@cdklabs/genai-idp-sagemaker-udop-processor

Constructs

BasicSagemakerClassifier

A basic SageMaker-based document classifier for the Pattern 3 document processor.

This construct provides a simple way to deploy a SageMaker endpoint with a document classification model that can categorize documents based on their content and structure. It supports models like RVL-CDIP or UDOP for specialized document classification tasks.

The basic classifier includes standard auto-scaling capabilities and sensible defaults for common use cases. For more advanced configurations, consider creating your own SageMaker endpoint and passing it directly to the SagemakerUdopProcessor.

Example

const classifier = new BasicSagemakerClassifier(this, 'Classifier', {
  outputBucket: bucket,
  modelData: ModelData.fromAsset('./model'),
  instanceType: InstanceType.ML_G4DN_XLARGE,
});

const processor = new SagemakerUdopProcessor(this, 'Processor', {
  environment,
  classifierEndpoint: classifier.endpoint,
  // ... other configuration
});

Initializers

import { BasicSagemakerClassifier } from '@cdklabs/genai-idp-sagemaker-udop-processor'

new BasicSagemakerClassifier(scope: Construct, id: string, props: BasicSagemakerClassifierProps)

Name	Type	Description
`scope`	`constructs.Construct`	No description.
`id`	`string`	No description.
`props`	`BasicSagemakerClassifierProps`	No description.

`scope`^Required

Type: constructs.Construct

`id`^Required

Type: string

`props`^Required

Type: BasicSagemakerClassifierProps

Methods

Name	Description
`toString`	Returns a string representation of this construct.
`with`	Applies one or more mixins to this construct.

`toString`

public toString(): string

Returns a string representation of this construct.

`with`

public with(mixins: ...IMixin[]): IConstruct

Applies one or more mixins to this construct.

Mixins are applied in order. The list of constructs is captured at the start of the call, so constructs added by a mixin will not be visited. Use multiple with() calls if subsequent mixins should apply to added constructs.

`mixins`^Required

Type: ...constructs.IMixin[]

The mixins to apply.

Static Functions

Name	Description
`isConstruct`	Checks if `x` is a construct.

`isConstruct`

import { BasicSagemakerClassifier } from '@cdklabs/genai-idp-sagemaker-udop-processor'

BasicSagemakerClassifier.isConstruct(x: any)

Checks if x is a construct.

Use this method instead of instanceof to properly detect Construct instances, even when the construct library is symlinked.

Explanation: in JavaScript, multiple copies of the constructs library on disk are seen as independent, completely different libraries. As a consequence, the class Construct in each copy of the constructs library is seen as a different class, and an instance of one class will not test as instanceof the other class. npm install will not create installations like this, but users may manually symlink construct libraries together or use a monorepo tool: in those cases, multiple copies of the constructs library can be accidentally installed, and instanceof will behave unpredictably. It is safest to avoid using instanceof, and using this type-testing method instead.

`x`^Required

Type: any

Any object.

Properties

Name	Type	Description
`node`	`constructs.Node`	The tree node.
`endpoint`	`@aws-cdk/aws-sagemaker-alpha.IEndpoint`	The SageMaker endpoint that hosts the document classification model.

`node`^Required

public readonly node: Node;

Type: constructs.Node

The tree node.

`endpoint`^Required

public readonly endpoint: IEndpoint;

Type: @aws-cdk/aws-sagemaker-alpha.IEndpoint

The SageMaker endpoint that hosts the document classification model.

This endpoint is invoked during document processing to determine document types and categories.

SagemakerUdopProcessor

Implements: ISagemakerUdopProcessor

SageMaker UDOP document processor implementation that uses specialized models for document processing.

Initializers

import { SagemakerUdopProcessor } from '@cdklabs/genai-idp-sagemaker-udop-processor'

new SagemakerUdopProcessor(scope: Construct, id: string, props: SagemakerUdopProcessorProps)

Name	Type	Description
`scope`	`constructs.Construct`	No description.
`id`	`string`	No description.
`props`	`SagemakerUdopProcessorProps`	No description.

`scope`^Required

Type: constructs.Construct

`id`^Required

Type: string

`props`^Required

Type: SagemakerUdopProcessorProps

Methods

Name	Description
`toString`	Returns a string representation of this construct.
`with`	Applies one or more mixins to this construct.
`metricClassificationRequestsTotal`	Creates a CloudWatch metric for total classification requests.
`metricInputDocumentPages`	Creates a CloudWatch metric for input document pages processed.
`metricInputDocuments`	Creates a CloudWatch metric for input documents processed.

`toString`

public toString(): string

Returns a string representation of this construct.

`with`

public with(mixins: ...IMixin[]): IConstruct

Applies one or more mixins to this construct.

Mixins are applied in order. The list of constructs is captured at the start of the call, so constructs added by a mixin will not be visited. Use multiple with() calls if subsequent mixins should apply to added constructs.

`mixins`^Required

Type: ...constructs.IMixin[]

The mixins to apply.

`metricClassificationRequestsTotal`

public metricClassificationRequestsTotal(props?: MetricOptions): Metric

Creates a CloudWatch metric for total classification requests.

`props`^Optional

Type: aws-cdk-lib.aws_cloudwatch.MetricOptions

Optional metric configuration properties.

`metricInputDocumentPages`

public metricInputDocumentPages(props?: MetricOptions): Metric

Creates a CloudWatch metric for input document pages processed.

`props`^Optional

Type: aws-cdk-lib.aws_cloudwatch.MetricOptions

Optional metric configuration properties.

`metricInputDocuments`

public metricInputDocuments(props?: MetricOptions): Metric

Creates a CloudWatch metric for input documents processed.

`props`^Optional

Type: aws-cdk-lib.aws_cloudwatch.MetricOptions

Optional metric configuration properties.

Static Functions

Name	Description
`isConstruct`	Checks if `x` is a construct.

`isConstruct`

import { SagemakerUdopProcessor } from '@cdklabs/genai-idp-sagemaker-udop-processor'

SagemakerUdopProcessor.isConstruct(x: any)

Checks if x is a construct.

Use this method instead of instanceof to properly detect Construct instances, even when the construct library is symlinked.

Explanation: in JavaScript, multiple copies of the constructs library on disk are seen as independent, completely different libraries. As a consequence, the class Construct in each copy of the constructs library is seen as a different class, and an instance of one class will not test as instanceof the other class. npm install will not create installations like this, but users may manually symlink construct libraries together or use a monorepo tool: in those cases, multiple copies of the constructs library can be accidentally installed, and instanceof will behave unpredictably. It is safest to avoid using instanceof, and using this type-testing method instead.

`x`^Required

Type: any

Any object.

Properties

Name	Type	Description
`node`	`constructs.Node`	The tree node.
`environment`	`@cdklabs/genai-idp.IProcessingEnvironment`	The processing environment that provides shared infrastructure resources.
`maxProcessingConcurrency`	`number`	The maximum number of documents that can be processed concurrently.
`stateMachine`	`aws-cdk-lib.aws_stepfunctions.IStateMachine`	The Step Functions state machine that orchestrates the document processing workflow.

`node`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

This processor implements an intelligent document processing workflow that uses specialized models like UDOP (Unified Document Processing) or RVL-CDIP deployed on SageMaker for document classification, followed by foundation models for information extraction.

SageMaker UDOP Processor is ideal for specialized document types that require custom classification models beyond what's possible with foundation models alone, such as complex forms, technical documents, or domain-specific content. It provides the highest level of customization for document classification while maintaining the flexibility of foundation models for extraction.

public readonly node: Node;

Type: constructs.Node

The tree node.

`environment`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

This processor implements an intelligent document processing workflow that uses specialized models like UDOP (Unified Document Processing) or RVL-CDIP deployed on SageMaker for document classification, followed by foundation models for information extraction.

SageMaker UDOP Processor is ideal for specialized document types that require custom classification models beyond what's possible with foundation models alone, such as complex forms, technical documents, or domain-specific content. It provides the highest level of customization for document classification while maintaining the flexibility of foundation models for extraction.

public readonly environment: IProcessingEnvironment;

Type: @cdklabs/genai-idp.IProcessingEnvironment

The processing environment that provides shared infrastructure resources.

Includes buckets, tables, API, encryption, and VPC configuration used by all processing functions within this processor.

`maxProcessingConcurrency`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

This processor implements an intelligent document processing workflow that uses specialized models like UDOP (Unified Document Processing) or RVL-CDIP deployed on SageMaker for document classification, followed by foundation models for information extraction.

SageMaker UDOP Processor is ideal for specialized document types that require custom classification models beyond what's possible with foundation models alone, such as complex forms, technical documents, or domain-specific content. It provides the highest level of customization for document classification while maintaining the flexibility of foundation models for extraction.

public readonly maxProcessingConcurrency: number;

Type: number
Default: 100

The maximum number of documents that can be processed concurrently.

Controls the parallelism of the Step Functions state machine to balance throughput against resource consumption.

`stateMachine`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

This processor implements an intelligent document processing workflow that uses specialized models like UDOP (Unified Document Processing) or RVL-CDIP deployed on SageMaker for document classification, followed by foundation models for information extraction.

SageMaker UDOP Processor is ideal for specialized document types that require custom classification models beyond what's possible with foundation models alone, such as complex forms, technical documents, or domain-specific content. It provides the highest level of customization for document classification while maintaining the flexibility of foundation models for extraction.

public readonly stateMachine: IStateMachine;

Type: aws-cdk-lib.aws_stepfunctions.IStateMachine

The Step Functions state machine that orchestrates the document processing workflow.

Coordinates OCR, classification, extraction, assessment, summarization, and evaluation steps in the correct sequence.

Structs

BasicSagemakerClassifierProps

Configuration properties for the basic SageMaker-based document classifier.

This classifier uses a SageMaker endpoint to categorize documents based on their content and structure, enabling targeted extraction strategies.

Initializer

import { BasicSagemakerClassifierProps } from '@cdklabs/genai-idp-sagemaker-udop-processor'

const basicSagemakerClassifierProps: BasicSagemakerClassifierProps = { ... }

Properties

Name	Type	Description
`instanceType`	`@aws-cdk/aws-sagemaker-alpha.InstanceType`	The instance type to use for the SageMaker endpoint.
`modelData`	`@aws-cdk/aws-sagemaker-alpha.ModelData`	The model data for the SageMaker endpoint.
`outputBucket`	`aws-cdk-lib.aws_s3.IBucket`	The S3 bucket where classification outputs will be stored.
`key`	`aws-cdk-lib.aws_kms.IKey`	Optional KMS key for encrypting classifier resources.
`maxInstanceCount`	`number`	The maximum number of instances for the SageMaker endpoint.
`minInstanceCount`	`number`	The minimum number of instances for the SageMaker endpoint.
`scaleInCooldown`	`aws-cdk-lib.Duration`	The cooldown period after scaling in before another scale-in action can occur.
`scaleOutCooldown`	`aws-cdk-lib.Duration`	The cooldown period after scaling out before another scale-out action can occur.
`targetInvocationsPerInstancePerMinute`	`number`	The target number of invocations per instance per minute.

`instanceType`^Required

public readonly instanceType: InstanceType;

Type: @aws-cdk/aws-sagemaker-alpha.InstanceType

The instance type to use for the SageMaker endpoint.

Determines the computational resources available for document classification. For deep learning models, GPU instances are typically recommended.

`modelData`^Required

public readonly modelData: ModelData;

Type: @aws-cdk/aws-sagemaker-alpha.ModelData

The model data for the SageMaker endpoint.

Contains the trained model artifacts that will be deployed to the endpoint. This can be a pre-trained document classification model like RVL-CDIP or UDOP.

`outputBucket`^Required

public readonly outputBucket: IBucket;

Type: aws-cdk-lib.aws_s3.IBucket

The S3 bucket where classification outputs will be stored.

Contains intermediate results from the document classification process.

`key`^Optional

public readonly key: IKey;

Type: aws-cdk-lib.aws_kms.IKey

Optional KMS key for encrypting classifier resources.

When provided, ensures data security for the SageMaker endpoint and associated resources.

`maxInstanceCount`^Optional

public readonly maxInstanceCount: number;

Type: number
Default: 4

The maximum number of instances for the SageMaker endpoint.

Controls the maximum capacity for document classification during high load.

`minInstanceCount`^Optional

public readonly minInstanceCount: number;

Type: number
Default: 1

The minimum number of instances for the SageMaker endpoint.

Controls the baseline capacity for document classification.

`scaleInCooldown`^Optional

public readonly scaleInCooldown: Duration;

Type: aws-cdk-lib.Duration
Default: cdk.Duration.minutes(5)

The cooldown period after scaling in before another scale-in action can occur.

Prevents rapid fluctuations in endpoint capacity.

`scaleOutCooldown`^Optional

public readonly scaleOutCooldown: Duration;

Type: aws-cdk-lib.Duration
Default: cdk.Duration.minutes(1)

The cooldown period after scaling out before another scale-out action can occur.

Prevents rapid fluctuations in endpoint capacity.

`targetInvocationsPerInstancePerMinute`^Optional

public readonly targetInvocationsPerInstancePerMinute: number;

Type: number
Default: 20

The target number of invocations per instance per minute.

Used to determine when to scale the endpoint in or out.

SagemakerUdopProcessorConfigurationDefinitionOptions

Options for configuring the SageMaker UDOP processor configuration definition.

Allows customization of extraction, evaluation, and summarization stages.

Initializer

import { SagemakerUdopProcessorConfigurationDefinitionOptions } from '@cdklabs/genai-idp-sagemaker-udop-processor'

const sagemakerUdopProcessorConfigurationDefinitionOptions: SagemakerUdopProcessorConfigurationDefinitionOptions = { ... }

Properties

Name	Type	Description
`assessmentModel`	`@aws-cdk/aws-bedrock-alpha.IBedrockInvokable`	Optional invokable model used for evaluating assessment results.
`customPromptGeneratorFunction`	`aws-cdk-lib.aws_lambda.IFunction`	Optional custom prompt generator Lambda function.
`evaluationModel`	`@aws-cdk/aws-bedrock-alpha.IBedrockInvokable`	Optional configuration for the evaluation stage.
`extractionModel`	`@aws-cdk/aws-bedrock-alpha.IBedrockInvokable`	Optional configuration for the extraction stage.
`summarizationModel`	`@aws-cdk/aws-bedrock-alpha.IBedrockInvokable`	Optional configuration for the summarization stage.

`assessmentModel`^Optional

public readonly assessmentModel: IBedrockInvokable;

Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable
Default: as defined in the definition file

Optional invokable model used for evaluating assessment results.

Can be a Bedrock foundation model, Bedrock inference profile, or custom model. Used to assess the quality and accuracy of extracted information by comparing assessment results against expected values.

`customPromptGeneratorFunction`^Optional

public readonly customPromptGeneratorFunction: IFunction;

Type: aws-cdk-lib.aws_lambda.IFunction

Optional custom prompt generator Lambda function.

When provided, the function ARN will be injected into the configuration at extraction.custom_prompt_lambda_arn.

`evaluationModel`^Optional

public readonly evaluationModel: IBedrockInvokable;

Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable

Optional configuration for the evaluation stage.

Defines the model and parameters used for evaluating extraction accuracy.

`extractionModel`^Optional

public readonly extractionModel: IBedrockInvokable;

Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable

Optional configuration for the extraction stage.

Defines the model and parameters used for information extraction.

`summarizationModel`^Optional

public readonly summarizationModel: IBedrockInvokable;

Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable

Optional configuration for the summarization stage.

Defines the model and parameters used for generating document summaries.

SagemakerUdopProcessorProps

Configuration properties for the SageMaker UDOP document processor.

Initializer

import { SagemakerUdopProcessorProps } from '@cdklabs/genai-idp-sagemaker-udop-processor'

const sagemakerUdopProcessorProps: SagemakerUdopProcessorProps = { ... }

Properties

Name	Type	Description
`environment`	`@cdklabs/genai-idp.IProcessingEnvironment`	The processing environment that provides shared infrastructure and services.
`maxProcessingConcurrency`	`number`	The maximum number of documents that can be processed concurrently.
`classifierEndpoint`	`@aws-cdk/aws-sagemaker-alpha.IEndpoint`	The SageMaker endpoint used for document classification.
`configuration`	`ISagemakerUdopProcessorConfiguration`	Configuration for the SageMaker UDOP document processor.
`assessmentGuardrail`	`@aws-cdk/aws-bedrock-alpha.IGuardrail`	Optional Bedrock guardrail to apply to assessment model interactions.
`classificationGuardrail`	`@aws-cdk/aws-bedrock-alpha.IGuardrail`	Optional Bedrock guardrail to apply to classification model interactions.
`enableEditSections`	`boolean`	Enable edit sections feature for classification updates.
`evaluationBaselineBucket`	`aws-cdk-lib.aws_s3.IBucket`	Optional S3 bucket containing baseline documents for evaluation.
`evaluationEnabled`	`boolean`	Controls whether extraction results are evaluated for accuracy.
`extractionGuardrail`	`@aws-cdk/aws-bedrock-alpha.IGuardrail`	Optional Bedrock guardrail to apply to extraction model interactions.
`ocrMaxWorkers`	`number`	The maximum number of concurrent workers for OCR processing.
`sectionSplittingStrategy`	`@cdklabs/genai-idp.SectionSplittingStrategy`	Section splitting strategy configuration.
`summarizationGuardrail`	`@aws-cdk/aws-bedrock-alpha.IGuardrail`	Optional Bedrock guardrail to apply to summarization model interactions.

`environment`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly environment: IProcessingEnvironment;

Type: @cdklabs/genai-idp.IProcessingEnvironment

The processing environment that provides shared infrastructure and services.

Contains input/output buckets, tracking tables, API endpoints, and other resources needed for document processing operations.

`maxProcessingConcurrency`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly maxProcessingConcurrency: number;

Type: number
Default: 100 concurrent workflows

The maximum number of documents that can be processed concurrently.

Controls the throughput and resource utilization of the document processing system.

`classifierEndpoint`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly classifierEndpoint: IEndpoint;

Type: @aws-cdk/aws-sagemaker-alpha.IEndpoint

The SageMaker endpoint used for document classification.

Determines document types based on content and structure analysis using specialized models like RVL-CDIP or UDOP deployed on SageMaker.

This is a key component of Pattern 3, enabling specialized document classification beyond what's possible with foundation models alone. Users can create their own SageMaker endpoint using any method (CDK constructs, existing endpoints, etc.) and pass it directly to the processor.

`configuration`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly configuration: ISagemakerUdopProcessorConfiguration;

Type: ISagemakerUdopProcessorConfiguration

Configuration for the SageMaker UDOP document processor.

Provides customization options for the processing workflow, including schema definitions, prompts, and evaluation settings.

`assessmentGuardrail`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly assessmentGuardrail: IGuardrail;

Type: @aws-cdk/aws-bedrock-alpha.IGuardrail
Default: No guardrail is applied

Optional Bedrock guardrail to apply to assessment model interactions.

Helps ensure model outputs adhere to content policies and guidelines by filtering inappropriate content and enforcing usage policies.

`classificationGuardrail`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly classificationGuardrail: IGuardrail;

Type: @aws-cdk/aws-bedrock-alpha.IGuardrail
Default: No guardrail is applied

Optional Bedrock guardrail to apply to classification model interactions.

Helps ensure model outputs adhere to content policies and guidelines by filtering inappropriate content and enforcing usage policies.

`enableEditSections`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly enableEditSections: boolean;

Type: boolean
Default: false

Enable edit sections feature for classification updates.

When enabled, allows users to modify document classification through the UI and trigger selective reprocessing of affected sections. This provides flexibility to correct classification errors without reprocessing entire documents.

`evaluationBaselineBucket`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly evaluationBaselineBucket: IBucket;

Type: aws-cdk-lib.aws_s3.IBucket
Default: No evaluation baseline bucket is configured

Optional S3 bucket containing baseline documents for evaluation.

Used as ground truth when evaluating extraction accuracy by comparing extraction results against known correct values.

Required when evaluationEnabled is true.

`evaluationEnabled`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly evaluationEnabled: boolean;

Type: boolean
Default: false

Controls whether extraction results are evaluated for accuracy.

When enabled, compares extraction results against expected values to measure extraction quality and identify improvement areas.

`extractionGuardrail`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly extractionGuardrail: IGuardrail;

Type: @aws-cdk/aws-bedrock-alpha.IGuardrail
Default: No guardrail is applied

Optional Bedrock guardrail to apply to extraction model interactions.

Helps ensure model outputs adhere to content policies and guidelines by filtering inappropriate content and enforcing usage policies.

`ocrMaxWorkers`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly ocrMaxWorkers: number;

Type: number
Default: 20

The maximum number of concurrent workers for OCR processing.

Controls parallelism during the text extraction phase to optimize throughput while managing resource utilization.

`sectionSplittingStrategy`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly sectionSplittingStrategy: SectionSplittingStrategy;

Type: @cdklabs/genai-idp.SectionSplittingStrategy
Default: SectionSplittingStrategy.LLM_DETERMINED

Section splitting strategy configuration.

Controls how multi-page documents are divided into sections during classification. This affects how documents of the same type are grouped together and processed.

Options: - DISABLED: Entire document treated as single section with first detected class - PAGE: One section per page preventing automatic joining of same-type documents - LLM_DETERMINED: Uses LLM boundary detection with "Start"/"Continue" indicators

`summarizationGuardrail`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models for accurate document categorization before extraction.

SageMaker UDOP Processor offers the highest level of customization for document processing, allowing you to deploy and use specialized models for document classification while still leveraging foundation models for extraction tasks. This processor is particularly useful for domain-specific document processing needs.

public readonly summarizationGuardrail: IGuardrail;

Type: @aws-cdk/aws-bedrock-alpha.IGuardrail
Default: No guardrail is applied

Optional Bedrock guardrail to apply to summarization model interactions.

Helps ensure model outputs adhere to content policies and guidelines by filtering inappropriate content and enforcing usage policies.

Classes

SagemakerUdopProcessorConfiguration

Implements: ISagemakerUdopProcessorConfiguration

Configuration management for SageMaker UDOP document processing using SageMaker for classification.

This construct creates and manages the configuration for SageMaker UDOP document processing, including schema definitions, extraction prompts, and configuration values. It provides a centralized way to manage document classes, extraction schemas, and model parameters for specialized document processing with SageMaker.

Initializers

import { SagemakerUdopProcessorConfiguration } from '@cdklabs/genai-idp-sagemaker-udop-processor'

new SagemakerUdopProcessorConfiguration(definition: ISagemakerUdopProcessorConfigurationDefinition)

Name	Type	Description
`definition`	`ISagemakerUdopProcessorConfigurationDefinition`	The configuration definition instance.

`definition`^Required

Type: ISagemakerUdopProcessorConfigurationDefinition

The configuration definition instance.

Methods

Name	Description
`bind`	Binds the configuration to a processor instance.

`bind`

public bind(processor: ISagemakerUdopProcessor): ISagemakerUdopProcessorConfigurationDefinition

Binds the configuration to a processor instance.

This method applies the configuration to the processor.

`processor`^Required

Type: ISagemakerUdopProcessor

Static Functions

Name	Description
`fromFile`	Creates a configuration from a YAML file.
`rvlCdipPackageSample`	Creates a default configuration with standard settings.

`fromFile`

import { SagemakerUdopProcessorConfiguration } from '@cdklabs/genai-idp-sagemaker-udop-processor'

SagemakerUdopProcessorConfiguration.fromFile(filePath: string, options?: SagemakerUdopProcessorConfigurationDefinitionOptions)

Creates a configuration from a YAML file.

`filePath`^Required

Type: string

Path to the YAML configuration file.

`options`^Optional

Type: SagemakerUdopProcessorConfigurationDefinitionOptions

Optional configuration options to override file settings.

`rvlCdipPackageSample`

import { SagemakerUdopProcessorConfiguration } from '@cdklabs/genai-idp-sagemaker-udop-processor'

SagemakerUdopProcessorConfiguration.rvlCdipPackageSample(options?: SagemakerUdopProcessorConfigurationDefinitionOptions)

Creates a default configuration with standard settings.

`options`^Optional

Type: SagemakerUdopProcessorConfigurationDefinitionOptions

Optional configuration options.

SagemakerUdopProcessorConfigurationDefinition

Configuration definition for SageMaker UDOP document processing.

Provides methods to create and customize configuration for SageMaker UDOP processing.

Initializers

import { SagemakerUdopProcessorConfigurationDefinition } from '@cdklabs/genai-idp-sagemaker-udop-processor'

new SagemakerUdopProcessorConfigurationDefinition()

Name	Type	Description

Static Functions

Name	Description
`fromFile`	Creates a configuration definition from a YAML file.
`rvlCdipPackageSample`	Creates a default configuration definition for SageMaker UDOP processing.

`fromFile`

import { SagemakerUdopProcessorConfigurationDefinition } from '@cdklabs/genai-idp-sagemaker-udop-processor'

SagemakerUdopProcessorConfigurationDefinition.fromFile(filePath: string, options?: SagemakerUdopProcessorConfigurationDefinitionOptions)

Creates a configuration definition from a YAML file.

Allows users to provide custom configuration files for document processing.

`filePath`^Required

Type: string

Path to the YAML configuration file.

`options`^Optional

Type: SagemakerUdopProcessorConfigurationDefinitionOptions

Optional customization for processing stages.

`rvlCdipPackageSample`

import { SagemakerUdopProcessorConfigurationDefinition } from '@cdklabs/genai-idp-sagemaker-udop-processor'

SagemakerUdopProcessorConfigurationDefinition.rvlCdipPackageSample(options?: SagemakerUdopProcessorConfigurationDefinitionOptions)

Creates a default configuration definition for SageMaker UDOP processing.

This configuration includes basic settings for extraction, evaluation, and summarization when using SageMaker for document classification.

`options`^Optional

Type: SagemakerUdopProcessorConfigurationDefinitionOptions

Optional customization for processing stages.

SagemakerUdopProcessorConfigurationSchema

Implements: ISagemakerUdopProcessorConfigurationSchema

Schema definition for SageMaker UDOP processor configuration. Provides JSON Schema validation rules for the configuration UI and API.

This class defines the structure, validation rules, and UI presentation for the SageMaker UDOP processor configuration, including document classes, attributes, extraction parameters, evaluation criteria, and summarization options. It's specialized for use with SageMaker endpoints for document classification.

Initializers

import { SagemakerUdopProcessorConfigurationSchema } from '@cdklabs/genai-idp-sagemaker-udop-processor'

new SagemakerUdopProcessorConfigurationSchema()

Name	Type	Description

Methods

Name	Description
`bind`	Binds the configuration schema to a processor instance.

`bind`

public bind(processor: SagemakerUdopProcessor): void

Binds the configuration schema to a processor instance.

Creates a custom resource that updates the schema in the configuration table.

`processor`^Required

Type: SagemakerUdopProcessor

The SageMaker UDOP document processor to apply the schema to.

Protocols

ISagemakerUdopProcessor

Extends: @cdklabs/genai-idp.IDocumentProcessor
Implemented By: SagemakerUdopProcessor, ISagemakerUdopProcessor

Interface for SageMaker UDOP document processor implementation.

Properties

Name	Type	Description
`node`	`constructs.Node`	The tree node.
`environment`	`@cdklabs/genai-idp.IProcessingEnvironment`	The processing environment that provides shared infrastructure and services.
`maxProcessingConcurrency`	`number`	The maximum number of documents that can be processed concurrently.
`stateMachine`	`aws-cdk-lib.aws_stepfunctions.IStateMachine`	The Step Functions state machine that orchestrates the document processing workflow.
`evaluationFunction`	`any`	The evaluation function if evaluation is enabled for this processor.

`node`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models like RVL-CDIP or UDOP for accurate document categorization before extraction.

Use SageMaker UDOP Processor when: - Processing highly specialized or complex document types - You need custom classification models beyond what foundation models can provide - You have domain-specific document types requiring specialized handling - You want to leverage fine-tuned models for specific document domains

public readonly node: Node;

Type: constructs.Node

The tree node.

`environment`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models like RVL-CDIP or UDOP for accurate document categorization before extraction.

Use SageMaker UDOP Processor when: - Processing highly specialized or complex document types - You need custom classification models beyond what foundation models can provide - You have domain-specific document types requiring specialized handling - You want to leverage fine-tuned models for specific document domains

public readonly environment: IProcessingEnvironment;

Type: @cdklabs/genai-idp.IProcessingEnvironment

The processing environment that provides shared infrastructure and services.

Contains input/output buckets, tracking tables, API endpoints, and other resources needed for document processing operations.

`maxProcessingConcurrency`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models like RVL-CDIP or UDOP for accurate document categorization before extraction.

Use SageMaker UDOP Processor when: - Processing highly specialized or complex document types - You need custom classification models beyond what foundation models can provide - You have domain-specific document types requiring specialized handling - You want to leverage fine-tuned models for specific document domains

public readonly maxProcessingConcurrency: number;

Type: number

The maximum number of documents that can be processed concurrently.

Controls the throughput and resource utilization of the document processing system.

`stateMachine`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models like RVL-CDIP or UDOP for accurate document categorization before extraction.

Use SageMaker UDOP Processor when: - Processing highly specialized or complex document types - You need custom classification models beyond what foundation models can provide - You have domain-specific document types requiring specialized handling - You want to leverage fine-tuned models for specific document domains

public readonly stateMachine: IStateMachine;

Type: aws-cdk-lib.aws_stepfunctions.IStateMachine

The Step Functions state machine that orchestrates the document processing workflow.

Manages the sequence of processing steps and handles error conditions. This state machine is triggered for each document that needs processing and coordinates the entire extraction pipeline.

`evaluationFunction`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

SageMaker UDOP Processor uses specialized document processing with SageMaker endpoints for document classification, combined with foundation models for extraction. This processor is ideal for specialized document types that require custom classification models like RVL-CDIP or UDOP for accurate document categorization before extraction.

Use SageMaker UDOP Processor when: - Processing highly specialized or complex document types - You need custom classification models beyond what foundation models can provide - You have domain-specific document types requiring specialized handling - You want to leverage fine-tuned models for specific document domains

public readonly evaluationFunction: any;

Type: any

The evaluation function if evaluation is enabled for this processor.

The evaluation function is created by the ProcessingEnvironment when evaluation baseline bucket and model are provided.

ISagemakerUdopProcessorConfiguration

Implemented By: SagemakerUdopProcessorConfiguration, ISagemakerUdopProcessorConfiguration

Interface for SageMaker UDOP document processor configuration.

Provides configuration management for specialized document processing with SageMaker.

Methods

Name	Description
`bind`	Binds the configuration to a processor instance.

`bind`

public bind(processor: ISagemakerUdopProcessor): ISagemakerUdopProcessorConfigurationDefinition

Binds the configuration to a processor instance.

This method applies the configuration to the processor.

`processor`^Required

Type: ISagemakerUdopProcessor

The SageMaker UDOP document processor to apply to.

ISagemakerUdopProcessorConfigurationDefinition

Extends: @cdklabs/genai-idp.IConfigurationDefinition
Implemented By: ISagemakerUdopProcessorConfigurationDefinition

Interface for SageMaker UDOP processor configuration definition.

Defines the structure and capabilities of configuration for SageMaker UDOP processing.

Properties

Name	Type	Description
`extractionModel`	`@aws-cdk/aws-bedrock-alpha.IBedrockInvokable`	The invokable model used for information extraction.
`assessmentModel`	`@aws-cdk/aws-bedrock-alpha.IBedrockInvokable`	Optional invokable model used for document assessment.
`customPromptGenerator`	`aws-cdk-lib.aws_lambda.IFunction`	Optional custom prompt generator Lambda function.
`evaluationModel`	`@aws-cdk/aws-bedrock-alpha.IBedrockInvokable`	Optional invokable model used for evaluating extraction results.
`summarizationModel`	`@aws-cdk/aws-bedrock-alpha.IBedrockInvokable`	Optional invokable model used for document summarization.

`extractionModel`^Required

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

public readonly extractionModel: IBedrockInvokable;

Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable

The invokable model used for information extraction.

Can be a Bedrock foundation model, Bedrock inference profile, or custom model. Extracts structured data from documents based on defined schemas, transforming unstructured content into structured information.

`assessmentModel`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

public readonly assessmentModel: IBedrockInvokable;

Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable

Optional invokable model used for document assessment.

Can be a Bedrock foundation model, Bedrock inference profile, or custom model.

`customPromptGenerator`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

public readonly customPromptGenerator: IFunction;

Type: aws-cdk-lib.aws_lambda.IFunction
Default: undefined

Optional custom prompt generator Lambda function.

When provided, this function will be invoked during extraction to customize prompts. This is either the function provided via configuration options, or imported from the ARN specified in the configuration file.

`evaluationModel`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

public readonly evaluationModel: IBedrockInvokable;

Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable

Optional invokable model used for evaluating extraction results.

Can be a Bedrock foundation model, Bedrock inference profile, or custom model. Used to assess the quality and accuracy of extracted information by comparing extraction results against expected values.

`summarizationModel`^Optional

Deprecated: This processor pattern is deprecated and will be removed in v0.5.0. Please migrate to Pattern 1 (BDA Processor) or Pattern 2 (Bedrock LLM Processor).

public readonly summarizationModel: IBedrockInvokable;

Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable

Optional invokable model used for document summarization.

Can be a Bedrock foundation model, Bedrock inference profile, or custom model. When provided, enables automatic generation of document summaries that capture key information from processed documents.

ISagemakerUdopProcessorConfigurationSchema

Implemented By: SagemakerUdopProcessorConfigurationSchema, ISagemakerUdopProcessorConfigurationSchema

Interface for SageMaker UDOP configuration schema.

Defines the structure and validation rules for SageMaker UDOP processor configuration.

Methods

Name	Description
`bind`	Binds the configuration schema to a processor instance.

`bind`

public bind(processor: SagemakerUdopProcessor): void

Binds the configuration schema to a processor instance.

This method applies the schema definition to the processor's configuration table.

`processor`^Required

Type: SagemakerUdopProcessor

The SageMaker UDOP document processor to apply the schema to.

@cdklabs/genai-idp-sagemaker-udop-processor

Constructs

BasicSagemakerClassifier

Initializers

scopeRequired

idRequired

propsRequired

Methods

toString

with

mixinsRequired

Static Functions

isConstruct

xRequired

Properties

nodeRequired

endpointRequired

SagemakerUdopProcessor

Initializers

scopeRequired

idRequired

propsRequired

Methods

~~toString~~

~~with~~

mixinsRequired

~~metricClassificationRequestsTotal~~

propsOptional

~~metricInputDocumentPages~~

propsOptional

~~metricInputDocuments~~

propsOptional

Static Functions

~~isConstruct~~

xRequired

Properties

~~node~~Required

~~environment~~Required

~~maxProcessingConcurrency~~Required

~~stateMachine~~Required

Structs

BasicSagemakerClassifierProps

Initializer

Properties

instanceTypeRequired

modelDataRequired

outputBucketRequired

keyOptional

maxInstanceCountOptional

minInstanceCountOptional

scaleInCooldownOptional

scaleOutCooldownOptional

targetInvocationsPerInstancePerMinuteOptional

SagemakerUdopProcessorConfigurationDefinitionOptions

Initializer

Properties

assessmentModelOptional

customPromptGeneratorFunctionOptional

evaluationModelOptional

extractionModelOptional

summarizationModelOptional

SagemakerUdopProcessorProps

Initializer

Properties

~~environment~~Required

~~maxProcessingConcurrency~~Optional

~~classifierEndpoint~~Required

~~configuration~~Required

~~assessmentGuardrail~~Optional

~~classificationGuardrail~~Optional

~~enableEditSections~~Optional

~~evaluationBaselineBucket~~Optional

~~evaluationEnabled~~Optional

~~extractionGuardrail~~Optional

~~ocrMaxWorkers~~Optional

~~sectionSplittingStrategy~~Optional

~~summarizationGuardrail~~Optional

Classes

SagemakerUdopProcessorConfiguration

Initializers

`scope`^Required

`id`^Required

`props`^Required

`toString`

`with`

`mixins`^Required

`isConstruct`

`x`^Required

`node`^Required

`endpoint`^Required

`scope`^Required

`id`^Required

`props`^Required

`toString`

`with`

`mixins`^Required

`metricClassificationRequestsTotal`

`props`^Optional

`metricInputDocumentPages`

`props`^Optional

`metricInputDocuments`

`props`^Optional

`isConstruct`

`x`^Required

`node`^Required

`environment`^Required

`maxProcessingConcurrency`^Required

`stateMachine`^Required

`instanceType`^Required

`modelData`^Required

`outputBucket`^Required

`key`^Optional

`maxInstanceCount`^Optional

`minInstanceCount`^Optional

`scaleInCooldown`^Optional

`scaleOutCooldown`^Optional

`targetInvocationsPerInstancePerMinute`^Optional

`assessmentModel`^Optional

`customPromptGeneratorFunction`^Optional

`evaluationModel`^Optional

`extractionModel`^Optional

`summarizationModel`^Optional

`environment`^Required

`maxProcessingConcurrency`^Optional

`classifierEndpoint`^Required

`configuration`^Required

`assessmentGuardrail`^Optional

`classificationGuardrail`^Optional

`enableEditSections`^Optional

`evaluationBaselineBucket`^Optional

`evaluationEnabled`^Optional

`extractionGuardrail`^Optional

`ocrMaxWorkers`^Optional

`sectionSplittingStrategy`^Optional

`summarizationGuardrail`^Optional

`definition`^Required

`bind`

`processor`^Required

`fromFile`

`filePath`^Required

`options`^Optional

`rvlCdipPackageSample`

`options`^Optional

`fromFile`

`filePath`^Required

`options`^Optional

`rvlCdipPackageSample`

`options`^Optional

`bind`

`processor`^Required

`node`^Required

`environment`^Required

`maxProcessingConcurrency`^Required

`stateMachine`^Required

`evaluationFunction`^Optional

`bind`

`processor`^Required

`extractionModel`^Required

`assessmentModel`^Optional

`customPromptGenerator`^Optional