DOC-1314 Add dimensions field to cohere_embeddings processor (#244)

Author: asimms41

modules/components/pages/processors/cohere_embeddings.adoc

@@ -17,14 +17,15 @@ Introduced in version 4.37.0.
 endif::[]
 
 ```yml
-# Config fields, showing default values
+# Configuration fields, showing default values
 label: ""
 cohere_embeddings:
   base_url: https://api.cohere.com
   auth_token: "" # No default (required)
   model: embed-english-v3.0 # No default (required)
   text_mapping: "" # No default (optional)
-  dimensions: search_document
+  input_type: search_document
+  dimensions: "" # No default (optional)
 ```
 
 This processor sends text strings to your chosen large language model (LLM), which generates vector embeddings for them using the Cohere API. By default, the processor submits the entire payload of each message as a string, unless you use the `text_mapping` field to customize it.
@@ -101,7 +102,7 @@ The text you want to generate a vector embedding for. By default, the processor
 
 *Type*: `string`
 
-=== `dimensions`
+=== `input_type`
 
 The type of text input passed to the model.
 
@@ -110,15 +111,29 @@ The type of text input passed to the model.
 *Default*: `search_document`
 
 |===
-| Option | Summary
+| Option | Description
+
 | `classification`
 | For embeddings passed through a text classifier.
+
 | `clustering`
 | For embeddings run through a clustering algorithm.
+
 | `search_document`
-| For embeddings stored in a vector database for search use cases.
+| For embeddings stored in a vector database and used for search use cases.
+
 | `search_query`
 | For embeddings of search queries run against a vector database to find relevant documents.
 |===
 
+=== `dimensions`
+
+The number of dimensions (numerical values) in each vector embedding generated by this processor. This parameter only supports https://docs.cohere.com/v2/docs/embeddings[`embed-v4.0`^] and newer models.
+
+*Type*: `int`
+
+*Default*: `""`
+
+Options: `256`, `512`, `1024`, `1536`
+
 // end::single-source[]