BedrockBatchProcessing

Bedrock batch processing step that provides AWS Bedrock batch inference capabilities with automatic fallback to real-time processing for cost-efficient large dataset processing

SageMaker step type	Processing
Node type	internal (consumes upstream, produces downstream)
Container entry point	bedrock_batch_processing.py
Interface file	steps/interfaces/bedrock_batch_processing.step.yaml

Compute

Compute kind	framework
SDK class	PyTorch (SageMaker DLC via image_uris.retrieve)

Functionality

Bedrock batch processing script with batch inference and automatic fallback to real-time. Integrates with prompt templates and validation schemas from BedrockPromptTemplateGeneration.

Inputs (dependencies)

Input	Type	Required	Compatible producers
input_data	processing_output	yes	DummyDataLoading, CradleDataLoading, TabularPreprocessing, TemporalSequenceNormalization, TemporalFeatureEngineering, StratifiedSampling, MissingValueImputation, FeatureSelection, CurrencyConversion, SlipboxKnowledgeRouting
prompt_templates	processing_output	yes	BedrockPromptTemplateGeneration, SlipboxKnowledgeRouting

Outputs

Output	Type
processed_data	processing_output
analysis_summary	processing_output

Consumers (downstream steps)

Steps that declare this step as a compatible input source:

• ActiveSampleSelection

• LabelRulesetExecution

• LightGBMMTModelEval

• LightGBMMTModelInference

• PseudoLabelMerge

• XgboostMtModelEval

Framework requirements

Package	Version
pandas	>=1.2.0
boto3	>=1.26.0
pydantic	>=2.0.0
tenacity	>=8.0.0

---

← Back to the Step Catalog