Module Values.InputDataConfigSource

The input properties for an inference job. The document reader config field applies only to non-text inputs for custom analysis.

Sourcetype nonrec t = {
  1. s3Uri : S3Uri.t;
    (*

    The Amazon S3 URI for the input data. The URI must be in same Region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of data files. For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of them as input.

    *)
  2. inputFormat : InputFormat.t option;
    (*

    Specifies how the text in an input file should be processed: ONE_DOC_PER_FILE - Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers. ONE_DOC_PER_LINE - Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages.

    *)
  3. documentReaderConfig : DocumentReaderConfig.t option;
    (*

    Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.

    *)
}
Sourceval context_ : string
Sourceval make : ?inputFormat:??? -> ?documentReaderConfig:??? -> s3Uri:S3Uri.t -> unit -> t
Sourceval to_value : t -> [> `Structure of (string * [> `Enum of string | `String of S3Uri.t | `Structure of (string * [> `Enum of string | `List of [> `Enum of string ] list ]) list ]) list ]
Sourceval to_query : t -> Awso.Client.Query.t
Sourceval of_xml : Awso.Xml.t -> t
Sourceval of_string : string -> t
Sourceval of_json : Yojson.Safe.t -> t
Sourceval to_json : t -> Yojson.Safe.t