integrations/tgi/documentation.yaml

exporter_type: included
app_name_short: TGI
app_name: Text Generation Inference
app_site_name: {{app_name_short}}
app_site_url: https://huggingface.co/docs/text-generation-inference/en/index
exporter_name: the {{app_name_short}} exporter
exporter_repo_url: https://huggingface.co/docs/text-generation-inference/en/reference/metrics
gke_setup_url: /kubernetes-engine/docs/tutorials/serve-gemma-gpu-tgi
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}} 8080:8080
  </pre>

  2. Access the endpoint `localhost:8080/metrics` by using the browser
  or the `curl` utility in another terminal session.
dashboard_available: true
multiple_dashboards: false
dashboard_display_name: {{app_name_short}} Prometheus Overview
podmonitoring_config: |
  apiVersion: monitoring.googleapis.com/v1
  kind: PodMonitoring
  metadata:
    name: tgi
    labels:
      app.kubernetes.io/name: tgi
      app.kubernetes.io/part-of: google-cloud-managed-prometheus
  spec:
    endpoints:
    - port: 8080
      scheme: http
      interval: 30s
      path: /metrics
    selector:
      matchLabels:
        app: tgi-gemma-server
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.
sample_promql_query: up{job="tgi", cluster="{{cluster_name}}", namespace="{{namespace_name}}"}