LaunchDarkly sample Python application

We've built a simple console application that demonstrates how LaunchDarkly's SDK works.

Below, you'll find the build procedure. For more comprehensive instructions, you can visit your Quickstart page or the Python reference guide.

This demo requires Python 3.10 or higher.

Build Instructions

This repository includes examples for OpenAI, Bedrock, Gemini, LangChain, LangGraph, Judge, and Observability. Depending on your preferred provider, you may have to take some additional steps.

General setup

1. Create an AI Config using the key specified in each example, or copy the key of existing AI Config in your LaunchDarkly project that you want to evaluate.

2. Ensure you have Poetry installed.

3. Create a .env file in the repository root with at least your LaunchDarkly SDK key:

   LAUNCHDARKLY_SDK_KEY=your-launchdarkly-sdk-key
   

   Each example README describes the full set of environment variables needed. The .env file is loaded automatically when running any example.

Examples

Example	Description	README
OpenAI	Single provider using OpenAI	examples/openai
Bedrock	Single provider using AWS Bedrock	examples/bedrock
Gemini	Single provider using Google Gemini	examples/gemini
LangChain	Multiple providers via LangChain	examples/langchain
LangGraph Agent	Single agent using LangGraph	examples/langgraph_agent
LangGraph Multi-Agent	Multiple agents using LangGraph	examples/langgraph_multi_agent
Judge	Judge evaluation of AI responses	examples/judge
Chat with Observability	Observability plugin for AI chat monitoring	examples/chat_observability