converse

Bedrock Example (Single Provider)

This example demonstrates how to use LaunchDarkly's AI Config with the AWS Bedrock provider.

Prerequisites

• Python 3.10 or higher
• Poetry installed
• A LaunchDarkly account and SDK key
• AWS credentials configured for Bedrock access

Setup

1. Create the following config in your LaunchDarkly project. You can use a different key by setting the environment variable in your .env.

   • Create an AI Config with a Bedrock model and a system message. Default key: sample-completion.

2. Copy .env.example to .env and fill in your keys:

   cp .env.example .env

   LAUNCHDARKLY_COMPLETION_KEY defaults to sample-completion if not set.

   Ensure your AWS credentials can be auto-detected by the boto3 library. Setting them in .env is one option; role providers or shared credential files are also supported.

3. Install the required dependencies:

   poetry install

Run

poetry run bedrock