# HELP python_gc_objects_collected_total Objects collected during gc # TYPE python_gc_objects_collected_total counter python_gc_objects_collected_total{generation="0"} 21104.0 python_gc_objects_collected_total{generation="1"} 2890.0 python_gc_objects_collected_total{generation="2"} 1057.0 # 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"} 124.0 python_gc_collections_total{generation="1"} 11.0 python_gc_collections_total{generation="2"} 1.0 # HELP python_info Python platform information # TYPE python_info gauge python_info{implementation="CPython",major="3",minor="14",patchlevel="7",version="3.14.7"} 1.0 # HELP process_virtual_memory_bytes Virtual memory size in bytes. # TYPE process_virtual_memory_bytes gauge process_virtual_memory_bytes 6.17930752e+08 # HELP process_resident_memory_bytes Resident memory size in bytes. # TYPE process_resident_memory_bytes gauge process_resident_memory_bytes 2.33488384e+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 1.78817773192e+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 14.08 # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge process_open_fds 24.0 # 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="/metrics",method="GET",status="2xx"} 289.0 http_requests_total{handler="/",method="GET",status="2xx"} 11.0 http_requests_total{handler="none",method="GET",status="4xx"} 34.0 http_requests_total{handler="/v1/conversationQA",method="POST",status="4xx"} 10.0 http_requests_total{handler="/docs",method="GET",status="2xx"} 1.0 http_requests_total{handler="/openapi.json",method="GET",status="2xx"} 1.0 http_requests_total{handler="/v1/drafting",method="POST",status="4xx"} 1.0 http_requests_total{handler="none",method="HEAD",status="4xx"} 1.0 # HELP http_requests_created Total number of requests by method, status and handler. # TYPE http_requests_created gauge http_requests_created{handler="/metrics",method="GET",status="2xx"} 1.7881778057779708e+09 http_requests_created{handler="/",method="GET",status="2xx"} 1.7881778960166323e+09 http_requests_created{handler="none",method="GET",status="4xx"} 1.7881779366154554e+09 http_requests_created{handler="/v1/conversationQA",method="POST",status="4xx"} 1.788178049801566e+09 http_requests_created{handler="/docs",method="GET",status="2xx"} 1.7881785759412131e+09 http_requests_created{handler="/openapi.json",method="GET",status="2xx"} 1.788178576100211e+09 http_requests_created{handler="/v1/drafting",method="POST",status="4xx"} 1.788178822397538e+09 http_requests_created{handler="none",method="HEAD",status="4xx"} 1.7881826985086317e+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="/metrics"} 289.0 http_request_size_bytes_sum{handler="/metrics"} 0.0 http_request_size_bytes_count{handler="/"} 11.0 http_request_size_bytes_sum{handler="/"} 0.0 http_request_size_bytes_count{handler="none"} 35.0 http_request_size_bytes_sum{handler="none"} 0.0 http_request_size_bytes_count{handler="/v1/conversationQA"} 10.0 http_request_size_bytes_sum{handler="/v1/conversationQA"} 40165.0 http_request_size_bytes_count{handler="/docs"} 1.0 http_request_size_bytes_sum{handler="/docs"} 0.0 http_request_size_bytes_count{handler="/openapi.json"} 1.0 http_request_size_bytes_sum{handler="/openapi.json"} 0.0 http_request_size_bytes_count{handler="/v1/drafting"} 1.0 http_request_size_bytes_sum{handler="/v1/drafting"} 64.0 # 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="/metrics"} 1.7881778057779899e+09 http_request_size_bytes_created{handler="/"} 1.78817789601667e+09 http_request_size_bytes_created{handler="none"} 1.788177936615469e+09 http_request_size_bytes_created{handler="/v1/conversationQA"} 1.7881780498015823e+09 http_request_size_bytes_created{handler="/docs"} 1.7881785759412303e+09 http_request_size_bytes_created{handler="/openapi.json"} 1.7881785761002269e+09 http_request_size_bytes_created{handler="/v1/drafting"} 1.7881788223975532e+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="/metrics"} 289.0 http_response_size_bytes_sum{handler="/metrics"} 4.302754e+06 http_response_size_bytes_count{handler="/"} 11.0 http_response_size_bytes_sum{handler="/"} 19206.0 http_response_size_bytes_count{handler="none"} 35.0 http_response_size_bytes_sum{handler="none"} 779.0 http_response_size_bytes_count{handler="/v1/conversationQA"} 10.0 http_response_size_bytes_sum{handler="/v1/conversationQA"} 1070.0 http_response_size_bytes_count{handler="/docs"} 1.0 http_response_size_bytes_sum{handler="/docs"} 958.0 http_response_size_bytes_count{handler="/openapi.json"} 1.0 http_response_size_bytes_sum{handler="/openapi.json"} 24668.0 http_response_size_bytes_count{handler="/v1/drafting"} 1.0 http_response_size_bytes_sum{handler="/v1/drafting"} 111.0 # 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="/metrics"} 1.7881778057780147e+09 http_response_size_bytes_created{handler="/"} 1.7881778960166905e+09 http_response_size_bytes_created{handler="none"} 1.7881779366154833e+09 http_response_size_bytes_created{handler="/v1/conversationQA"} 1.7881780498015978e+09 http_response_size_bytes_created{handler="/docs"} 1.7881785759412513e+09 http_response_size_bytes_created{handler="/openapi.json"} 1.7881785761002436e+09 http_response_size_bytes_created{handler="/v1/drafting"} 1.7881788223975713e+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"} 46.0 http_request_duration_highr_seconds_bucket{le="0.025"} 330.0 http_request_duration_highr_seconds_bucket{le="0.05"} 335.0 http_request_duration_highr_seconds_bucket{le="0.075"} 336.0 http_request_duration_highr_seconds_bucket{le="0.1"} 337.0 http_request_duration_highr_seconds_bucket{le="0.25"} 337.0 http_request_duration_highr_seconds_bucket{le="0.5"} 337.0 http_request_duration_highr_seconds_bucket{le="0.75"} 338.0 http_request_duration_highr_seconds_bucket{le="1.0"} 347.0 http_request_duration_highr_seconds_bucket{le="1.5"} 348.0 http_request_duration_highr_seconds_bucket{le="2.0"} 348.0 http_request_duration_highr_seconds_bucket{le="2.5"} 348.0 http_request_duration_highr_seconds_bucket{le="3.0"} 348.0 http_request_duration_highr_seconds_bucket{le="3.5"} 348.0 http_request_duration_highr_seconds_bucket{le="4.0"} 348.0 http_request_duration_highr_seconds_bucket{le="4.5"} 348.0 http_request_duration_highr_seconds_bucket{le="5.0"} 348.0 http_request_duration_highr_seconds_bucket{le="7.5"} 348.0 http_request_duration_highr_seconds_bucket{le="10.0"} 348.0 http_request_duration_highr_seconds_bucket{le="30.0"} 348.0 http_request_duration_highr_seconds_bucket{le="60.0"} 348.0 http_request_duration_highr_seconds_bucket{le="+Inf"} 348.0 http_request_duration_highr_seconds_count 348.0 http_request_duration_highr_seconds_sum 12.657873207703233 # 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 1.7881777610433688e+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="/metrics",le="0.1",method="GET"} 289.0 http_request_duration_seconds_bucket{handler="/metrics",le="0.5",method="GET"} 289.0 http_request_duration_seconds_bucket{handler="/metrics",le="1.0",method="GET"} 289.0 http_request_duration_seconds_bucket{handler="/metrics",le="+Inf",method="GET"} 289.0 http_request_duration_seconds_count{handler="/metrics",method="GET"} 289.0 http_request_duration_seconds_sum{handler="/metrics",method="GET"} 3.6245055785402656 http_request_duration_seconds_bucket{handler="/",le="0.1",method="GET"} 11.0 http_request_duration_seconds_bucket{handler="/",le="0.5",method="GET"} 11.0 http_request_duration_seconds_bucket{handler="/",le="1.0",method="GET"} 11.0 http_request_duration_seconds_bucket{handler="/",le="+Inf",method="GET"} 11.0 http_request_duration_seconds_count{handler="/",method="GET"} 11.0 http_request_duration_seconds_sum{handler="/",method="GET"} 0.010549413040280342 http_request_duration_seconds_bucket{handler="none",le="0.1",method="GET"} 34.0 http_request_duration_seconds_bucket{handler="none",le="0.5",method="GET"} 34.0 http_request_duration_seconds_bucket{handler="none",le="1.0",method="GET"} 34.0 http_request_duration_seconds_bucket{handler="none",le="+Inf",method="GET"} 34.0 http_request_duration_seconds_count{handler="none",method="GET"} 34.0 http_request_duration_seconds_sum{handler="none",method="GET"} 0.04591968096792698 http_request_duration_seconds_bucket{handler="/v1/conversationQA",le="0.1",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="/v1/conversationQA",le="0.5",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="/v1/conversationQA",le="1.0",method="POST"} 9.0 http_request_duration_seconds_bucket{handler="/v1/conversationQA",le="+Inf",method="POST"} 10.0 http_request_duration_seconds_count{handler="/v1/conversationQA",method="POST"} 10.0 http_request_duration_seconds_sum{handler="/v1/conversationQA",method="POST"} 8.30513416416943 http_request_duration_seconds_bucket{handler="/docs",le="0.1",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/docs",le="0.5",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/docs",le="1.0",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/docs",le="+Inf",method="GET"} 1.0 http_request_duration_seconds_count{handler="/docs",method="GET"} 1.0 http_request_duration_seconds_sum{handler="/docs",method="GET"} 0.0011054929345846176 http_request_duration_seconds_bucket{handler="/openapi.json",le="0.1",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/openapi.json",le="0.5",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/openapi.json",le="1.0",method="GET"} 1.0 http_request_duration_seconds_bucket{handler="/openapi.json",le="+Inf",method="GET"} 1.0 http_request_duration_seconds_count{handler="/openapi.json",method="GET"} 1.0 http_request_duration_seconds_sum{handler="/openapi.json",method="GET"} 0.06394084170460701 http_request_duration_seconds_bucket{handler="/v1/drafting",le="0.1",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="/v1/drafting",le="0.5",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="/v1/drafting",le="1.0",method="POST"} 1.0 http_request_duration_seconds_bucket{handler="/v1/drafting",le="+Inf",method="POST"} 1.0 http_request_duration_seconds_count{handler="/v1/drafting",method="POST"} 1.0 http_request_duration_seconds_sum{handler="/v1/drafting",method="POST"} 0.6058563459664583 http_request_duration_seconds_bucket{handler="none",le="0.1",method="HEAD"} 1.0 http_request_duration_seconds_bucket{handler="none",le="0.5",method="HEAD"} 1.0 http_request_duration_seconds_bucket{handler="none",le="1.0",method="HEAD"} 1.0 http_request_duration_seconds_bucket{handler="none",le="+Inf",method="HEAD"} 1.0 http_request_duration_seconds_count{handler="none",method="HEAD"} 1.0 http_request_duration_seconds_sum{handler="none",method="HEAD"} 0.000861690379679203 # 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="/metrics",method="GET"} 1.7881778057780454e+09 http_request_duration_seconds_created{handler="/",method="GET"} 1.788177896016718e+09 http_request_duration_seconds_created{handler="none",method="GET"} 1.7881779366155088e+09 http_request_duration_seconds_created{handler="/v1/conversationQA",method="POST"} 1.7881780498016236e+09 http_request_duration_seconds_created{handler="/docs",method="GET"} 1.7881785759412825e+09 http_request_duration_seconds_created{handler="/openapi.json",method="GET"} 1.7881785761002667e+09 http_request_duration_seconds_created{handler="/v1/drafting",method="POST"} 1.788178822397596e+09 http_request_duration_seconds_created{handler="none",method="HEAD"} 1.7881826985087175e+09 # HELP python_gc_objects_collected_total Objects collected during gc # TYPE python_gc_objects_collected_total counter python_gc_objects_collected_total{generation="0"} 359.0 python_gc_objects_collected_total{generation="1"} 0.0 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"} 35.0 python_gc_collections_total{generation="1"} 3.0 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="7",version="3.14.7"} 1.0 # HELP process_virtual_memory_bytes Virtual memory size in bytes. # TYPE process_virtual_memory_bytes gauge process_virtual_memory_bytes 3.76991744e+08 # HELP process_resident_memory_bytes Resident memory size in bytes. # TYPE process_resident_memory_bytes gauge process_resident_memory_bytes 5.216256e+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 1.78817773032e+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 2.16 # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge process_open_fds 7.0 # 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 0.0 # HELP busy_worker Number of successful calls # TYPE busy_worker gauge busy_worker 0.0