Updated vector content

Author: haileytap

articles/search/search-features-list.md

@@ -36,7 +36,7 @@ The following table summarizes features by category. There's feature parity in a
 |-------------------|----------|
 | Vector indexing | Within a search index, add [vector fields](vector-search-how-to-create-index.md) to support  [**vector search**](vector-search-overview.md) scenarios. Vector fields can coexist with nonvector fields in the same search document. |
 | Vector queries | [Formulate single and multiple vector queries](vector-search-how-to-query.md). |
-| Vector search algorithms | Use [Hierarchical Navigable Small World (HNSW)](vector-search-ranking.md#when-to-use-hnsw) or [exhaustive K-Nearest Neighbors (KNN)](vector-search-ranking.md#when-to-use-exhaustive-knn) to find similar vectors in a search index. |
+| Vector search algorithms | Use [hierarchical navigable small world (HNSW)](vector-search-ranking.md#about-hnsw) or [exhaustive k-nearest neighbors (KNN)](vector-search-ranking.md#about-exhaustive-knn) to find similar vectors in a search index. |
 | Vector filters | [Apply filters before or after query execution](vector-search-filters.md) for greater precision during information retrieval. |
 | Hybrid information retrieval | Search for concepts and keywords in a single [hybrid query request](hybrid-search-how-to-query.md). </p>[**Hybrid search**](hybrid-search-overview.md) consolidates vector and text search, with optional semantic ranking and relevance tuning for best results.|
 | 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 [AzureOpenAIEmbeddingModel](cognitive-search-skill-azure-openai-embedding.md), [Azure AI Vision multimodal](cognitive-search-skill-vision-vectorize.md), and the [AML skill](cognitive-search-aml-skill.md) that you can use to connect to endpoints in the Azure AI Foundry model catalog. </p>[**Integrated vectorization**](vector-search-integrated-vectorization.md) provides an end-to-end indexing pipeline from source files to queries.|

articles/search/vector-search-overview.md

@@ -9,7 +9,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 06/20/2025
+ms.date: 07/03/2025
 ---
 
 # Vector search in Azure AI Search
@@ -20,7 +20,7 @@ Vector search is an information retrieval approach that supports indexing and qu
 + 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 covers vector support in Azure AI Search, including its integration with other Azure services. It also introduces concepts and terminology related to vector search development.
+This article provides an overview of vector search in Azure AI Search, including supported scenarios, availability, and integration with other Azure services.
 
 > [!TIP]
 > Want to get started right away? Follow these steps:
@@ -92,73 +92,6 @@ Azure AI Search is deeply integrated across the Azure AI platform. The following
 
 It's also commonly used in open-source frameworks like [LangChain](https://js.langchain.com/docs/integrations/vectorstores/azure_aisearch).
 
-## Vector search concepts
-
-If you're new to vectors, this section explains some core concepts.
-
-### About vector search
-
-Vector search is a method of information retrieval where documents and queries are represented as vectors instead of plain text. In vector search, machine learning models generate the vector representations of source inputs, which can be text, images, or other content.
-
-Having a mathematic representation of content provides a common language for comparing disparate content. If everything is a vector, a query can find a match in vector space, even if the associated original content is in different media or language than the query.
-
-### Why use vector search?
-
-When searchable content is represented as vectors, a query can find close matches in similar content. The embedding model used for vector generation knows which words and concepts are similar and places the resulting vectors close together in the embedding space.
-
-For example, vectorized source documents about "clouds" and "fog" are more likely to show up in a query about "mist" because they're semantically similar, even if they aren't a lexical match.
-
-### Embeddings and vectorization
-
-Machine learning models create *embeddings*, a specific type of vector representation of content or queries. These models capture the semantic meaning of text or representations of other content, such as images.
-
-Natural-language machine learning models are trained on large amounts of data to identify patterns and relationships between words. During training, the models learn to represent any input as a vector of real numbers in an intermediary step called the *encoder*. After training, the models can be modified so that the intermediary vector representation becomes their output. The resulting embeddings are high-dimensional vectors, where words with similar meanings are closer together in the vector space. For more information about embeddings, see [Understand embeddings in Azure OpenAI in Azure AI Foundry Models](/azure/ai-services/openai/concepts/understand-embeddings).
-
-The effectiveness of vector search in retrieving relevant information depends on how effectively the embedding model distills the meaning of documents and queries into the resulting vector. The best models are well-trained on the types of data they represent. You can evaluate existing models, such as Azure OpenAI text-embedding-ada-002; bring your own model that's trained directly on the problem space; or fine-tune a general-purpose model. Azure AI Search doesn't impose constraints on which model you choose, so pick the best one for your data.
-
-To create effective embeddings for vector search, it's important to consider input size limitations. We recommend following the [guidelines for chunking data](vector-search-how-to-chunk-documents.md) before generating embeddings. This best practice ensures that the embeddings accurately capture the relevant information and enable more efficient vector search.
-
-### What is an embedding space?
-
-An *embedding space* is the corpus for vector queries. Within a [search index](search-what-is-an-index.md), the embedding space is all of the vector fields populated with embeddings from the same embedding model. Machine learning models create the embedding space by mapping individual words, phrases, documents (for natural-language processing), images, or other data into representations comprised of vectors of real numbers that act as coordinates in a high-dimensional space.
-
-In the embedding space, similar items are located close together, while dissimilar items are located farther apart. For example, documents about different species of dogs would be clustered close together. Documents about cats would be close together but farther from the dogs cluster, while still being in the neighborhood for animals. Dissimilar concepts, such as cloud computing, would be much farther away.
-
-In practice, embedding spaces are abstract and don't have well-defined, human-interpretable meanings, but the core idea stays the same.
-
-<a name="eknn"></a>
-
-### Nearest neighbors search
-
-In vector search, the search engine scans vectors within the embedding space to identify vectors that are closest to the query vector. This technique is called [*nearest neighbor search*](https://en.wikipedia.org/wiki/Nearest_neighbor_search).
-
-Nearest neighbors quantify the similarity between items. A high degree of vector similarity indicates that the original data is also similar. To expedite nearest neighbor search and reduce the search space, the search engine uses data structures and data partitioning. Each vector search algorithm solves the nearest neighbor problems differently, optimizing for minimum latency, maximum throughput, recall, and memory. To compute similarity, similarity metrics provide the mechanism for computing distance.
-
-Azure AI Search supports the following algorithms:
-
-+ **Hierarchical navigable small world (HNSW)**. HNSW is a leading ANN algorithm optimized for high-recall, low-latency applications with unknown or volatile data distribution. It organizes high-dimensional data points into a hierarchical graph structure that enables fast, scalable similarity search and allows a tunable trade-off between search accuracy and computational cost. Because the algorithm requires all data points to reside in memory for fast random access, HNSW consumes [vector index size](vector-search-index-size.md) quota.
-
-+ **Exhaustive k-nearest neighbors (KNN)**. KNN calculates the distances between the query vector and all data points. It's computationally intensive and works best for smaller datasets. Because the algorithm doesn't require fast random access of data points, KNN doesn't consume vector index size quota. However, it provides the global set of nearest neighbors.
-
-To learn how to specify the algorithm, vector profile, and profile assignment for HNSW or KNN, see [Create a vector field](vector-search-how-to-create-index.md).
-
-Algorithm parameters that are used to initialize the index during index creation are immutable and can't be changed after the index is built. However, parameters that affect the query-time characteristics (`efSearch`) can be modified.
-
-Fields that specify the HNSW algorithm also support exhaustive KNN search using the [query request](vector-search-how-to-query.md) parameter `"exhaustive": true`. However, the opposite isn't true. If a field is indexed for `exhaustiveKnn`, you can't use HNSW in the query because the extra data structures that enable efficient search don't exist.
-
-### Approximate nearest neighbors
-
-Approximate nearest neighbor (ANN) is a class of algorithms for finding matches in vector space. This class of algorithms uses different data structures or data partitioning methods to significantly reduce the search space and accelerate query processing.
-
-ANN algorithms sacrifice some accuracy but offer scalable and faster retrieval of approximate nearest neighbors, which makes them ideal for balancing accuracy and efficiency in modern information retrieval applications. You can adjust the parameters of your algorithm to fine-tune the recall, latency, memory, and disk footprint requirements of your search application.
-
-Azure AI Search uses HNSW for its ANN algorithm.
-
-<!-- > [!NOTE]
-> Finding the true set of [nearest neighbors](https://en.wikipedia.org/wiki/Nearest_neighbor_search) requires comparing the input vector exhaustively against all vectors in the dataset. While each vector similarity calculation is relatively fast, performing these exhaustive comparisons across large datasets is computationally expensive and slow due to the sheer number of comparisons. For example, if a dataset contains 10 million 1,000-dimensional vectors, computing the distance between the query vector and all vectors in the dataset would require scanning 37 GB of data (assuming single-precision floating point vectors) and a high number of similarity calculations.
-> 
-> To address this challenge, approximate nearest neighbor (ANN) search methods are used to trade off recall for speed. These methods can efficiently find a small set of candidate vectors that are similar to the query vector and have high likelihood to be in the globally most similar neighbors. Each algorithm has a different approach to reducing the total number of vectors comparisons, but they all share the ability to balance accuracy and efficiency by tweaking the algorithm configuration parameters. -->
-
 ## Related content
 
 + [Quickstart: Vector search using REST](search-get-started-vector.md)