2026/04/02 - Data Automation for Amazon Bedrock - 10 new4 updated api methods
Changes Data Automation Library is a BDA capability that lets you create reusable entity resources to improve extraction accuracy. Libraries support Custom Vocabulary entities that enhance speech recognition for audio and video content with domain-specific terminology shared across projects
Gets an existing entity based on entity type from the library
See also: AWS API Documentation
Request Syntax
client.get_data_automation_library_entity(
libraryArn='string',
entityType='VOCABULARY',
entityId='string'
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
string
[REQUIRED]
The entity type for which the entity is requested
string
[REQUIRED]
Unique identifier for the entity
dict
Response Syntax
{
'entity': {
'vocabulary': {
'entityId': 'string',
'description': 'string',
'language': 'EN'|'DE'|'ES'|'FR'|'IT'|'PT'|'JA'|'KO'|'CN'|'TW'|'HK',
'phrases': [
{
'text': 'string',
'displayAsText': 'string'
},
],
'lastModifiedTime': datetime(2015, 1, 1)
}
}
}
Response Structure
(dict) --
Get DataAutomationLibraryEntity Response
entity (dict) --
Detailed information about the entity
vocabulary (dict) --
Vocabulary entity with detailed information
entityId (string) --
Unique identifier for the entity
description (string) --
Description of the entity
language (string) --
Supported input languages
phrases (list) --
List of phrases
(dict) --
Phrase structure for vocabulary
text (string) --
Text content of the phrase
displayAsText (string) --
Text to configure how phrase is displayed in Transcript
lastModifiedTime (datetime) --
Time Stamp
Creates an Amazon Bedrock Data Automation Library
See also: AWS API Documentation
Request Syntax
client.create_data_automation_library(
libraryName='string',
libraryDescription='string',
clientToken='string',
encryptionConfiguration={
'kmsKeyId': 'string',
'kmsEncryptionContext': {
'string': 'string'
}
},
tags=[
{
'key': 'string',
'value': 'string'
},
]
)
string
[REQUIRED]
Name of the DataAutomationLibrary
string
Description of the DataAutomationLibrary
string
Client specified token used for idempotency checks
This field is autopopulated if not provided.
dict
KMS Encryption Configuration
kmsKeyId (string) -- [REQUIRED]
KMS Key Identifier
kmsEncryptionContext (dict) --
KMS Encryption Context
(string) --
Encryption context key.
(string) --
Encryption context value.
list
List of tags
(dict) --
Key value pair of a tag
key (string) -- [REQUIRED]
Defines the context of the tag.
value (string) -- [REQUIRED]
Defines the value within the context. e.g. <key=reason, value=training>.
dict
Response Syntax
{
'libraryArn': 'string',
'status': 'ACTIVE'|'DELETING'
}
Response Structure
(dict) --
Create DataAutomationLibrary Response
libraryArn (string) --
ARN generated at the server side when a DataAutomationLibrary is created
status (string) --
Status of DataAutomationLibrary
Gets an existing Amazon Bedrock Data Automation Library
See also: AWS API Documentation
Request Syntax
client.get_data_automation_library(
libraryArn='string'
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
dict
Response Syntax
{
'library': {
'libraryArn': 'string',
'creationTime': datetime(2015, 1, 1),
'libraryName': 'string',
'libraryDescription': 'string',
'status': 'ACTIVE'|'DELETING',
'entityTypes': [
{
'entityType': 'VOCABULARY',
'entityMetadata': 'string'
},
],
'kmsKeyId': 'string',
'kmsEncryptionContext': {
'string': 'string'
}
}
}
Response Structure
(dict) --
Get DataAutomationLibrary Response
library (dict) --
Contains the information of a DataAutomationLibrary.
libraryArn (string) --
ARN generated at the server side when a DataAutomationLibrary is created
creationTime (datetime) --
Time Stamp
libraryName (string) --
Name of the DataAutomationLibrary
libraryDescription (string) --
Description of the DataAutomationLibrary
status (string) --
Status of DataAutomationLibrary
entityTypes (list) --
List of info for each entity type in the DataAutomationLibrary
(dict) --
Information about an entity type in the DataAutomationLibrary
entityType (string) --
Entity types supported in DataAutomationLibraries
entityMetadata (string) --
JSON string representing relevant metadata for the entity type
kmsKeyId (string) --
KMS Key Identifier
kmsEncryptionContext (dict) --
KMS Encryption Context
(string) --
Encryption context key.
(string) --
Encryption context value.
Deletes an existing Amazon Bedrock Data Automation Library
See also: AWS API Documentation
Request Syntax
client.delete_data_automation_library(
libraryArn='string'
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
dict
Response Syntax
{
'libraryArn': 'string',
'status': 'ACTIVE'|'DELETING'
}
Response Structure
(dict) --
Delete DataAutomationLibrary Response
libraryArn (string) --
ARN generated at the server side when a DataAutomationLibrary is created
status (string) --
Status of DataAutomationLibrary
Lists all stored entities in the library
See also: AWS API Documentation
Request Syntax
client.list_data_automation_library_entities(
libraryArn='string',
entityType='VOCABULARY',
maxResults=123,
nextToken='string'
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
string
[REQUIRED]
The entity type for which the entity list is requested
integer
Max Results
string
Pagination token for retrieving the next set of results
dict
Response Syntax
{
'entities': [
{
'vocabulary': {
'entityId': 'string',
'description': 'string',
'language': 'EN'|'DE'|'ES'|'FR'|'IT'|'PT'|'JA'|'KO'|'CN'|'TW'|'HK',
'numOfPhrases': 123,
'lastModifiedTime': datetime(2015, 1, 1)
}
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
List DataAutomationLibraryEntities Response
entities (list) --
List of entities
(dict) --
Summarized information about an entity
vocabulary (dict) --
Summary of a Vocabulary entity
entityId (string) --
Unique identifier for the entity
description (string) --
Description of the entity
language (string) --
Supported input languages
numOfPhrases (integer) --
num of phrases in the entity
lastModifiedTime (datetime) --
Time Stamp
nextToken (string) --
Pagination token for retrieving the next set of results
Async API: Invoke data automation library ingestion job
See also: AWS API Documentation
Request Syntax
client.invoke_data_automation_library_ingestion_job(
libraryArn='string',
clientToken='string',
inputConfiguration={
's3Object': {
's3Uri': 'string',
'version': 'string'
},
'inlinePayload': {
'upsertEntitiesInfo': [
{
'vocabulary': {
'entityId': 'string',
'description': 'string',
'language': 'EN'|'DE'|'ES'|'FR'|'IT'|'PT'|'JA'|'KO'|'CN'|'TW'|'HK',
'phrases': [
{
'text': 'string',
'displayAsText': 'string'
},
]
}
},
],
'deleteEntitiesInfo': {
'entityIds': [
'string',
]
}
}
},
entityType='VOCABULARY',
operationType='UPSERT'|'DELETE',
outputConfiguration={
's3Uri': 'string'
},
notificationConfiguration={
'eventBridgeConfiguration': {
'eventBridgeEnabled': True|False
}
},
tags=[
{
'key': 'string',
'value': 'string'
},
]
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
string
Idempotency token
This field is autopopulated if not provided.
dict
[REQUIRED]
Input configuration of DataAutomationLibraryIngestionJob request
s3Object (dict) --
S3 object
s3Uri (string) -- [REQUIRED]
S3 uri.
version (string) --
S3 object version.
inlinePayload (dict) --
Input Payload
upsertEntitiesInfo (list) --
List of UpsertEntityInfo for upserting data in a DataAutomationLibraryIngestionJob
(dict) --
Input configuration for upserting data in a DataAutomationLibraryIngestionJob
vocabulary (dict) --
Vocabulary entity info with detailed information
entityId (string) --
Unique identifier for the entity
description (string) --
Description of the entity
language (string) -- [REQUIRED]
Supported input languages
phrases (list) -- [REQUIRED]
List of phrases
(dict) --
Phrase structure for vocabulary
text (string) -- [REQUIRED]
Text content of the phrase
displayAsText (string) --
Text to configure how phrase is displayed in Transcript
deleteEntitiesInfo (dict) --
Input for entities needed to be deleted
entityIds (list) -- [REQUIRED]
List of EntityId
(string) --
Unique identifier for the entity
string
[REQUIRED]
The entity type for which DataAutomationLibraryIngestionJob is being run
string
[REQUIRED]
The operation to be performed by DataAutomationLibraryIngestionJob
dict
[REQUIRED]
Output configuration of DataAutomationLibraryIngestionJob
s3Uri (string) -- [REQUIRED]
S3 Uri
dict
Notification configuration.
eventBridgeConfiguration (dict) -- [REQUIRED]
Event bridge configuration.
eventBridgeEnabled (boolean) -- [REQUIRED]
Event bridge flag.
list
List of tags
(dict) --
Key value pair of a tag
key (string) -- [REQUIRED]
Defines the context of the tag.
value (string) -- [REQUIRED]
Defines the value within the context. e.g. <key=reason, value=training>.
dict
Response Syntax
{
'jobArn': 'string'
}
Response Structure
(dict) --
Invoke DataAutomationLibraryIngestionJob Response
jobArn (string) --
ARN of the DataAutomationLibraryIngestionJob
API used to get status of data automation library ingestion job
See also: AWS API Documentation
Request Syntax
client.get_data_automation_library_ingestion_job(
libraryArn='string',
jobArn='string'
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
string
[REQUIRED]
ARN of the DataAutomationLibraryIngestionJob
dict
Response Syntax
{
'job': {
'jobArn': 'string',
'creationTime': datetime(2015, 1, 1),
'entityType': 'VOCABULARY',
'operationType': 'UPSERT'|'DELETE',
'jobStatus': 'IN_PROGRESS'|'COMPLETED'|'COMPLETED_WITH_ERRORS'|'FAILED',
'outputConfiguration': {
's3Uri': 'string'
},
'completionTime': datetime(2015, 1, 1),
'errorMessage': 'string',
'errorType': 'string'
}
}
Response Structure
(dict) --
Get DataAutomationLibraryIngestionJob Response
job (dict) --
Contains the information of a library ingestion job
jobArn (string) --
ARN of the DataAutomationLibraryIngestionJob
creationTime (datetime) --
Timestamp when the DataAutomationLibraryIngestionJob was created
entityType (string) --
The entity type associated with DataAutomationLibraryIngestionJob
operationType (string) --
The operation associated with DataAutomationLibraryIngestionJob
jobStatus (string) --
The status of the DataAutomationLibraryIngestionJob
outputConfiguration (dict) --
Output configuration of DataAutomationLibraryIngestionJob
s3Uri (string) --
S3 Uri
completionTime (datetime) --
Timestamp when the DataAutomationLibraryIngestionJob was completed
errorMessage (string) --
Error message
errorType (string) --
Error type
Updates an existing Amazon Bedrock Data Automation Library
See also: AWS API Documentation
Request Syntax
client.update_data_automation_library(
libraryArn='string',
libraryDescription='string',
clientToken='string'
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
string
Description of the DataAutomationLibrary
string
Client specified token used for idempotency checks
This field is autopopulated if not provided.
dict
Response Syntax
{
'libraryArn': 'string',
'status': 'ACTIVE'|'DELETING'
}
Response Structure
(dict) --
Update DataAutomationLibrary Response
libraryArn (string) --
ARN generated at the server side when a DataAutomationLibrary is created
status (string) --
Status of DataAutomationLibrary
Lists all data automation library ingestion jobs
See also: AWS API Documentation
Request Syntax
client.list_data_automation_library_ingestion_jobs(
libraryArn='string',
maxResults=123,
nextToken='string'
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
integer
Max Results
string
Pagination token for retrieving the next set of results
dict
Response Syntax
{
'jobs': [
{
'jobArn': 'string',
'jobStatus': 'IN_PROGRESS'|'COMPLETED'|'COMPLETED_WITH_ERRORS'|'FAILED',
'entityType': 'VOCABULARY',
'operationType': 'UPSERT'|'DELETE',
'creationTime': datetime(2015, 1, 1),
'completionTime': datetime(2015, 1, 1)
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
List DataAutomationLibraryIngestionJobs Response
jobs (list) --
List of data automation library ingestion jobs
(dict) --
Summary of a DataAutomationLibraryIngestionJob
jobArn (string) --
ARN of the DataAutomationLibraryIngestionJob
jobStatus (string) --
Status of DataAutomationLibraryIngestionJob
entityType (string) --
Entity types supported in DataAutomationLibraries
operationType (string) --
DataAutomationLibraryIngestionJob operation type
creationTime (datetime) --
Time Stamp
completionTime (datetime) --
Time Stamp
nextToken (string) --
Pagination token for retrieving the next set of results
Lists all existing Amazon Bedrock Data Automation Libraries
See also: AWS API Documentation
Request Syntax
client.list_data_automation_libraries(
maxResults=123,
nextToken='string',
projectFilter={
'projectArn': 'string',
'projectStage': 'DEVELOPMENT'|'LIVE'
}
)
integer
Max Results
string
Pagination token
dict
Data Automation Project Filter
projectArn (string) -- [REQUIRED]
ARN of a DataAutomationProject
projectStage (string) --
Stage of the Project
dict
Response Syntax
{
'libraries': [
{
'libraryArn': 'string',
'libraryName': 'string',
'creationTime': datetime(2015, 1, 1)
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
List DataAutomationLibraries Response
libraries (list) --
List of DataAutomationLibrarySummary objects
(dict) --
Summary of a DataAutomationLibrary
libraryArn (string) --
ARN generated at the server side when a DataAutomationLibrary is created
libraryName (string) --
Name of the DataAutomationLibrary
creationTime (datetime) --
Time Stamp
nextToken (string) --
Pagination token
{'dataAutomationLibraryConfiguration': {'libraries': [{'libraryArn': 'string'}]}}
Creates an Amazon Bedrock Data Automation Project
See also: AWS API Documentation
Request Syntax
client.create_data_automation_project(
projectName='string',
projectDescription='string',
projectStage='DEVELOPMENT'|'LIVE',
projectType='ASYNC'|'SYNC',
standardOutputConfiguration={
'document': {
'extraction': {
'granularity': {
'types': [
'DOCUMENT'|'PAGE'|'ELEMENT'|'WORD'|'LINE',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED'
},
'outputFormat': {
'textFormat': {
'types': [
'PLAIN_TEXT'|'MARKDOWN'|'HTML'|'CSV',
]
},
'additionalFileFormat': {
'state': 'ENABLED'|'DISABLED'
}
}
},
'image': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'CONTENT_MODERATION'|'TEXT_DETECTION'|'LOGOS',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'IMAGE_SUMMARY'|'IAB',
]
}
},
'video': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'CONTENT_MODERATION'|'TEXT_DETECTION'|'TRANSCRIPT'|'LOGOS',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'VIDEO_SUMMARY'|'IAB'|'CHAPTER_SUMMARY',
]
}
},
'audio': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'AUDIO_CONTENT_MODERATION'|'TRANSCRIPT'|'TOPIC_CONTENT_MODERATION',
],
'typeConfiguration': {
'transcript': {
'speakerLabeling': {
'state': 'ENABLED'|'DISABLED'
},
'channelLabeling': {
'state': 'ENABLED'|'DISABLED'
}
}
}
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'AUDIO_SUMMARY'|'IAB'|'TOPIC_SUMMARY',
]
}
}
},
customOutputConfiguration={
'blueprints': [
{
'blueprintArn': 'string',
'blueprintVersion': 'string',
'blueprintStage': 'DEVELOPMENT'|'LIVE'
},
]
},
overrideConfiguration={
'document': {
'splitter': {
'state': 'ENABLED'|'DISABLED'
},
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'image': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'video': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'audio': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'languageConfiguration': {
'inputLanguages': [
'EN'|'DE'|'ES'|'FR'|'IT'|'PT'|'JA'|'KO'|'CN'|'TW'|'HK',
],
'generativeOutputLanguage': 'DEFAULT'|'EN',
'identifyMultipleLanguages': True|False
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'modalityRouting': {
'jpeg': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'png': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'mp4': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'mov': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO'
}
},
dataAutomationLibraryConfiguration={
'libraries': [
{
'libraryArn': 'string'
},
]
},
clientToken='string',
encryptionConfiguration={
'kmsKeyId': 'string',
'kmsEncryptionContext': {
'string': 'string'
}
},
tags=[
{
'key': 'string',
'value': 'string'
},
]
)
string
[REQUIRED]
Name of the DataAutomationProject
string
Description of the DataAutomationProject
string
Stage of the Project
string
Type of the DataAutomationProject
dict
[REQUIRED]
Standard output configuration
document (dict) --
Standard Output Configuration of Document
extraction (dict) --
Standard Extraction Configuration of Document
granularity (dict) -- [REQUIRED]
Granularity of Document Extraction
types (list) --
List of Document Extraction Granularity Type
(string) --
boundingBox (dict) -- [REQUIRED]
Bounding Box Configuration of Document Extraction
state (string) -- [REQUIRED]
State
generativeField (dict) --
Standard Generative Field Configuration of Document
state (string) -- [REQUIRED]
State
outputFormat (dict) --
Output Format of Document
textFormat (dict) -- [REQUIRED]
Text Format of Document Output
types (list) --
List of Document Output Text Format Type
(string) --
additionalFileFormat (dict) -- [REQUIRED]
Additional File Format of Document Output
state (string) -- [REQUIRED]
State
image (dict) --
Standard Output Configuration of Image
extraction (dict) --
Standard Extraction Configuration of Image
category (dict) -- [REQUIRED]
Category of Image Extraction
state (string) -- [REQUIRED]
State
types (list) --
List of Image Extraction Category
(string) --
boundingBox (dict) -- [REQUIRED]
Bounding Box Configuration of Image Extraction
state (string) -- [REQUIRED]
State
generativeField (dict) --
Standard Generative Field Configuration of Image
state (string) -- [REQUIRED]
State
types (list) --
List of Image Standard Generative Field Type
(string) --
video (dict) --
Standard Output Configuration of Video
extraction (dict) --
Standard Extraction Configuration of Video
category (dict) -- [REQUIRED]
Category of Video Extraction
state (string) -- [REQUIRED]
State
types (list) --
List of Video Extraction Category Type
(string) --
boundingBox (dict) -- [REQUIRED]
Bounding Box Configuration of Video Extraction
state (string) -- [REQUIRED]
State
generativeField (dict) --
Standard Generative Field Configuration of Video
state (string) -- [REQUIRED]
State
types (list) --
List of Video Standard Generative Field Type
(string) --
audio (dict) --
Standard Output Configuration of Audio
extraction (dict) --
Standard Extraction Configuration of Audio
category (dict) -- [REQUIRED]
Category of Audio Extraction
state (string) -- [REQUIRED]
State
types (list) --
List of Audio Extraction Category Type
(string) --
typeConfiguration (dict) --
Configuration for different audio extraction category types
transcript (dict) --
Configuration for transcript related features
speakerLabeling (dict) --
Speaker labeling configuration
state (string) -- [REQUIRED]
State
channelLabeling (dict) --
Channel labeling configuration
state (string) -- [REQUIRED]
State
generativeField (dict) --
Standard Generative Field Configuration of Audio
state (string) -- [REQUIRED]
State
types (list) --
List of Audio Standard Generative Field Type
(string) --
dict
Custom output configuration
blueprints (list) --
List of Blueprint Item
(dict) --
Blueprint Item
blueprintArn (string) -- [REQUIRED]
ARN of a Blueprint
blueprintVersion (string) --
Blueprint Version
blueprintStage (string) --
Stage of the Blueprint
dict
Override configuration
document (dict) --
Override Configuration of Document
splitter (dict) --
Configuration of Splitter
state (string) --
State
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) -- [REQUIRED]
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
image (dict) --
Override Configuration of Image
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) -- [REQUIRED]
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
video (dict) --
Override Configuration of Video
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) -- [REQUIRED]
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
audio (dict) --
Override Configuration of Audio
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
languageConfiguration (dict) --
Optional configuration for audio language settings
inputLanguages (list) --
List of supported audio languages
(string) --
Supported input languages
generativeOutputLanguage (string) --
Configuration for Audio output language
identifyMultipleLanguages (boolean) --
Enable multiple language identification in audio
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) -- [REQUIRED]
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
modalityRouting (dict) --
Configuration for routing file type to desired modality
jpeg (string) --
Desired Modality types
png (string) --
Desired Modality types
mp4 (string) --
Desired Modality types
mov (string) --
Desired Modality types
dict
DataAutomation Library configuration
libraries (list) --
List of DataAutomationLibrary Items
(dict) --
DataAutomationLibrary Item
libraryArn (string) -- [REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
string
Client specified token used for idempotency checks
This field is autopopulated if not provided.
dict
KMS Encryption Configuration
kmsKeyId (string) -- [REQUIRED]
KMS Key Identifier
kmsEncryptionContext (dict) --
KMS Encryption Context
(string) --
Encryption context key.
(string) --
Encryption context value.
list
List of tags
(dict) --
Key value pair of a tag
key (string) -- [REQUIRED]
Defines the context of the tag.
value (string) -- [REQUIRED]
Defines the value within the context. e.g. <key=reason, value=training>.
dict
Response Syntax
{
'projectArn': 'string',
'projectStage': 'DEVELOPMENT'|'LIVE',
'status': 'COMPLETED'|'IN_PROGRESS'|'FAILED'
}
Response Structure
(dict) --
Create DataAutomationProject Response
projectArn (string) --
ARN of a DataAutomationProject
projectStage (string) --
Stage of the Project
status (string) --
Status of Data Automation Project
{'project': {'dataAutomationLibraryConfiguration': {'libraries': [{'libraryArn': 'string'}]}}}
Gets an existing Amazon Bedrock Data Automation Project
See also: AWS API Documentation
Request Syntax
client.get_data_automation_project(
projectArn='string',
projectStage='DEVELOPMENT'|'LIVE'
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationProject is created
string
Optional field to delete a specific DataAutomationProject stage
dict
Response Syntax
{
'project': {
'projectArn': 'string',
'creationTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'projectName': 'string',
'projectStage': 'DEVELOPMENT'|'LIVE',
'projectType': 'ASYNC'|'SYNC',
'projectDescription': 'string',
'standardOutputConfiguration': {
'document': {
'extraction': {
'granularity': {
'types': [
'DOCUMENT'|'PAGE'|'ELEMENT'|'WORD'|'LINE',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED'
},
'outputFormat': {
'textFormat': {
'types': [
'PLAIN_TEXT'|'MARKDOWN'|'HTML'|'CSV',
]
},
'additionalFileFormat': {
'state': 'ENABLED'|'DISABLED'
}
}
},
'image': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'CONTENT_MODERATION'|'TEXT_DETECTION'|'LOGOS',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'IMAGE_SUMMARY'|'IAB',
]
}
},
'video': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'CONTENT_MODERATION'|'TEXT_DETECTION'|'TRANSCRIPT'|'LOGOS',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'VIDEO_SUMMARY'|'IAB'|'CHAPTER_SUMMARY',
]
}
},
'audio': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'AUDIO_CONTENT_MODERATION'|'TRANSCRIPT'|'TOPIC_CONTENT_MODERATION',
],
'typeConfiguration': {
'transcript': {
'speakerLabeling': {
'state': 'ENABLED'|'DISABLED'
},
'channelLabeling': {
'state': 'ENABLED'|'DISABLED'
}
}
}
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'AUDIO_SUMMARY'|'IAB'|'TOPIC_SUMMARY',
]
}
}
},
'customOutputConfiguration': {
'blueprints': [
{
'blueprintArn': 'string',
'blueprintVersion': 'string',
'blueprintStage': 'DEVELOPMENT'|'LIVE'
},
]
},
'overrideConfiguration': {
'document': {
'splitter': {
'state': 'ENABLED'|'DISABLED'
},
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'image': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'video': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'audio': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'languageConfiguration': {
'inputLanguages': [
'EN'|'DE'|'ES'|'FR'|'IT'|'PT'|'JA'|'KO'|'CN'|'TW'|'HK',
],
'generativeOutputLanguage': 'DEFAULT'|'EN',
'identifyMultipleLanguages': True|False
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'modalityRouting': {
'jpeg': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'png': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'mp4': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'mov': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO'
}
},
'dataAutomationLibraryConfiguration': {
'libraries': [
{
'libraryArn': 'string'
},
]
},
'status': 'COMPLETED'|'IN_PROGRESS'|'FAILED',
'kmsKeyId': 'string',
'kmsEncryptionContext': {
'string': 'string'
}
}
}
Response Structure
(dict) --
Get DataAutomationProject Response
project (dict) --
Contains the information of a DataAutomationProject.
projectArn (string) --
ARN of a DataAutomationProject
creationTime (datetime) --
Time Stamp
lastModifiedTime (datetime) --
Time Stamp
projectName (string) --
Name of the DataAutomationProject
projectStage (string) --
Stage of the Project
projectType (string) --
Type of the DataAutomationProject
projectDescription (string) --
Description of the DataAutomationProject
standardOutputConfiguration (dict) --
Standard output configuration
document (dict) --
Standard Output Configuration of Document
extraction (dict) --
Standard Extraction Configuration of Document
granularity (dict) --
Granularity of Document Extraction
types (list) --
List of Document Extraction Granularity Type
(string) --
boundingBox (dict) --
Bounding Box Configuration of Document Extraction
state (string) --
State
generativeField (dict) --
Standard Generative Field Configuration of Document
state (string) --
State
outputFormat (dict) --
Output Format of Document
textFormat (dict) --
Text Format of Document Output
types (list) --
List of Document Output Text Format Type
(string) --
additionalFileFormat (dict) --
Additional File Format of Document Output
state (string) --
State
image (dict) --
Standard Output Configuration of Image
extraction (dict) --
Standard Extraction Configuration of Image
category (dict) --
Category of Image Extraction
state (string) --
State
types (list) --
List of Image Extraction Category
(string) --
boundingBox (dict) --
Bounding Box Configuration of Image Extraction
state (string) --
State
generativeField (dict) --
Standard Generative Field Configuration of Image
state (string) --
State
types (list) --
List of Image Standard Generative Field Type
(string) --
video (dict) --
Standard Output Configuration of Video
extraction (dict) --
Standard Extraction Configuration of Video
category (dict) --
Category of Video Extraction
state (string) --
State
types (list) --
List of Video Extraction Category Type
(string) --
boundingBox (dict) --
Bounding Box Configuration of Video Extraction
state (string) --
State
generativeField (dict) --
Standard Generative Field Configuration of Video
state (string) --
State
types (list) --
List of Video Standard Generative Field Type
(string) --
audio (dict) --
Standard Output Configuration of Audio
extraction (dict) --
Standard Extraction Configuration of Audio
category (dict) --
Category of Audio Extraction
state (string) --
State
types (list) --
List of Audio Extraction Category Type
(string) --
typeConfiguration (dict) --
Configuration for different audio extraction category types
transcript (dict) --
Configuration for transcript related features
speakerLabeling (dict) --
Speaker labeling configuration
state (string) --
State
channelLabeling (dict) --
Channel labeling configuration
state (string) --
State
generativeField (dict) --
Standard Generative Field Configuration of Audio
state (string) --
State
types (list) --
List of Audio Standard Generative Field Type
(string) --
customOutputConfiguration (dict) --
Custom output configuration
blueprints (list) --
List of Blueprint Item
(dict) --
Blueprint Item
blueprintArn (string) --
ARN of a Blueprint
blueprintVersion (string) --
Blueprint Version
blueprintStage (string) --
Stage of the Blueprint
overrideConfiguration (dict) --
Override configuration
document (dict) --
Override Configuration of Document
splitter (dict) --
Configuration of Splitter
state (string) --
State
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) --
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
image (dict) --
Override Configuration of Image
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) --
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
video (dict) --
Override Configuration of Video
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) --
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
audio (dict) --
Override Configuration of Audio
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
languageConfiguration (dict) --
Optional configuration for audio language settings
inputLanguages (list) --
List of supported audio languages
(string) --
Supported input languages
generativeOutputLanguage (string) --
Configuration for Audio output language
identifyMultipleLanguages (boolean) --
Enable multiple language identification in audio
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) --
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
modalityRouting (dict) --
Configuration for routing file type to desired modality
jpeg (string) --
Desired Modality types
png (string) --
Desired Modality types
mp4 (string) --
Desired Modality types
mov (string) --
Desired Modality types
dataAutomationLibraryConfiguration (dict) --
DataAutomation Library configuration
libraries (list) --
List of DataAutomationLibrary Items
(dict) --
DataAutomationLibrary Item
libraryArn (string) --
ARN generated at the server side when a DataAutomationLibrary is created
status (string) --
Status of Data Automation Project
kmsKeyId (string) --
KMS Key Identifier
kmsEncryptionContext (dict) --
KMS Encryption Context
(string) --
Encryption context key.
(string) --
Encryption context value.
{'libraryFilter': {'libraryArn': 'string'}}
Lists all existing Amazon Bedrock Data Automation Projects
See also: AWS API Documentation
Request Syntax
client.list_data_automation_projects(
maxResults=123,
nextToken='string',
projectStageFilter='DEVELOPMENT'|'LIVE'|'ALL',
blueprintFilter={
'blueprintArn': 'string',
'blueprintVersion': 'string',
'blueprintStage': 'DEVELOPMENT'|'LIVE'
},
resourceOwner='SERVICE'|'ACCOUNT',
libraryFilter={
'libraryArn': 'string'
}
)
integer
Max Results
string
Pagination token
string
Project Stage filter
dict
Blueprint Filter
blueprintArn (string) -- [REQUIRED]
ARN of a Blueprint
blueprintVersion (string) --
Blueprint Version
blueprintStage (string) --
Stage of the Blueprint
string
Resource Owner
dict
Data Automation Library Filter
libraryArn (string) -- [REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
dict
Response Syntax
{
'projects': [
{
'projectArn': 'string',
'projectStage': 'DEVELOPMENT'|'LIVE',
'projectType': 'ASYNC'|'SYNC',
'projectName': 'string',
'creationTime': datetime(2015, 1, 1)
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
List DataAutomationProject Response
projects (list) --
List of DataAutomationProjectSummary
(dict) --
Summary of a DataAutomationProject
projectArn (string) --
ARN of a DataAutomationProject
projectStage (string) --
Stage of the Project
projectType (string) --
Type of the DataAutomationProject
projectName (string) --
Name of the DataAutomationProject
creationTime (datetime) --
Time Stamp
nextToken (string) --
Pagination token
{'dataAutomationLibraryConfiguration': {'libraries': [{'libraryArn': 'string'}]}}
Updates an existing Amazon Bedrock Data Automation Project
See also: AWS API Documentation
Request Syntax
client.update_data_automation_project(
projectArn='string',
projectStage='DEVELOPMENT'|'LIVE',
projectDescription='string',
standardOutputConfiguration={
'document': {
'extraction': {
'granularity': {
'types': [
'DOCUMENT'|'PAGE'|'ELEMENT'|'WORD'|'LINE',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED'
},
'outputFormat': {
'textFormat': {
'types': [
'PLAIN_TEXT'|'MARKDOWN'|'HTML'|'CSV',
]
},
'additionalFileFormat': {
'state': 'ENABLED'|'DISABLED'
}
}
},
'image': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'CONTENT_MODERATION'|'TEXT_DETECTION'|'LOGOS',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'IMAGE_SUMMARY'|'IAB',
]
}
},
'video': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'CONTENT_MODERATION'|'TEXT_DETECTION'|'TRANSCRIPT'|'LOGOS',
]
},
'boundingBox': {
'state': 'ENABLED'|'DISABLED'
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'VIDEO_SUMMARY'|'IAB'|'CHAPTER_SUMMARY',
]
}
},
'audio': {
'extraction': {
'category': {
'state': 'ENABLED'|'DISABLED',
'types': [
'AUDIO_CONTENT_MODERATION'|'TRANSCRIPT'|'TOPIC_CONTENT_MODERATION',
],
'typeConfiguration': {
'transcript': {
'speakerLabeling': {
'state': 'ENABLED'|'DISABLED'
},
'channelLabeling': {
'state': 'ENABLED'|'DISABLED'
}
}
}
}
},
'generativeField': {
'state': 'ENABLED'|'DISABLED',
'types': [
'AUDIO_SUMMARY'|'IAB'|'TOPIC_SUMMARY',
]
}
}
},
customOutputConfiguration={
'blueprints': [
{
'blueprintArn': 'string',
'blueprintVersion': 'string',
'blueprintStage': 'DEVELOPMENT'|'LIVE'
},
]
},
overrideConfiguration={
'document': {
'splitter': {
'state': 'ENABLED'|'DISABLED'
},
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'image': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'video': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'audio': {
'modalityProcessing': {
'state': 'ENABLED'|'DISABLED'
},
'languageConfiguration': {
'inputLanguages': [
'EN'|'DE'|'ES'|'FR'|'IT'|'PT'|'JA'|'KO'|'CN'|'TW'|'HK',
],
'generativeOutputLanguage': 'DEFAULT'|'EN',
'identifyMultipleLanguages': True|False
},
'sensitiveDataConfiguration': {
'detectionMode': 'DETECTION'|'DETECTION_AND_REDACTION',
'detectionScope': [
'STANDARD'|'CUSTOM',
],
'piiEntitiesConfiguration': {
'piiEntityTypes': [
'ALL'|'ADDRESS'|'AGE'|'NAME'|'EMAIL'|'PHONE'|'USERNAME'|'PASSWORD'|'DRIVER_ID'|'LICENSE_PLATE'|'VEHICLE_IDENTIFICATION_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'PIN'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'SWIFT_CODE'|'IP_ADDRESS'|'MAC_ADDRESS'|'URL'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER',
],
'redactionMaskMode': 'PII'|'ENTITY_TYPE'
}
}
},
'modalityRouting': {
'jpeg': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'png': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'mp4': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO',
'mov': 'IMAGE'|'DOCUMENT'|'AUDIO'|'VIDEO'
}
},
dataAutomationLibraryConfiguration={
'libraries': [
{
'libraryArn': 'string'
},
]
},
encryptionConfiguration={
'kmsKeyId': 'string',
'kmsEncryptionContext': {
'string': 'string'
}
}
)
string
[REQUIRED]
ARN generated at the server side when a DataAutomationProject is created
string
Stage of the Project
string
Description of the DataAutomationProject
dict
[REQUIRED]
Standard output configuration
document (dict) --
Standard Output Configuration of Document
extraction (dict) --
Standard Extraction Configuration of Document
granularity (dict) -- [REQUIRED]
Granularity of Document Extraction
types (list) --
List of Document Extraction Granularity Type
(string) --
boundingBox (dict) -- [REQUIRED]
Bounding Box Configuration of Document Extraction
state (string) -- [REQUIRED]
State
generativeField (dict) --
Standard Generative Field Configuration of Document
state (string) -- [REQUIRED]
State
outputFormat (dict) --
Output Format of Document
textFormat (dict) -- [REQUIRED]
Text Format of Document Output
types (list) --
List of Document Output Text Format Type
(string) --
additionalFileFormat (dict) -- [REQUIRED]
Additional File Format of Document Output
state (string) -- [REQUIRED]
State
image (dict) --
Standard Output Configuration of Image
extraction (dict) --
Standard Extraction Configuration of Image
category (dict) -- [REQUIRED]
Category of Image Extraction
state (string) -- [REQUIRED]
State
types (list) --
List of Image Extraction Category
(string) --
boundingBox (dict) -- [REQUIRED]
Bounding Box Configuration of Image Extraction
state (string) -- [REQUIRED]
State
generativeField (dict) --
Standard Generative Field Configuration of Image
state (string) -- [REQUIRED]
State
types (list) --
List of Image Standard Generative Field Type
(string) --
video (dict) --
Standard Output Configuration of Video
extraction (dict) --
Standard Extraction Configuration of Video
category (dict) -- [REQUIRED]
Category of Video Extraction
state (string) -- [REQUIRED]
State
types (list) --
List of Video Extraction Category Type
(string) --
boundingBox (dict) -- [REQUIRED]
Bounding Box Configuration of Video Extraction
state (string) -- [REQUIRED]
State
generativeField (dict) --
Standard Generative Field Configuration of Video
state (string) -- [REQUIRED]
State
types (list) --
List of Video Standard Generative Field Type
(string) --
audio (dict) --
Standard Output Configuration of Audio
extraction (dict) --
Standard Extraction Configuration of Audio
category (dict) -- [REQUIRED]
Category of Audio Extraction
state (string) -- [REQUIRED]
State
types (list) --
List of Audio Extraction Category Type
(string) --
typeConfiguration (dict) --
Configuration for different audio extraction category types
transcript (dict) --
Configuration for transcript related features
speakerLabeling (dict) --
Speaker labeling configuration
state (string) -- [REQUIRED]
State
channelLabeling (dict) --
Channel labeling configuration
state (string) -- [REQUIRED]
State
generativeField (dict) --
Standard Generative Field Configuration of Audio
state (string) -- [REQUIRED]
State
types (list) --
List of Audio Standard Generative Field Type
(string) --
dict
Custom output configuration
blueprints (list) --
List of Blueprint Item
(dict) --
Blueprint Item
blueprintArn (string) -- [REQUIRED]
ARN of a Blueprint
blueprintVersion (string) --
Blueprint Version
blueprintStage (string) --
Stage of the Blueprint
dict
Override configuration
document (dict) --
Override Configuration of Document
splitter (dict) --
Configuration of Splitter
state (string) --
State
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) -- [REQUIRED]
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
image (dict) --
Override Configuration of Image
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) -- [REQUIRED]
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
video (dict) --
Override Configuration of Video
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) -- [REQUIRED]
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
audio (dict) --
Override Configuration of Audio
modalityProcessing (dict) --
Configuration to enable/disable processing of modality
state (string) --
State
languageConfiguration (dict) --
Optional configuration for audio language settings
inputLanguages (list) --
List of supported audio languages
(string) --
Supported input languages
generativeOutputLanguage (string) --
Configuration for Audio output language
identifyMultipleLanguages (boolean) --
Enable multiple language identification in audio
sensitiveDataConfiguration (dict) --
Configuration for sensitive data detection and redaction
detectionMode (string) -- [REQUIRED]
Mode for sensitive data detection
detectionScope (list) --
Scope of detection - what types of sensitive data to detect
(string) --
Types of sensitive data detection scope
piiEntitiesConfiguration (dict) --
Configuration for PII entities detection and redaction
piiEntityTypes (list) --
Types of PII entities to detect
(string) --
Types of PII entities that can be detected, we will support every types that Guardrails can support
redactionMaskMode (string) --
Mode for redacting detected PII
modalityRouting (dict) --
Configuration for routing file type to desired modality
jpeg (string) --
Desired Modality types
png (string) --
Desired Modality types
mp4 (string) --
Desired Modality types
mov (string) --
Desired Modality types
dict
DataAutomation Library configuration
libraries (list) --
List of DataAutomationLibrary Items
(dict) --
DataAutomationLibrary Item
libraryArn (string) -- [REQUIRED]
ARN generated at the server side when a DataAutomationLibrary is created
dict
KMS Encryption Configuration
kmsKeyId (string) -- [REQUIRED]
KMS Key Identifier
kmsEncryptionContext (dict) --
KMS Encryption Context
(string) --
Encryption context key.
(string) --
Encryption context value.
dict
Response Syntax
{
'projectArn': 'string',
'projectStage': 'DEVELOPMENT'|'LIVE',
'status': 'COMPLETED'|'IN_PROGRESS'|'FAILED'
}
Response Structure
(dict) --
Update DataAutomationProject Response
projectArn (string) --
ARN of a DataAutomationProject
projectStage (string) --
Stage of the Project
status (string) --
Status of Data Automation Project