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 3.8 or higher.

Build Instructions

This repository includes examples for OpenAI, Bedrock, and LangChain for multi-provider support. Depending on your preferred provider, you may have to take some additional steps.

General setup

1. Set the environment variable LAUNCHDARKLY_SDK_KEY to your LaunchDarkly SDK key. If there is an existing an AI Config in your LaunchDarkly project that you want to evaluate, set LAUNCHDARKLY_AI_CONFIG_KEY to the flag key; otherwise, an AI Config of sample-ai-config will be assumed.

   export LAUNCHDARKLY_SDK_KEY="1234567890abcdef"
   export LAUNCHDARKLY_AI_CONFIG_KEY="sample-ai-config"

2. Ensure you have Poetry installed.

Provider-Specific Setup

OpenAI setup

1. Install the required dependencies with poetry install -E openai or poetry install --all-extras.
2. Set the environment variable OPENAI_API_KEY to your OpenAI key.
3. On the command line, run poetry run openai-example.

Bedrock setup

1. Install the required dependencies with poetry install -E bedrock or poetry install --all-extras.
2. Ensure the required AWS credentials can be auto-detected by the boto3 library. Examples might include environment variables, role providers, or shared credential files.
3. On the command line, run poetry run bedrock-example.

LangChain Multi-Provider setup

This example uses OpenAI, Bedrock, and Gemini LangChain provider packages. You can add additional LangChain providers using the poetry add command.

1. Install all dependencies with poetry install -E langchain or poetry install --all-extras.
2. Set up API keys for the providers you want to use
3. On the command line, run poetry run langchain-example