AWS Bedrock Agents

AWS Bedrock Agents allow you to make both Bedrock Agents and Bedrock AgentCore Agents available as a standard Dataiku Agent (represented by a pink diamond in the Dataiku Flow). Once configured, it can be leveraged anywhere a Dataiku Agent is supported, including:

  • The Dataiku Flow (notably Prompt Recipes)

  • Chat UIs such as Agent Hub

  • The LLM Mesh API

  • Prompt Studios

  • /agents/agent-review

  • /agent/agent-evaluation

Key Features

  • Real-time streaming of agent responses to provide an interactive user experience is supported

  • DSS automatically extracts and displays citations from Bedrock Knowledge Banks and information from Action Group (tool) invocations.

  • Authentication to AWS Bedrock is fully managed through the use of an existing S3 connection

Prerequisites

AWS Bedrock Agents support is provided by the “AWS Bedrock Agents” plugin, which you need to install

AWS Requirements

  • Bedrock Agent

    • An existing agent must be created and configured in the AWS Console.

    • You must have the Bedrock Agent ID and Alias ID (not to be confused with Agent Name and Alias Name. The ID are numeric)

    • The identity configured in the linked S3 connection must have the bedrock:InvokeAgent permission.

  • Bedrock AgentCore

    • An existing agent must be created and configured in the AWS Console.

    • You must have the Bedrock AgentCore runtime ARN, and optionally, qualifier

    • The identity configured in the linked S3 connection must have the bedrock:InvokeAgent permission.

Usage (Bedrock Agent)

  1. Navigate to your Dataiku project.

  2. Go to Agents & GenAI Models > + New Agent.

  3. Select Bedrock Agent.

  4. Select the AWS region and S3 connection to use for authentication

  5. Enter the specific identifiers for your Bedrock agent.

You can then use the built-in chat interface within the Agent configuration page to test your agent.

Usage (Bedrock AgentCore)

  1. Navigate to your Dataiku project.

  2. Go to Agents & GenAI Models > + New Agent.

  3. Select Bedrock Agent.

  4. Select the AWS region and S3 connection to use for authentication

  5. Enter the runtime ARN for your AgentCore agent

You can then use the built-in chat interface within the Agent configuration page to test your agent.

Cautions

  • In order to properly support multi-turn conversation, when using the LLM Mesh API, you need to pass a stable conversationId in the request context. Note that when using the built-in chat, or Agent Hub, this is autoamtically handled

  • Bedrock Agents using Action Groups that require user confirmation (returning control to the user) are not supported.

  • Only text-only interactions are supported. Image inputs are not supported