bedrockagentruntime_invoke_agent: Sends a prompt for the agent to process and respond to

In paws.machine.learning: 'Amazon Web Services' Machine Learning Services

Sends a prompt for the agent to process and respond to

Description

Sends a prompt for the agent to process and respond to. Note the following fields for the request:

See https://www.paws-r-sdk.com/docs/bedrockagentruntime_invoke_agent/ for full documentation.

Usage

bedrockagentruntime_invoke_agent(
  agentAliasId,
  agentId,
  bedrockModelConfigurations = NULL,
  enableTrace = NULL,
  endSession = NULL,
  inputText = NULL,
  memoryId = NULL,
  sessionId,
  sessionState = NULL,
  sourceArn = NULL,
  streamingConfigurations = NULL
)

Arguments

agentAliasId	[required] The alias of the agent to use.
agentId	[required] The unique identifier of the agent to use.
bedrockModelConfigurations	Model performance settings for the request.
enableTrace	Specifies whether to turn on the trace or not to track the agent's reasoning process. For more information, see Trace enablement.
endSession	Specifies whether to end the session with the agent or not.
inputText	The prompt text to send the agent. If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.
memoryId	The unique identifier of the agent memory.
sessionId	[required] The unique identifier of the session. Use the same value across requests to continue the same conversation.
sessionState	Contains parameters that specify various attributes of the session. For more information, see Control session context. If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.
sourceArn	The ARN of the resource making the request.
streamingConfigurations	Specifies the configurations for streaming. To use agent streaming, you need permissions to perform the bedrock:InvokeModelWithResponseStream action.

paws.machine.learning documentation built on April 3, 2025, 8:41 p.m.