Merge pull request #186912 from HeidiSteen/heidist-fresh3

misc edits: h1 and h2 consistency pass

Author: GitHubber17

articles/search/cognitive-search-concept-intro.md

@@ -13,13 +13,13 @@ ms.custom: references_regions
 ---
 # AI enrichment in Azure Cognitive Search
 
-In Azure Cognitive Search, AI enrichment refers to a pipeline process that adds machine learning to [indexer-based indexing](search-indexer-overview.md). Steps in the pipeline create new information where none previously existed: extracting information from images, detecting sentiment or key phrases from chunks of text, and recognizing entities, to name a few. All of these processes result in making previously unsearchable content available to full text search and knowledge mining scenarios.
+In Azure Cognitive Search, AI enrichment refers to a pipeline process that adds machine learning to [indexer-based indexing](search-indexer-overview.md). Steps in the pipeline create information where none previously existed. For example, steps in the pipeline can extract information from images, detect sentiment or key phrases from chunks of text, and recognize entities. These processes transform unsearchable content into searchable text, for full text search and knowledge mining scenarios.
 
-[**Azure Blob Storage**](../storage/blobs/storage-blobs-overview.md)) is the most commonly used input, but any indexer-supported data source can provide the initial content. A [**skillset**](cognitive-search-working-with-skillsets.md), attached to an indexer, adds the AI processing. The indexer extracts content and sets up the pipeline, while AI processing identifies, analyzes, and creates new information out of blobs, images, and raw text. Output is a [**search index**](search-what-is-an-index.md) or optional [**knowledge store**](knowledge-store-concept-intro.md).
+[**Azure Blob Storage**](../storage/blobs/storage-blobs-overview.md) is a frequently used input, but any supported data source can provide the initial content. A [**skillset**](cognitive-search-working-with-skillsets.md), attached to an indexer, adds the AI processing. The indexer extracts content and sets up the pipeline. The AI processing identifies, analyzes, and creates information out of blob, image, and raw text inputs. Output is always a [**search index**](search-what-is-an-index.md), and optionally a [**knowledge store**](knowledge-store-concept-intro.md).
 
 ![Enrichment pipeline diagram](./media/cognitive-search-intro/cogsearch-architecture.png "enrichment pipeline overview")
 
-Skillsets are composed of built-in skills from Cognitive Search or [*custom skills*](cognitive-search-create-custom-skill-example.md) for external processing that you provide. Custom skills might sound complex but can be simple and straightforward in terms of implementation. If you have existing packages that provide pattern matching or document classification models, the content you extract during indexing could be passed to these models for processing. 
+Skillsets are composed of [*built-in skills*](cognitive-search-predefined-skills.md) from Cognitive Search or [*custom skills*](cognitive-search-create-custom-skill-example.md) for external processing that you provide. Custom skills are not always complex. For example, if you have existing packages that provide pattern matching or document classification models, you can wrap them in a custom skill. 
 
 Built-in skills fall into these categories:
 
@@ -29,45 +29,47 @@ Built-in skills fall into these categories:
 
 + **Natural language processing** skills include [entity recognition](cognitive-search-skill-entity-recognition-v3.md), [language detection](cognitive-search-skill-language-detection.md), [key phrase extraction](cognitive-search-skill-keyphrases.md), text manipulation, [sentiment detection (including opinion mining)](cognitive-search-skill-sentiment-v3.md), and [personal identifiable information detection](cognitive-search-skill-pii-detection.md). With these skills, unstructured text is mapped as searchable and filterable fields in an index.
 
-Built-in skills are based on pre-trained machine learning models in Cognitive Services APIs: [Computer Vision](../cognitive-services/computer-vision/index.yml) and [Language Service](../cognitive-services/language-service/overview.md). You should [attach a billable Cognitive Services resource](cognitive-search-attach-cognitive-services.md) if you want these resources for larger workloads.
+Built-in skills are based on the Cognitive Services APIs: [Computer Vision](../cognitive-services/computer-vision/index.yml) and [Language Service](../cognitive-services/language-service/overview.md). Unless your content input is small, expect to [attach a billable Cognitive Services resource](cognitive-search-attach-cognitive-services.md) to run larger workloads.
 
-Natural language and image processing is applied during the data ingestion phase, with results becoming part of a document's composition in a searchable index in Azure Cognitive Search. Data is sourced as an Azure data set and then pushed through an indexing pipeline using whichever [built-in skills](cognitive-search-predefined-skills.md) you need.  
+## Availability and pricing
 
-## Feature availability
-
-AI enrichment is available in regions where Azure Cognitive Services is also available. You can check the current availability of AI enrichment on the [Azure products available by region](https://azure.microsoft.com/global-infrastructure/services/?products=search) page. AI enrichment is available in all supported regions except:
+AI enrichment is available in regions that have Azure Cognitive Services. You can check the availability of AI enrichment on the [Azure products available by region](https://azure.microsoft.com/global-infrastructure/services/?products=search) page. AI enrichment is available in all regions except:
 
 + Australia Southeast
 + China North 2
 + Germany West Central
 
-If your search service is located in one of these regions, you will not be able to create and use skillsets, but all other search service functionality is available and fully supported.
+Billing follows a pay-as-you-go pricing model. The costs of using built-in skills are passed on when a multi-region Cognitive Services key is specified in the skillset. There are also costs associated with image extraction, as metered by Cognitive Search. Text extraction and utility skills, however, aren't billable. For more information, see [How you're charged for Azure Cognitive Search](search-sku-manage-costs.md#how-youre-charged-for-azure-cognitive-search).
 
 ## When to use AI enrichment
 
-You should consider enrichment if your raw content is unstructured text, image content, or content that needs language detection and translation. Applying AI through the built-in cognitive skills can unlock this content for full text search and data science applications.
+Enrichment is useful if raw content is unstructured text, image content, or content that needs language detection and translation. Applying AI through the built-in cognitive skills can unlock this content for full text search and data science applications.
 
-Additionally, you might consider adding a custom skill if you have open-source, third-party, or first-party code that you'd like to integrate into the pipeline. Classification models that identify salient characteristics of various document types fall into this category, but any package that adds value to your content could be used.
+Enrichment also unlocks external processing. Open-source, third-party, or first-party code can be integrated into the pipeline as a custom skill. Classification models that identify salient characteristics of various document types fall into this category, but any external package that adds value to your content could be used.
 
 ### Use-cases for built-in skills
 
 A [skillset](cognitive-search-defining-skillset.md) that's assembled using built-in skills is well suited for the following application scenarios:
 
-+ [Optical Character Recognition (OCR)](cognitive-search-skill-ocr.md) that recognizes typeface and handwritten text in scanned documents (JPEG) is perhaps the most commonly used skill. Attaching the OCR skill will identify, extract, and ingest text from JPEG files.
++ [Optical Character Recognition (OCR)](cognitive-search-skill-ocr.md) that recognizes typeface and handwritten text in scanned documents (JPEG) is perhaps the most commonly used skill. 
 
-+ [Text translation](cognitive-search-skill-text-translation.md) of multilingual content is another commonly used skill. Language detection is built into Text Translation, but you can also run [Language Detection](cognitive-search-skill-language-detection.md) independently if you just want the language codes of the content in your corpus.
++ [Text translation](cognitive-search-skill-text-translation.md) of multilingual content is another commonly used skill. Language detection is built into Text Translation, but you can also run [Language Detection](cognitive-search-skill-language-detection.md) as a separate skill to output a language code for each chunk of content.
 
-+ PDFs with combined image and text. Text in PDFs can be extracted during indexing without the use of enrichment steps, but the addition of image and natural language processing can often produce a better outcome than a standard indexing provides.
++ PDFs with combined image and text. Embedded text can be extracted without AI enrichment, but adding image and language skills can unlock more information than what could be obtained through standard text-based indexing.
 
 + Unstructured or semi-structured documents containing content that has inherent meaning or context that is hidden in the larger document. 
 
-  Blobs in particular often contain a large body of content that is packed into a single "field". By attaching image and natural language processing skills to an indexer, you can create new information that is extant in the raw content, but not otherwise surfaced as distinct fields. Some ready-to-use built-in cognitive skills that can help: [Key Phrase Extraction](cognitive-search-skill-keyphrases.md) and [Entity Recognition](cognitive-search-skill-entity-recognition-v3.md) (people, organizations, and locations to name a few).
+  Blobs in particular often contain a large body of content that is packed into a single "field". By attaching image and natural language processing skills to an indexer, you can create information that is extant in the raw content, but not otherwise surfaced as distinct fields. Some ready-to-use built-in cognitive skills that can help: [Key Phrase Extraction](cognitive-search-skill-keyphrases.md) and [Entity Recognition](cognitive-search-skill-entity-recognition-v3.md) (people, organizations, and locations to name a few).
 
   Additionally, built-in skills can also be used restructure content through text split, merge, and shape operations.
 
 ### Use-cases for custom skills
 
-Custom skills can support more complex scenarios, such as recognizing forms, or custom entity detection using a model that you provide and wrap in the [custom skill web interface](cognitive-search-custom-skill-interface.md). Several examples of custom skills include [Forms Recognizer](../applied-ai-services/form-recognizer/overview.md), integration of the [Bing Entity Search API](./cognitive-search-create-custom-skill-example.md), and [custom entity recognition](https://github.com/Microsoft/SkillsExtractorCognitiveSearch).
+Custom skills can support more complex scenarios, such as recognizing forms, or custom entity detection using a model that you provide and wrap in the [custom skill web interface](cognitive-search-custom-skill-interface.md). Several examples of custom skills include:
+
++ [Forms Recognizer](../applied-ai-services/form-recognizer/overview.md)
++ Integration of the [Bing Entity Search API](./cognitive-search-create-custom-skill-example.md)
++ [Custom entity recognition](https://github.com/Microsoft/SkillsExtractorCognitiveSearch)
 
 ## Enrichment steps <a name="enrichment-steps"></a>
 
@@ -97,55 +99,53 @@ Internally, the pipeline generates a collection of enriched documents. You can d
 
 ### Step 3: Indexing
 
-Indexing is the process wherein raw and enriched content is ingested as fields in a search index, and as [projections](knowledge-store-projection-overview.md) if you are also creating a knowledge store. The same enriched content can appear in both, using implicit or explicit field mappings to send the content to the correct fields.
+Indexing is the process wherein raw and enriched content is ingested as fields in a search index, and as [projections](knowledge-store-projection-overview.md) if you're also creating a knowledge store. The same enriched content can appear in both, using implicit or explicit field mappings to send the content to the correct fields.
 
 Enriched content is generated during skillset execution, and is temporary unless you save it. In order for enriched content to appear in a search index, the indexer must have mapping information so that it can send enriched content to a field in a search index. [Output field mappings](cognitive-search-output-field-mapping.md) set up these associations.
 
-## Saving enriched output
+## Storing enriched output
 
 In Azure Cognitive Search, an indexer saves the output it creates.
 
 A [**searchable index**](search-what-is-an-index.md) is one of the outputs that is always created by an indexer. Specification of an index is an indexer requirement, and when you attach a skillset, the output of the skillset, plus any fields that are mapped directly from the source, are used to populate the index. Usually, the outputs of specific skills, such as key phrases or sentiment scores, are ingested into the index in fields created for that purpose.
 
-A [**knowledge store**](knowledge-store-concept-intro.md) is an optional output, used for downstream apps like knowledge mining. A knowledge store is defined within a skillset. Its definition determines whether your enriched documents are projected as tables or objects (files or blobs). Tabular projections are well suited for interactive analysis in tools like Power BI, whereas files and blobs are typically used in data science or similar processes.
+A [**knowledge store**](knowledge-store-concept-intro.md) is an optional output, used for downstream apps like knowledge mining. A knowledge store is defined within a skillset. Its definition determines whether your enriched documents are projected as tables or objects (files or blobs). Tabular projections are recommended for interactive analysis in tools like Power BI. Files and blobs are typically used in data science or similar workloads.
 
 Finally, an indexer can [**cache enriched documents**](cognitive-search-incremental-indexing-conceptual.md) in Azure Blob Storage for potential reuse in subsequent skillset executions. The cache is for internal use. Cached enrichments are consumable by the same skillset that you rerun at a later date. Caching is helpful if your skillset include image analysis or OCR, and you want to avoid the time and expense of reprocessing image files.
 
 Indexes and knowledge stores are fully independent of each other. While you must attach an index to satisfy indexer requirements, if your sole objective is a knowledge store, you can ignore the index after it's populated. Avoid deleting it though. If you want to rerun the indexer and skillset, you'll need the index in order for the indexer to run.
 
-## Consume enriched content
+## Consuming enriched content
 
 The output of AI enrichment is either a [fully text-searchable index](search-what-is-an-index.md) on Azure Cognitive Search, or a [knowledge store](knowledge-store-concept-intro.md) in Azure Storage.
 
 ### Accessing content in a search index
 
-[**Querying the index**](search-query-overview.md) is how developers and users access the enriched content generated by the pipeline. The index is like any other you might create for Azure Cognitive Search: you can supplement text analysis with custom analyzers, invoke fuzzy search queries, add filters, or experiment with scoring profiles to tune search relevance.
+[*Run queries**](search-query-overview.md) to access the enriched content generated by the pipeline. The index is like any other you might create for Azure Cognitive Search: you can supplement text analysis with custom analyzers, invoke fuzzy search queries, add filters, or experiment with scoring profiles to tune search relevance.
 
 ### Accessing content in a knowledge store
 
-In Azure Storage, a [knowledge store](knowledge-store-concept-intro.md) has two manifestations: a blob container of JSON document, a blob container of image objects, or tables in Table storage. You can use [Storage Browser](knowledge-store-view-storage-explorer.md), [Power BI](knowledge-store-connect-power-bi.md), or any app that connects to Azure Storage.
-
-+ A blob container captures enriched documents in their entirety, which is useful if you want to feed into other processes. 
+In Azure Storage, a [knowledge store](knowledge-store-concept-intro.md) can assume the following forms: a blob container of JSON documents, a blob container of image objects, or tables in Table Storage. You can use [Storage Browser](knowledge-store-view-storage-explorer.md), [Power BI](knowledge-store-connect-power-bi.md), or any app that connects to Azure Storage to access your content.
 
-+ In contrast, Table storage can accommodate physical projections of enriched documents. You can create slices or layers of enriched documents that include or exclude specific parts. For analysis in Power BI, the tables in Azure Table Storage become the data source for further visualization and exploration.
++ A blob container captures enriched documents in their entirety, which is useful if you're creating a feed into other processes. 
 
-An enriched document at the output of the pipeline differs from its original source input  by the presence of additional fields containing new information that was extracted or generated during enrichment. As such, you can work with a combination of original and created content, regardless of which output structure you use.
++ A table is useful if you need slices of enriched documents, or if you want to include or exclude specific parts of the output. For analysis in Power BI, tables are the recommended data source for data exploration and visualization in Power BI.
 
 ## Checklist: A typical workflow
 
-1. When beginning a project, it's helpful to work with a subset of data. Indexer and skillset design is an iterative process, and you'll iterate more quickly if you're working with a small representative data set.
+1. When beginning a project, it's helpful to work with a subset of data. Indexer and skillset design is an iterative process, and the work goes faster with a small representative data set.
 
 1. Create a [data source](/rest/api/searchservice/create-data-source) that specifies a connection to your data.
 
 1. Create a [skillset](/rest/api/searchservice/create-skillset) to add enrichment.
 
 1. Create an [index schema](/rest/api/searchservice/create-index) that defines a search index.
 
-1. Create an [indexer](/rest/api/searchservice/create-indexer) to bring all of the above components together. Creating or running indexer retrieves the data, runs the skillset, and loads the index.
+1. Create an [indexer](/rest/api/searchservice/create-indexer) to bring all of the above components together. This step retrieves the data, runs the skillset, and loads the index.
 
 1. Run queries to evaluate results and modify code to update skillsets, schema, or indexer configuration.
 
-To iterate over the above steps, [reset the indexer](search-howto-reindex.md) before rebuilding the pipeline, or delete and recreate the objects on each run (recommended if you are using the free tier). You should also [enable enrichment caching](cognitive-search-incremental-indexing-conceptual.md) to reuse existing enrichments wherever possible.
+To repeat any of the above steps, [reset the indexer](search-howto-reindex.md) before you run it. Or, delete and recreate the objects on each run (recommended if you are using the free tier). You should also [enable enrichment caching](cognitive-search-incremental-indexing-conceptual.md) to reuse existing enrichments wherever possible.
 
 ## Next steps