Update the doc.

Author: afoucret

docs/reference/query-languages/esql/_snippets/commands/examples/rerank.csv-spec/combine.md

@@ -5,15 +5,14 @@ FROM books METADATA _score
 | WHERE MATCH(description, "hobbit") OR MATCH(author, "Tolkien")
 | SORT _score DESC
 | LIMIT 100
-| RERANK rerank_score = "hobbit" ON description, author WITH { "inference_id" : "test_reranker" }
+| RERANK rerank_score = "hobbit" ON title, description WITH { "inference_id" : "test_reranker" }
 | EVAL original_score = _score, _score = rerank_score + original_score
 | SORT _score
 | LIMIT 3
-| KEEP title, original_score, rerank_score, _score
 ```
 
-| title:text | _score:double | rerank_score:double | rerank_score:double |
-| --- | --- | --- | --- |
-| Poems from the Hobbit | 4.012462615966797 | 0.001396648003719747 | 0.001396648003719747 |
-| The Lord of the Rings - Boxed Set | 3.768855094909668 | 0.0010020040208473802 | 0.001396648003719747 |
-| Return of the King Being the Third Part of The Lord of the Rings | 3.6248698234558105 | 9.000900317914784E-4 | 0.001396648003719747 |
+| title:text | _score:double | rerank_score:double |
+| --- | --- | --- |
+| The Lord of the Rings Poster Collection: Six Paintings by Alan Lee (No. 1) | 0.7976278 | 0.125 |
+| A Middle English Reader and Vocabulary | 1.043297 | 0.07692308 |
+| FINAL WITNESS | 1.405817 | 0.07692308 |

docs/reference/query-languages/esql/_snippets/commands/examples/rerank.csv-spec/rerank-top-snippets.md

@@ -0,0 +1,12 @@
+% This is generated by ESQL's AbstractFunctionTestCase. Do not edit it. See ../README.md for how to regenerate it.
+
+```esql
+FROM books
+| WHERE MATCH(title, "return")
+| RERANK "Tolkien" ON TOP_SNIPPETS(description, "Tolkien", { "num_snippets": 3, "num_words": 25 }) WITH { "inference_id" : "test_reranker" }
+```
+
+| book_no:keyword | title:text | _score:double |
+| --- | --- | --- |
+| 2714 | Return of the King Being the Third Part of The Lord of the Rings | 0.007092198356986046 |
+| 7350 | Return of the Shadow | 0.012500000186264515 |

docs/reference/query-languages/esql/_snippets/commands/examples/rerank.csv-spec/two-queries.md

@@ -6,13 +6,12 @@ FROM books METADATA _score
 | SORT _score DESC
 | LIMIT 100
 | RERANK rerank_score = "hobbit" ON description, author WITH { "inference_id" : "test_reranker" }
-| SORT rerank_score
+| SORT rerank_score DESC, book_no DESC
 | LIMIT 3
-| KEEP title, _score, rerank_score
 ```
 
 | title:text | _score:double | rerank_score:double |
 | --- | --- | --- |
-| Return of the Shadow | 3.4218082427978516 | 5.740527994930744E-4 |
-| Return of the King Being the Third Part of The Lord of the Rings | 2.8398752212524414 | 9.000900317914784E-4 |
-| The Lays of Beleriand | 1.5629040002822876 | 9.36329597607255E-4 |
+| The Lord of the Rings Poster Collection: Six Paintings by Alan Lee (No. 1) | 0.7976278066635132 | 0.125 |
+| A Middle English Reader and Vocabulary | 1.043297290802002 | 0.07692307978868484 |
+| FINAL WITNESS | 1.4058171510696411 | 0.07692307978868484 |

docs/reference/query-languages/esql/_snippets/commands/layout/rerank.md

@@ -7,14 +7,13 @@ stack: preview 9.2.0
 The `RERANK` command uses an inference model to compute a new relevance score
 for an initial set of documents, directly within your ES|QL queries.
 
-:::::{important}
-**RERANK processes each row through an inference model, which impacts performance and costs.**
+::::{tab-set}
 
-::::{applies-switch}
+:::{tab-item} 9.3.0+
 
-:::{applies-item} stack: ga 9.3+
-
-`RERANK` automatically limits processing to **1000 rows by default** to prevent accidental high consumption. This limit is applied before the `RERANK` command executes.
+Starting in version 9.3.0, `RERANK` automatically limits processing to **1000
+rows by default** to prevent accidental high consumption. This limit is applied
+before the `RERANK` command executes.
 
 If you need to process more rows, you can adjust the limit using the cluster setting:
 ```
@@ -37,7 +36,7 @@ PUT _cluster/settings
 ```
 :::
 
-:::{applies-item} stack: ga =9.2
+:::{tab-item} 9.2.x
 
 No automatic row limit is applied. **You should always use `LIMIT` before or after `RERANK` to control the number of documents processed**, to avoid accidentally reranking large datasets which can result in high latency and increased costs.
 
@@ -52,7 +51,6 @@ FROM books
 :::
 
 ::::
-:::::
 
 **Syntax**
 
@@ -108,36 +106,31 @@ necessary.
 
 How you increase the timeout depends on your deployment type:
 
-::::::{applies-switch}
-
-:::::{applies-item} ess:
+::::{tab-set}
+:::{tab-item} {{ech}}
 
 * You can adjust {{es}} settings in
   the [Elastic Cloud Console](docs-content://deploy-manage/deploy/elastic-cloud/edit-stack-settings.md)
 * You can also adjust the `search.default_search_timeout` cluster setting
   using [Kibana's Advanced settings](kibana://reference/advanced-settings.md#kibana-search-settings)
+  :::
 
-:::::
-
-:::::{applies-item} self:
+:::{tab-item} Self-managed
 
 * You can configure at the cluster level by setting
   `search.default_search_timeout` in `elasticsearch.yml` or updating
   via [Cluster Settings API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-cluster-put-settings)
 * You can also adjust the `search:timeout` setting
   using [Kibana's Advanced settings](kibana://reference/advanced-settings.md#kibana-search-settings)
 * Alternatively, you can add timeout parameters to individual queries
+  :::
 
-:::::
-
-:::::{applies-item} serverless:
+:::{tab-item} {{serverless-full}}
 
 * Requires a manual override from Elastic Support because you cannot modify
   timeout settings directly
-
-:::::
-
-::::::
+  :::
+  ::::
 
 If you don't want to increase the timeout limit, try the following:
 
@@ -165,3 +158,9 @@ Combine the original score with the reranked score:
 
 :::{include} ../examples/rerank.csv-spec/combine.md
 :::
+
+Rerank using snippets extracted from the document with the `TOP_SNIPPETS`
+function:
+
+:::{include} ../examples/rerank.csv-spec/rerank-top-snippets.md
+:::