# 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"} 826.0 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"} 20.0 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="4",version="3.14.4"} 1.0 # HELP process_virtual_memory_bytes Virtual memory size in bytes. # TYPE process_virtual_memory_bytes gauge process_virtual_memory_bytes 8.63985664e+08 # HELP process_resident_memory_bytes Resident memory size in bytes. # TYPE process_resident_memory_bytes gauge process_resident_memory_bytes 1.88665856e+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 1.77830389882e+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 16.53 # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge process_open_fds 32.0 # 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="none",method="POST",status="4xx"} 1.0 http_requests_total{handler="none",method="GET",status="4xx"} 172.0 http_requests_total{handler="/",method="GET",status="2xx"} 20.0 http_requests_total{handler="none",method="OPTIONS",status="4xx"} 1.0 http_requests_total{handler="/openapi.json",method="GET",status="2xx"} 4.0 http_requests_total{handler="/metrics",method="GET",status="2xx"} 3.0 http_requests_total{handler="/docs",method="GET",status="2xx"} 4.0 http_requests_total{handler="/redoc",method="GET",status="2xx"} 4.0 http_requests_total{handler="/v1/chat_start",method="POST",status="5xx"} 1.0 # HELP http_requests_created Total number of requests by method, status and handler. # TYPE http_requests_created gauge http_requests_created{handler="none",method="POST",status="4xx"} 1.778304974537576e+09 http_requests_created{handler="none",method="GET",status="4xx"} 1.77830497534755e+09 http_requests_created{handler="/",method="GET",status="2xx"} 1.778304994525022e+09 http_requests_created{handler="none",method="OPTIONS",status="4xx"} 1.7783049957822263e+09 http_requests_created{handler="/openapi.json",method="GET",status="2xx"} 1.7783051138237112e+09 http_requests_created{handler="/metrics",method="GET",status="2xx"} 1.7783051138732777e+09 http_requests_created{handler="/docs",method="GET",status="2xx"} 1.7783051673175027e+09 http_requests_created{handler="/redoc",method="GET",status="2xx"} 1.7783062829097877e+09 http_requests_created{handler="/v1/chat_start",method="POST",status="5xx"} 1.778309646710319e+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="none"} 174.0 http_request_size_bytes_sum{handler="none"} 92.0 http_request_size_bytes_count{handler="/"} 20.0 http_request_size_bytes_sum{handler="/"} 0.0 http_request_size_bytes_count{handler="/openapi.json"} 4.0 http_request_size_bytes_sum{handler="/openapi.json"} 0.0 http_request_size_bytes_count{handler="/metrics"} 3.0 http_request_size_bytes_sum{handler="/metrics"} 0.0 http_request_size_bytes_count{handler="/docs"} 4.0 http_request_size_bytes_sum{handler="/docs"} 0.0 http_request_size_bytes_count{handler="/redoc"} 4.0 http_request_size_bytes_sum{handler="/redoc"} 0.0 http_request_size_bytes_count{handler="/v1/chat_start"} 1.0 http_request_size_bytes_sum{handler="/v1/chat_start"} 373.0 # 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="none"} 1.7783049745375962e+09 http_request_size_bytes_created{handler="/"} 1.7783049945250401e+09 http_request_size_bytes_created{handler="/openapi.json"} 1.7783051138237255e+09 http_request_size_bytes_created{handler="/metrics"} 1.778305113873295e+09 http_request_size_bytes_created{handler="/docs"} 1.7783051673175166e+09 http_request_size_bytes_created{handler="/redoc"} 1.7783062829098039e+09 http_request_size_bytes_created{handler="/v1/chat_start"} 1.7783096467103336e+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="none"} 174.0 http_response_size_bytes_sum{handler="none"} 3837.0 http_response_size_bytes_count{handler="/"} 20.0 http_response_size_bytes_sum{handler="/"} 34620.0 http_response_size_bytes_count{handler="/openapi.json"} 4.0 http_response_size_bytes_sum{handler="/openapi.json"} 115792.0 http_response_size_bytes_count{handler="/metrics"} 3.0 http_response_size_bytes_sum{handler="/metrics"} 44431.0 http_response_size_bytes_count{handler="/docs"} 4.0 http_response_size_bytes_sum{handler="/docs"} 3852.0 http_response_size_bytes_count{handler="/redoc"} 4.0 http_response_size_bytes_sum{handler="/redoc"} 3672.0 http_response_size_bytes_count{handler="/v1/chat_start"} 1.0 http_response_size_bytes_sum{handler="/v1/chat_start"} 1681.0 # 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="none"} 1.7783049745376194e+09 http_response_size_bytes_created{handler="/"} 1.7783049945250566e+09 http_response_size_bytes_created{handler="/openapi.json"} 1.7783051138237426e+09 http_response_size_bytes_created{handler="/metrics"} 1.7783051138733184e+09 http_response_size_bytes_created{handler="/docs"} 1.7783051673175333e+09 http_response_size_bytes_created{handler="/redoc"} 1.7783062829098284e+09 http_response_size_bytes_created{handler="/v1/chat_start"} 1.77830964671035e+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"} 197.0 http_request_duration_highr_seconds_bucket{le="0.025"} 208.0 http_request_duration_highr_seconds_bucket{le="0.05"} 208.0 http_request_duration_highr_seconds_bucket{le="0.075"} 209.0 http_request_duration_highr_seconds_bucket{le="0.1"} 209.0 http_request_duration_highr_seconds_bucket{le="0.25"} 210.0 http_request_duration_highr_seconds_bucket{le="0.5"} 210.0 http_request_duration_highr_seconds_bucket{le="0.75"} 210.0 http_request_duration_highr_seconds_bucket{le="1.0"} 210.0 http_request_duration_highr_seconds_bucket{le="1.5"} 210.0 http_request_duration_highr_seconds_bucket{le="2.0"} 210.0 http_request_duration_highr_seconds_bucket{le="2.5"} 210.0 http_request_duration_highr_seconds_bucket{le="3.0"} 210.0 http_request_duration_highr_seconds_bucket{le="3.5"} 210.0 http_request_duration_highr_seconds_bucket{le="4.0"} 210.0 http_request_duration_highr_seconds_bucket{le="4.5"} 210.0 http_request_duration_highr_seconds_bucket{le="5.0"} 210.0 http_request_duration_highr_seconds_bucket{le="7.5"} 210.0 http_request_duration_highr_seconds_bucket{le="10.0"} 210.0 http_request_duration_highr_seconds_bucket{le="30.0"} 210.0 http_request_duration_highr_seconds_bucket{le="60.0"} 210.0 http_request_duration_highr_seconds_bucket{le="+Inf"} 210.0 http_request_duration_highr_seconds_count 210.0 http_request_duration_highr_seconds_sum 0.901846395310713 # 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 1.7783039016705961e+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="none",le="0.1",method="POST"} 1.0 http_request_duration_seconds_bucket{handler="none",le="0.5",method="POST"} 1.0 http_request_duration_seconds_bucket{handler="none",le="1.0",method="POST"} 1.0 http_request_duration_seconds_bucket{handler="none",le="+Inf",method="POST"} 1.0 http_request_duration_seconds_count{handler="none",method="POST"} 1.0 http_request_duration_seconds_sum{handler="none",method="POST"} 0.006231448001926765 http_request_duration_seconds_bucket{handler="none",le="0.1",method="GET"} 172.0 http_request_duration_seconds_bucket{handler="none",le="0.5",method="GET"} 172.0 http_request_duration_seconds_bucket{handler="none",le="1.0",method="GET"} 172.0 http_request_duration_seconds_bucket{handler="none",le="+Inf",method="GET"} 172.0 http_request_duration_seconds_count{handler="none",method="GET"} 172.0 http_request_duration_seconds_sum{handler="none",method="GET"} 0.5004502422234509 http_request_duration_seconds_bucket{handler="/",le="0.1",method="GET"} 20.0 http_request_duration_seconds_bucket{handler="/",le="0.5",method="GET"} 20.0 http_request_duration_seconds_bucket{handler="/",le="1.0",method="GET"} 20.0 http_request_duration_seconds_bucket{handler="/",le="+Inf",method="GET"} 20.0 http_request_duration_seconds_count{handler="/",method="GET"} 20.0 http_request_duration_seconds_sum{handler="/",method="GET"} 0.01620967502822168 http_request_duration_seconds_bucket{handler="none",le="0.1",method="OPTIONS"} 1.0 http_request_duration_seconds_bucket{handler="none",le="0.5",method="OPTIONS"} 1.0 http_request_duration_seconds_bucket{handler="none",le="1.0",method="OPTIONS"} 1.0 http_request_duration_seconds_bucket{handler="none",le="+Inf",method="OPTIONS"} 1.0 http_request_duration_seconds_count{handler="none",method="OPTIONS"} 1.0 http_request_duration_seconds_sum{handler="none",method="OPTIONS"} 0.0007203569984994829 http_request_duration_seconds_bucket{handler="/openapi.json",le="0.1",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/openapi.json",le="0.5",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/openapi.json",le="1.0",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/openapi.json",le="+Inf",method="GET"} 4.0 http_request_duration_seconds_count{handler="/openapi.json",method="GET"} 4.0 http_request_duration_seconds_sum{handler="/openapi.json",method="GET"} 0.05486247502267361 http_request_duration_seconds_bucket{handler="/metrics",le="0.1",method="GET"} 3.0 http_request_duration_seconds_bucket{handler="/metrics",le="0.5",method="GET"} 3.0 http_request_duration_seconds_bucket{handler="/metrics",le="1.0",method="GET"} 3.0 http_request_duration_seconds_bucket{handler="/metrics",le="+Inf",method="GET"} 3.0 http_request_duration_seconds_count{handler="/metrics",method="GET"} 3.0 http_request_duration_seconds_sum{handler="/metrics",method="GET"} 0.045432331011397764 http_request_duration_seconds_bucket{handler="/docs",le="0.1",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/docs",le="0.5",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/docs",le="1.0",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/docs",le="+Inf",method="GET"} 4.0 http_request_duration_seconds_count{handler="/docs",method="GET"} 4.0 http_request_duration_seconds_sum{handler="/docs",method="GET"} 0.015103945013834164 http_request_duration_seconds_bucket{handler="/redoc",le="0.1",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/redoc",le="0.5",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/redoc",le="1.0",method="GET"} 4.0 http_request_duration_seconds_bucket{handler="/redoc",le="+Inf",method="GET"} 4.0 http_request_duration_seconds_count{handler="/redoc",method="GET"} 4.0 http_request_duration_seconds_sum{handler="/redoc",method="GET"} 0.014506193023407832 http_request_duration_seconds_bucket{handler="/v1/chat_start",le="0.1",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="/v1/chat_start",le="0.5",method="POST"} 1.0 http_request_duration_seconds_bucket{handler="/v1/chat_start",le="1.0",method="POST"} 1.0 http_request_duration_seconds_bucket{handler="/v1/chat_start",le="+Inf",method="POST"} 1.0 http_request_duration_seconds_count{handler="/v1/chat_start",method="POST"} 1.0 http_request_duration_seconds_sum{handler="/v1/chat_start",method="POST"} 0.24832972898730077 # 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="none",method="POST"} 1.778304974537646e+09 http_request_duration_seconds_created{handler="none",method="GET"} 1.7783049753475995e+09 http_request_duration_seconds_created{handler="/",method="GET"} 1.7783049945250807e+09 http_request_duration_seconds_created{handler="none",method="OPTIONS"} 1.7783049957822697e+09 http_request_duration_seconds_created{handler="/openapi.json",method="GET"} 1.7783051138237646e+09 http_request_duration_seconds_created{handler="/metrics",method="GET"} 1.7783051138733468e+09 http_request_duration_seconds_created{handler="/docs",method="GET"} 1.778305167317561e+09 http_request_duration_seconds_created{handler="/redoc",method="GET"} 1.7783062829098537e+09 http_request_duration_seconds_created{handler="/v1/chat_start",method="POST"} 1.7783096467103732e+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="4",version="3.14.4"} 1.0 # HELP process_virtual_memory_bytes Virtual memory size in bytes. # TYPE process_virtual_memory_bytes gauge process_virtual_memory_bytes 3.7537792e+08 # HELP process_resident_memory_bytes Resident memory size in bytes. # TYPE process_resident_memory_bytes gauge process_resident_memory_bytes 5.1941376e+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 1.77825842296e+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 8.7 # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge process_open_fds 8.0 # 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 1.0 # HELP busy_worker Number of successful calls # TYPE busy_worker gauge busy_worker 0.0 # HELP processed_requests_total Number of successful calls # TYPE processed_requests_total gauge processed_requests_total 44.0 # HELP values_processed_requests_total Value gauge for processed_requests_total # TYPE values_processed_requests_total gauge values_processed_requests_total 44.0 # HELP values_request_duration_ms EMA gauge for request_duration_ms # TYPE values_request_duration_ms gauge values_request_duration_ms 259.00786924236854