# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for NVIDIA NIM Biology (BioNeMo) ASR Health API
  version: 1.0.0
extends: openapi/nvidia-nim-health-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-10-01'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 3
- target: $.paths['/v1/health/live'].get
  update:
    x-apievangelist-phrasing:
      intent: Check that the NIM container process is alive
      effect: read
      questions:
      - Is my NIM container process still running, for a Kubernetes liveness probe?
      - Which endpoint tells me whether the inference container has crashed or hung?
      instructions:
      - text: Check whether the NIM container process is alive.
      - text: Run the liveness probe against my NIM container.
      method: generated
      generated: '2026-10-01'
- target: $.paths['/v1/health/ready'].get
  update:
    x-apievangelist-phrasing:
      intent: Check that the model is loaded and ready
      effect: read
      questions:
      - Has the model engine finished loading so the NIM can start accepting traffic?
      - Which check tells a load balancer the container is ready to serve inference requests?
      instructions:
      - text: Check whether the NIM model engine is loaded and ready for requests.
      - text: Run the readiness probe before sending traffic to the container.
      method: generated
      generated: '2026-10-01'
- target: $.paths['/v1/metrics'].get
  update:
    x-apievangelist-phrasing:
      intent: Get Prometheus metrics for a NIM container
      effect: read
      questions:
      - Where can I scrape GPU utilization and request latency metrics for my NIM deployment?
      - Can I see the current request queue depth for an inference container in Prometheus format?
      instructions:
      - text: Fetch the Prometheus metrics from my NIM container.
      - text: Show the GPU utilization, latency histograms and queue depth for this NIM.
      method: generated
      generated: '2026-10-01'