Health Gated Completion
A 3-step recipe with NVIDIA NIM. We can help you get access.
Recipe · 3 steps
Health Gated Completion
with NVIDIA NIM · Artificial Intelligence Management
Gate a text completion behind the container readiness probe.
- Probe the container readiness endpoint. A 200 means the model engine has loaded and the container can accept traffic.
- List the models the ready container serves to confirm the requested model is available before inference.
- Run a legacy text completion against the requested model now that the container is confirmed ready.
What you'll need to have ready
- apiKey: NVIDIA developer API key (nvapi-...) sent as a Bearer token.
- prompt: Raw text prompt for the legacy completions endpoint.
- modelId: Model id to run the completion against.
- maxTokens: Maximum number of tokens to generate.
For your developer
Arazzo workflow nvidia-nim:health-gated-completion, 3 operations: getReadiness → listModels → createCompletion. Specs on APIs.io.