Metrics

This endpoint serves Prometheus metrics via a HTTP-based interface that provides access to metrics data in a format suitable for scraping by Prometheus servers. The endpoint provides real-time insights into how the system is functioning. The endpoint exposed the metrics in a time-series format, allowing you to track various types of data, including system resources usage, application performance, and other custom metrics.

Currently following metrics are available:

  • cpu_usage_percent (CPU usage in percentage.)
  • cpu_memory_used_bytes (Used CPU memory, in bytes.)
  • cpu_memory_total_bytes (Total CPU memory, in bytes.)
  • cpu_load_percent (CPU load, in percentage. Calculated for last 1m, 5m & 15m.)
  • system_info (System information, like platform & cpu count.)
  • system_uptime (Tell how long system has been running.)
  • container_info (Container information, like container version.)
  • http_request_size_bytes (HTTP request sizes in bytes grouped by method, status and handler.)
  • http_requests_total (Total number of requests grouped by method, status and handler.)
  • http_request_duration_seconds (The HTTP request latencies in seconds.)
Responses
200

Successful Response

get/metrics
Request samples
Response samples
text/plain
# HELP cpu_usage_percent Multiprocess metric
# TYPE cpu_usage_percent gauge
cpu_usage_percent 53.9
# HELP cpu_memory_used_bytes Multiprocess metric
# TYPE cpu_memory_used_bytes gauge
cpu_memory_used_bytes 2.260492288e+010
# HELP cpu_memory_total_bytes Multiprocess metric
# TYPE cpu_memory_total_bytes gauge
cpu_memory_total_bytes 6.7373068288e+010
# HELP cpu_load_percent Multiprocess metric
# TYPE cpu_load_percent gauge
cpu_load_percent{duration="1m"} 1.1666666666666667cpu_load_percent{duration="5m"} 0.8333333333333334cpu_load_percent{duration="15m"} 0.9583333333333335# HELP system_info Multiprocess metric
# TYPE system_info gauge
system_info{cpu_count="16",platform="Linux-5.13.0-52-generic-x86_64-with-glibc2.29"} 0.1
# HELP system_uptime Tell how long system has been running
# TYPE system_uptime gauge
system_uptime{cpu_count="8",platform="macOS-13.1-arm64-arm-64bit"} 1.3138956941900253e+06
# HELP container_info Multiprocess metric
# TYPE container_info gauge
container_info{app_version="Unknown versionfull_gpu"} 0.1
# HELP http_request_size_bytes Multiprocess metric
# TYPE http_request_size_bytes summary
http_request_size_bytes_count{handler="/v3/process/text",method="GET",status="2xx"} 3.0
# HELP http_requests_total Multiprocess metric
# TYPE http_requests_total counter
http_requests_total{handler="/v3/process/text",method="POST",status="2xx"} 3.0
# HELP http_request_duration_seconds Multiprocess metric
# TYPE http_request_duration_seconds histogram
http_request_duration_seconds_sum{handler="/v3/process/text",method="POST",status="2xx"} 0.8316442219074816
http_request_duration_seconds_bucket{handler="/v3/process/text",le="0.1",method="POST",status="2xx"} 0.0
http_request_duration_seconds_bucket{handler="/v3/process/text",le="0.25",method="POST",status="2xx"} 2.0
http_request_duration_seconds_bucket{handler="/v3/process/text",le="0.5",method="POST",status="2xx"} 3.0
http_request_duration_seconds_bucket{handler="/v3/process/text",le="1.0",method="POST",status="2xx"} 3.0
http_request_duration_seconds_count{handler="/v3/process/text",method="POST",status="2xx"} 3.0
© Copyright 2024 Private AI.