Prometheus is an adaptable system for tracking and alerting, commonly used to scrape and review numerous operating metrics. This document details how to incorporate Prometheus into a privately hosted setup for Rime.

​
Prerequisites

Before proceeding, confirm:

  1. You can access a self-hosted instance where the /metrics endpoint is exposed (assuming port 8080).
  2. You have permissions to edit the main configuration file, typically prometheus.yml.
  3. You have permissions to run a Docker container in your environment.

​
Running Prometheus

Step 1: Include a Prometheus Target

Open prometheus.yml. Add a job pointing to your Rime Engine container:

global:
  scrape_interval: 5s  # Scrape metrics every 5 seconds

scrape_configs:
  - job_name: "model-rime-tts"
    static_configs:
      - targets: ["<instance_ip>:8080"]  # Adjust this
    metrics_path: "/metrics"  # Default path for Prometheus metrics

Replace instance_ip with the relevant hostname or IP address, then save the file.

Step 2: Use the following command to pull and run Prometheus in a container:

docker run -d \
  --rm \
  -p 9090:9090 \
  -v $(pwd)/prometheus.yml:/etc/prometheus/prometheus.yml \
  prom/prometheus:latest

Step 3: Validate the Setup

Access the Prometheus UI (commonly at http://localhost:9090), navigate to Status → Targets, and look for the model-rime-tts job. Its status should be UP, confirming Prometheus is successfully collecting metrics.

Exploring Metrics With Prometheus integrated, you can retrieve metrics through its web interface or API. Many users combine Prometheus with platforms like Grafana to build dashboards and set up alerts.