[8.x] Removing tech-preview header and updating documentation for retrievers and RRF (#114810)

docs/reference/search/retriever.asciidoc

@@ -1,8 +1,6 @@
 [[retriever]]
 === Retriever
 
-preview::["This functionality is in technical preview and may be changed or removed in a future release. The syntax will likely change before GA. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features."]
-
 A retriever is a specification to describe top documents returned from a
 search. A retriever replaces other elements of the <<search-search, search API>>
 that also return top documents such as <<query-dsl, `query`>> and
@@ -75,7 +73,7 @@ Collapses the top documents by a specified key into a single top document per ke
 ===== Restrictions
 
 When a retriever tree contains a compound retriever (a retriever with two or more child
-retrievers) *only* the query element is allowed.
+retrievers) the <<search-after, search after>> parameter is not supported.
 
 [discrete]
 [[standard-retriever-example]]
@@ -245,12 +243,6 @@ include::{es-ref-dir}/rest-api/common-parms.asciidoc[tag=rrf-rank-window-size]
 
 include::{es-ref-dir}/rest-api/common-parms.asciidoc[tag=rrf-filter]
 
-===== Restrictions
-
-An RRF retriever is a compound retriever. Child retrievers may not use
-elements that are restricted by having a compound retriever as part of
-the retriever tree.
-
 [discrete]
 [[rrf-retriever-example-hybrid]]
 ==== Example: Hybrid search
@@ -413,10 +405,6 @@ Applies the specified <<query-dsl-bool-query, boolean query filter>> to the chil
 If the child retriever already specifies any filters, then this top-level filter is applied in conjuction
 with the filter defined in the child retriever.
 
-===== Restrictions
-
-A text similarity re-ranker retriever is a compound retriever. Child retrievers may not use elements that are restricted by having a compound retriever as part of the retriever tree.
-
 [discrete]
 [[text-similarity-reranker-retriever-example-cohere]]
 ==== Example: Cohere Rerank
@@ -555,4 +543,3 @@ at the top-level and instead are only allowed as elements of specific retrievers
 * <<request-body-search-terminate-after, `terminate_after`>>
 * <<search-sort-param, `sort`>>
 * <<rescore, `rescore`>>
-* <<search-api-min-score, `min_score`>>

docs/reference/search/rrf.asciidoc

@@ -1,8 +1,6 @@
 [[rrf]]
 === Reciprocal rank fusion
 
-preview::["This functionality is in technical preview and may be changed or removed in a future release. The syntax will likely change before GA. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features."]
-
 https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf[Reciprocal rank fusion (RRF)]
 is a method for combining multiple result sets with different relevance indicators into a single result set.
 RRF requires no tuning, and the different relevance indicators do not have to be related to each other to achieve high-quality results.
@@ -95,19 +93,21 @@ The `rrf` retriever supports:
 
 * <<search-aggregations, aggregations>>
 * <<search-from-param, from>>
+* <<search-suggesters, suggesters>>
+* <<highlighting, highlighting>>
+* <<collapse-search-results, collapse>>
+* <<profiling-queries, profiling>>
 
 The `rrf` retriever does not currently support:
 
 * <<search-api-scroll-query-param, scroll>>
-* <<search-api-pit, point in time>>
 * <<search-sort-param, sort>>
 * <<rescore, rescore>>
-* <<search-suggesters, suggesters>>
-* <<highlighting, highlighting>>
-* <<collapse-search-results, collapse>>
-* <<profiling-queries, profiling>>
 
 Using unsupported features as part of a search with an `rrf` retriever results in an exception.
++
+IMPORTANT: It is best to avoid providing a <<search-api-pit, point in time>> as part of the request, as
+RRF creates one internally that is shared by all sub-retrievers to ensure consistent results.
 
 [[rrf-using-multiple-standard-retrievers]]
 ==== Reciprocal rank fusion using multiple standard retrievers

docs/reference/search/search-your-data/retrievers-overview.asciidoc

@@ -1,9 +1,7 @@
 [[retrievers-overview]]
 === Retrievers
 
-preview::[]
-
-A retriever is an abstraction that was added to the Search API in *8.14.0*.
+A retriever is an abstraction that was added to the Search API in *8.14.0* and was made generally available in *8.16.0*.
 This abstraction enables the configuration of multi-stage retrieval pipelines within a single `_search` call.
 This simplifies your search application logic, because you no longer need to configure complex searches via multiple {es} calls or implement additional client-side logic to combine results from different queries.
 
@@ -32,8 +30,7 @@ with different relevance indicators into a single result set.
 An RRF retriever is a *compound retriever*, where its `filter` element is
 propagated to its sub retrievers.
 +
-Sub retrievers may not use elements that are restricted by having a compound retriever as part of the retriever tree.
-See the <<rrf-using-multiple-standard-retrievers,RRF documentation>> for detailed examples and information on how to use the RRF retriever.
+
 * <<text-similarity-reranker-retriever,*Text Similarity Re-ranker Retriever*>>. Used for <<semantic-reranking,semantic reranking>>.
 Requires first creating a `rerank` task using the <<put-inference-api,{es} Inference API>>.
 
@@ -72,82 +69,56 @@ When using compound retrievers, only the query element is allowed, which enforce
 [[retrievers-overview-example]]
 ==== Example
 
-The following example demonstrates how using retrievers simplify the composability of queries for RRF ranking.
+The following example demonstrates the powerful queries that we can now compose, and how retrievers simplify this process. We can use any combination of retrievers we want, propagating the
+results of a nested retriever to its parent. In this scenario, we'll make use of all 4 (currently) available retrievers, i.e. `standard`, `knn`, `text_similarity_reranker` and `rrf`.
+We'll first combine the results of a `semantic` query using the `standard` retriever, and that of a `knn` search on a dense vector field, using `rrf` to get the top 100 results.
+Finally, we'll then rerank the top-50 results of `rrf` using the `text_similarity_reranker`
 
 [source,js]
 ----
 GET example-index/_search
 {
   "retriever": {
-    "rrf": {
-      "retrievers": [
-        {
-          "standard": {
-            "query": {
-              "sparse_vector": {
-                "field": "vector.tokens",
-                "inference_id": "my-elser-endpoint",
-                "query": "What blue shoes are on sale?"
+    "text_similarity_reranker": {
+      "retriever": {
+        "rrf": {
+          "retrievers": [
+            {
+                "standard": {
+                  "query": {
+                    "semantic": {
+                      "field": "inference_field",
+                      "query": "state of the art vector database"
+                    }
+                  }
+                }
+            },
+            {
+              "knn": {
+                "query_vector": [
+                  0.54,
+                  ...,
+                  0.245
+                ],
+                "field": "embedding",
+                "k": 10,
+                "num_candidates": 15
               }
             }
-          }
-        },
-        {
-          "standard": {
-            "query": {
-              "match": {
-                "text": "blue shoes sale"
-              }
-            }
-          }
-        }
-      ]
-    }
-  }
-}
-----
-//NOTCONSOLE
-
-This example demonstrates how you can combine different retrieval strategies into a single `retriever` pipeline.
-
-Compare to `RRF` with `sub_searches` approach:
-
-.*Expand* for example
-[%collapsible]
-==============
-
-[source,js]
-----
-GET example-index/_search
-{
-  "sub_searches":[
-    {
-      "query":{
-        "match":{
-          "text":"blue shoes sale"
-        }
-      }
-    },
-    {
-      "query":{
-        "sparse_vector": {
-            "field": "vector.tokens",
-            "inference_id": "my-elser-endoint",
-            "query": "What blue shoes are on sale?"
-          }
+          ],
+          "rank_window_size": 100,
+          "rank_constant": 10
         }
-      }
-  ],
-  "rank":{
-    "rrf":{
-      "rank_window_size":50,
-      "rank_constant":20
+      },
+      "rank_window_size": 50,
+      "field": "description",
+      "inference_text": "what's the best way to create complex pipelines and retrieve documents?",
+      "inference_id": "my-awesome-rerank-model"
     }
   }
 }
 ----
 //NOTCONSOLE
-==============
 
 [discrete]
 [[retrievers-overview-glossary]]

server/src/main/java/org/elasticsearch/search/retriever/CompoundRetrieverBuilder.java

@@ -194,6 +194,9 @@ public ActionRequestValidationException validate(
                 validationException
             );
         }
+        for (RetrieverSource innerRetriever : innerRetrievers) {
+            validationException = innerRetriever.retriever().validate(source, validationException, allowPartialSearchResults);
+        }
         return validationException;
     }