Optional ReadonlydisplayWhether to display inline citations in responses
Optional ReadonlyguardrailBedrock Guardrail ID for content filtering
Optional ReadonlyguardrailKMS key ARN for Guardrail encryption
Optional ReadonlyguardrailGuardrail version to use
Optional ReadonlyinferenceMaximum tokens for inference
Optional ReadonlyinferenceTemperature for inference (0.0-1.0)
Optional ReadonlyinferenceTop-p for inference (0.0-1.0)
Optional ReadonlykbNumber of results to retrieve from knowledge base
Optional ReadonlylambdaLambda architecture (ARM64 or x86_64). If undefined, Architecture.X86_64 is used
Optional ReadonlylambdaMemory allocation for the Lambda function in MB. If undefined, 1024MB is used.
ReadonlylambdaIAM role reference for Lambda execution
Optional ReadonlylambdaTimeout for the Lambda function in seconds. If unspecified, 10 minutes is used (600 seconds)
ReadonlymodelBedrock model ID for generation (e.g., 'anthropic.claude-3-sonnet-20240229-v1:0')
Optional ReadonlyorchestrationMaximum tokens for orchestration inference
Optional ReadonlyorchestrationStop sequences for orchestration inference
Optional ReadonlyorchestrationTemperature for orchestration inference
Optional ReadonlyorchestrationTop-p for orchestration inference
Optional ReadonlyorchestrationPerformance vs latency trade-off setting. (e.g. : standard | optimized)
Optional ReadonlyorchestrationCustom orchestration prompt template
Optional ReadonlyorchestrationQuery transformation type for orchestration. (e.g. : QUERY_DECOMPOSITION)
Optional ReadonlypromptCustom prompt template for generation
Optional ReadonlyprovisionedProvisioned concurrent executions for Lambda
Optional ReadonlypythonPython runtime version. If undefined, Runtime.PYTHON_3_13 is used.
Optional ReadonlyreservedReserved concurrent executions for Lambda
RAG data source using Bedrock Knowledge Base for document-based question answering with citation support. Configures the foundation model used to generate answers, the Lambda role that executes the namespace handler, and retrieval-time parameters such as the number of knowledge base results and the prompt and orchestration templates.