Update README with nesting for telemetry

This commit is contained in:
Jack Colquitt 2025-08-31 12:34:03 -07:00 committed by GitHub
parent e5db961e2a
commit f62de4e644
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -202,18 +202,24 @@ password: admin
The default Grafana dashboard tracks the following: The default Grafana dashboard tracks the following:
- LLM Latency <details>
- Error Rate <summary>Telemetry</summary>
- Service Request Rates <br>
- Queue Backlogs
- Chunking Histogram - LLM Latency<br>
- Error Source by Service - Error Rate<br>
- Rate Limit Events - Service Request Rates<br>
- CPU usage by Service - Queue Backlogs<br>
- Memory usage by Service - Chunking Histogram<br>
- Models Deployed - Error Source by Service<br>
- Token Throughput (Tokens/second) - Rate Limit Events<br>
- Cost Throughput (Cost/second) - CPU usage by Service<br>
- Memory usage by Service<br>
- Models Deployed<br>
- Token Throughput (Tokens/second)<br>
- Cost Throughput (Cost/second)<br>
</details>
## Contributing ## Contributing