Updating 8.x docs for cohere bit embedding addition

Author: ymao1

docs/reference/inference/service-cohere.asciidoc

@@ -62,7 +62,7 @@ include::inference-shared.asciidoc[tag=chunking-settings-strategy]
 
 `service`::
 (Required, string)
-The type of service supported for the specified task type. In this case, 
+The type of service supported for the specified task type. In this case,
 `cohere`.
 
 `service_settings`::
@@ -127,6 +127,8 @@ Valid values are:
 * `byte`: use it for signed int8 embeddings (this is a synonym of `int8`).
 * `float`: use it for the default float embeddings.
 * `int8`: use it for signed int8 embeddings.
+* `binary`: use it for binary embeddings, which are encoded as bytes with signed int8 precision.
+* `bit`: use it for binary embeddings, which are encoded as bytes with signed int8 precision (this is a synonym of `binary`).
 
 `model_id`:::
 (Optional, string)
@@ -228,4 +230,4 @@ PUT _inference/rerank/cohere-rerank
 // TEST[skip:TBD]
 
 For more examples, also review the
-https://docs.cohere.com/docs/elasticsearch-and-cohere#rerank-search-results-with-cohere-and-elasticsearch[Cohere documentation].
+https://docs.cohere.com/docs/elasticsearch-and-cohere#rerank-search-results-with-cohere-and-elasticsearch[Cohere documentation].