Restructuring vector search docs and adding vector landing page and conceptual page

explore-analyze/ai-features.md

@@ -44,9 +44,9 @@ This general-purpose API enables you to perform {{infer}} operations using EIS,
 
 Natural Language Processing (NLP) enables you to analyze natural language data and make predictions.  Elastic offers a range of [built-in NLP models](/explore-analyze/machine-learning/nlp/ml-nlp-built-in-models.md) such as the Elastic-trained [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md) or [Jina models](/explore-analyze/machine-learning/nlp/ml-nlp-jina.md). You can also [deploy custom NLP models](/explore-analyze/machine-learning/nlp/ml-nlp-overview.md).
 
-### AI-powered search
+### Vector search
 
-[AI-powered search](/solutions/search/ai-search/ai-search.md) helps you find data based on intent and contextual meaning using vector search technology, which uses {{ml}} models to capture meaning in content.
+[Vector search](/solutions/search/vector.md) helps you find data based on intent and contextual meaning using vector embeddings, which use {{ml}} models to capture meaning in content.
 
 #### Semantic and hybrid search
 
@@ -55,7 +55,7 @@ Depending on your team's technical expertise and requirements, you can choose fr
 - For a minimal configuration, managed workflow use [semantic_text](https://www.elastic.co/docs/solutions/search/semantic-search/semantic-search-semantic-text).
 - For more control over the implementation details, implement dense or sparse [vector search](https://www.elastic.co/docs/solutions/search/vector) manually.
 
-[Hybrid search](/solutions/search/hybrid-search.md) combines traditional full-text search with AI-powered search for more powerful search experiences that serve a wider range of user needs.
+[Hybrid search](/solutions/search/hybrid-search.md) combines traditional full-text search with vector search for more powerful search experiences that serve a wider range of user needs.
 
 ### Semantic re-ranking
 

solutions/search/get-started/semantic-search.md

@@ -224,4 +224,4 @@ For example, if you have both a `text` field and a `semantic_text` field, you ca
 A [hybrid search](/solutions/search/hybrid-semantic-text.md) provides comprehensive search capabilities to find relevant information based on both the raw text and its underlying meaning.
 
 To learn about more options, such as vector and keyword search, go to [](/solutions/search/search-approaches.md).
-For a summary of the AI-powered search use cases, go to [](/solutions/search/ai-search/ai-search.md).
+For a summary of vector search use cases, go to [](/solutions/search/vector.md).

solutions/search/hybrid-search.md

@@ -12,8 +12,8 @@ products:
 ---
 # Hybrid search
 
-Hybrid search combines traditional [full-text search](full-text.md) with [AI-powered search](ai-search/ai-search.md) for more powerful search experiences that serve a wider range of user needs.
+Hybrid search combines traditional [full-text search](full-text.md) with [vector search](vector.md) for more powerful search experiences that serve a wider range of user needs.
 
-The recommended way to use hybrid search in the Elastic Stack is following the `semantic_text` workflow. Check out the [hands-on tutorial](hybrid-semantic-text.md) for a step-by-step guide.
+The recommended way to use hybrid search in the {{stack}} is following the `semantic_text` workflow. Check out the [hands-on tutorial](hybrid-semantic-text.md) for a step-by-step guide.
 
 We recommend implementing hybrid search with the [reciprocal rank fusion (RRF)](elasticsearch://reference/elasticsearch/rest-apis/reciprocal-rank-fusion.md) algorithm. This approach merges rankings from both semantic and lexical queries, giving more weight to results that rank high in either search. This ensures that the final results are balanced and relevant.

solutions/search/search-approaches.md

@@ -21,8 +21,8 @@ The following table provides an overview of the fundamental search techniques av
 | Name | Description | Notes |
 |------|-------------|--------|
 | [**Full-text search**](full-text.md) | Traditional lexical search with analyzers and relevance tuning | Essential foundation for keyword matching, works out of the box |
-| [**AI-powered search**](ai-search/ai-search.md) | Machine learning-based search using natural language understanding | Includes [vector search](vector.md) and [semantic search](semantic-search.md) approaches |
-| [**Hybrid search**](hybrid-search.md) | Combines lexical and vector/semantic approaches | Best balance for both keyword precision and semantic relevance |
+| [**Vector search**](vector.md) | Machine learning-based search using natural language understanding | Includes [semantic search](semantic-search.md), [dense](vector/dense-vector.md) and [sparse](vector/sparse-vector.md) vector approaches |
+| [**Hybrid search**](hybrid-search.md) | Combines full-text and vector search approaches | Best balance for both keyword precision and semantic relevance |
 | [**Ranking and reranking**](ranking.md) | Post-processing results to improve relevance | Optional ML-based enhancement for fine-tuned relevance |
 | [**Geospatial search**](/explore-analyze/geospatial-analysis.md) | Location-based search and spatial relationships | For maps, distance calculations, and shape queries |
 

solutions/search/semantic-search.md

@@ -16,11 +16,9 @@ products:
 This page focuses on the semantic search workflows available in {{es}}. For detailed information about lower-level vector search implementations, refer to [vector search](vector.md).
 :::
 
-{{es}} provides various semantic search capabilities using [natural language processing (NLP)](/explore-analyze/machine-learning/nlp.md) and [vector search](vector.md).
+Semantic search uses [{{nlp}} (NLP)](/explore-analyze/machine-learning/nlp.md) models and [vector search](vector.md) to find results based on meaning, not just keywords. This page covers the managed workflows available in {{es}} for implementing semantic search.
 
-To understand the infrastructure that powers semantic search and other NLP tasks, including managed services and inference endpoints, see the [Elastic Inference overview](../../explore-analyze/elastic-inference.md) page.
-
-Learn more about use cases for AI-powered search in the [overview](ai-search/ai-search.md) page.
+For the foundational concepts behind vector search, refer to [How vector search works](vector/how-vector-search-works.md). To understand the infrastructure that powers semantic search and other NLP tasks, including managed services and inference endpoints, refer to the [Elastic Inference overview](../../explore-analyze/elastic-inference.md) page.
 
 ## Overview of semantic search workflows [semantic-search-workflows-overview]
 
@@ -42,7 +40,7 @@ This diagram summarizes the relative complexity of each workflow:
 
 The simplest way to use NLP models in the {{stack}} is through the [`semantic_text` workflow](semantic-search/semantic-search-semantic-text.md). We recommend using this approach because it abstracts away a lot of manual work. All you need to do is create an index mapping to start ingesting, embedding, and querying data. There is no need to define model-related settings and parameters, or to create {{infer}} ingest pipelines. For guidance on the available query types for `semantic_text`, see [Querying `semantic_text` fields](elasticsearch://reference/elasticsearch/mapping-reference/semantic-text.md#querying-semantic-text-fields).
 
-To learn more about supported services, refer to [](/explore-analyze/elastic-inference/inference-api.md) and the [{{infer}} API](https://www.elastic.co/docs/api/doc/elasticsearch/group/endpoint-inference) documentation. For an end-to-end tutorial, refer to [Semantic search with `semantic_text`](semantic-search/semantic-search-semantic-text.md).
+To learn more about supported services, refer to the [Elastic Inference API](/explore-analyze/elastic-inference/inference-api.md) and the [{{infer}} API](https://www.elastic.co/docs/api/doc/elasticsearch/group/endpoint-inference) documentation. For an end-to-end tutorial, refer to [Semantic search with `semantic_text`](semantic-search/semantic-search-semantic-text.md).
 
 ### Option 2: Inference API [_infer_api_workflow]
 
@@ -57,7 +55,7 @@ You can also deploy NLP in {{es}} manually, without using an {{infer}} endpoint.
 For an end-to-end tutorial, refer to [Semantic search with a model deployed in {{es}}](vector/dense-versus-sparse-ingest-pipelines.md).
 
 ::::{tip}
-Refer to [vector queries and field types](vector.md#vector-queries-and-field-types) for a quick reference overview.
+Refer to [vector search workflows](vector.md#which-workflow-should-i-use) for a quick reference overview.
 ::::
 
 ## Learn more [semantic-search-read-more]