This is the new Amazon CloudFormation Template Reference Guide. Please update your bookmarks and links. For help getting started with CloudFormation, see the Amazon CloudFormation User Guide.
AWS::Bedrock::DataSource VectorIngestionConfiguration
Contains details about how to ingest the documents in a data source.
Syntax
To declare this entity in your Amazon CloudFormation template, use the following syntax:
JSON
{ "ChunkingConfiguration" :ChunkingConfiguration, "ContextEnrichmentConfiguration" :ContextEnrichmentConfiguration, "CustomTransformationConfiguration" :CustomTransformationConfiguration, "ParsingConfiguration" :ParsingConfiguration}
YAML
ChunkingConfiguration:ChunkingConfigurationContextEnrichmentConfiguration:ContextEnrichmentConfigurationCustomTransformationConfiguration:CustomTransformationConfigurationParsingConfiguration:ParsingConfiguration
Properties
ChunkingConfiguration-
Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
Required: No
Type: ChunkingConfiguration
Update requires: Replacement
ContextEnrichmentConfiguration-
The context enrichment configuration used for ingestion of the data into the vector store.
Required: No
Type: ContextEnrichmentConfiguration
Update requires: No interruption
CustomTransformationConfiguration-
A custom document transformer for parsed data source documents.
Required: No
Type: CustomTransformationConfiguration
Update requires: No interruption
ParsingConfiguration-
Configurations for a parser to use for parsing documents in your data source. If you exclude this field, the default parser will be used.
Required: No
Type: ParsingConfiguration
Update requires: Replacement