Start Flow Execution

bedrockagentruntime_start_flow_execution

R Documentation

Starts an execution of an Amazon Bedrock flow

Description

Starts an execution of an Amazon Bedrock flow. Unlike flows that run until completion or time out after five minutes, flow executions let you run flows asynchronously for longer durations. Flow executions also yield control so that your application can perform other tasks.

This operation returns an Amazon Resource Name (ARN) that you can use to track and manage your flow execution.

Flow executions is in preview release for Amazon Bedrock and is subject to change.

Usage

bedrockagentruntime_start_flow_execution(flowAliasIdentifier,
  flowExecutionName, flowIdentifier, inputs,
  modelPerformanceConfiguration)

Arguments

flowAliasIdentifier	[required] The unique identifier of the flow alias to use for the flow execution.
flowExecutionName	The unique name for the flow execution. If you don't provide one, a system-generated name is used.
flowIdentifier	[required] The unique identifier of the flow to execute.
inputs	[required] The input data required for the flow execution. This must match the input schema defined in the flow.
modelPerformanceConfiguration	The performance settings for the foundation model used in the flow execution.

Value

A list with the following syntax:

list(
  executionArn = "string"
)

Request syntax

svc$start_flow_execution(
  flowAliasIdentifier = "string",
  flowExecutionName = "string",
  flowIdentifier = "string",
  inputs = list(
    list(
      content = list(
        document = list()
      ),
      nodeInputName = "string",
      nodeName = "string",
      nodeOutputName = "string"
    )
  ),
  modelPerformanceConfiguration = list(
    performanceConfig = list(
      latency = "standard"|"optimized"
    )
  )
)