@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: error-reference
 ms.date: 10/14/2025
 ms.update-cycle: 180-days
 ---

@@ -7,7 +7,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: concept-article
 ms.date: 05/27/2025
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/06/2025
 ms.update-cycle: 180-days
 ---

@@ -7,7 +7,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: best-practice
 ms.date: 05/08/2025
 ms.update-cycle: 365-days
 ---

@@ -5,7 +5,7 @@ description: Demonstrates using the Bing Entity Search service in a custom skill
 author: gmndrg
 ms.author: gimondra
 ms.service: azure-ai-search
-ms.topic: article
+ms.topic: how-to
 ms.date: 01/18/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 01/18/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 04/14/2025
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/21/2025
 ms.update-cycle: 365-days
 ---

@@ -9,7 +9,7 @@ ms.custom:
   - ignite-2023
   - build-2024
   - ignite-2024
-ms.topic: article
+ms.topic: reference
 ms.date: 11/04/2025
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
   - build-2024
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
   - build-2024
-ms.topic: article
+ms.topic: reference
 ms.date: 10/23/2025
 ---
 

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -9,7 +9,7 @@ ms.service: azure-ai-search
 ms.custom:
   - references_regions
   - ignite-2025
-ms.topic: article
+ms.topic: reference
 ms.date: 11/10/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.custom:
   - references_regions
   - ignite-2024
-ms.topic: article
+ms.topic: reference
 ms.date: 01/16/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - build-2025
-ms.topic: article
+ms.topic: reference
 ms.date: 10/23/2025
 ---
 

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 09/17/2025
 ---
 

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: reference
 ms.date: 01/07/2026
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.custom:
   - build-2024
   - references_regions
-ms.topic: article
+ms.topic: reference
 ms.date: 01/16/2026
 ---
 

@@ -5,16 +5,16 @@ description: Skillsets are used to apply AI processing to indexing pipelines in
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
-ms.date: 07/11/2025
+ms.topic: concept-article
+ms.date: 01/26/2026
 ms.update-cycle: 180-days
 ---
 
 # Skillset concepts in Azure AI Search
 
-This article is for developers who need a deeper understanding of skillset composition, and assumes familiarity with the high-level concepts of [AI enrichment](cognitive-search-concept-intro.md), or applied AI, in Azure AI Search.
+This article is for developers who need a deeper understanding of skillset composition, and assumes familiarity with the high-level concepts of [AI enrichment](cognitive-search-concept-intro.md) or how AI is applied in Azure AI Search to transform raw content during indexing.
 
-A skillset is a reusable object in Azure AI Search that's attached to [an indexer](search-indexer-overview.md). It contains one or more skills that call built-in AI or external custom processing over documents retrieved from an external data source.
+A skillset is a reusable object in Azure AI Search that's attached to [an indexer](search-indexer-overview.md). It contains one or more skills that call built-in AI or external custom processing over raw content retrieved from an external data source.
 
 The following diagram illustrates the basic data flow of skillset execution. 
 

@@ -7,7 +7,7 @@ ms.author: robertlee
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/21/2025
 ---
 

@@ -7,7 +7,7 @@ ms.author: jlembicz
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 01/21/2026
 ---
 

@@ -6,7 +6,7 @@ manager: nitinme
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: how-to
 ms.date: 09/11/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -7,7 +7,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 08/27/2025
 ms.update-cycle: 365-days
 ---

@@ -6,7 +6,7 @@ author: HeidiSteen
 manager: nitinme
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/21/2025
 ms.update-cycle: 180-days
 ms.custom:

@@ -6,7 +6,7 @@ author: HeidiSteen
 ms.author: heidist
 manager: nitinme
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: how-to
 ms.date: 10/21/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -6,7 +6,7 @@ manager: nitinme
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/21/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -5,7 +5,7 @@ description: Define the data structures in a knowledge store by creating data sh
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/21/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -6,7 +6,7 @@ manager: nitinme
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/21/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -3,7 +3,7 @@ title: Multimodal Search Concepts and Guidance
 titleSuffix: Azure AI Search
 description: Learn what multimodal search is, how Azure AI Search supports it for text and image content, and where to find detailed concepts, tutorials, and samples.
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/21/2025
 author: gmndrg
 ms.author: gimondra

@@ -5,7 +5,7 @@ description: Use existing code samples or build your own tools for working with
 author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 07/28/2025
 ms.update-cycle: 365-days
 ---

@@ -6,7 +6,7 @@ manager: nitinme
 author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 04/07/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: heidist
 manager: nitinme
 ms.date: 01/15/2026
 ms.service: azure-ai-search
-ms.topic: article
+ms.topic: concept-article
 ms.custom:
   - ignite-2023
   - ignite-2024

@@ -6,7 +6,7 @@ author: HeidiSteen
 manager: nitinme
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 07/11/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -10,7 +10,7 @@ ms.custom:
   - ignite-2023
   - build-2024
   - ignite-2024
-ms.topic: conceptual
+ms.topic: upgrade-and-migration-article
 ms.date: 12/17/2025
 ---
 

@@ -9,7 +9,7 @@ ms.service: azure-ai-search
 ms.custom:
   - build-2024
   - ignite-2024
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 12/17/2025
 ---
 

@@ -12,7 +12,7 @@ ms.custom:
   - devx-track-js
   - devx-track-python
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/21/2025
 ---
 

@@ -6,7 +6,7 @@ manager: nitinme
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: article
+ms.topic: concept-article
 ms.date: 10/06/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -9,7 +9,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
   - ignite-2024
-ms.topic: article
+ms.topic: how-to
 ms.date: 11/19/2025
 ms.update-cycle: 180-days
 ---

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/21/2025
 ---
 

@@ -6,7 +6,7 @@ author: gmndrg
 ms.author: gimondra
 ms.date: 11/18/2025
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.custom:
   - build-2025
 ---

@@ -10,7 +10,7 @@ ms.devlang: csharp
 ms.custom:
   - devx-track-dotnet
   - ignite-2023
-ms.topic: conceptual
+ms.topic: upgrade-and-migration-article
 ms.date: 02/24/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
 ms.devlang: csharp
-ms.topic: conceptual
+ms.topic: upgrade-and-migration-article
 ms.date: 05/29/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -8,8 +8,8 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2024
-ms.topic: conceptual
-ms.date: 08/13/2025
+ms.topic: concept-article
+ms.date: 01/23/2026
 ---
 
 # Features of Azure AI Search
@@ -21,20 +21,31 @@ The following table summarizes features by category. There's feature parity in a
 > [!NOTE]
 > Looking for preview features? See the [preview features list](search-api-preview.md).
 
+## Agentic retrieval
+
+| Category                             | Features |
+|-------------------|----------|
+| Knowledge bases | [**Knowledge bases (preview)**](agentic-retrieval-how-to-create-knowledge-base.md) orchestrate the agentic retrieval pipeline, connecting to your LLM and managing query parameters. A knowledge base references one or more knowledge sources and defines the retrieval behavior. |
+| Knowledge sources | [**Knowledge sources (preview)**](agentic-knowledge-source-overview.md) specify the content used for agentic retrieval. Create knowledge sources from [search indexes](agentic-knowledge-source-how-to-search-index.md), [Azure Blob Storage](agentic-knowledge-source-how-to-blob.md), [OneLake](agentic-knowledge-source-how-to-onelake.md), [SharePoint (indexed)](agentic-knowledge-source-how-to-sharepoint-indexed.md), [SharePoint (remote)](agentic-knowledge-source-how-to-sharepoint-remote.md), or [web (Bing)](agentic-knowledge-source-how-to-web.md). |
+| Query planning | Query planning uses an LLM to analyze conversation context and break down complex questions into focused subqueries. This includes chat history processing, query decomposition, synonym expansion, and spelling correction. |
+| Parallel query execution | Subqueries run simultaneously across all knowledge sources. Each subquery supports keyword, vector, and hybrid search with automatic semantic reranking. |
+| Retrieval reasoning effort | [**Retrieval reasoning effort (preview)**](agentic-retrieval-how-to-set-retrieval-reasoning-effort.md) controls the level of LLM processing in the pipeline. Set to minimal for speed (no LLM), low for balanced processing, or medium for maximum relevance optimization. |
+| Response synthesis | Results are combined into a unified response with three parts: merged content for grounding data, source references for citations, and execution details showing the query plan. |
+
 ## Indexing and data extraction
 
 | Category                             | Features |
 |-------------------|----------|
-| Data sources | Search indexes can accept text from any source, provided it's submitted as a JSON document. </br></br> [**Indexers**](search-indexer-overview.md) are a feature that automates data import from supported data sources to extract searchable content in primary data stores. Indexers handle JSON serialization for you and most support some form of change and deletion detection. You can connect to a [variety of data sources](search-data-sources-gallery.md), including [Microsoft OneLake](search-how-to-index-onelake-files.md), [Azure SQL Database](search-how-to-index-sql-database.md), [Azure Cosmos DB](search-how-to-index-cosmosdb-sql.md), or [Azure Blob storage](search-how-to-index-azure-blob-storage.md).  </br></br>[**Logic Apps connectors (preview)**](search-how-to-index-logic-apps.md) give you access to a broader range of data sources, including data on other cloud platforms. This indexing and enrichment pipeline is created in Azure AI Search but managed in Azure Logic Apps.|
+| Data sources | Search indexes can accept text from any source, provided it's submitted as a JSON document. </br></br> [**Indexers**](search-indexer-overview.md) are a feature that automates data import from supported data sources to extract searchable content in primary data stores. Indexers handle JSON serialization for you and most support some form of change and deletion detection. You can connect to a [variety of data sources](search-data-sources-gallery.md), including [Microsoft OneLake](search-how-to-index-onelake-files.md), [Azure SQL Database](search-how-to-index-sql-database.md), [Azure Cosmos DB](search-how-to-index-cosmosdb-sql.md), or [Azure Blob storage](search-how-to-index-azure-blob-storage.md).  </br></br>[**Logic Apps connectors (preview)**](search-how-to-index-logic-apps.md) give you access to a broader range of data sources, including data on other cloud platforms. This indexing and enrichment pipeline is created in Azure AI Search but managed in Azure Logic Apps. </br></br>[**Knowledge sources (preview)**](agentic-knowledge-source-overview.md) are a feature of agentic retrieval. They're used during indexing and at query time to support a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).|
 | Hierarchical and nested data structures | [**Complex types**](search-howto-complex-data-types.md) and collections allow you to model virtually any type of JSON structure within a search index. One-to-many and many-to-many cardinality can be expressed natively through collections, complex types, and collections of complex types.|
-| Linguistic analysis | Analyzers are components used for text processing during indexing and search operations. By default, you can use the general-purpose Standard Lucene analyzer, or override the default with a language analyzer, a custom analyzer that you configure, or another predefined analyzer that produces tokens in the format you require. </br></br>[**Language analyzers**](index-add-language-analyzers.md) from Lucene or Microsoft are used to intelligently handle language-specific linguistics including verb tenses, gender, irregular plural nouns (for example, 'mouse' vs. 'mice'), word decompounding, word-breaking (for languages with no spaces), and more. </br></br>[**Custom lexical analyzers**](index-add-custom-analyzers.md) are used for complex query forms such as phonetic matching and regular expressions.</br></br> |
+| Linguistic analysis | Analyzers are components of classic search used for text processing during indexing and search operations. By default, you can use the general-purpose Standard Lucene analyzer, or override the default with a language analyzer, a custom analyzer that you configure, or another predefined analyzer that produces tokens in the format you require. </br></br>[**Language analyzers**](index-add-language-analyzers.md) from Lucene or Microsoft are used to intelligently handle language-specific linguistics including verb tenses, gender, irregular plural nouns (for example, 'mouse' vs. 'mice'), word decompounding, word-breaking (for languages with no spaces), and more. </br></br>[**Custom lexical analyzers**](index-add-custom-analyzers.md) are used for complex query forms such as phonetic matching and regular expressions.</br></br> |
 
 ## Chat model and agent integration
 
 | Category&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;  | Features |
 |-------------------|----------|
 | Chat completion models used during indexing | [**GenAI prompt skill (preview)**](cognitive-search-skill-genai-prompt.md) is a skill that calls a large language model during indexing and provides a prompt that determines the task. You decide what the task is. It might describing an image, summarizing or manipulating content, or any task the model can perform. Output is added as a new field in a searchable index. |
-| Chat completion models used at query time | [**Agentic retrieval (preview)**](agentic-retrieval-overview.md) uses a large language model for query planning, decomposing and paraphrasing complex queries for better query coverage over your index. Responses from agentic retrieval are designed for agent-to-agent workflows. You can pass search results as single large string, which simplifies agent consumption of your proprietary content. The response also includes citations and query execution information. </br></br>[**RAG patterns**](retrieval-augmented-generation-overview.md) can be implemented using existing capabilities. The ability to [tune for relevance](search-relevance-overview.md) and construct hybrid queries improve the quality of the content sent to chat bots for answer generation. |
+| Chat completion models used at query time | [**Agentic retrieval (preview)**](agentic-retrieval-overview.md) uses a large language model for query planning, decomposing and paraphrasing complex queries for better query coverage over your index. Responses from agentic retrieval are designed for agent-to-agent workflows. You can pass search results as single large string, which simplifies agent consumption of your proprietary content. The response also includes citations and query execution information. </br></br>[**Answer synthesis (preview)**](agentic-retrieval-how-to-answer-synthesis.md) uses the LLM to generate citation-backed responses from search results returned by agentic retrieval. </br></br>[**RAG patterns**](retrieval-augmented-generation-overview.md) can be implemented using existing capabilities. The ability to [tune for relevance](search-relevance-overview.md) and construct hybrid queries improve the quality of the content sent to chat bots for answer generation. |
 
 ## Applied AI and AI enriched content
 
@@ -57,7 +68,7 @@ The following table summarizes features by category. There's feature parity in a
 | Integrated data chunking and vectorization | Native data chunking through [Text Split skill](cognitive-search-skill-textsplit.md). Native vectorization through [vectorizers](vector-search-how-to-configure-vectorizer.md) and embedding skills such as [Azure OpenAI Embedding](cognitive-search-skill-azure-openai-embedding.md), [Azure Vision multimodal](cognitive-search-skill-vision-vectorize.md), and [AML](cognitive-search-aml-skill.md) that you can use to connect to endpoints in the Microsoft Foundry model catalog. </p>[**Integrated vectorization**](vector-search-integrated-vectorization.md) provides an end-to-end indexing pipeline from source files to queries.|
 | Integrated vector compression and quantization | Use [built-in scalar and binary quantization](vector-search-how-to-quantization.md) to reduce vector index size in memory and on disk. You can also forego storage of vectors you don't need, or assign narrow data types to vector fields for reduced storage requirements. |
 
-## Full text and other query forms
+## Classic full text and other query forms
 
 | Category&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;  | Features |
 |-------------------|----------|
@@ -87,7 +98,7 @@ The following table summarizes features by category. There's feature parity in a
 
 | Category&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;  | Features |
 |-------------------|----------|
-| REST | [**Service REST API**](/rest/api/searchservice/) is for data plane operations, including all operations related to indexing, queries, and AI enrichment. You can also use this client library to retrieve system information and statistics. </br></br>[**Management REST API**](/rest/api/searchmanagement/) is for service creation and provisioning through Azure Resource Manager. You can also use this API to manage keys and capacity.|
+| REST | [**Service REST API**](/rest/api/searchservice/) is for data plane operations, including all operations related to indexing, queries, and AI enrichment. You can also use this client library to retrieve system information and statistics. </br></br>[**Knowledge Retrieval API (preview)**](/rest/api/searchservice/knowledge-retrieval/retrieve?view=rest-searchservice-2025-11-01-preview&preserve-view=true) is for agentic retrieval operations, including knowledge sources, knowledge bases, and retrieve actions. </br></br>[**Management REST API**](/rest/api/searchmanagement/) is for service creation and provisioning through Azure Resource Manager. You can also use this API to manage keys and capacity.|
 | Azure SDK for .NET | [**Azure.Search.Documents**](/dotnet/api/overview/azure/search.documents-readme) is for data plane operations, including all operations related to indexing, queries, and AI enrichment. You can also use this client library to retrieve system information and statistics. </br></br>[**Microsoft.Azure.Management.Search**](/dotnet/api/microsoft.azure.management.search) is for service creation and provisioning through Azure Resource Manager. You can also use this API to manage keys and capacity.|
 | Azure SDK for Java | [**com.azure.search.documents**](/java/api/com.azure.search.documents) is for data plane operations, including all operations related to indexing, queries, and AI enrichment. You can also use this client library to retrieve system information and statistics. </br></br>[**com.microsoft.azure.management.search**](/java/api/overview/azure/search/management) is for service creation and provisioning through Azure Resource Manager. You can also use this API to manage keys and capacity.|
 | Azure SDK for Python | [**azure-search-documents**](/python/api/overview/azure/search-documents-readme) is for data plane operations, including all operations related to indexing, queries, and AI enrichment. You can also use this client library to retrieve system information and statistics. </br></br>[**azure-mgmt-search**](/python/api/azure-mgmt-search/) is for service creation and provisioning through Azure Resource Manager. You can also use this API to manage keys and capacity. |

@@ -7,7 +7,7 @@ author: mattgotteiner
 ms.author: magottei
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 05/08/2025
+ms.date: 01/23/2026
 ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023

@@ -8,48 +8,39 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 05/08/2025
+ms.date: 01/26/2026
 ms.update-cycle: 180-days
 ---
 
 # Define an index projection for parent-child indexing
 
-For indexes containing chunked documents, an *index projection* specifies how parent-child content is mapped to fields in a search index for one-to-many indexing. Through an index projection, you can send content to:
+If you're chunking content for either a RAG pattern or vectorization, you can specify an *index projection* to control whether elements of the parent document, such as a file name or creation date, repeat for each child (chunk) or are indexed as standalone search documents in a second index.
 
-- A single index, where the parent fields repeat for each chunk, but the grain of the index is at the chunk level. The [classic RAG example](https://github.com/Azure-Samples/azure-search-classic-rag/blob/main/README.md) shows this approach.
-
-- Two or more indexes, where the parent index has fields related to the parent document, and the child index is organized around chunks. The child index is the primary search corpus, but the parent index could be used for [lookup queries](/rest/api/searchservice/documents/get) when you want to retrieve the parent fields of a particular chunk, or for independent queries.
-
-Most implementations are a single index organized around chunks with parent fields, such as the document filename, repeating for each chunk. However, the system is designed to support separate and multiple child indexes if that's your requirement. Azure AI Search doesn't support index joins so your application code must handle which index to use.
+We recommend repeating fields in a single index because splitting content into two indexes can be difficult to query, especially in classic search where index joins aren't supported.
 
-An index projection is defined in a [skillset](cognitive-search-working-with-skillsets.md). It's responsible for coordinating the indexing process that sends chunks of content to a search index, along with the parent content associated with each chunk. It improves how native data chunking works by giving your more options for controlling how parent-child content is indexed.
-
-This article explains how to create a single index schema and indexer projection patterns for one-to-many indexing.
+In Azure AI Search, chunking is performed by skills and thus depends on indexers. To define an index projection, specify it in a [skillset](cognitive-search-working-with-skillsets.md). 
 
 ## Prerequisites
 
 - An [indexer-based indexing pipeline](search-indexer-overview.md).
 
 - An index (one or more) that accepts the output of the indexer pipeline.
 
-- A [supported data source](search-indexer-overview.md#supported-data-sources) having content that you want to chunk. It can be vector or nonvector content.
+- A [supported data source](search-indexer-overview.md#supported-data-sources) having content that you want to chunk.
 
 - A skill that splits content into chunks, either the [Text Split skill](cognitive-search-skill-textsplit.md) or a custom skill that provides equivalent functionality. 
 
 The skillset contains the indexer projection that shapes the data for one-to-many indexing. A skillset could also have other skills, such as an embedding skill like [AzureOpenAIEmbedding](cognitive-search-skill-azure-openai-embedding.md) if your scenario includes integrated vectorization.
 
-### Dependency on indexer processing
+### Choose an approach
 
-One-to-many indexing takes a dependency on skillsets and indexer-based indexing that includes the following four components:
+Through an index projection, you can send content to:
 
-- A data source
-- One or more indexes for your searchable content
-- A skillset that contains an index projection*
-- An indexer
+- A single index, where the parent fields repeat for each chunk, but the grain of the index is at the chunk level. The [classic RAG example](https://github.com/Azure-Samples/azure-search-classic-rag/blob/main/README.md) shows this approach.
 
-Your data can originate from any supported data source, but the assumption is that the content is large enough that you want to chunk it, and the reason for chunking it is that you're implementing a RAG pattern that provides grounding data to a chat model. Or, you're implementing vector search and need to meet the smaller input size requirements of embedding models.
+- Two or more indexes, where the parent index has fields related to the parent document, and the child index is organized around chunks. The child index is the primary search corpus, but the parent index could be used for [lookup queries](/rest/api/searchservice/documents/get) when you want to retrieve the parent fields of a particular chunk, or for independent queries.
 
-Indexers load indexed data into a predefined index. How you define the schema and whether to use one or more indexes is the first decision to make in a one-to-many indexing scenario. The next section covers index design.
+Most implementations are a single index organized around chunks with parent fields, such as the document filename, repeating for each chunk. However, the system is designed to support separate and multiple child indexes if that's your requirement. Azure AI Search doesn't support index joins so your application code must handle which index to use.
 
 ## Create an index for one-to-many indexing
 

@@ -8,7 +8,7 @@ ms.author: arjagann
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 01/14/2026
 ms.update-cycle: 365-days
 ---

@@ -5,7 +5,7 @@ description: Use an Azure Logic Apps workflow for automated indexing in Azure AI
 author: HeidiSteen
 ms.author: heidist
 manager: nitinme
-ms.date: 09/28/2025
+ms.date: 01/23/2026
 ms.service: azure-ai-search
 ms.topic: how-to
 ms.custom:
@@ -130,7 +130,6 @@ It also supports the following query actions:
 + Deletion detection isn't supported. You must manually [delete orphaned documents](search-how-to-delete-documents.md#delete-a-single-document) from the index.
 + Duplicate documents in the search index are a known issue in this preview. Consider deleting objects and starting over if this becomes an issue.
 + No support for private endpoints in the logic app workflow created by the portal wizard. The workflow is hosted using the [**Consumption** hosting option](/azure/logic-apps/single-tenant-overview-compare) and is subject to its constraints. To use the **Standard** hosting option, use a programmatic approach to creating the workflow.
-+ All actions are generally available except for 
 
 ## Create a logic app workflow
 

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/06/2025
 ms.update-cycle: 180-days
 ---

@@ -6,7 +6,7 @@ author: mattgotteiner
 ms.author: magottei
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 01/27/2025
+ms.date: 01/23/2026
 ms.update-cycle: 365-days
 ms.custom: sfi-ropc-nochange
 ---

@@ -7,100 +7,44 @@ author: mrcarter8
 ms.author: mcarter
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 12/15/2025
+ms.date: 01/23/2026
 ms.update-cycle: 180-days
 ms.custom:
   - ignite-2024
   - sfi-image-nochange
+  - dev-focus
+ai-usage: ai-assisted
 ---
 
 # Make outbound connections through a shared private link
 
-This article explains how to configure private, outbound calls from Azure AI Search to an Azure resource that runs within an Azure virtual network.
+This article explains how to configure a *shared private link* for private, outbound connections from Azure AI Search to an Azure resource running in a virtual network. With a shared private link, the search service connects to a virtual network IP address instead of a public endpoint.
 
-Setting up a private connection allows a search service to connect to a virtual network IP address instead of a port that's open to the internet. The object created for the connection is called a *shared private link*. On the connection, the search service uses the shared private link internally to reach an Azure resource inside the network boundary.
-
-Shared private link is a premium feature that's billed by usage. When you set up a shared private link, charges for the private endpoint are added to your Azure invoice. As you use the shared private link, data transfer rates for inbound and outbound access are also invoiced. For details, see [Azure Private Link pricing](https://azure.microsoft.com/pricing/details/private-link/).
+Shared private link is a premium feature billed by usage. For details, see [Azure Private Link pricing](https://azure.microsoft.com/pricing/details/private-link/).
 
 > [!NOTE]
-> If you're setting up a private indexer connection to a SQL Managed Instance, see [this article](search-indexer-how-to-access-private-sql.md) instead for steps specific to that resource type.
-
-## When to use a shared private link
-
-Azure AI Search makes outbound calls to other Azure resources in the following scenarios:
-
-+ Knowledge base connections to Azure OpenAI for agentic retrieval workflows
-+ Indexer or query connections to Azure OpenAI or Azure Vision in Foundry Tools for vectorization
-+ Indexer connections to supported data sources
-+ Indexer (skillset) connections to Azure Storage for caching enrichments, debug session sate, or writing to a knowledge store
-+ Indexer (skillset) connections to Foundry Tools for billing purposes
-+ Encryption key requests to Azure Key Vault
-+ Custom skill requests to Azure Functions or similar resource
-
-Shared private links only work for Azure-to-Azure connections. If you're connecting to OpenAI or another external model provider, the connection must be over the public internet.
-
-Shared private links are for operations and data accessed through a [private endpoint](/azure/private-link/private-endpoint-overview) for Azure resources or clients that run in an Azure virtual network.
-
-A shared private link is:
-
-+ Created using Azure AI Search tooling, APIs, or SDKs
-+ Approved by the Azure resource owner
-+ Used internally by Azure AI Search on a private connection to a specific Azure resource
-
-Only your search service can use the private links that it creates, and there can be only one shared private link created on your service for each resource and subresource combination.
-
-Once you set up the private link, it's used automatically whenever the search service connects to that resource. You don't need to modify the connection string or alter the client you're using to issue the requests, although the device used for the connection must connect using an authorized IP in the Azure resource's firewall.
-
-There are two scenarios for using [Azure Private Link](/azure/private-link/private-link-overview) and Azure AI Search together.
-
-+ Scenario one: create a shared private link when an *outbound* (indexer or knowledge base) connection to Azure requires a private connection.
-
-+ Scenario two: [configure search for a private *inbound* connection](service-create-private-endpoint.md) from clients that run in a virtual network.
-
-Scenario one is covered in this article.
-
-While both scenarios have a dependency on Azure Private Link, they're independent. You can create a shared private link without having to configure your own search service for a private endpoint.
-
-### Limitations
-
-When evaluating shared private links for your scenario, remember these constraints.
-
-+ Several of the resource types used in a shared private link are in preview. If you're connecting to a preview resource (Azure Database for MySQL or Azure SQL Managed Instance), use a preview version of the Management REST API to create the shared private link. These versions include `2020-08-01-preview`, `2021-04-01-preview`, `2024-03-01-preview`, `2024-06-01-preview`, and `2025-02-01-preview`. We recommend the latest preview API.
-
-+ Indexer execution must use the [private execution environment](search-howto-run-reset-indexers.md#indexer-execution-environment) that's specific to your search service. Private endpoint connections aren't supported from the multitenant content processing environment. The configuration setting for this requirement is covered in this article.
-
-+ Review shared private link [resource limits for each tier](search-limits-quotas-capacity.md#shared-private-link-resource-limits).
-
-+ The resource type `Microsoft.CognitiveServices/accounts` for kind `AIServices` isn't currently supported.  This means that shared private link for Foundry resources with this kind can't be created at this time. If you require to use an Azure OpenAI embedding model for your skill or vectorizer, and need private communication, create an Azure OpenAI resource and a shared private link with the `Microsoft.CognitiveServices/accounts` with subtype `openai_account` as a workaround.
+> If you're setting up a private indexer connection to a SQL Managed Instance, see [Create a shared private link for SQL Managed Instance](search-indexer-how-to-access-private-sql.md) instead.
 
 ## Prerequisites
 
 + [A supported Azure resource](#supported-resource-types), configured to run in a virtual network.
 
-+ An Azure AI Search service with tier and region requirements, by workload:
++ An Azure AI Search service. Requirements vary by workload:
 
   | Workload | Tier requirements | Region requirements | Service creation requirements |
-  |----------|-------------------|---------------------|---------------------|
+  |----------|-------------------|---------------------|--------------------|
   | Indexers without skillsets | Basic and higher | None | None |
   | Skillsets with embedding skills ([integrated vectorization](vector-search-integrated-vectorization.md)) | Basic and higher | [High capacity regions](search-limits-quotas-capacity.md#partition-storage-gb) | [After April 3, 2024](search-how-to-upgrade.md#check-your-service-creation-or-upgrade-date) |
   | Skillsets using other [built-in](cognitive-search-predefined-skills.md) or custom skills | Standard 1 (S1) and higher | None | [After April 3, 2024](search-how-to-upgrade.md#check-your-service-creation-or-upgrade-date) |
-  | Knowledge bases calling Azure OpenAI for query planning or passing search results | Basic and higher | None | None |
+  | Knowledge bases calling Azure OpenAI | Basic and higher | None | None |
 
-+ Permissions on both Azure AI Search and the Azure resource:
++ **Contributor** or **Owner** role on both Azure AI Search and the target Azure resource, or the following specific permissions:
 
   | Resource | Permissions |
   |----------|-------------|
   | Azure AI Search | `Microsoft.Search/searchServices/sharedPrivateLinkResources/write`<br> `Microsoft.Search/searchServices/sharedPrivateLinkResources/read`<br> `Microsoft.Search/searchServices/sharedPrivateLinkResources/operationStatuses/read` |
   | Other Azure resource | Permission to approve private endpoint connections. For example, on Azure Storage, you need `Microsoft.Storage/storageAccounts/privateEndpointConnectionsApproval/action`. |
 
-<!-- + For [integrated vectorization](vector-search-integrated-vectorization.md) only, outbound connections through shared private link are supported on all billable tiers, on services [created after April 3, 2024](search-how-to-upgrade.md#check-your-service-creation-or-upgrade-date), in regions providing [higher capacity](search-limits-quotas-capacity.md#partition-storage-gb).  -->
-
-<!-- + For [AI enrichment](cognitive-search-concept-intro.md) and skillset processing, shared private link in services [created before April 3, 2024](search-how-to-upgrade.md#check-your-service-creation-or-upgrade-date), Azure AI Search must be Standard 2 (S2) or higher. -->
-
-<!-- + For [AI enrichment](cognitive-search-concept-intro.md) and skillset processing, shared private link in services [created after April 3, 2024](search-how-to-upgrade.md#check-your-service-creation-or-upgrade-date), Azure AI Search must be Standard 1 (S1) or higher. -->
-
-<!-- + For all other use cases, that don't involve skillsets, Azure AI Search can be Basic or higher. -->
-
 <a name="group-ids"></a>
 
 ### Supported resource types
@@ -440,6 +384,52 @@ After the indexer is created successfully, it should connect to the Azure resour
 
 1. Run the indexer. If the indexer execution succeeds and the search index is populated, the shared private link is working.
 
+## When to use a shared private link
+
+Azure AI Search makes outbound calls to other Azure resources in the following scenarios:
+
++ Knowledge base connections to Azure OpenAI for agentic retrieval workflows
++ Indexer or query connections to Azure OpenAI or Azure Vision in Foundry Tools for vectorization
++ Indexer connections to supported data sources
++ Indexer (skillset) connections to Azure Storage for caching enrichments, debug session state, or writing to a knowledge store
++ Indexer (skillset) connections to Foundry Tools for billing purposes
++ Encryption key requests to Azure Key Vault
++ Custom skill requests to Azure Functions or similar resource
+
+Shared private links only work for Azure-to-Azure connections. If you're connecting to OpenAI or another external model provider, the connection must be over the public internet.
+
+Shared private links are for operations and data accessed through a [private endpoint](/azure/private-link/private-endpoint-overview) for Azure resources or clients that run in an Azure virtual network.
+
+A shared private link is:
+
++ Created using Azure AI Search tooling, APIs, or SDKs
++ Approved by the Azure resource owner
++ Used internally by Azure AI Search on a private connection to a specific Azure resource
+
+Only your search service can use the private links that it creates, and there can be only one shared private link created on your service for each resource and subresource combination.
+
+Once you set up the private link, it's used automatically whenever the search service connects to that resource. You don't need to modify the connection string or alter the client you're using to issue the requests, although the device used for the connection must connect using an authorized IP in the Azure resource's firewall.
+
+There are two scenarios for using [Azure Private Link](/azure/private-link/private-link-overview) and Azure AI Search together:
+
++ Scenario one: create a shared private link when an *outbound* (indexer or knowledge base) connection to Azure requires a private connection. This scenario is covered in this article.
+
++ Scenario two: [configure search for a private *inbound* connection](service-create-private-endpoint.md) from clients that run in a virtual network.
+
+While both scenarios have a dependency on Azure Private Link, they're independent. You can create a shared private link without configuring your search service for a private endpoint.
+
+## Limitations
+
+When evaluating shared private links for your scenario, remember these constraints:
+
++ Several of the resource types used in a shared private link are in preview. If you're connecting to a preview resource (Azure Database for MySQL or Azure SQL Managed Instance), use a preview version of the Management REST API to create the shared private link. We recommend the [latest preview API](/rest/api/searchmanagement/operation-groups?view=rest-searchmanagement-2025-02-01-preview&preserve-view=true).
+
++ Indexer execution must use the [private execution environment](search-howto-run-reset-indexers.md#indexer-execution-environment) that's specific to your search service. Private endpoint connections aren't supported from the multitenant content processing environment. The configuration setting for this requirement is covered in this article.
+
++ Review shared private link [resource limits for each tier](search-limits-quotas-capacity.md#shared-private-link-resource-limits).
+
++ The resource type `Microsoft.CognitiveServices/accounts` for kind `AIServices` isn't currently supported. This means that shared private link for Foundry resources with this kind can't be created at this time. If you require to use an Azure OpenAI embedding model for your skill or vectorizer, and need private communication, create an Azure OpenAI resource and a shared private link with the `Microsoft.CognitiveServices/accounts` with subtype `openai_account` as a workaround.
+
 ## Troubleshooting
 
 + If your indexer creation fails with "Data source credentials are invalid," check the approval status of the shared private link before debugging the connection. If the status is `Approved`, check the `properties.provisioningState` property. If it's `Incomplete`, there might be a problem with underlying dependencies. In this case, reissue the `PUT` request to re-create the shared private link. You might also need to repeat the approval step.

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 06/23/2025
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.author: arjagann
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 05/12/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: gimondra
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: troubleshooting-general
 ms.date: 10/23/2025
 ms.update-cycle: 365-days
 ---

@@ -6,7 +6,7 @@ manager: nitinme
 author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: limits-and-quotas
 ms.date: 01/09/2026
 ms.update-cycle: 180-days
 ms.custom:

@@ -8,7 +8,7 @@ ms.author: jlembicz
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 03/07/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: haileytapia
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 05/29/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: how-to
 ms.date: 05/29/2025
 ms.update-cycle: 365-days
 ---

@@ -5,7 +5,7 @@ description: Learn about multi-region deployments in Azure AI Search, including
 author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 08/08/2025
 ms.update-cycle: 365-days
 ---

@@ -5,7 +5,7 @@ description: Learn about the tools, behaviors, and approaches for analyzing quer
 author: mattgotteiner
 ms.author: magottei
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 01/22/2026
 ms.update-cycle: 365-days
 ---

@@ -5,7 +5,7 @@ description: Learn about tips and best practices for maximizing performance on a
 author: mattgotteiner
 ms.author: magottei
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: best-practice
 ms.date: 08/01/2025
 ms.update-cycle: 365-days
 ---

@@ -3,7 +3,7 @@ title: Query-Time ACL and RBAC Enforcement
 titleSuffix: Azure AI Search  
 description: Learn how query-time ACL and RBAC enforcement ensures secure document retrieval in Azure AI Search for indexes containing permission filters from data sources such as Azure Data Lake Storage (ADLS) Gen2 and SharePoint in Microsoft 365.  
 ms.service: azure-ai-search  
-ms.topic: article  
+ms.topic: concept-article  
 ms.date: 01/15/2026  
 author: mattgotteiner  
 ms.author: magottei 

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 04/14/2025
 ms.update-cycle: 365-days
 ---

@@ -6,7 +6,7 @@ manager: nitinme
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 05/29/2025
 ms.update-cycle: 365-days
 ---

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: how-to
 ms.date: 04/14/2025
 ms.update-cycle: 365-days
 ---

@@ -3,7 +3,7 @@ title: Query-Time Microsoft Purview Sensitivity Label Enforcement in Azure AI Se
 titleSuffix: Azure AI Search  
 description: Learn how query-time enforcement of Microsoft Purview sensitivity labels ensures secure document retrieval in Azure AI Search for indexes containing label metadata.  
 ms.service: azure-ai-search  
-ms.topic: conceptual  
+ms.topic: concept-article  
 ms.date: 11/18/2025  
 author: gmndrg  
 ms.author: gimondra  

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 04/14/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: beloh
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 05/29/2025
 ms.update-cycle: 365-days
 ---

@@ -7,7 +7,7 @@ ms.author: haileytapia
 manager: nitinme
 ms.date: 11/19/2025
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.custom:
   - references_regions
   - build-2025

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: how-to
 ms.date: 04/14/2025
 ms.update-cycle: 365-days
 ---

@@ -10,7 +10,7 @@ ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023
   - horz-security
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 09/25/2025
 ---
 

@@ -10,7 +10,7 @@ ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 07/16/2025
+ms.date: 01/23/2026
 ---
 
 # Security filters for trimming results in Azure AI Search

@@ -6,7 +6,7 @@ manager: nitinme
 author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/06/2025
 ---
 

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: article
+ms.topic: concept-article
 ms.date: 06/20/2025
 ms.update-cycle: 365-days
 ---

@@ -9,12 +9,14 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: concept-article
-ms.date: 09/23/2025
+ms.date: 01/23/2026
 ---
 
 # Data import in Azure AI Search
 
-In Azure AI Search, queries execute over your content that's loaded into a [search index](search-what-is-an-index.md). This article describes the two basic workflows for populating an index: *push* your data into the index programmatically, or *pull* in the data using a [search indexer](search-indexer-overview.md).
+In Azure AI Search, queries execute over content that's loaded into a [search index](search-what-is-an-index.md), or over [remote knowledge sources](agentic-knowledge-source-overview.md#supported-knowledge-sources) if you use agentic retrieval.
+
+This article describes the two basic workflows for populating an index on a search service: *push* your data into the index programmatically, or *pull* in the data using a [search indexer](search-indexer-overview.md).
 
 Both approaches load documents from an external data source. Although you can create an empty index, it's not queryable until you add the content.
 
@@ -49,7 +51,6 @@ For an introduction to the push APIs, see:
 
 + [Quickstart: Full-text search](search-get-started-text.md)
 + [C# Tutorial: Optimize indexing with the push API](tutorial-optimize-indexing-push-api.md)
-+ [REST Quickstart: Create an Azure AI Search index using PowerShell](search-get-started-text.md)
 
 <a name="indexing-actions"></a>
 
@@ -69,7 +70,9 @@ Whether you use the REST API or an Azure SDK, the following document operations
 
 ## Pulling data into an index
 
-The pull model uses *indexers* connecting to a supported data source, automatically uploading the data into your index. Indexers from Microsoft are available for these platforms:
+The pull model uses *indexers* anx *Logic Apps workflows* connecting to a supported data source, automatically uploading the data into your index. 
+
+Indexers from Microsoft are available for these platforms:
 
 + [Azure Blob storage](search-how-to-index-azure-blob-storage.md)
 + [Azure Table storage](search-how-to-index-azure-tables.md)
@@ -80,9 +83,11 @@ The pull model uses *indexers* connecting to a supported data source, automatica
 + [Microsoft OneLake files and shortcuts](search-how-to-index-onelake-files.md)
 + [SharePoint in Microsoft 365 (preview)](search-how-to-index-sharepoint-online.md)
 
-You can use third-party connectors, developed and maintained by Microsoft partners. For more information and links, see [Data source gallery](search-data-sources-gallery.md).
+If you configure an [indexed knowledge source](agentic-knowledge-source-overview.md#supported-knowledge-sources) for agentic retrieval, Azure AI Search creates an indexer pipeline and loads an index using properties in the knowledge source.
+
+You can also use [Logic Apps workflows](search-how-to-index-logic-apps.md) or third-party connectors, developed and maintained by Microsoft partners. For more information and links, see [Data source gallery](search-data-sources-gallery.md).
 
-Indexers connect an index to a data source (usually a table, view, or equivalent structure), and map source fields to equivalent fields in the index. During execution, the rowset is automatically transformed to JSON and loaded into the specified index. All indexers support schedules so that you can specify how frequently the data is to be refreshed. Most indexers provide change tracking if the data source supports it. By tracking changes and deletes to existing documents in addition to recognizing new documents, indexers remove the need to actively manage the data in your index.
+With these automated approaches, you connect your index to a data source (usually a table, view, container, or equivalent structure), and map source fields to equivalent fields in the index. During execution, the rowset is automatically transformed to JSON and loaded into the specified index. All indexers support schedules so that you can specify how frequently the data is to be refreshed. Most indexers provide change tracking if the data source supports it. By tracking changes and deletes to existing documents in addition to recognizing new documents, indexers remove the need to actively manage the data in your index.
 
 ### How to pull data into an Azure AI Search index
 

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/06/2025
 ms.update-cycle: 365-days
 ---

@@ -6,7 +6,7 @@ manager: nitinme
 author: arv100kri
 ms.author: arjagann
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: troubleshooting-general
 ms.date: 06/04/2025
 ms.update-cycle: 365-days
 ms.custom:

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 10/30/2025
 ---
 

@@ -6,7 +6,7 @@ author: robertklee
 ms.author: robertlee
 ms.service: azure-ai-search
 ms.update-cycle: 180-days
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 11/21/2025
 ms.custom:
   - build-2024

@@ -2,28 +2,28 @@
 title: Integrated vectorization
 titleSuffix: Azure AI Search
 description: Add a vector embedding step in an Azure AI Search skillset to vectorize content during indexing or queries.
-author: heidisteen
-ms.author: heidist
+author: haileytap
+ms.author: haileytapia
 ms.service: azure-ai-search
 ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
-ms.date: 06/11/2025
+ms.topic: concept-article
+ms.date: 01/23/2026
 ---
 
 # Integrated vector embedding in Azure AI Search
 
 Integrated vectorization is an extension of the indexing and query pipelines in Azure AI Search. It adds the following capabilities:
 
-+ Vector encoding during indexing
++ Vector encoding during indexer-driven indexing
 + Vector encoding during queries
 
 [Data chunking](vector-search-how-to-chunk-documents.md) isn't a hard requirement, but unless your raw documents are small, chunking is necessary for meeting the token input requirements of embedding models.
 
 Vector conversions are one-way: nonvector-to-vector. For example, there's no vector-to-text conversion for queries or results, such as converting a vector result to a human-readable string, which is why indexes contain both vector and nonvector fields.
 
-Integrated vectorization speeds up the development and minimizes maintenance tasks during data ingestion and query time because there are fewer operations that you have to implement manually. This capability is now generally available.
+Integrated vectorization speeds up the development and minimizes maintenance tasks during data ingestion and query time because there are fewer operations that you have to implement manually. 
 
 ## Using integrated vectorization during indexing
 
@@ -35,7 +35,7 @@ For integrated data chunking and vector conversions, you're taking a dependency
 
 + [A skillset](cognitive-search-working-with-skillsets.md) configured for:
 
-  + [Text Split skill](cognitive-search-skill-textsplit.md), used to chunk the data.
+  + A chunking strategy: [Text Split skill](cognitive-search-skill-textsplit.md), [Document Layout skill](cognitive-search-skill-document-intelligence-layout.md), [Continent Understanding skill](cognitive-search-skill-content-understanding.md), or one of the [document parsing modes](vector-search-how-to-chunk-documents.md#common-chunking-techniques). 
   
   + An embedding skill, used to generate vector arrays, which can be any of the following:
 

@@ -6,7 +6,7 @@ author: gmndrg
 ms.author: gimondra
 ms.service: azure-ai-search
 ms.update-cycle: 180-days
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 08/27/2025
 ---
 

@@ -7,7 +7,7 @@ ms.author: robertlee
 ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
-ms.topic: conceptual
+ms.topic: concept-article
 ms.date: 01/15/2026
 ai-usage: ai-assisted
 ---