data_sources

Creates, updates, deletes, gets or lists a data_sources resource.

Overview

Name	data_sources
Type	Resource
Id	aws.bedrock_agent.data_sources

Fields

The following fields are returned by SELECT queries:

get_data_source

Name	Datatype	Description
name	string	The name of the data source. (pattern: <code>([0-9a-zA-Z][_-]?){1,100}</code>)
created_at	string (date-time)	The time at which the data source was created.
data_deletion_policy	string	The data deletion policy for the data source. (RETAIN, DELETE)
data_source_configuration	object	The connection configuration for the data source.
data_source_id	string	The unique identifier of the data source. (pattern: <code>[0-9a-zA-Z]{10}</code>)
description	string	The description of the data source.
failure_reasons	array	The detailed reasons on the failure to delete a data source.
knowledge_base_id	string	The unique identifier of the knowledge base to which the data source belongs. (pattern: <code>[0-9a-zA-Z]{10}</code>)
server_side_encryption_configuration	object	Contains the configuration for server-side encryption for your managed knowledge base.
status	string	The status of the data source. The following statuses are possible: Available – The data source has been created and is ready for ingestion into the knowledge base. Deleting – The data source is being deleted. (AVAILABLE, DELETING, DELETE_UNSUCCESSFUL, CREATING, UPDATING, FAILED)
updated_at	string (date-time)	The time at which the data source was last updated.
vector_ingestion_configuration	object	Contains details about how to ingest the documents in a data source.

list_data_sources

Name	Datatype	Description
name	string	The name of the data source. (pattern: <code>([0-9a-zA-Z][_-]?){1,100}</code>)
data_source_id	string	The unique identifier of the data source. (pattern: <code>[0-9a-zA-Z]{10}</code>)
description	string	The description of the data source.
knowledge_base_id	string	The unique identifier of the knowledge base to which the data source belongs. (pattern: <code>[0-9a-zA-Z]{10}</code>)
status	string	The status of the data source. (AVAILABLE, DELETING, DELETE_UNSUCCESSFUL, CREATING, UPDATING, FAILED)
updated_at	string (date-time)	The time at which the data source was last updated.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get_data_source	select	knowledge_base_id, data_source_id, region		Gets information about a data source.
list_data_sources	select	knowledge_base_id, region		Lists the data sources in a knowledge base and information about each one.
create_data_source	insert	knowledge_base_id, region, name, dataSourceConfiguration		Connects a knowledge base to a data source. You specify the configuration for the specific data source service in the dataSourceConfiguration field. You can't change the chunkingConfiguration after you create the data source connector.
update_data_source	update	knowledge_base_id, data_source_id, region, name, dataSourceConfiguration		Updates the configurations for a data source connector. You can't change the chunkingConfiguration after you create the data source connector. Specify the existing chunkingConfiguration.
delete_data_source	delete	knowledge_base_id, data_source_id, region		Deletes a data source from a knowledge base.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
data_source_id	string	The unique identifier of the data source to delete.
knowledge_base_id	string	The unique identifier of the knowledge base from which to delete the data source.
region	string	AWS region (default: us-east-1)

SELECT examples

get_data_source

Gets information about a data source.

SELECT
name,
created_at,
data_deletion_policy,
data_source_configuration,
data_source_id,
description,
failure_reasons,
knowledge_base_id,
server_side_encryption_configuration,
status,
updated_at,
vector_ingestion_configuration
FROM aws.bedrock_agent.data_sources
WHERE knowledge_base_id = '{{ knowledge_base_id }}' -- required
AND data_source_id = '{{ data_source_id }}' -- required
AND region = '{{ region }}' -- required
;

list_data_sources

Lists the data sources in a knowledge base and information about each one.

SELECT
name,
data_source_id,
description,
knowledge_base_id,
status,
updated_at
FROM aws.bedrock_agent.data_sources
WHERE knowledge_base_id = '{{ knowledge_base_id }}' -- required
AND region = '{{ region }}' -- required
;

INSERT examples

create_data_source

Connects a knowledge base to a data source. You specify the configuration for the specific data source service in the dataSourceConfiguration field. You can't change the chunkingConfiguration after you create the data source connector.

INSERT INTO aws.bedrock_agent.data_sources (
clientToken,
name,
description,
dataSourceConfiguration,
dataDeletionPolicy,
serverSideEncryptionConfiguration,
vectorIngestionConfiguration,
knowledge_base_id,
region
)
SELECT 
'{{ clientToken }}',
'{{ name }}' /* required */,
'{{ description }}',
'{{ dataSourceConfiguration }}' /* required */,
'{{ dataDeletionPolicy }}',
'{{ serverSideEncryptionConfiguration }}',
'{{ vectorIngestionConfiguration }}',
'{{ knowledge_base_id }}',
'{{ region }}'
RETURNING
data_source
;

Manifest

# Description fields are for documentation purposes
- name: data_sources
props:
  - name: knowledge_base_id
    value: "{{ knowledge_base_id }}"
    description: Required parameter for the data_sources resource.
  - name: region
    value: "{{ region }}"
    description: Required parameter for the data_sources resource.
  - name: clientToken
    value: "{{ clientToken }}"
  - name: name
    value: "{{ name }}"
  - name: description
    value: "{{ description }}"
  - name: dataSourceConfiguration
    description: |
      The connection configuration for the data source.
    value:
      type_: "{{ type_ }}"
      managedKnowledgeBaseConnectorConfiguration:
        deletionProtectionConfiguration:
          deletionProtectionStatus: "{{ deletionProtectionStatus }}"
          deletionProtectionThreshold: {{ deletionProtectionThreshold }}
        mediaExtractionConfiguration:
          imageExtractionConfiguration:
            imageExtractionStatus: "{{ imageExtractionStatus }}"
          audioExtractionConfiguration:
            audioExtractionStatus: "{{ audioExtractionStatus }}"
          videoExtractionConfiguration:
            videoExtractionStatus: "{{ videoExtractionStatus }}"
        connectorParameters: "{{ connectorParameters }}"
      s3Configuration:
        bucketArn: "{{ bucketArn }}"
        inclusionPrefixes:
          - "{{ inclusionPrefixes }}"
        bucketOwnerAccountId: "{{ bucketOwnerAccountId }}"
      webConfiguration:
        sourceConfiguration:
          urlConfiguration:
            seedUrls:
              - url: "{{ url }}"
        crawlerConfiguration:
          crawlerLimits:
            rateLimit: {{ rateLimit }}
            maxPages: {{ maxPages }}
          inclusionFilters:
            - "{{ inclusionFilters }}"
          exclusionFilters:
            - "{{ exclusionFilters }}"
          scope: "{{ scope }}"
          userAgent: "{{ userAgent }}"
          userAgentHeader: "{{ userAgentHeader }}"
      confluenceConfiguration:
        sourceConfiguration:
          hostUrl: "{{ hostUrl }}"
          hostType: "{{ hostType }}"
          authType: "{{ authType }}"
          credentialsSecretArn: "{{ credentialsSecretArn }}"
        crawlerConfiguration:
          filterConfiguration:
            type_: "{{ type_ }}"
            patternObjectFilter:
              filters: "{{ filters }}"
      salesforceConfiguration:
        sourceConfiguration:
          hostUrl: "{{ hostUrl }}"
          authType: "{{ authType }}"
          credentialsSecretArn: "{{ credentialsSecretArn }}"
        crawlerConfiguration:
          filterConfiguration:
            type_: "{{ type_ }}"
            patternObjectFilter:
              filters: "{{ filters }}"
      sharePointConfiguration:
        sourceConfiguration:
          tenantId: "{{ tenantId }}"
          domain: "{{ domain }}"
          siteUrls:
            - "{{ siteUrls }}"
          hostType: "{{ hostType }}"
          authType: "{{ authType }}"
          credentialsSecretArn: "{{ credentialsSecretArn }}"
        crawlerConfiguration:
          filterConfiguration:
            type_: "{{ type_ }}"
            patternObjectFilter:
              filters: "{{ filters }}"
  - name: dataDeletionPolicy
    value: "{{ dataDeletionPolicy }}"
    valid_values: ['RETAIN', 'DELETE']
  - name: serverSideEncryptionConfiguration
    description: |
      Contains the configuration for server-side encryption for your managed knowledge base.
    value:
      kmsKeyArn: "{{ kmsKeyArn }}"
  - name: vectorIngestionConfiguration
    description: |
      Contains details about how to ingest the documents in a data source.
    value:
      chunkingConfiguration:
        chunkingStrategy: "{{ chunkingStrategy }}"
        fixedSizeChunkingConfiguration:
          maxTokens: {{ maxTokens }}
          overlapPercentage: {{ overlapPercentage }}
        hierarchicalChunkingConfiguration:
          levelConfigurations:
            - maxTokens: {{ maxTokens }}
          overlapTokens: {{ overlapTokens }}
        semanticChunkingConfiguration:
          maxTokens: {{ maxTokens }}
          bufferSize: {{ bufferSize }}
          breakpointPercentileThreshold: {{ breakpointPercentileThreshold }}
      customTransformationConfiguration:
        intermediateStorage:
          s3Location:
            uri: "{{ uri }}"
        transformations:
          - transformationFunction:
              transformationLambdaConfiguration:
                lambdaArn: "{{ lambdaArn }}"
            stepToApply: "{{ stepToApply }}"
      parsingConfiguration:
        parsingStrategy: "{{ parsingStrategy }}"
        bedrockFoundationModelConfiguration:
          modelArn: "{{ modelArn }}"
          parsingPrompt:
            parsingPromptText: "{{ parsingPromptText }}"
          parsingModality: "{{ parsingModality }}"
        bedrockDataAutomationConfiguration:
          parsingModality: "{{ parsingModality }}"
      contextEnrichmentConfiguration:
        type_: "{{ type_ }}"
        bedrockFoundationModelConfiguration:
          enrichmentStrategyConfiguration:
            method: "{{ method }}"
          modelArn: "{{ modelArn }}"

UPDATE examples

update_data_source

Updates the configurations for a data source connector. You can't change the chunkingConfiguration after you create the data source connector. Specify the existing chunkingConfiguration.

UPDATE aws.bedrock_agent.data_sources
SET 
name = '{{ name }}',
description = '{{ description }}',
dataSourceConfiguration = '{{ dataSourceConfiguration }}',
dataDeletionPolicy = '{{ dataDeletionPolicy }}',
serverSideEncryptionConfiguration = '{{ serverSideEncryptionConfiguration }}',
vectorIngestionConfiguration = '{{ vectorIngestionConfiguration }}'
WHERE 
knowledge_base_id = '{{ knowledge_base_id }}' --required
AND data_source_id = '{{ data_source_id }}' --required
AND region = '{{ region }}' --required
AND name = '{{ name }}' --required
AND dataSourceConfiguration = '{{ dataSourceConfiguration }}' --required
RETURNING
data_source;

DELETE examples

delete_data_source

Deletes a data source from a knowledge base.

DELETE FROM aws.bedrock_agent.data_sources
WHERE knowledge_base_id = '{{ knowledge_base_id }}' --required
AND data_source_id = '{{ data_source_id }}' --required
AND region = '{{ region }}' --required
;