacy [OCR in version 3.2](https://github.com/Azure/azure-rest-api-specs/tree/master/specification/cognitiveservices/data-plane/ComputerVision/stable/v3.2) API is used.
 
-The **OCR** skill extracts text from image files. Supported file formats include:
+The **OCR** skill extracts text from image files and embedded images. Supported file formats include:
 
 + .JPEG
 + .JPG
 + .PNG
 + .BMP
 + .TIFF
 
+Supported data sources for OCR and image analysis are blobs in Azure Blob Storage and Azure Data Lake Storage (ADLS) Gen2, and image content in OneLake. Images can be standalone files or embedded images in a PDF or other files.
+
 > [!NOTE]
 > This skill is bound to Azure AI services and requires [a billable resource](cognitive-search-attach-cognitive-services.md) for transactions that exceed 20 documents per indexer per day. Execution of built-in skills is charged at the existing [Azure AI services pay-as-you go price](https://azure.microsoft.com/pricing/details/cognitive-services/).
 >

articles/search/search-get-started-portal-import-vectors.md

@@ -42,7 +42,7 @@ The **Import and vectorize data** wizard supports the following data sources:
 + [Azure SQL Database](/azure/azure-sql/database/single-database-create-quickstart), [Azure SQL Managed Instance](/azure/azure-sql/managed-instance/instance-create-quickstart), and Azure SQL Server virtual machines.
 
 > [!NOTE]
-> This quicktart provides steps for just those data sources that work with whole files: Azure Blob storage, ADLS Gen2, OneLake. To use the wizard with other data sources, see [Azure Table indexer](search-howto-indexing-azure-tables.md), [Cosmos DB for NoSQL indexer](search-howto-index-cosmosdb.md), and [Azuer SQL indexer](search-how-to-index-sql-database.md).
+> This quicktart provides steps for just those data sources that work with whole files: Azure Blob sSazure-tables.md), [Cosmos DB for NoSQL indexer](search-howto-index-cosmosdb.md), and [Azuer SQL indexer](search-how-to-index-sql-database.md).
 
 ### Supported embedding models
 

articles/search/cognitive-search-quickstart-blob.md renamed to articles/search/search-get-started-skillset.md

@@ -10,7 +10,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: quickstart
-ms.date: 10/15/2024
+ms.date: 11/20/2024
 ---
 
 # Quickstart: Create a skillset in the Azure portal
@@ -84,6 +84,8 @@ If you get *Error detecting index schema from data source*, the indexer that pow
 
 Next, configure AI enrichment to invoke OCR, image analysis, and natural language processing. 
 
+OCR and image analysis are available for blobs in Azure Blob Storage and Azure Data Lake Storage (ADLS) Gen2, and for image content in OneLake. Images can be standalone files or embedded images in a PDF or other files.
+
 1. For this quickstart, we're using the **Free** Azure AI services resource. The sample data consists of 14 files, so the free allotment of 20 transactions on Azure AI services is sufficient for this quickstart. 
 
    :::image type="content" source="media/cognitive-search-quickstart-blob/cog-search-attach.png" alt-text="Screenshot of the Attach Azure AI services tab." border="true":::

articles/search/search-import-data-portal.md

@@ -59,7 +59,9 @@ Microsoft hosts sample data so that you can omit a data source configuration ste
 
 ### Skills
 
-The wizards generate skillset and output field mappings based on options you select. You can modify a skillset's JSON definition to add more skills later. Text Split and Text Merge are added for data chunking if you choose an embedding model, and for other skills if the granularity is set to pages or sentences. Shaper is added if you configure a knowledge store.
+The wizards generate skillset and output field mappings based on options you select. You can modify a skillset's JSON definition to add more skills later.
+
+OCR and image analysis options are available for blobs and whole-file indexing in OneLake, assuming the default parsing mode. Shaper is added if you configure a knowledge store. Text Split and Text Merge are added for data chunking if you choose an embedding model, and for other skills if the granularity is set to pages or sentences.
 
 | Skills | Import data wizard | Import and vectorize data wizard |
 |------|--------------------|----------------------------------|
@@ -68,9 +70,11 @@ The wizards generate skillset and output field mappings based on options you sel
 | [Azure Machine Learning (AI Studio model catalog)](cognitive-search-aml-skill.md)  | ❌ | ✅ |
 | [Document layout](cognitive-search-skill-document-intelligence-layout.md)  | ❌ | ✅ |
 | [Entity recognition](cognitive-search-skill-entity-recognition-v3.md)  | ✅ | ❌ |
+| [Image analysis (applies to blobs, default parsing, whole file indexing](cognitive-search-skill-image-analysis.md)  | ✅ | ❌ |
 | [Keyword extraction](cognitive-search-skill-keyphrases.md)  | ✅ | ❌ |
 | [Language detection](cognitive-search-skill-language-detection.md)  | ✅ | ❌ |
 | [Text translation](cognitive-search-skill-text-translation.md)  | ✅ | ❌ |
+| [OCR (applies to blobs, default parsing, whole file indexing)](cognitive-search-skill-ocr.md)  | ✅ | ✅ |
 | [PII detection](cognitive-search-skill-pii-detection.md)  | ✅ | ❌ |
 | [Sentiment analysis](cognitive-search-skill-sentiment.md)  | ✅ | ❌ |
 | [Shaper (applies to knowledge store)](cognitive-search-skill-shaper.md)  | ✅ | ❌ |

articles/search/toc.yml

@@ -37,7 +37,7 @@ items:
     - name: Create a demo app
       href: search-create-app-portal.md
     - name: Create a skillset
-      href: cognitive-search-quickstart-blob.md
+      href: search-get-started-skillset.md
     - name: Create a knowledge store
       href: knowledge-store-create-portal.md
     - name: Query with Search Explorer