# HELP python_gc_objects_collected_total Objects collected during gc # TYPE python_gc_objects_collected_total counter python_gc_objects_collected_total{generation="0"} 0.0 python_gc_objects_collected_total{generation="1"} 785.0 python_gc_objects_collected_total{generation="2"} 0.0 # HELP python_gc_objects_uncollectable_total Uncollectable objects found during GC # TYPE python_gc_objects_uncollectable_total counter python_gc_objects_uncollectable_total{generation="0"} 0.0 python_gc_objects_uncollectable_total{generation="1"} 0.0 python_gc_objects_uncollectable_total{generation="2"} 0.0 # HELP python_gc_collections_total Number of times this generation was collected # TYPE python_gc_collections_total counter python_gc_collections_total{generation="0"} 0.0 python_gc_collections_total{generation="1"} 19.0 python_gc_collections_total{generation="2"} 0.0 # HELP python_info Python platform information # TYPE python_info gauge python_info{implementation="CPython",major="3",minor="14",patchlevel="3",version="3.14.3"} 1.0 # HELP process_virtual_memory_bytes Virtual memory size in bytes. # TYPE process_virtual_memory_bytes gauge process_virtual_memory_bytes 9.30881536e+08 # HELP process_resident_memory_bytes Resident memory size in bytes. # TYPE process_resident_memory_bytes gauge process_resident_memory_bytes 2.99261952e+08 # HELP process_start_time_seconds Start time of the process since unix epoch in seconds. # TYPE process_start_time_seconds gauge process_start_time_seconds 1.77312884811e+09 # HELP process_cpu_seconds_total Total user and system CPU time spent in seconds. # TYPE process_cpu_seconds_total counter process_cpu_seconds_total 20.71 # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge process_open_fds 80.0 # HELP process_max_fds Maximum number of open file descriptors. # TYPE process_max_fds gauge process_max_fds 1.048576e+06 # HELP http_requests_total Total number of requests by method, status and handler. # TYPE http_requests_total counter http_requests_total{handler="/",method="GET",status="2xx"} 2.0 http_requests_total{handler="/v1/chat_start",method="POST",status="2xx"} 8.0 http_requests_total{handler="/v1/train",method="GET",status="2xx"} 1.0 http_requests_total{handler="/v1/status_training",method="GET",status="2xx"} 2.0 http_requests_total{handler="none",method="GET",status="4xx"} 3.0 http_requests_total{handler="/v1/chat_start",method="POST",status="4xx"} 3.0 http_requests_total{handler="/v1/chat",method="POST",status="2xx"} 32.0 # HELP http_requests_created Total number of requests by method, status and handler. # TYPE http_requests_created gauge http_requests_created{handler="/",method="GET",status="2xx"} 1.7731288763554862e+09 http_requests_created{handler="/v1/chat_start",method="POST",status="2xx"} 1.773129294745472e+09 http_requests_created{handler="/v1/train",method="GET",status="2xx"} 1.7731294690995264e+09 http_requests_created{handler="/v1/status_training",method="GET",status="2xx"} 1.7731294779133086e+09 http_requests_created{handler="none",method="GET",status="4xx"} 1.7731304611944106e+09 http_requests_created{handler="/v1/chat_start",method="POST",status="4xx"} 1.7731321595932581e+09 http_requests_created{handler="/v1/chat",method="POST",status="2xx"} 1.7731337981206443e+09 # HELP http_request_size_bytes Content length of incoming requests by handler. Only value of header is respected. Otherwise ignored. No percentile calculated. # TYPE http_request_size_bytes summary http_request_size_bytes_count{handler="/"} 2.0 http_request_size_bytes_sum{handler="/"} 0.0 http_request_size_bytes_count{handler="/v1/chat_start"} 11.0 http_request_size_bytes_sum{handler="/v1/chat_start"} 94898.0 http_request_size_bytes_count{handler="/v1/train"} 1.0 http_request_size_bytes_sum{handler="/v1/train"} 0.0 http_request_size_bytes_count{handler="/v1/status_training"} 2.0 http_request_size_bytes_sum{handler="/v1/status_training"} 0.0 http_request_size_bytes_count{handler="none"} 3.0 http_request_size_bytes_sum{handler="none"} 0.0 http_request_size_bytes_count{handler="/v1/chat"} 32.0 http_request_size_bytes_sum{handler="/v1/chat"} 6426.0 # HELP http_request_size_bytes_created Content length of incoming requests by handler. Only value of header is respected. Otherwise ignored. No percentile calculated. # TYPE http_request_size_bytes_created gauge http_request_size_bytes_created{handler="/"} 1.7731288763555062e+09 http_request_size_bytes_created{handler="/v1/chat_start"} 1.7731292947454896e+09 http_request_size_bytes_created{handler="/v1/train"} 1.7731294690995433e+09 http_request_size_bytes_created{handler="/v1/status_training"} 1.7731294779133244e+09 http_request_size_bytes_created{handler="none"} 1.7731304611944282e+09 http_request_size_bytes_created{handler="/v1/chat"} 1.7731337981206586e+09 # HELP http_response_size_bytes Content length of outgoing responses by handler. Only value of header is respected. Otherwise ignored. No percentile calculated. # TYPE http_response_size_bytes summary http_response_size_bytes_count{handler="/"} 2.0 http_response_size_bytes_sum{handler="/"} 3462.0 http_response_size_bytes_count{handler="/v1/chat_start"} 11.0 http_response_size_bytes_sum{handler="/v1/chat_start"} 7466.0 http_response_size_bytes_count{handler="/v1/train"} 1.0 http_response_size_bytes_sum{handler="/v1/train"} 393.0 http_response_size_bytes_count{handler="/v1/status_training"} 2.0 http_response_size_bytes_sum{handler="/v1/status_training"} 557.0 http_response_size_bytes_count{handler="none"} 3.0 http_response_size_bytes_sum{handler="none"} 66.0 http_response_size_bytes_count{handler="/v1/chat"} 32.0 http_response_size_bytes_sum{handler="/v1/chat"} 30593.0 # HELP http_response_size_bytes_created Content length of outgoing responses by handler. Only value of header is respected. Otherwise ignored. No percentile calculated. # TYPE http_response_size_bytes_created gauge http_response_size_bytes_created{handler="/"} 1.7731288763555298e+09 http_response_size_bytes_created{handler="/v1/chat_start"} 1.7731292947455096e+09 http_response_size_bytes_created{handler="/v1/train"} 1.7731294690995646e+09 http_response_size_bytes_created{handler="/v1/status_training"} 1.7731294779133427e+09 http_response_size_bytes_created{handler="none"} 1.77313046119445e+09 http_response_size_bytes_created{handler="/v1/chat"} 1.7731337981206775e+09 # HELP http_request_duration_highr_seconds Latency with many buckets but no API specific labels. Made for more accurate percentile calculations. # TYPE http_request_duration_highr_seconds histogram http_request_duration_highr_seconds_bucket{le="0.01"} 8.0 http_request_duration_highr_seconds_bucket{le="0.025"} 8.0 http_request_duration_highr_seconds_bucket{le="0.05"} 9.0 http_request_duration_highr_seconds_bucket{le="0.075"} 10.0 http_request_duration_highr_seconds_bucket{le="0.1"} 11.0 http_request_duration_highr_seconds_bucket{le="0.25"} 11.0 http_request_duration_highr_seconds_bucket{le="0.5"} 11.0 http_request_duration_highr_seconds_bucket{le="0.75"} 11.0 http_request_duration_highr_seconds_bucket{le="1.0"} 21.0 http_request_duration_highr_seconds_bucket{le="1.5"} 35.0 http_request_duration_highr_seconds_bucket{le="2.0"} 42.0 http_request_duration_highr_seconds_bucket{le="2.5"} 49.0 http_request_duration_highr_seconds_bucket{le="3.0"} 50.0 http_request_duration_highr_seconds_bucket{le="3.5"} 50.0 http_request_duration_highr_seconds_bucket{le="4.0"} 50.0 http_request_duration_highr_seconds_bucket{le="4.5"} 50.0 http_request_duration_highr_seconds_bucket{le="5.0"} 50.0 http_request_duration_highr_seconds_bucket{le="7.5"} 51.0 http_request_duration_highr_seconds_bucket{le="10.0"} 51.0 http_request_duration_highr_seconds_bucket{le="30.0"} 51.0 http_request_duration_highr_seconds_bucket{le="60.0"} 51.0 http_request_duration_highr_seconds_bucket{le="+Inf"} 51.0 http_request_duration_highr_seconds_count 51.0 http_request_duration_highr_seconds_sum 63.61911896907259 # HELP http_request_duration_highr_seconds_created Latency with many buckets but no API specific labels. Made for more accurate percentile calculations. # TYPE http_request_duration_highr_seconds_created gauge http_request_duration_highr_seconds_created 1.773128858726169e+09 # HELP http_request_duration_seconds Latency with only few buckets by handler. Made to be only used if aggregation by handler is important. # TYPE http_request_duration_seconds histogram http_request_duration_seconds_bucket{handler="/",le="0.1",method="GET"} 2.0 http_request_duration_seconds_bucket{handler="/",le="0.5",method="GET"} 2.0 http_request_duration_seconds_bucket{handler="/",le="1.0",method="GET"} 2.0 http_request_duration_seconds_bucket{handler="/",le="+Inf",method="GET"} 2.0 http_request_duration_seconds_count{handler="/",method="GET"} 2.0 http_request_duration_seconds_sum{handler="/",method="GET"} 0.005700214998796582 http_request_duration_seconds_bucket{handler="/v1/chat_start",le="0.1",method="POST"} 3.0 http_request_duration_seconds_bucket{handler="/v1/chat_start",le="0.5",method="POST"} 3.0 http_request_duration_seconds_bucket{handler="/v1/chat_start",le="1.0",method="POST"} 3.0 http_request_duration_seconds_bucket{handler="/v1/chat_start",le="+Inf",method="POST"} 11.0 http_request_duration_seconds_count{handler="/v1/chat_start",method="POST"} 11.0 http_request_duration_seconds_sum{handler="/v1/chat_start",method="POST"} 16.062108845915645 http_request_duration_seconds_bucket{handler="/v1/train",le="0.1",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/v1/train",le="0.5",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/v1/train",le="1.0",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/v1/train",le="+Inf",method="GET"} 1.0 http_request_duration_seconds_count{handler="/v1/train",method="GET"} 1.0 http_request_duration_seconds_sum{handler="/v1/train",method="GET"} 0.07474765204824507 http_request_duration_seconds_bucket{handler="/v1/status_training",le="0.1",method="GET"} 2.0 http_request_duration_seconds_bucket{handler="/v1/status_training",le="0.5",method="GET"} 2.0 http_request_duration_seconds_bucket{handler="/v1/status_training",le="1.0",method="GET"} 2.0 http_request_duration_seconds_bucket{handler="/v1/status_training",le="+Inf",method="GET"} 2.0 http_request_duration_seconds_count{handler="/v1/status_training",method="GET"} 2.0 http_request_duration_seconds_sum{handler="/v1/status_training",method="GET"} 0.009973686013836414 http_request_duration_seconds_bucket{handler="none",le="0.1",method="GET"} 3.0 http_request_duration_seconds_bucket{handler="none",le="0.5",method="GET"} 3.0 http_request_duration_seconds_bucket{handler="none",le="1.0",method="GET"} 3.0 http_request_duration_seconds_bucket{handler="none",le="+Inf",method="GET"} 3.0 http_request_duration_seconds_count{handler="none",method="GET"} 3.0 http_request_duration_seconds_sum{handler="none",method="GET"} 0.00201799301430583 http_request_duration_seconds_bucket{handler="/v1/chat",le="0.1",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="/v1/chat",le="0.5",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="/v1/chat",le="1.0",method="POST"} 10.0 http_request_duration_seconds_bucket{handler="/v1/chat",le="+Inf",method="POST"} 32.0 http_request_duration_seconds_count{handler="/v1/chat",method="POST"} 32.0 http_request_duration_seconds_sum{handler="/v1/chat",method="POST"} 47.46457057708176 # HELP http_request_duration_seconds_created Latency with only few buckets by handler. Made to be only used if aggregation by handler is important. # TYPE http_request_duration_seconds_created gauge http_request_duration_seconds_created{handler="/",method="GET"} 1.773128876355558e+09 http_request_duration_seconds_created{handler="/v1/chat_start",method="POST"} 1.7731292947455385e+09 http_request_duration_seconds_created{handler="/v1/train",method="GET"} 1.7731294690995955e+09 http_request_duration_seconds_created{handler="/v1/status_training",method="GET"} 1.773129477913371e+09 http_request_duration_seconds_created{handler="none",method="GET"} 1.773130461194476e+09 http_request_duration_seconds_created{handler="/v1/chat",method="POST"} 1.773133798120703e+09 # HELP env_worker_threads Environment variable WORKER_THREADS # TYPE env_worker_threads gauge env_worker_threads 2.0 # HELP python_gc_objects_collected_total Objects collected during gc # TYPE python_gc_objects_collected_total counter python_gc_objects_collected_total{generation="0"} 0.0 python_gc_objects_collected_total{generation="1"} 247.0 python_gc_objects_collected_total{generation="2"} 0.0 # HELP python_gc_objects_uncollectable_total Uncollectable objects found during GC # TYPE python_gc_objects_uncollectable_total counter python_gc_objects_uncollectable_total{generation="0"} 0.0 python_gc_objects_uncollectable_total{generation="1"} 0.0 python_gc_objects_uncollectable_total{generation="2"} 0.0 # HELP python_gc_collections_total Number of times this generation was collected # TYPE python_gc_collections_total counter python_gc_collections_total{generation="0"} 0.0 python_gc_collections_total{generation="1"} 7.0 python_gc_collections_total{generation="2"} 0.0 # HELP python_info Python platform information # TYPE python_info gauge python_info{implementation="CPython",major="3",minor="14",patchlevel="3",version="3.14.3"} 1.0 # HELP process_virtual_memory_bytes Virtual memory size in bytes. # TYPE process_virtual_memory_bytes gauge process_virtual_memory_bytes 4.46226432e+08 # HELP process_resident_memory_bytes Resident memory size in bytes. # TYPE process_resident_memory_bytes gauge process_resident_memory_bytes 5.029888e+07 # HELP process_start_time_seconds Start time of the process since unix epoch in seconds. # TYPE process_start_time_seconds gauge process_start_time_seconds 1.77312884719e+09 # HELP process_cpu_seconds_total Total user and system CPU time spent in seconds. # TYPE process_cpu_seconds_total counter process_cpu_seconds_total 2.21 # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge process_open_fds 10.0 # HELP process_max_fds Maximum number of open file descriptors. # TYPE process_max_fds gauge process_max_fds 1.048576e+06 # HELP requests_per_minute Requests processed in the last minute # TYPE requests_per_minute gauge requests_per_minute 6.0 # HELP busy_worker Number of successful calls # TYPE busy_worker gauge busy_worker 1.0 # HELP processed_requests_total Number of successful calls # TYPE processed_requests_total gauge processed_requests_total 63.0 # HELP values_processed_requests_total Value gauge for processed_requests_total # TYPE values_processed_requests_total gauge values_processed_requests_total 63.0 # HELP values_request_duration_ms EMA gauge for request_duration_ms # TYPE values_request_duration_ms gauge values_request_duration_ms 1226.3376276711797