integrations/gateway-api-inference-extension/documentation.yaml

exporter_type: included
app_name_short: GKE Inference Gateway
app_name: {{app_name_short}}
app_site_name: {{app_name_short}}
app_site_url: https://github.com/kubernetes-sigs/gateway-api-inference-extension/
exporter_name: the {{app_name_short}} exporter
exporter_pkg_name: inference-extension
exporter_repo_url: https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/main/site-src/guides/metrics.md
additional_prereq_info: |
  {{app_site_name}} exposes Prometheus-format metrics automatically; you do not
  have to install it separately. To verify that {{exporter_name}} is emitting
  metrics on the expected endpoints, do the following:

  1. Set up port forwarding by using the following command:

  <pre class="devsite-click-to-copy">
  kubectl -n {{namespace_name}} port-forward {{pod_name}} 9090
  </pre>

  2. Access the endpoint `localhost:9090/metrics` by using the `curl` utility in another terminal session
  with token in command following the instruction: https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/main/site-src/guides/metrics.md#scrape-metrics
dashboard_available: true
multiple_dashboards: false
dashboard_display_name: {{app_name_short}} Prometheus Overview
podmonitoring_config: |
  apiVersion: monitoring.googleapis.com/v1
  kind: ClusterPodMonitoring
  metadata:
    name: inference-extension
    labels:
      app.kubernetes.io/name: inference-gateway
      app.kubernetes.io/part-of: google-cloud-managed-prometheus
  spec:
    endpoints:
    - port: metrics
      scheme: http
      interval: 5s
      path: /metrics
      authorization:
      type: Bearer
      credentials:
        secret:
          name: inference-gateway-sa-metrics-reader-secret
          key: token
          namespace: default
    selector:
      matchLabels:
        app: inference-gateway-ext-proc
additional_podmonitoring_info: |
  Ensure that the values of the `port` and `matchLabels` fields match those of the {{app_name_short}} pods you want to monitor. For how to install the secret
  `inference-gateway-sa-metrics-reader-secret`, please follow the [instruction](https://cloud.google.com/stackdriver/docs/managed-prometheus/exporters/inference-optimized-gateway).
sample_promql_query: inference_model_request_total{cluster="{{cluster_name}}", namespace="{{namespace_name}}"}