Values.ParsingConfigurationSourceSettings for parsing document contents. By default, the service converts the contents of each document into text before splitting it into chunks. To improve processing of PDF files with tables and images, you can configure the data source to convert the pages of text into images and use a model to describe the contents of each page.
type nonrec t = {parsingStrategy : ParsingStrategy.t;The parsing strategy for the data source.
*)bedrockFoundationModelConfiguration : BedrockFoundationModelConfigurationForParsing.t
option;Settings for a foundation model used to parse documents for a data source.
*)}val make :
?bedrockFoundationModelConfiguration:??? ->
parsingStrategy:ParsingStrategy.t ->
unit ->
tval to_value :
t ->
[> `Structure of
(string
* [> `Enum of string
| `Structure of
(string
* [> `String of BedrockModelArnForParsing.t
| `Structure of
(string * [> `String of ParsingPromptText.t ]) list ])
list ])
list ]