Skip to content

@cdklabs/genai-idp-bedrock-llm-processor

Constructs

BedrockLlmProcessor

Bedrock LLM document processor facade over UnifiedDocumentProcessor.

Delegates all processing to the unified processor using the pipeline path (non-BDA). Uses Amazon Bedrock foundation models for OCR, classification, extraction, assessment, summarization, and evaluation.

Initializers 

import { BedrockLlmProcessor } from '@cdklabs/genai-idp-bedrock-llm-processor'

new BedrockLlmProcessor(scope: Construct, id: string, props: BedrockLlmProcessorProps)
Name Type Description
scope constructs.Construct No description.
id string No description.
props BedrockLlmProcessorProps No description.
scopeRequired
  • Type: constructs.Construct
idRequired
  • Type: string
propsRequired

Methods

Name Description
toString Returns a string representation of this construct.
with Applies one or more mixins to this construct.
metricBedrockMaxRetriesExceeded Bedrock requests that exceeded max retries.
metricBedrockNonRetryableErrors Bedrock non-retryable errors.
metricBedrockRequestLatency Bedrock single-request latency in milliseconds.
metricBedrockRequestsFailed Failed Bedrock model invocation requests.
metricBedrockRequestsSucceeded Successful Bedrock model invocation requests.
metricBedrockRequestsTotal Total Bedrock model invocation requests.
metricBedrockRetrySuccess Bedrock requests that succeeded after retry.
metricBedrockThrottles Bedrock request throttles.
metricBedrockTotalLatency Bedrock total latency including retries in milliseconds.
metricBedrockUnexpectedErrors Bedrock unexpected errors.
metricInputDocumentPages Document pages submitted for extraction.
metricInputDocuments Documents submitted for extraction.
metricInputTokens Input tokens consumed.
metricLambdaHookRequestsFailed Failed LambdaHook invocation requests.
metricLambdaHookRequestsSucceeded Successful LambdaHook invocation requests.
metricLambdaHookRequestsTotal Total LambdaHook invocation requests.
metricOutputTokens Output tokens generated.
metricTotalTokens Total tokens used.
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.

mixinsRequired
  • Type: ...constructs.IMixin[]

The mixins to apply.

metricBedrockMaxRetriesExceeded 
public metricBedrockMaxRetriesExceeded(props?: MetricOptions): Metric

Bedrock requests that exceeded max retries.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockNonRetryableErrors 
public metricBedrockNonRetryableErrors(props?: MetricOptions): Metric

Bedrock non-retryable errors.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockRequestLatency 
public metricBedrockRequestLatency(props?: MetricOptions): Metric

Bedrock single-request latency in milliseconds.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockRequestsFailed 
public metricBedrockRequestsFailed(props?: MetricOptions): Metric

Failed Bedrock model invocation requests.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockRequestsSucceeded 
public metricBedrockRequestsSucceeded(props?: MetricOptions): Metric

Successful Bedrock model invocation requests.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockRequestsTotal 
public metricBedrockRequestsTotal(props?: MetricOptions): Metric

Total Bedrock model invocation requests.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockRetrySuccess 
public metricBedrockRetrySuccess(props?: MetricOptions): Metric

Bedrock requests that succeeded after retry.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockThrottles 
public metricBedrockThrottles(props?: MetricOptions): Metric

Bedrock request throttles.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockTotalLatency 
public metricBedrockTotalLatency(props?: MetricOptions): Metric

Bedrock total latency including retries in milliseconds.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricBedrockUnexpectedErrors 
public metricBedrockUnexpectedErrors(props?: MetricOptions): Metric

Bedrock unexpected errors.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricInputDocumentPages 
public metricInputDocumentPages(props?: MetricOptions): Metric

Document pages submitted for extraction.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricInputDocuments 
public metricInputDocuments(props?: MetricOptions): Metric

Documents submitted for extraction.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricInputTokens 
public metricInputTokens(props?: MetricOptions): Metric

Input tokens consumed.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricLambdaHookRequestsFailed 
public metricLambdaHookRequestsFailed(props?: MetricOptions): Metric

Failed LambdaHook invocation requests.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricLambdaHookRequestsSucceeded 
public metricLambdaHookRequestsSucceeded(props?: MetricOptions): Metric

Successful LambdaHook invocation requests.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricLambdaHookRequestsTotal 
public metricLambdaHookRequestsTotal(props?: MetricOptions): Metric

Total LambdaHook invocation requests.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricOutputTokens 
public metricOutputTokens(props?: MetricOptions): Metric

Output tokens generated.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions
metricTotalTokens 
public metricTotalTokens(props?: MetricOptions): Metric

Total tokens used.

propsOptional
  • Type: aws-cdk-lib.aws_cloudwatch.MetricOptions

Static Functions

Name Description
isConstruct Checks if x is a construct.
isConstruct 
import { BedrockLlmProcessor } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessor.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.

xRequired
  • 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 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 @cdklabs/genai-idp.EvaluationFunction The evaluation function if evaluation is enabled for this processor.
nodeRequired 
public readonly node: Node;
  • Type: constructs.Node

The tree node.

environmentRequired 
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.

maxProcessingConcurrencyRequired 
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.

stateMachineRequired 
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.

evaluationFunctionOptional 
public readonly evaluationFunction: EvaluationFunction;
  • Type: @cdklabs/genai-idp.EvaluationFunction

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.

Structs

BedrockLlmProcessorConfigurationDefinitionOptions

Options for configuring the Bedrock LLM processor configuration definition.

Allows customization of all processing stages via Invokable providers.

Initializer 

import { BedrockLlmProcessorConfigurationDefinitionOptions } from '@cdklabs/genai-idp-bedrock-llm-processor'

const bedrockLlmProcessorConfigurationDefinitionOptions: BedrockLlmProcessorConfigurationDefinitionOptions = { ... }

Properties

Name Type Description
assessmentInvokable @cdklabs/genai-idp.Invokable Optional inference provider for the assessment stage.
classificationInvokable @cdklabs/genai-idp.Invokable Optional inference provider for the classification stage.
classificationMethod ClassificationMethod Optional classification method for document categorization.
customPromptGeneratorFunction aws-cdk-lib.aws_lambda.IFunction Optional custom prompt generator Lambda function.
evaluationModel @aws-cdk/aws-bedrock-alpha.IBedrockInvokable Optional model for the evaluation stage (Bedrock only, no LambdaHook).
extractionInvokable @cdklabs/genai-idp.Invokable Optional inference provider for the extraction stage.
ocrInvokable @cdklabs/genai-idp.Invokable Optional inference provider for the OCR stage.
summarizationInvokable @cdklabs/genai-idp.Invokable Optional inference provider for the summarization stage.
assessmentInvokableOptional 
public readonly assessmentInvokable: Invokable;
  • Type: @cdklabs/genai-idp.Invokable

Optional inference provider for the assessment stage.

classificationInvokableOptional 
public readonly classificationInvokable: Invokable;
  • Type: @cdklabs/genai-idp.Invokable

Optional inference provider for the classification stage.

classificationMethodOptional 
public readonly classificationMethod: ClassificationMethod;

Optional classification method for document categorization.

customPromptGeneratorFunctionOptional 
public readonly customPromptGeneratorFunction: IFunction;
  • Type: aws-cdk-lib.aws_lambda.IFunction

Optional custom prompt generator Lambda function.

evaluationModelOptional 
public readonly evaluationModel: IBedrockInvokable;
  • Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable

Optional model for the evaluation stage (Bedrock only, no LambdaHook).

extractionInvokableOptional 
public readonly extractionInvokable: Invokable;
  • Type: @cdklabs/genai-idp.Invokable

Optional inference provider for the extraction stage.

ocrInvokableOptional 
public readonly ocrInvokable: Invokable;
  • Type: @cdklabs/genai-idp.Invokable

Optional inference provider for the OCR stage.

summarizationInvokableOptional 
public readonly summarizationInvokable: Invokable;
  • Type: @cdklabs/genai-idp.Invokable

Optional inference provider for the summarization stage.

BedrockLlmProcessorProps

Configuration properties for the Bedrock LLM document processor facade.

Initializer 

import { BedrockLlmProcessorProps } from '@cdklabs/genai-idp-bedrock-llm-processor'

const bedrockLlmProcessorProps: BedrockLlmProcessorProps = { ... }

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.
configuration IBedrockLlmProcessorConfiguration Configuration for the Bedrock LLM document processor.
configurationBucket aws-cdk-lib.aws_s3.IBucket The S3 bucket containing configuration files.
environmentRequired 
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.

maxProcessingConcurrencyOptional 
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.

configurationRequired 
public readonly configuration: IBedrockLlmProcessorConfiguration;

Configuration for the Bedrock LLM document processor.

configurationBucketRequired 
public readonly configurationBucket: IBucket;
  • Type: aws-cdk-lib.aws_s3.IBucket

The S3 bucket containing configuration files.

Classes

BedrockLlmProcessorConfiguration

Configuration management for Bedrock LLM document processing.

Provides factory methods for preset configurations and custom YAML files. Delegates to UnifiedDocumentProcessorConfigurationDefinition for loading configs from the unified config library.

Initializers 

import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

new BedrockLlmProcessorConfiguration(definition: IBedrockLlmProcessorConfigurationDefinition)
Name Type Description
definition IBedrockLlmProcessorConfigurationDefinition The configuration definition.
definitionRequired

The configuration definition.

Methods

Name Description
bind Binds the configuration to a processor scope.
bind 
public bind(scope: Construct, environment: IProcessingEnvironment): IBedrockLlmProcessorConfigurationDefinition

Binds the configuration to a processor scope.

Writes the default configuration to the configuration table.

scopeRequired
  • Type: constructs.Construct
environmentRequired
  • Type: @cdklabs/genai-idp.IProcessingEnvironment

Static Functions

Name Description
bankStatementSample No description.
docSplit No description.
fromFile No description.
healthcareMultisectionPackage No description.
lendingPackageSample No description.
lendingPackageSampleGovCloud No description.
ocrBenchmark No description.
realkieFccVerified No description.
ruleExtraction No description.
ruleValidation No description.
rvlCdip No description.
rvlCdipWithFewShotExamples No description.
bankStatementSample 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.bankStatementSample(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
docSplit 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.docSplit(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
fromFile 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.fromFile(filePath: string, options?: BedrockLlmProcessorConfigurationDefinitionOptions)
filePathRequired
  • Type: string
optionsOptional
healthcareMultisectionPackage 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.healthcareMultisectionPackage(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
lendingPackageSample 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.lendingPackageSample(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
lendingPackageSampleGovCloud 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.lendingPackageSampleGovCloud(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
ocrBenchmark 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.ocrBenchmark(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
realkieFccVerified 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.realkieFccVerified(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
ruleExtraction 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.ruleExtraction(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
ruleValidation 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.ruleValidation(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
rvlCdip 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.rvlCdip(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
rvlCdipWithFewShotExamples 
import { BedrockLlmProcessorConfiguration } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfiguration.rvlCdipWithFewShotExamples(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional

Properties

Name Type Description
definition IBedrockLlmProcessorConfigurationDefinition The configuration definition.
definitionRequired 
public readonly definition: IBedrockLlmProcessorConfigurationDefinition;

The configuration definition.

BedrockLlmProcessorConfigurationDefinition

Configuration definition for Bedrock LLM document processing.

Delegates to UnifiedDocumentProcessorConfigurationDefinition for loading configs from the unified config library. Maps bedrock-llm-specific options to unified options.

Initializers 

import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

new BedrockLlmProcessorConfigurationDefinition()
Name Type Description

Static Functions

Name Description
bankStatementSample No description.
docSplit No description.
fromFile No description.
healthcareMultisectionPackage No description.
lendingPackageSample No description.
lendingPackageSampleGovCloud No description.
ocrBenchmark No description.
realkieFccVerified No description.
ruleExtraction No description.
ruleValidation No description.
rvlCdip No description.
rvlCdipWithFewShotExamples No description.
bankStatementSample 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.bankStatementSample(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
docSplit 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.docSplit(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
fromFile 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.fromFile(filePath: string, options?: BedrockLlmProcessorConfigurationDefinitionOptions)
filePathRequired
  • Type: string
optionsOptional
healthcareMultisectionPackage 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.healthcareMultisectionPackage(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
lendingPackageSample 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.lendingPackageSample(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
lendingPackageSampleGovCloud 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.lendingPackageSampleGovCloud(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
ocrBenchmark 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.ocrBenchmark(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
realkieFccVerified 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.realkieFccVerified(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
ruleExtraction 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.ruleExtraction(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
ruleValidation 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.ruleValidation(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
rvlCdip 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.rvlCdip(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional
rvlCdipWithFewShotExamples 
import { BedrockLlmProcessorConfigurationDefinition } from '@cdklabs/genai-idp-bedrock-llm-processor'

BedrockLlmProcessorConfigurationDefinition.rvlCdipWithFewShotExamples(options?: BedrockLlmProcessorConfigurationDefinitionOptions)
optionsOptional

Invokable

  • Implements: @cdklabs/genai-idp.IInvokable

Unified wrapper for Bedrock models and Lambda functions that implements IInvokable.

Use the static factory methods to create instances:

Example

// From a Bedrock model
const provider = Invokable.fromModel(model);

// From a Lambda function (LambdaHook)
const provider = Invokable.fromFunction(fn);@since[object Object]

Methods

Name Description
grantInvoke Grant the given identity permissions to invoke this resource.
grantInvoke 
public grantInvoke(grantee: IGrantable): Grant

Grant the given identity permissions to invoke this resource.

granteeRequired
  • Type: aws-cdk-lib.aws_iam.IGrantable

Static Functions

Name Description
fromFunction Create an Invokable from a Lambda function (LambdaHook pattern).
fromModel Create an Invokable from a Bedrock model or inference profile.
fromFunction 
import { Invokable } from '@cdklabs/genai-idp-bedrock-llm-processor'

Invokable.fromFunction(fn: IFunction)

Create an Invokable from a Lambda function (LambdaHook pattern).

fnRequired
  • Type: aws-cdk-lib.aws_lambda.IFunction

The Lambda function that implements the Converse API-compatible contract.

fromModel 
import { Invokable } from '@cdklabs/genai-idp-bedrock-llm-processor'

Invokable.fromModel(model: IBedrockInvokable)

Create an Invokable from a Bedrock model or inference profile.

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

The Bedrock invokable model.

Protocols

IBedrockLlmProcessor

Interface for Bedrock LLM 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 @cdklabs/genai-idp.EvaluationFunction The evaluation function if evaluation is enabled for this processor.
nodeRequired 
public readonly node: Node;
  • Type: constructs.Node

The tree node.

environmentRequired 
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.

maxProcessingConcurrencyRequired 
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.

stateMachineRequired 
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.

evaluationFunctionOptional 
public readonly evaluationFunction: EvaluationFunction;
  • Type: @cdklabs/genai-idp.EvaluationFunction

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.

IBedrockLlmProcessorConfiguration

Interface for Bedrock LLM document processor configuration.

Methods

Name Description
bind Binds the configuration to a processor scope.
bind 
public bind(scope: Construct, environment: IProcessingEnvironment): IBedrockLlmProcessorConfigurationDefinition

Binds the configuration to a processor scope.

Writes the default configuration to the configuration table.

scopeRequired
  • Type: constructs.Construct

The construct scope for creating custom resources.

environmentRequired
  • Type: @cdklabs/genai-idp.IProcessingEnvironment

The processing environment providing the configuration function and table.

Properties

Name Type Description
definition IBedrockLlmProcessorConfigurationDefinition The configuration definition.
definitionRequired 
public readonly definition: IBedrockLlmProcessorConfigurationDefinition;

The configuration definition.

IBedrockLlmProcessorConfigurationDefinition

Interface for Bedrock LLM processor configuration definition.

Exposes resolved inference providers for each processing stage.

Properties

Name Type Description
classificationMethod ClassificationMethod No description.
ocrBackend string No description.
assessmentInferenceProvider @cdklabs/genai-idp.IInvokable No description.
classificationInferenceProvider @cdklabs/genai-idp.IInvokable No description.
customPromptGenerator aws-cdk-lib.aws_lambda.IFunction No description.
evaluationModel @aws-cdk/aws-bedrock-alpha.IBedrockInvokable No description.
extractionInferenceProvider @cdklabs/genai-idp.IInvokable No description.
ocrInferenceProvider @cdklabs/genai-idp.IInvokable No description.
summarizationInferenceProvider @cdklabs/genai-idp.IInvokable No description.
classificationMethodRequired 
public readonly classificationMethod: ClassificationMethod;
ocrBackendRequired 
public readonly ocrBackend: string;
  • Type: string
assessmentInferenceProviderOptional 
public readonly assessmentInferenceProvider: IInvokable;
  • Type: @cdklabs/genai-idp.IInvokable
classificationInferenceProviderOptional 
public readonly classificationInferenceProvider: IInvokable;
  • Type: @cdklabs/genai-idp.IInvokable
customPromptGeneratorOptional 
public readonly customPromptGenerator: IFunction;
  • Type: aws-cdk-lib.aws_lambda.IFunction
evaluationModelOptional 
public readonly evaluationModel: IBedrockInvokable;
  • Type: @aws-cdk/aws-bedrock-alpha.IBedrockInvokable
extractionInferenceProviderOptional 
public readonly extractionInferenceProvider: IInvokable;
  • Type: @cdklabs/genai-idp.IInvokable
ocrInferenceProviderOptional 
public readonly ocrInferenceProvider: IInvokable;
  • Type: @cdklabs/genai-idp.IInvokable
summarizationInferenceProviderOptional 
public readonly summarizationInferenceProvider: IInvokable;
  • Type: @cdklabs/genai-idp.IInvokable

IInvokable

Unified interface for any resource that can serve as an inference backend.

Abstracts over Bedrock models and Lambda functions so that processing stage constructs can grant invoke permissions without knowing the underlying type.

Methods

Name Description
grantInvoke Grant the given identity permissions to invoke this resource.
grantInvoke 
public grantInvoke(grantee: IGrantable): Grant

Grant the given identity permissions to invoke this resource.

granteeRequired
  • Type: aws-cdk-lib.aws_iam.IGrantable

The principal to grant invoke permissions to.

Enums

ClassificationMethod

Defines the methods available for document classification in Pattern 2 processing.

Document classification is a critical step in the IDP workflow that determines how documents are categorized and processed. Different classification methods offer varying levels of accuracy, performance, and capabilities.

Members

Name Description
MULTIMODAL_PAGE_LEVEL_CLASSIFICATION Uses multimodal models to classify documents at the page level.
TEXTBASED_HOLISTIC_CLASSIFICATION Uses text-based analysis to classify the entire document holistically. Considers the full document text content for classification decisions.
MULTIMODAL_PAGE_LEVEL_CLASSIFICATION

Uses multimodal models to classify documents at the page level.

Analyzes both text and visual elements on each page for classification.

This method is effective for documents where each page may belong to a different document type or category. It provides high accuracy for complex layouts by considering both textual content and visual structure of each page individually.

TEXTBASED_HOLISTIC_CLASSIFICATION

Uses text-based analysis to classify the entire document holistically. Considers the full document text content for classification decisions.

This method is more efficient and cost-effective as it only processes the extracted text. It works well for text-heavy documents where the document type is consistent across all pages and visual elements are less important for classification.

InvokableType

The type of inference backend wrapped by an Invokable.

Members

Name Description
MODEL A Bedrock foundation model or inference profile.
FUNCTION A Lambda function implementing the LambdaHook contract.
MODEL

A Bedrock foundation model or inference profile.

FUNCTION

A Lambda function implementing the LambdaHook contract.