Getting Started
Run your first eval in under 5 minutes.
1. Install the SDK
npm install @launchgate/sdk
2. Create an API key
Sign up at app.launchgate.ai and create an API key in Settings. Set it as an environment variable:
export LAUNCHGATE_API_KEY=lg_live_your_key_here
3. Run your first eval
import { LaunchGate } from "@launchgate/sdk";
const lg = new LaunchGate({
apiKey: process.env.LAUNCHGATE_API_KEY,
});
const result = await lg.run("rag-faithfulness", {
input: {
context: "The Eiffel Tower was built in 1889.",
query: "When was the Eiffel Tower built?",
},
output: "The Eiffel Tower was built in 1889.",
});
console.log(result.status); // "cleared"
console.log(result.passRate); // 1.04. Add to your CI/CD
Using the CLI:
npm install -g @launchgate/cli
launchgate run rag-faithfulness \
--output "The Eiffel Tower was built in 1889." \
--input '{"context": "...", "query": "..."}'Or the GitHub Action:
- name: Run LaunchGate Eval
uses: launchgate/eval-action@v1
with:
api-key: ${{ secrets.LAUNCHGATE_API_KEY }}
suite: "rag-faithfulness"
output: ${{ steps.generate.outputs.text }}What's next?
- Create custom eval suites in the dashboard
- Add your LLM provider keys for AI-powered scoring
- Set up the GitHub Action for automated PR gating
- Browse the 6 starter templates for common use cases