LaunchDarkly AI SDK OpenAI Provider for Server-Side JavaScript

[!CAUTION] This SDK is in pre-release and not subject to backwards compatibility guarantees. The API may change based on feedback.

Pin to a specific minor version and review the changelog before upgrading.

[!NOTE] This provider currently uses OpenAI's completion API. We plan to migrate to the responses API in a future release to take advantage of improved functionality and performance.

LaunchDarkly overview

LaunchDarkly is a feature management platform that serves over 100 billion feature flags daily to help teams build better software, faster. Get started using LaunchDarkly today!

Quick Setup

This package provides OpenAI integration for the LaunchDarkly AI SDK. The simplest way to use it is with the LaunchDarkly AI SDK's initChat method:

1. Install the required packages:

npm install @launchdarkly/server-sdk-ai @launchdarkly/server-sdk-ai-openai --save

2. Create a chat session and use it:

import { init } from '@launchdarkly/node-server-sdk';
import { initAi } from '@launchdarkly/server-sdk-ai';

// Initialize LaunchDarkly client
const ldClient = init(sdkKey);
const aiClient = initAi(ldClient);

// Create a chat session
const defaultConfig = { 
  enabled: true, 
  model: { name: 'gpt-4' },
  provider: { name: 'openai' }
};
const chat = await aiClient.initChat('my-chat-config', context, defaultConfig);

if (chat) {
  const response = await chat.invoke("What is the capital of France?");
  console.log(response.message.content);
}

For more information about using the LaunchDarkly AI SDK, see the LaunchDarkly AI SDK documentation.

Advanced Usage

For more control, you can use the OpenAI provider package directly with LaunchDarkly configurations:

import { OpenAIProvider } from '@launchdarkly/server-sdk-ai-openai';
import { OpenAI } from 'openai';

// Create an OpenAI client
const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

// Combine LaunchDarkly AI Config messages with user message
const configMessages = aiConfig.messages || [];
const userMessage = { role: 'user', content: 'What is the capital of France?' };
const allMessages = [...configMessages, userMessage];

// Track the model call with LaunchDarkly tracking
const tracker = aiConfig.createTracker();
const response = await tracker.trackMetricsOf(
  OpenAIProvider.getAIMetricsFromResponse,
  () => client.chat.completions.create({
    model: 'gpt-4',
    messages: allMessages,
    temperature: 0.7,
  })
);

console.log('AI Response:', response.choices[0].message.content);

Observability

This provider automatically instruments OpenAI API calls for OpenTelemetry tracing when the optional @traceloop/instrumentation-openai package is installed. No additional configuration is required — instrumentation is applied the first time the provider is used.

To enable automatic tracing, install the instrumentation package:

npm install @traceloop/instrumentation-openai @opentelemetry/api --save

When these packages are available, the provider patches the OpenAI ESM module so that all chat completion calls produce OpenTelemetry spans. These spans are emitted through whatever TracerProvider is active in your application (for example, one configured by @launchdarkly/observability-node or any other OpenTelemetry setup).

If the instrumentation packages are not installed, the provider operates normally without tracing.

Contributing

We encourage pull requests and other contributions from the community. Check out our contributing guidelines for instructions on how to contribute to this SDK.

About LaunchDarkly

• LaunchDarkly is a continuous delivery platform that provides feature flags as a service and allows developers to iterate quickly and safely. We allow you to easily flag your features and manage them from the LaunchDarkly dashboard. With LaunchDarkly, you can:
  • Roll out a new feature to a subset of your users (like a group of users who opt-in to a beta tester group), gathering feedback and bug reports from real-world use cases.
  • Gradually roll out a feature to an increasing percentage of users, and track the effect that the feature has on key metrics (for instance, how likely is a user to complete a purchase if they have feature A versus feature B?).
  • Turn off a feature that you realize is causing performance problems in production, without needing to re-deploy, or even restart the application with a changed configuration file.
  • Grant access to certain features based on user attributes, like payment plan (eg: users on the 'gold' plan get access to more features than users in the 'silver' plan).
  • Disable parts of your application to facilitate maintenance, without taking everything offline.
• LaunchDarkly provides feature flag SDKs for a wide variety of languages and technologies. Check out our documentation for a complete list.
• Explore LaunchDarkly
  • launchdarkly.com for more information
  • docs.launchdarkly.com for our documentation and SDK reference guides
  • apidocs.launchdarkly.com for our API documentation
  • blog.launchdarkly.com for the latest product updates