Skip to content

/AWS1/CL_BDAPARSINGCONF

Settings 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.

To use a model to parse PDF documents, set the parsing strategy to BEDROCK_FOUNDATION_MODEL and specify the model or inference profile to use by ARN. You can also override the default parsing prompt with instructions for how to interpret images and tables in your documents. The following models are supported.

  • Anthropic Claude 3 Sonnet - anthropic.claude-3-sonnet-20240229-v1:0

  • Anthropic Claude 3 Haiku - anthropic.claude-3-haiku-20240307-v1:0

You can get the ARN of a model with the ListFoundationModels action. Standard model usage charges apply for the foundation model parsing strategy.

CONSTRUCTOR

IMPORTING

Required arguments:

IV_PARSINGSTRATEGY TYPE /AWS1/BDAPARSINGSTRATEGY /AWS1/BDAPARSINGSTRATEGY

The parsing strategy for the data source.

Optional arguments:

IO_BEDROCKFNDATIONMODELCONF TYPE REF TO /AWS1/CL_BDABEDROCKFNDATIONM00 /AWS1/CL_BDABEDROCKFNDATIONM00

Settings for a foundation model used to parse documents for a data source.

Queryable Attributes

parsingStrategy

The parsing strategy for the data source.

Accessible with the following methods

Method Description
GET_PARSINGSTRATEGY() Getter for PARSINGSTRATEGY, with configurable default
ASK_PARSINGSTRATEGY() Getter for PARSINGSTRATEGY w/ exceptions if field has no val
HAS_PARSINGSTRATEGY() Determine if PARSINGSTRATEGY has a value

bedrockFoundationModelConfiguration

Settings for a foundation model used to parse documents for a data source.

Accessible with the following methods

Method Description
GET_BEDROCKFNDATIONMODELCONF() Getter for BEDROCKFOUNDATIONMODELCONF