Amazon Bedrock Agents code examples for the SDK for Python

Overview

Shows how to use the AWS SDK for Python (Boto3) to work with Amazon Bedrock Agents.

Amazon Bedrock Agents offer you the ability to build and configure autonomous agents in your application.

⚠ Important

• Running this code might result in charges to your AWS account. For more details, see AWS Pricing and Free Tier.
• Running the tests might result in charges to your AWS account.
• We recommend that you grant your code least privilege. At most, grant only the minimum permissions required to perform the task. For more information, see Grant least privilege.
• This code is not tested in every AWS Region. For more information, see AWS Regional Services.

Code examples

Prerequisites

For prerequisites, see the README in the python folder.

Install the packages required by these examples by running the following in a virtual environment:

python -m pip install -r requirements.txt

Single actions

Code excerpts that show you how to call individual service functions.

• CreateAgent
• CreateAgentActionGroup
• CreateAgentAlias
• CreateFlow
• CreateFlowAlias
• CreateFlowVersion
• CreateKnowledgeBase
• CreatePrompt
• CreatePromptVersion
• DeleteAgent
• DeleteAgentAlias
• DeleteFlow
• DeleteFlowAlias
• DeleteFlowVersion
• DeleteKnowledgeBase
• DeletePrompt
• GetAgent
• GetFlow
• GetFlowVersion
• GetKnowledgeBase
• GetPrompt
• ListAgentActionGroups
• ListAgentKnowledgeBases
• ListAgents
• ListFlowAliases
• ListFlowVersions
• ListFlows
• ListKnowledgeBases
• ListPrompts
• PrepareAgent
• PrepareFlow
• UpdateFlow
• UpdateFlowAlias
• UpdateKnowledgeBase

Scenarios

Code examples that show you how to accomplish a specific task by calling multiple functions within the same service.

• Create and invoke a flow
• Create and invoke a managed prompt
• Create and invoke an agent

Run the examples

Instructions

Create and invoke a flow

This example shows you how to do the following:

• Create an execution role for the flow.
• Create the flow.
• Deploy the fully configured flow.
• Invoke the flow with user-provided prompts.
• Delete all created resources.

The flow includes a prompt node that generates a playlist for a chosen genre and number of songs. The example creates the nodes and permissions for the flow.

Start the example by running the following at a command prompt:

python flows/playlist_flow.py

Create and invoke a managed prompt

This example shows you how to do the following:

• Create a managed prompt.
• Create a version of the prompt.
• Invoke the prompt using the version.
• Clean up resources (optional).

Start the example by running the following at a command prompt:

python prompts/scenario_get_started_with_prompts.py

Create and invoke an agent

This example shows you how to do the following:

• Create an execution role for the agent.
• Create the agent and deploy a DRAFT version.
• Create a Lambda function that implements the agent's capabilities.
• Create an action group that connects the agent to the Lambda function.
• Deploy the fully configured agent.
• Invoke the agent with user-provided prompts.
• Delete all created resources.

Start the example by running the following at a command prompt:

python scenario_get_started_with_agents.py

Tests

⚠ Running tests might result in charges to your AWS account.

To find instructions for running these tests, see the README in the python folder.

Additional resources

• Amazon Bedrock Agents User Guide
• Amazon Bedrock Agents API Reference
• SDK for Python Amazon Bedrock Agents reference

Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.

SPDX-License-Identifier: Apache-2.0