Updated vector content

Author: haileytap

articles/search/vector-search-overview.md

@@ -9,18 +9,18 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 05/08/2025
+ms.date: 06/17/2025
 ---
 
-# Vectors in Azure AI Search
+# Vector search in Azure AI Search
 
-Vector search is an approach in information retrieval that supports indexing and query execution over numeric representations of content. Because the content is numeric rather than plain text, matching is based on vectors that are most similar to the query vector, which enables matching across:
+Vector search is an information retrieval approach that supports indexing and querying over numeric representations of content. Because the content is numeric rather than plain text, matching is based on vectors that are most similar to the query vector, which enables matching across:
 
-+ semantic or conceptual likeness ("dog" and "canine", conceptually similar yet linguistically distinct)
-+ multilingual content ("dog" in English and "hund" in German)
-+ multiple content types ("dog" in plain text and a photograph of a dog in an image file)
++ Semantic or conceptual likeness. For example, "dog" and "canine" are conceptually similar but linguistically distinct.
++ Multilingual content, such as "dog" in English and "hund" in German.
++ Multiple content types, such as "dog" in plain text and an image of a dog.
 
-This article provides [a high-level introduction to vector support](#vector-search-concepts) in Azure AI Search. It also explains integration with other Azure services and covers [terminology and concepts](#vector-search-concepts) related to vector search development.
+This article provides a high-level introduction to vector support in Azure AI Search. It also explains integration with other Azure services and covers [terminology and concepts](#vector-search-concepts) related to vector search development.
 
 We recommend this article for background, but if you'd rather get started, follow these steps:
 
@@ -29,7 +29,7 @@ We recommend this article for background, but if you'd rather get started, follo
 > + [Create a vector index](vector-search-how-to-create-index.md)
 > + [Run vector queries](vector-search-how-to-query.md)
 
-You could also begin with the [vector quickstart](search-get-started-vector.md) or the [code samples on GitHub](https://github.com/Azure/azure-search-vector-samples). 
+You can also begin with the [vector quickstart](search-get-started-vector.md) or the [code samples on GitHub](https://github.com/Azure/azure-search-vector-samples).
 
 ## What scenarios can vector search support?
 

articles/search/vector-store.md

@@ -31,9 +31,9 @@ This article covers the key concepts for creating and managing a vector index, i
 
 Azure AI Search supports two patterns for vector retrieval:
 
-+ **Classic search.** After users enter queries into a search bar, your application code or the search engine vectorizes the input and performs a vector search over the vector fields in your index. The search engine returns results as a flattened row set, and you can choose which fields to include in the response. Because there's no chat model or extra reasoning, you should include nonvector fields in your index to present human-readable results to users. For more information, see [Create a vector query](vector-search-how-to-query.md) and [Create a hybrid query](hybrid-search-how-to-query.md).
++ **Classic search**. After users enter queries into a search bar, your application code or the search engine vectorizes the input and performs a vector search over the vector fields in your index. The search engine returns results as a flattened row set, and you can choose which fields to include in the response. Because there's no chat model or extra reasoning, you should include nonvector fields in your index to present human-readable results to users. For more information, see [Create a vector query](vector-search-how-to-query.md) and [Create a hybrid query](hybrid-search-how-to-query.md).
 
-+ **Generative search.** Language models use data from Azure AI Search to respond to user queries. An orchestration layer typically coordinates prompts and maintains context, feeding search results into chat models like GPT. This pattern is based on the [retrieval-augmented generation (RAG)](retrieval-augmented-generation-overview.md) architecture, where the search index supplies grounding data.
++ **Generative search**. Language models use data from Azure AI Search to respond to user queries. An orchestration layer typically coordinates prompts and maintains context, feeding search results into chat models like GPT. This pattern is based on the [retrieval-augmented generation (RAG)](retrieval-augmented-generation-overview.md) architecture, where the search index supplies grounding data.
 
 ## Schema of a vector index
 
@@ -85,7 +85,7 @@ Vector indexes require more than just vector fields. For example, all indexes mu
 ]
 ```
 
-Other fields, such as `content`, provide the human-readable equivalent of the `content_vector` field. If you're using language models exclusively for response formulation, you can omit nonvector content fields, but solutions that push search results directly to client apps should have nonvector content.
+Other fields, such as the `content` field, provide the human-readable equivalent of the `content_vector` field. If you're using language models exclusively for response formulation, you can omit nonvector content fields, but solutions that push search results directly to client apps should have nonvector content.
 
 Metadata fields are useful for filters, especially if they include origin information about the source document. Although you can't filter directly on a vector field, you can set prefilter or postfilter modes to filter before or after vector query execution.