Values.DocumentSourceInformation about a document from a search service such as OpenSearch (self managed). Amazon Kendra Intelligent Ranking uses this information to rank and score on.
type nonrec t = {id : DocumentId.t;The identifier of the document from the search service.
*)groupId : GroupId.t option;The optional group identifier of the document from the search service. Documents with the same group identifier are grouped together and processed as one document within the service.
*)title : DocumentTitle.t option;The title of the search service's document.
*)body : DocumentBody.t option;The body text of the search service's document.
*)tokenizedTitle : TitleTokensList.t option;The title of the search service's document represented as a list of tokens or words. You must choose to provide Title or TokenizedTitle. You cannot provide both.
*)tokenizedBody : BodyTokensList.t option;The body text of the search service's document represented as a list of tokens or words. You must choose to provide Body or TokenizedBody. You cannot provide both.
*)originalScore : Float_.t;The original document score or rank from the search service. Amazon Kendra Intelligent Ranking gives the document a new score or rank based on its intelligent search algorithms.
*)}val make :
?groupId:??? ->
?title:??? ->
?body:??? ->
?tokenizedTitle:??? ->
?tokenizedBody:??? ->
id:DocumentId.t ->
originalScore:Float_.t ->
unit ->
tval to_value :
t ->
[> `Structure of
(string
* [> `Float of Float_.t
| `List of [> `String of Tokens.t ] list
| `String of DocumentId.t ])
list ]