Obtaining the Request Number for Inference

Function Description

Obtains the statistics on the number of inference requests after the inference service is enabled.

URI

The request method is as follows:

GET /metrics

Example Response

The total number of received requests, inference service creation time, number of requests received per second, and request processing time per second are returned. The following is an example:

# HELP http_requests_total Total request cout of the host
# TYPE http_requests_total counter
http_requests_total{endpoint="/infer",method="get"} 13.0
# HELP http_requests_created Total request cout of the host
# TYPE http_requests_created gauge
http_requests_created{endpoint="/infer",method="get"} 1.6369808622964778e+09
# HELP request_processing_seconds Time spent processing request
# TYPE request_processing_seconds summary
request_processing_seconds_count 0.0
request_processing_seconds_sum 0.0
# HELP request_processing_seconds_created Time spent processing request
# TYPE request_processing_seconds_created gauge
request_processing_seconds_created 1.6369808298391838e+09