About AI SDKs
While LaunchDarkly server-side, client-side, and edge SDKs focus on interacting with feature flags, LaunchDarkly AI SDKs interact with AgentControl configs. Configs are resources that you create in LaunchDarkly and use to customize, test, and roll out new large language models (LLMs) within your generative AI applications. You can use the AI SDKs to customize each config based on the context that you provide. This means both the message and the model evaluation are specific to each end user, at runtime. You can also use the AI SDKs to record metrics from your AI model generation, including duration and tokens. AI metrics and traces are recorded differently. AI metrics are captured through the AI SDK tracker methods. If you use the LaunchDarkly observability plugin to capture traces, run your model calls inside an active span so LaunchDarkly can associate traces with the evaluated config.AI SDKs
Additional resources
You can follow development or contribute on GitHub with the following links.| SDK | SDK API documentation | GitHub repository |
|---|---|---|
| .NET AI SDK | .NET AI SDK API docs | .NET AI SDK |
| Go AI SDK | Go AI SDK API docs | Go AI SDK |
| Node.js (server-side) AI SDK | Node.js (server-side) AI SDK API docs | node-server-sdk-ai |
| Python AI SDK | Python AI SDK API docs | tmp-launchdarkly-ai-sdk |
| Python AI SDK (Legacy) | Python AI SDK API docs | Python AI SDK |
| Ruby AI SDK | Ruby AI SDK API docs | Ruby AI SDK |