BedrockProcessing

Bedrock processing step that processes input data through AWS Bedrock models using generated prompt templates and validation schemas

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

Compute

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

Functionality

Bedrock processing script with invoke_model, structured output, and Converse API modes. Supports self-contained mode via env var templates. Circuit breaker and adaptive rate limiting.

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	no	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

• EdxUploading

• LabelRulesetExecution

• LightGBMMTModelEval

• LightGBMMTModelInference

• LightGBMTraining

• PseudoLabelMerge

• PyTorchModelEval

• PyTorchModelInference

• PyTorchTraining

• TSATabularPreprocessing

• TabularPreprocessing

• XGBoostTraining

• 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