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

Amazon Bedrock Runtime is a fully managed service that makes it easy to use foundation models from third-party providers and Amazon.

• 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.

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

⚠ You must request access to a model before you can use it. If you try to use the model (with the API or console) before you have requested access to it, you will receive an error message. For more information, see Model access.

• Hello Amazon Bedrock Runtime (InvokeModel)

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

• Create and invoke a managed prompt
• Tool use with the Converse API

• Converse
• InvokeModel

• Converse
• ConverseStream
• Document understanding

• InvokeModel

• Text-to-video

• InvokeModel

• Converse
• ConverseStream
• InvokeModel
• InvokeModelWithResponseStream

• InvokeModel

• Converse
• ConverseStream
• Document understanding
• InvokeModel
• InvokeModelWithResponseStream
• Scenario: Tool use with the Converse API

• Converse
• ConverseStream
• Document understanding
• InvokeModel: Command R and R+
• InvokeModel: Command and Command Light
• InvokeModelWithResponseStream: Command R and R+
• InvokeModelWithResponseStream: Command and Command Light
• Scenario: Tool use with the Converse API

• Document understanding

• Converse
• ConverseStream
• Document understanding
• InvokeModel
• InvokeModelWithResponseStream

• Converse
• ConverseStream
• Document understanding
• InvokeModel
• InvokeModelWithResponseStream

• InvokeModel

The examples are wrapped into two separate scripts, with claude_3.py demonstrating the use of Claude 3, and bedrock_runtime_wrapper.py demonstrating Claude 2, Titan, Stable Diffusion, Jurassic-2, Llama 2, and both models from Mistral AI.

• To run the demo for Anthropic Claude 3, navigate to the python/example/code/bedrock-runtime directory and type:

  python models/anthropic/claude_3.py
  

• To run the demo for the other models, navigate to the python/example/code/bedrock-runtime directory and type:

  python bedrock_runtime_wrapper.py
  

This example shows you how to get started using Amazon Bedrock Runtime.

python hello/hello_bedrock_runtime_invoke.py

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 ../bedrock-agent/prompts/scenario_get_started_with_prompts.py

This example shows you how to build a typical interaction between an application, a generative AI model, and connected tools or APIs to mediate interactions between the AI and the outside world. It uses the example of connecting an external weather API to the AI model so it can provide real-time weather information based on user input.

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

python cross-model-scenarios/tool_use_demo/tool_use_demo.py

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

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

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

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

SPDX-License-Identifier: Apache-2.0