Prometheus integration

Export Rime on-prem OpenTelemetry metrics for Prometheus to scrape.

Rime model containers export OpenTelemetry metrics. An OpenTelemetry Collector can receive those metrics and expose a Prometheus-compatible endpoint.

Configure the model container

Point the model at a collector available as otelcol on the same Docker network:

services:
  model:
    environment:
      OTEL_COLLECTOR_PROTOCOL: grpc
      OTEL_COLLECTOR_ENDPOINT: http://otelcol:4317

See Health checks and metrics for the emitted series and histogram controls.

Configure the collector

Create otelcol.yaml:

receivers:
  otlp:
    protocols:
      grpc:
        endpoint: 0.0.0.0:4317

exporters:
  prometheus:
    endpoint: 0.0.0.0:9090

service:
  pipelines:
    metrics:
      receivers: [otlp]
      exporters: [prometheus]

Run the collector on the model’s Docker network and expose its Prometheus port:

docker run -d \
  --name rime-otelcol \
  --network "<rime-network>" \
  -p 9090:9090 \
  -v "$(pwd)/otelcol.yaml:/etc/otelcol-contrib/config.yaml:ro" \
  otel/opentelemetry-collector-contrib:0.139.0

Configure Prometheus

Add the collector to prometheus.yml:

global:
  scrape_interval: 5s

scrape_configs:
  - job_name: "rime-tts"
    static_configs:
      - targets: ["<collector-host>:9090"]

Reload Prometheus, open Status > Targets, and confirm that the rime-tts target is up.