Rationalize solutions/search nav (#3753)

based on our discussion yesterday, tried to clean up the
nav here and avoid inconsistencies in the search approaches

- restructured search navigation to nest related pages under
search-approaches.md
- reordered nav a bit more logically : moved querying-for-search.md up,
cross-cluster-search.md down
- updated apis-and-tools.md: added agent builder first in genai section,
simplified mcp reference now that we have multiple

---------

Co-authored-by: Benjamin Ironside Goldstein <[email protected]>

Author: leemthompo

solutions/search/apis-and-tools.md

@@ -74,14 +74,14 @@ The accompanying [GitHub repository](https://www.github.com/elastic/elasticsearc
 
 ## Generative AI tools
 
-### Playground
+### Agent Builder
 
-Use [Playground](rag/playground.md) to combine your {{es}} data with the power of large language models (LLMs) for retrieval augmented generation (RAG), using a chat interface. Playground is also very useful for testing and debugging your {{es}} queries, using the [retrievers](retrievers-overview.md) syntax with the `_search` endpoint.
+[Agent Builder](elastic-agent-builder.md) enables you to create AI agents that can interact with your Elasticsearch data, execute queries, and provide intelligent responses. It provides a complete framework for building conversational AI experiences on top of your search infrastructure.
 
-### {{es}} Model Context Protocol (MCP) server
+### Playground
 
-Connect to your Elasticsearch data directly from any MCP Client (like Claude Desktop) using the Model Context Protocol (MCP).
+[Playground](rag/playground.md) enables you to use large language models (LLMs) to understand, explore, and analyze your {{es}} data using retrieval augmented generation (RAG), via a chat interface. Playground is also very useful for testing and debugging your {{es}} queries, using the [retrievers](retrievers-overview.md) syntax with the `_search` endpoint.
 
-This server enables connecting agents to your Elasticsearch data and allows you to interact with your Elasticsearch indices through natural language conversations.
+### Model Context Protocol (MCP)
 
-Learn more in the [elastic/mcp-server-elasticsearch](https://github.com/elastic/mcp-server-elasticsearch?tab=readme-ov-file#elasticsearch-mcp-server) GitHub repository.
+The [Model Context Protocol (MCP)](mcp.md) lets you connect AI agents and assistants to your {{es}} data to enable natural language interactions with your indices.

solutions/search/search-approaches.md

@@ -7,15 +7,16 @@ applies_to:
 
 To deliver relevant search results, you need to choose the right search approach for your data and use case.
 
+## Overview of search techniques
+
 The following table provides an overview of the fundamental search techniques available in {{es}}:
 
 | 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 |
-| [**Vector search**](vector.md) | Similarity search using numerical vectors | Requires extra setup/resources, ideal for finding similar documents |
-| [**Semantic search**](semantic-search.md) | Meaning-based search using natural language understanding | Requires ML models and vector infrastructure |
-| [**Hybrid search**](hybrid-semantic-text.md) | Combines lexical and vector/semantic approaches | Best balance for both keyword precision and semantic relevance |
-| [**Re-ranking**](ranking/semantic-reranking.md) | Post-processing results to improve relevance | Optional ML-based enhancement for fine-tuned relevance |
+| [**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 |
+| [**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 |
 
 :::::{tip}

solutions/toc.yml

@@ -15,35 +15,53 @@ toc:
         children:
           - file: search/search-pipelines.md
       - file: search/search-approaches.md
-      - file: search/full-text.md
         children:
-          - file: search/full-text/how-full-text-works.md
-          - file: search/full-text/search-with-synonyms.md
+          - file: search/full-text.md
             children:
-              - file: search/full-text/create-update-synonyms-api-example.md
-          - file: search/full-text/text-analysis-during-search.md
-          - file: search/full-text/search-relevance.md
-            children:
-              - file: search/full-text/search-relevance/mixing-exact-search-with-stemming.md
-              - file: search/full-text/search-relevance/consistent-scoring.md
-              - file: search/full-text/search-relevance/static-scoring-signals.md
-      - file: search/ai-search/ai-search.md
-        children:
-          - file: search/vector.md
+              - file: search/full-text/how-full-text-works.md
+              - file: search/full-text/search-with-synonyms.md
+                children:
+                  - file: search/full-text/create-update-synonyms-api-example.md
+              - file: search/full-text/text-analysis-during-search.md
+              - file: search/full-text/search-relevance.md
+                children:
+                  - file: search/full-text/search-relevance/mixing-exact-search-with-stemming.md
+                  - file: search/full-text/search-relevance/consistent-scoring.md
+                  - file: search/full-text/search-relevance/static-scoring-signals.md
+          - file: search/ai-search/ai-search.md
             children:
-              - file: search/vector/dense-vector.md
+              - file: search/vector.md
                 children:
-                  - file: search/vector/knn.md
-                  - file: search/vector/bring-own-vectors.md
-              - file: search/vector/sparse-vector.md
-              - file: search/vector/dense-versus-sparse-ingest-pipelines.md
-          - file: search/semantic-search.md
-            children:
-              - file: search/semantic-search/semantic-search-semantic-text.md
-              - file: search/semantic-search/semantic-search-inference.md
-              - file: search/semantic-search/semantic-search-elser-ingest-pipelines.md
-              - file: search/semantic-search/cohere-es.md
-          - file: search/using-openai-compatible-models.md
+                  - file: search/vector/dense-vector.md
+                    children:
+                      - file: search/vector/knn.md
+                      - file: search/vector/bring-own-vectors.md
+                  - file: search/vector/sparse-vector.md
+                  - file: search/vector/dense-versus-sparse-ingest-pipelines.md
+              - file: search/semantic-search.md
+                children:
+                  - file: search/semantic-search/semantic-search-semantic-text.md
+                  - file: search/semantic-search/semantic-search-inference.md
+                  - file: search/semantic-search/semantic-search-elser-ingest-pipelines.md
+                  - file: search/semantic-search/cohere-es.md
+              - file: search/using-openai-compatible-models.md
+          - file: search/hybrid-search.md
+            children:
+              - file: search/hybrid-semantic-text.md
+          - file: search/ranking.md
+            children:
+              - file: search/ranking/semantic-reranking.md
+              - file: search/ranking/learning-to-rank-ltr.md
+                children:
+                  - file: search/ranking/learning-to-rank-model-training.md
+                  - file: search/ranking/learning-to-rank-search-usage.md
+      - file: search/querying-for-search.md
+        children:
+          - file: search/the-search-api.md
+          - file: search/async-search-api.md
+          - file: search/esql-for-search.md
+          - file: search/retrievers-overview.md
+          - file: search/search-templates.md
       - file: search/elastic-agent-builder.md
         children:
           - file: search/agent-builder/get-started.md
@@ -68,26 +86,6 @@ toc:
               - file: search/rag/playground-query.md
               - file: search/rag/playground-troubleshooting.md
           - file: search/mcp.md
-      - file: search/hybrid-search.md
-        children:
-          - file: search/hybrid-semantic-text.md
-      - file: search/ranking.md
-        children:
-          - file: search/ranking/semantic-reranking.md
-          - file: search/ranking/learning-to-rank-ltr.md
-            children:
-              - file: search/ranking/learning-to-rank-model-training.md
-              - file: search/ranking/learning-to-rank-search-usage.md
-      - file: search/cross-cluster-search.md
-        children:
-          - file: search/using-resolve-cluster-endpoint-before-cross-cluster-search.md
-      - file: search/querying-for-search.md
-        children:
-          - file: search/the-search-api.md
-          - file: search/async-search-api.md
-          - file: search/esql-for-search.md
-          - file: search/retrievers-overview.md
-          - file: search/search-templates.md
       - file: search/site-or-app.md
         children:
           - file: search/site-or-app/clients.md
@@ -97,6 +95,9 @@ toc:
               - file: search/search-applications/search-application-api.md
               - file: search/search-applications/search-application-security.md
               - file: search/search-applications/search-application-client.md
+      - file: search/cross-cluster-search.md
+        children:
+          - file: search/using-resolve-cluster-endpoint-before-cross-cluster-search.md
       - file: search/apis-and-tools.md
       - file: search/ai-assistant.md
       - file: search/query-rules-ui.md