@cdklabs/generative-ai-cdk-constructs
@cdklabs/generative-ai-cdk-constructs / bedrock / FoundationModelParsingStategyProps
Properties for configuring a Foundation Model parsing strategy.
readonly
optional
parsingModality:MULTIMODAL
Specifies whether to enable parsing of multimodal data, including both text and/or images.
undefined - Text only
readonly
parsingModel:IInvokable
The Foundation Model to use for parsing non-textual information. Currently supported models are Claude 3 Sonnet and Claude 3 Haiku.
readonly
optional
parsingPrompt:string
Custom prompt to instruct the parser on how to interpret the document.
- Uses the default instruction prompt as provided in the AWS Console.