managed_agent

Managed Agent Example

This example demonstrates how to use LaunchDarkly's managed agent functionality, which handles model creation, metric tracking, and judge evaluation dispatch automatically.

Prerequisites

• Python 3.10 or higher
• Poetry installed
• A LaunchDarkly account and SDK key
• API keys for the provider you want to use (OpenAI, Bedrock, or Gemini)

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 Agent Config with a model and agent instructions. Default key: sample-agent-config.

2. Create a .env file in this directory with the following variables:

   LAUNCHDARKLY_SDK_KEY=your-launchdarkly-sdk-key
   LAUNCHDARKLY_AGENT_CONFIG_KEY=sample-agent-config
   OPENAI_API_KEY=your-openai-api-key
   

3. Install the required dependencies:

   poetry install

Run

poetry run agent