Merge pull request #266276 from HeidiSteen/heidist-docs

[azure search] Vector store doc updates

Author: Jill Grant

articles/search/TOC.yml

@@ -127,7 +127,7 @@
     href: samples-rest.md
 - name: Concepts
   items:
-  - name: Storage (indexes)
+  - name: Storage
     items:
     - name: Search index
       href: search-what-is-an-index.md
@@ -137,7 +137,7 @@
       href: knowledge-store-concept-intro.md
     - name: Data import strategies
       href: search-what-is-data-import.md
-  - name: Enrichment (skills)
+  - name: Enrichment
     items:
     - name: Enrichment overview
       href: cognitive-search-concept-intro.md
@@ -147,7 +147,7 @@
       href: cognitive-search-working-with-skillsets.md
     - name: Integrated vectorization (preview)
       href: vector-search-integrated-vectorization.md
-  - name: Retrieval (queries)
+  - name: Retrieval
     items:
     - name: Full-text search
       href: search-lucene-query-architecture.md

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

@@ -12,20 +12,25 @@ ms.custom:
 ms.topic: conceptual
 ms.date: 01/30/2024
 ---
+
 # AI enrichment in Azure AI Search
 
 In Azure AI Search, *AI enrichment* refers to integration with [Azure AI services](/azure/ai-services/what-are-ai-services) to process content that isn't searchable in its raw form. Through enrichment, analysis and inference are used to create searchable content and structure where none previously existed. 
 
-Because Azure AI Search is a text and vector search solution, the purpose of AI enrichment is to improve the utility of your content in search-related scenarios. Source content must be textual (you can't enrich vectors), but the content created by an enrichment pipeline can be vectorized and indexed in a vector store using skills like [Text Split skill](cognitive-search-skill-textsplit.md) for chunking and [AzureOpenAiEmbedding skill](cognitive-search-skill-azure-openai-embedding.md) for encoding.
+Because Azure AI Search is a text and vector search solution, the purpose of AI enrichment is to improve the utility of your content in search-related scenarios. Source content must be textual (you can't enrich vectors), but the content created by an enrichment pipeline can be vectorized and indexed in a vector store using skills like [Text Split skill](cognitive-search-skill-textsplit.md) for chunking and [AzureOpenAiEmbedding skill](cognitive-search-skill-azure-openai-embedding.md) for encoding. 
+
+AI enrichment is based on [*skills*](cognitive-search-working-with-skillsets.md).
 
-Built-in skills apply the following transformation and processing to raw content:
+Built-in skills tap Azure AI services. They apply the following transformations and processing to raw content:
 
 + Translation and language detection for multi-lingual search
 + Entity recognition to extract people names, places, and other entities from large chunks of text
 + Key phrase extraction to identify and output important terms
 + Optical Character Recognition (OCR) to recognize printed and handwritten text in binary files
 + Image analysis to describe image content, and output the descriptions as searchable text fields
 
+Custom skills run your external code. Custom skills can be used for any custom processing that you want to include in the pipeline.
+
 AI enrichment is an extension of an [**indexer pipeline**](search-indexer-overview.md) that connects to Azure data sources. An enrichment pipeline has all of the components of an indexer pipeline (indexer, data source, index), plus a [**skillset**](cognitive-search-working-with-skillsets.md) that specifies atomic enrichment steps.
 
 The following diagram shows the progression of AI enrichment:

articles/search/media/vector-search-index-size/deployment-details.png

@@ -1,5 +1,5 @@
 ---
-title: Index overview
+title: Search index overview
 titleSuffix: Azure AI Search
 description: Explains what is a search index in Azure AI Search and describes content, construction, physical expression, and the index schema.
 
@@ -14,7 +14,7 @@ ms.topic: conceptual
 ms.date: 01/19/2024
 ---
 
-# Indexes in Azure AI Search
+# Search indexes in Azure AI Search
 
 In Azure AI Search, a *search index* is your searchable content, available to the search engine for indexing, full text search, vector search, hybrid search, and filtered queries. An index is defined by a schema and saved to the search service, with data import following as a second step. This content exists within your search service, apart from your primary data stores, which is necessary for the millisecond response times expected in modern search applications. Except for indexer-driven indexing scenarios, the search service never connects to or queries your source data.
 
@@ -170,6 +170,13 @@ All indexing and query requests target an index. Endpoints are usually one of th
 | `<your-service>.search.windows.net/indexes` | Targets the indexes collection. Used when creating, listing, or deleting an index. Admin rights are required for these operations, available through admin [API keys](search-security-api-keys.md) or a [Search Contributor role](search-security-rbac.md#built-in-roles-used-in-search). |
 | `<your-service>.search.windows.net/indexes/<your-index>/docs` | Targets the documents collection of a single index. Used when querying an index or data refresh. For queries, read rights are sufficient, and available through query API keys or a data reader role. For data refresh, admin rights are required. |
 
+Search subscribers, or the person who created the search service, can manage the search service in the Azure portal. An Azure subscription requires Contributor or above permissions to create or delete services. You can [sign in to the Azure portal](https://portal.azure.com) for a direct connection to your search service.
+
+For other clients, we recommend reviewing the quickstarts for connection steps:
+
++ [Quickstart: REST](search-get-started-rest.md)
++ [Quickstart: Azure SDKs](search-get-started-text.md)
+
 ## Next steps
 
 You can get hands-on experience creating an index using almost any sample or walkthrough for Azure AI Search. For starters, you could choose any of the quickstarts from the table of contents.

articles/search/media/vector-search-index-size/portal-vector-index-size.png

@@ -9,12 +9,14 @@ ms.service: cognitive-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 11/01/2023
+ms.date: 02/14/2024
 ---
 
 # Filters in vector queries
 
-You can set a [vector filter modes on a vector query](vector-search-how-to-query.md) to specify whether you want filtering before or after query execution. Filters are set on and iterate over string and numeric fields attributed as `filterable` in the index, but the effects of filtering determine *what* the vector query executes over: the searchable space, or the documents in the search results.
+You can set a [**vector filter modes on a vector query**](vector-search-how-to-query.md) to specify whether you want filtering before or after query execution. 
+
+Filters determine the scope of a vector query. Filters are set on and iterate over nonvector string and numeric fields attributed as `filterable` in the index, but the purpose of a filter determines *what* the vector query executes over: the entire searchable space, or the contents of a search result.
 
 This article describes each filter mode and provides guidance on when to use each one.
 
@@ -40,21 +42,21 @@ To understand the conditions under which one filter mode performs better than th
 
 For the small and medium workloads, we used a Standard 2 (S2) service with one partition and one replica. For the large workload, we used a Standard 3 (S3) service with 12 partitions and one replica.
 
-Indexes had an identical construction: one key field, one vector field, one text field, and one numeric filterable field.
+Indexes had an identical construction: one key field, one vector field, one text field, and one numeric filterable field. The following index is defined using the 2023-07-01-preview syntax.
 
 ```python
 def get_index_schema(self, index_name, dimensions):
     return {
         "name": index_name,
         "fields": [
             {"name": "id", "type": "Edm.String", "key": True, "searchable": True},
-            {"name": "myvector", "type": "Collection(Edm.Single)", "dimensions": dimensions,
+            {"name": "content_vector", "type": "Collection(Edm.Single)", "dimensions": dimensions,
               "searchable": True, "retrievable": True, "filterable": False, "facetable": False, "sortable": False,
               "vectorSearchConfiguration": "defaulthnsw"},
             {"name": "text", "type": "Edm.String", "searchable": True, "filterable": False, "retrievable": True,
-              "sortable": False, "facetable": False, "key": False},
+              "sortable": False, "facetable": False},
             {"name": "score", "type": "Edm.Double", "searchable": False, "filterable": True,
-              "retrievable": True, "sortable": True, "facetable": True, "key": False}
+              "retrievable": True, "sortable": True, "facetable": True}
         ],
         "vectorSearch":
         {

articles/search/media/vector-search-index-size/resource-group-deployments.png

@@ -696,6 +696,22 @@ api-key: {{admin-api-key}}
 
 ---
 
+## Update a vector store
+
+To update a vector store, modify the schema and if necessary, reload documents to populate new fields. APIs for schema updates include [Create or Update Index (REST)](/rest/api/searchservice/indexes/create-or-update), [CreateOrUpdateIndex](/dotnet/api/azure.search.documents.indexes.searchindexclient.createorupdateindexasync) in the Azure SDK for .NET, [create_or_update_index](/python/api/azure-search-documents/azure.search.documents.indexes.searchindexclient?view=azure-python#azure-search-documents-indexes-searchindexclient-create-or-update-index&preserve-view=true) in the Azure SDK for Python, and similar methods in other Azure SDKs.
+
+The standard guidance for updating an index is covered in [Drop and rebuild an index](search-howto-reindex.md). 
+
+Key points include:
+
++ Drop and rebuild is often required for updates to and deletion of existing fields.
+
++ However, you can update an existing schema with the following modifications, with no rebuild required:
+
+  + Add new fields to a fields collection.
+  + Add new vector configurations, assigned to new fields but not existing fields that have already been vectorized.
+  + Change "retrievable" (values are true or false) on an existing field. Vector fields must be searchable and retrievable, but if you want to disable access to a vector field in situations where drop and rebuild isn't feasible, you can set retrievable to false.
+
 ## Next steps
 
 As a next step, we recommend [Query vector data in a search index](vector-search-how-to-query.md).