AWS::Bedrock::KnowledgeBase RdsFieldMapping - AWS CloudFormation
SyntaxProperties

This is the new AWS CloudFormation Template Reference Guide. Please update your bookmarks and links. For help getting started with CloudFormation, see the AWS CloudFormation User Guide.

AWS::Bedrock::KnowledgeBase RdsFieldMapping

Contains the names of the fields to which to map information about the vector store.

Syntax

To declare this entity in your AWS CloudFormation template, use the following syntax:

JSON

{
  "CustomMetadataField" : String,
  "MetadataField" : String,
  "PrimaryKeyField" : String,
  "TextField" : String,
  "VectorField" : String
}

YAML

  CustomMetadataField: String
  MetadataField: String
  PrimaryKeyField: String
  TextField: String
  VectorField: String

Properties

CustomMetadataField

Provide a name for the universal metadata field where Amazon Bedrock will store any custom metadata from your data source.

Required: No

Type: String

Pattern: ^[a-zA-Z0-9_\-]+$

Maximum: 63

Update requires: Replacement

MetadataField

The name of the field in which Amazon Bedrock stores metadata about the vector store.

Required: Yes

Type: String

Pattern: ^[a-zA-Z0-9_\-]+$

Maximum: 63

Update requires: Replacement

PrimaryKeyField

The name of the field in which Amazon Bedrock stores the ID for each entry.

Required: Yes

Type: String

Pattern: ^[a-zA-Z0-9_\-]+$

Maximum: 63

Update requires: Replacement

TextField

The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.

Required: Yes

Type: String

Pattern: ^[a-zA-Z0-9_\-]+$

Maximum: 63

Update requires: Replacement

VectorField

The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources.

Required: Yes

Type: String

Pattern: ^[a-zA-Z0-9_\-]+$

Maximum: 63

Update requires: Replacement