H2 and intro revisions

Author: HeidiSteen

articles/search/search-agentic-retrieval-how-to-create.md

@@ -196,7 +196,7 @@ PUT https://{{search-url}}/agents/{{agent-name}}?api-version=2025-05-01-preview
     }
     ```
 
-+ `defaultRerankerThreshold` is the minimum semantic reranker score that's acceptable for inclusion in a response. [Reranker scores](semantic-search-overview.md#how-ranking-is-scored) range from 1 to 4. Plan on revising this value based on testing and what works for your content.
++ `defaultRerankerThreshold` is the minimum semantic reranker score that's acceptable for inclusion in a response. [Reranker scores](semantic-search-overview.md#how-results-are-scored) range from 1 to 4. Plan on revising this value based on testing and what works for your content.
 
 + `defaultIncludeReferenceSourceData` is a boolean that determines whether the reference portion of the response includes source data. We recommend starting with this value set to true if you want to shape your own response using output from the search engine. Otherwise, if you want to use the output in the response `content` string, you can set it to false.
 

articles/search/search-agentic-retrieval-how-to-retrieve.md

@@ -103,7 +103,7 @@ POST https://{{search-url}}/agents/{{agent-name}}/retrieve?api-version=2025-05-0
 
   + `rerankerThreshold` and `maxDocsForReranker` are also initially set in the knowledge agent definition as defaults. You can override them in the retrieve action to configure [semantic reranker](semantic-how-to-configure.md), setting minimum thresholds and the maximum number of inputs sent to the reranker.
 
-    `rerankerThreshold` is the minimum semantic reranker score that's acceptable for inclusion in a response. [Reranker scores](semantic-search-overview.md#how-ranking-is-scored) range from 1 to 4. Plan on revising this value based on testing and what works for your content.
+    `rerankerThreshold` is the minimum semantic reranker score that's acceptable for inclusion in a response. [Reranker scores](semantic-search-overview.md#how-results-are-scored) range from 1 to 4. Plan on revising this value based on testing and what works for your content.
 
     `maxDocsForReranker` dictates the maximum number of documents to consider for the final response string. Semantic reranker accepts 50 documents. If the maximum is 200, four more subqueries are added to the query plan to ensure all 200 documents are semantically ranked. for semantic ranking. If the number isn't evenly divisible by 50, the query plan rounds up to nearest whole number. 
 

articles/search/search-relevance-overview.md

@@ -1,7 +1,7 @@
 ---
-title: How scoring works
+title: How relevance scoring works
 titleSuffix: Azure AI Search
-description: Describes the ranking algorithms in Azure AI Search and how to use them together.
+description: Describes how the scoring and ranking algorithms work in Azure AI Search and how to use them together.
 
 manager: nitinme
 author: HeidiSteen
@@ -11,25 +11,29 @@ ms.topic: concept-article
 ms.date: 07/23/2025
 ---
 
-# How scoring works in Azure AI Search
+# Relevance in Azure AI Search
 
-The query engine in Azure AI Search supports a multi-level approach to ranking search results where there's a built-in ranking modality for each query type, plus extra ranking capabilities for more relevance tuning.
+In a query operation, the relevance of any given result is measured by a ranking algorithm that determines the strength of a match based on how closely it aligns in content or characteristics. An algorithm assigns a score, and results are rank ordered by that score, with the most relevant matches returned in the response. 
 
 Ranking occurs whenever the query request includes full text or vector queries. It doesn't occur if the query invokes strict pattern matching, such as a filter-only query or a specialized query form like autocomplete, suggestions, geospatial search, fuzzy search, or regular expression search. A uniform search score of 1.0 indicates the absence of a ranking algorithm.
 
+The query engine in Azure AI Search supports a multi-level approach to ranking search results, where there's a built-in ranking modality for each query type, plus extra ranking capabilities for extended relevance tuning.
+
 ## Levels of ranking
 
-### Initial ranking
+This section describes the levels of scoring operations. For an illustration of how they work together, see the [diagram](#diagram-of-ranking-algorithms) in this article. A [comparison of search score types and ranges](#types-of-search-scores) is also provided in this article.
+
+### Level 1 (L1) ranking
 
-Assuming the query engine performs a scoring operation, the initial scoring for level 1 (L1) ranking varies by query type.
+Assuming the query engine performs a scoring operation, the initial search score varies by query type.
 
 + Text queries, which match on tokenized strings, are always initially ranked using the [BM25 ranking algorithm](index-similarity-and-scoring.md).
 
-+ Vector query L1 ranking is either Hierarchical Navigable Small World (HNSW) or exhaustive K-nearest neighbor (KNN). Image search or multimodal searches are based on vector queries and scored using the vector L2 ranking algorithms.
++ Vector query L1 ranking is either [Hierarchical Navigable Small World (HNSW) or exhaustive K-nearest neighbor (KNN)](vector-search-ranking.md). Image search or multimodal searches are based on vector queries and scored using the vector L2 ranking algorithms.
 
-### Fused ranking
+### Fused L1 ranking
 
-Hybrid queries that include text and vector components are ranked using the Reciprocal Ranking Fusion (RRF) algorithm that's used for merging the results of multiple queries. RRF is also used if multiple vector queries execute in parallel.
+Hybrid queries that include text and vector components are ranked using the [Reciprocal Ranking Fusion (RRF) algorithm](hybrid-search-ranking.md) that's used for merging the results of multiple queries. RRF is also used if multiple vector queries execute in parallel.
 
 ### Level 2 (L2) ranking
 
@@ -65,7 +69,7 @@ Scored results are indicated for each match in the query response. This table li
 | @search.score | 0 through unlimited | [BM25 ranking algorithm](index-similarity-and-scoring.md#scores-in-a-text-results) for text search |
 | @search.score | 0.333 - 1.00 | [HNSW or exhaustive KNN algorithm](vector-search-ranking.md#scores-in-a-vector-search-results) for vector search |
 | @search.score | 0 through an upper limit determined by the number of queries | [RRF algorithm](hybrid-search-ranking.md#scores-in-a-hybrid-search-results) |
-| @search.rerankerScore | 0.00 - 4.00 | [Semantic ranking algorithm](semantic-search-overview.md#how-ranking-is-scored) for L2 ranking |
+| @search.rerankerScore | 0.00 - 4.00 | [Semantic ranking algorithm](semantic-search-overview.md#how-results-are-scored) for L2 ranking |
 | @search.rerankerScoreBoosted | 0.00 - 4.00 | Semantic ranking algorithm for L2 ranking and custom boosting through a scoring profile |
 
 ## Diagram of ranking algorithms

articles/search/search-security-overview.md

@@ -14,7 +14,7 @@ ms.topic: conceptual
 ms.date: 02/28/2025
 ---
 
-# Security overview for Azure AI Search
+# Security in Azure AI Search
 
 This article describes the security features in Azure AI Search that protect data and operations.
 

articles/search/semantic-how-to-query-request.md

@@ -261,7 +261,7 @@ SearchResults<Hotel> response = await searchClient.SearchAsync<Hotel>(
 
 Only the top 50 matches from the initial results can be semantically ranked. As with all queries, a response is composed of all fields marked as retrievable, or just those fields listed in the `select` parameter. A response includes the original relevance score, and might also include a count, or batched results, depending on how you formulated the request.
 
-In semantic ranking, the response has more elements: a new [semantically ranked relevance score](semantic-search-overview.md#how-ranking-is-scored), an optional caption in plain text and with highlights, and an optional [answer](semantic-answers.md). If your results don't include these extra elements, then your query might be misconfigured. As a first step towards troubleshooting the problem, check the semantic configuration to ensure it's specified in both the index definition and query.
+In semantic ranking, the response has more elements: a new [semantically ranked relevance score](semantic-search-overview.md#how-results-are-scored), an optional caption in plain text and with highlights, and an optional [answer](semantic-answers.md). If your results don't include these extra elements, then your query might be misconfigured. As a first step towards troubleshooting the problem, check the semantic configuration to ensure it's specified in both the index definition and query.
 
 In a client app, you can structure the search page to include a caption as the description of the match, rather than the entire contents of a specific field. This approach is useful when individual fields are too dense for the search results page.
 

articles/search/semantic-search-overview.md

@@ -80,7 +80,7 @@ In semantic ranking, the query subsystem passes search results as an input to su
 
    As of November 2024, the maximum length of each generated summary string passed to the semantic ranker is 2,048 tokens. Previously, it was 256 tokens.
 
-### How ranking is scored
+## How results are scored
 
 Scoring is done over the caption, and any other content from the summary string that fills out the 2,048 token length.