AWS sagemaker-unified-studio documentation change
Summary
Added 'Agent node' documentation with input/output details and updated section headers
Security assessment
The change adds documentation about a new Agent node feature but does not include security-specific content or address vulnerabilities.
Diff
diff --git a/sagemaker-unified-studio/latest/userguide/nodes.md b/sagemaker-unified-studio/latest/userguide/nodes.md index 2b0b25d3c..14a207922 100644 --- a//sagemaker-unified-studio/latest/userguide/nodes.md +++ b//sagemaker-unified-studio/latest/userguide/nodes.md @@ -5 +5 @@ -Input nodeOutput nodeCollector nodeCondition nodeIterator nodeIterator node outputsPrompt nodeKnowledge Base node +Input nodeOutput nodeCollector nodeCondition nodeIterator nodeIterator node outputsPrompt nodeKnowledge Base nodeAgent node @@ -47,0 +48,2 @@ Amazon Bedrock in SageMaker Unified Studio supports a subset of the nodes that a + * Agent node + @@ -224,0 +227,18 @@ You can assign a guardrail to a knowledge base node. When you create the knowled +## Agent node + +An agent node lets you send a prompt to an agent, which orchestrates between foundation models and associated resources to identify and carry out actions for an end-user. The inputs into the node are the prompt for the agent and any associated prompt or session attributes. For more information, see [Control agent session context](https://docs.aws.amazon.com/bedrock/latest/userguide/agents-session-state.html) in the _Amazon Bedrock user guide_. + +### Agent node inputs + +Name | Type | Expression +---|---|--- +agentInputText | String, Number, Boolean, Object, Array | string +promptAttributes | Object | string +sessionAttributes | Object | string + +### Agent node outputs + +Name | Type +---|--- +agentResponse | String + @@ -231 +251 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Use logic nodes to control flow +Use a chat agent app in a flow app