You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: solutions/search/retrievers-examples.md
+4-12Lines changed: 4 additions & 12 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -401,8 +401,7 @@ Which would return the following results:
401
401
402
402
## Example: Grouping results by year with `collapse`[retrievers-examples-collapsing-retriever-results]
403
403
404
-
In our result set, we have many documents with the same `year` value. We can clean this up using the `collapse` parameter with our retriever. This, as with the standard
In our result set, we have many documents with the same `year` value. We can clean this up using the `collapse` parameter with our retriever. This, as with the standard [collapse](https://www.elastic.co/guide/en/elasticsearch/reference/current/collapse-search-results.html) feature,
406
405
enables grouping results by any field and returns only the highest-scoring document from each group. In this example we’ll collapse our results based on the `year` field.
407
406
408
407
```console
@@ -552,9 +551,7 @@ This returns the following response with collapsed results.
552
551
553
552
## Example: Highlighting results based on nested sub-retrievers [retrievers-examples-highlighting-retriever-results]
554
553
555
-
Highlighting is now also available for nested sub-retrievers matches. For example, consider the same `rrf` retriever as above, with a `knn` and `standard` retriever as its sub-retrievers. We can specify a `highlight` section,
556
-
% TODO URL as defined in the [highlighting](/raw-migrated-files/elasticsearch/elasticsearch-reference/highlighting.md) documentation,
557
-
and compute highlights for the top results.
554
+
Highlighting is now also available for nested sub-retrievers matches. For example, consider the same `rrf` retriever as above, with a `knn` and `standard` retriever as its sub-retrievers. We can specify a `highlight` section, as defined in the [highlighting](https://www.elastic.co/guide/en/elasticsearch/reference/current/highlighting.html) documentation, and compute highlights for the top results.
558
555
559
556
```console
560
557
GET /retrievers_example/_search
@@ -751,9 +748,7 @@ POST /retrievers_example_nested/_doc/3
751
748
POST /retrievers_example_nested/_refresh
752
749
```
753
750
754
-
Now we can run an `rrf` retriever query and also compute inner hits
755
-
% TODO URL [inner hits](/raw-migrated-files/elasticsearch/elasticsearch-reference/inner-hits.md)
756
-
for the `nested_field.nested_vector` field, based on the `knn` query specified.
751
+
Now we can run an `rrf` retriever query and also compute [inner hits](https://www.elastic.co/guide/en/elasticsearch/reference/current/inner-hits.html) for the `nested_field.nested_vector` field, based on the `knn` query specified.
757
752
758
753
```console
759
754
GET /retrievers_example_nested/_search
@@ -1276,10 +1271,7 @@ The output of which, albeit a bit verbose, will provide all the necessary info t
1276
1271
1277
1272
## Example: Rerank results of an RRF retriever [retrievers-examples-text-similarity-reranker-on-top-of-rrf]
1278
1273
1279
-
To demonstrate the full functionality of retrievers, the following examples also require access to a semantic reranking model
1280
-
% TODO URL [semantic reranking model](/raw-migrated-files/elasticsearch/elasticsearch-reference/semantic-reranking.md#semantic-reranking-models)
To demonstrate the full functionality of retrievers, the following examples also require access to a [semantic reranking model](https://www.elastic.co/guide/en/elasticsearch/reference/current/semantic-reranking.html) set up using the [Elastic inference APIs](https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html).
1283
1275
1284
1276
In this example we’ll set up a reranking service and use it with the `text_similarity_reranker` retriever to rerank our top results.
0 commit comments