# HELP python_gc_objects_collected_total Objects collected during gc
# TYPE python_gc_objects_collected_total counter
python_gc_objects_collected_total{generation="0"} 819226.0
python_gc_objects_collected_total{generation="1"} 75164.0
python_gc_objects_collected_total{generation="2"} 1244.0
# 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"} 761.0
python_gc_collections_total{generation="1"} 69.0
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="6",version="3.14.6"} 1.0
# HELP process_virtual_memory_bytes Virtual memory size in bytes.
# TYPE process_virtual_memory_bytes gauge
process_virtual_memory_bytes 6.13707776e+08
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 2.31694336e+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 1.79195798494e+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 1479.67
# HELP process_open_fds Number of open file descriptors.
# TYPE process_open_fds gauge
process_open_fds 25.0
# 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"} 13340.0
http_requests_total{handler="/",method="GET",status="2xx"} 4.0
http_requests_total{handler="none",method="GET",status="4xx"} 112.0
http_requests_total{handler="/v1/logs",method="GET",status="4xx"} 13.0
http_requests_total{handler="/v1/conversationQA",method="POST",status="2xx"} 102.0
http_requests_total{handler="/v1/conversationQA",method="POST",status="4xx"} 34.0
http_requests_total{handler="/v1/logs",method="GET",status="2xx"} 2.0
http_requests_total{handler="/v1/qa",method="POST",status="2xx"} 3.0
http_requests_total{handler="/v1/drafting",method="POST",status="2xx"} 3.0
# 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"} 1.791958074847243e+09
http_requests_created{handler="/",method="GET",status="2xx"} 1.791965184201848e+09
http_requests_created{handler="none",method="GET",status="4xx"} 1.7919651842640061e+09
http_requests_created{handler="/v1/logs",method="GET",status="4xx"} 1.791970138743012e+09
http_requests_created{handler="/v1/conversationQA",method="POST",status="2xx"} 1.792028366928785e+09
http_requests_created{handler="/v1/conversationQA",method="POST",status="4xx"} 1.7921306923736432e+09
http_requests_created{handler="/v1/logs",method="GET",status="2xx"} 1.7924715890934997e+09
http_requests_created{handler="/v1/qa",method="POST",status="2xx"} 1.792471592115282e+09
http_requests_created{handler="/v1/drafting",method="POST",status="2xx"} 1.7930006267041383e+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"} 13340.0
http_request_size_bytes_sum{handler="/metrics"} 0.0
http_request_size_bytes_count{handler="/"} 4.0
http_request_size_bytes_sum{handler="/"} 0.0
http_request_size_bytes_count{handler="none"} 112.0
http_request_size_bytes_sum{handler="none"} 0.0
http_request_size_bytes_count{handler="/v1/logs"} 15.0
http_request_size_bytes_sum{handler="/v1/logs"} 0.0
http_request_size_bytes_count{handler="/v1/conversationQA"} 136.0
http_request_size_bytes_sum{handler="/v1/conversationQA"} 540109.0
http_request_size_bytes_count{handler="/v1/qa"} 3.0
http_request_size_bytes_sum{handler="/v1/qa"} 231.0
http_request_size_bytes_count{handler="/v1/drafting"} 3.0
http_request_size_bytes_sum{handler="/v1/drafting"} 974.0
# 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"} 1.7919580748472617e+09
http_request_size_bytes_created{handler="/"} 1.7919651842018628e+09
http_request_size_bytes_created{handler="none"} 1.7919651842640178e+09
http_request_size_bytes_created{handler="/v1/logs"} 1.7919701387430265e+09
http_request_size_bytes_created{handler="/v1/conversationQA"} 1.792028366928804e+09
http_request_size_bytes_created{handler="/v1/qa"} 1.7924715921152997e+09
http_request_size_bytes_created{handler="/v1/drafting"} 1.7930006267041523e+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"} 13340.0
http_response_size_bytes_sum{handler="/metrics"} 1.90323995e+08
http_response_size_bytes_count{handler="/"} 4.0
http_response_size_bytes_sum{handler="/"} 6984.0
http_response_size_bytes_count{handler="none"} 112.0
http_response_size_bytes_sum{handler="none"} 2464.0
http_response_size_bytes_count{handler="/v1/logs"} 15.0
http_response_size_bytes_sum{handler="/v1/logs"} 14016.0
http_response_size_bytes_count{handler="/v1/conversationQA"} 136.0
http_response_size_bytes_sum{handler="/v1/conversationQA"} 132359.0
http_response_size_bytes_count{handler="/v1/qa"} 3.0
http_response_size_bytes_sum{handler="/v1/qa"} 1938.0
http_response_size_bytes_count{handler="/v1/drafting"} 3.0
http_response_size_bytes_sum{handler="/v1/drafting"} 1159.0
# 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"} 1.7919580748472862e+09
http_response_size_bytes_created{handler="/"} 1.7919651842018793e+09
http_response_size_bytes_created{handler="none"} 1.7919651842640328e+09
http_response_size_bytes_created{handler="/v1/logs"} 1.7919701387430482e+09
http_response_size_bytes_created{handler="/v1/conversationQA"} 1.792028366928824e+09
http_response_size_bytes_created{handler="/v1/qa"} 1.792471592115325e+09
http_response_size_bytes_created{handler="/v1/drafting"} 1.7930006267041736e+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"} 145.0
http_request_duration_highr_seconds_bucket{le="0.025"} 12869.0
http_request_duration_highr_seconds_bucket{le="0.05"} 13484.0
http_request_duration_highr_seconds_bucket{le="0.075"} 13485.0
http_request_duration_highr_seconds_bucket{le="0.1"} 13486.0
http_request_duration_highr_seconds_bucket{le="0.25"} 13486.0
http_request_duration_highr_seconds_bucket{le="0.5"} 13486.0
http_request_duration_highr_seconds_bucket{le="0.75"} 13487.0
http_request_duration_highr_seconds_bucket{le="1.0"} 13488.0
http_request_duration_highr_seconds_bucket{le="1.5"} 13490.0
http_request_duration_highr_seconds_bucket{le="2.0"} 13494.0
http_request_duration_highr_seconds_bucket{le="2.5"} 13502.0
http_request_duration_highr_seconds_bucket{le="3.0"} 13512.0
http_request_duration_highr_seconds_bucket{le="3.5"} 13520.0
http_request_duration_highr_seconds_bucket{le="4.0"} 13536.0
http_request_duration_highr_seconds_bucket{le="4.5"} 13553.0
http_request_duration_highr_seconds_bucket{le="5.0"} 13558.0
http_request_duration_highr_seconds_bucket{le="7.5"} 13594.0
http_request_duration_highr_seconds_bucket{le="10.0"} 13610.0
http_request_duration_highr_seconds_bucket{le="30.0"} 13612.0
http_request_duration_highr_seconds_bucket{le="60.0"} 13612.0
http_request_duration_highr_seconds_bucket{le="+Inf"} 13613.0
http_request_duration_highr_seconds_count 13613.0
http_request_duration_highr_seconds_sum 826.1131852585833
# 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 1.7919580234455743e+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"} 13340.0
http_request_duration_seconds_bucket{handler="/metrics",le="0.5",method="GET"} 13340.0
http_request_duration_seconds_bucket{handler="/metrics",le="1.0",method="GET"} 13340.0
http_request_duration_seconds_bucket{handler="/metrics",le="+Inf",method="GET"} 13340.0
http_request_duration_seconds_count{handler="/metrics",method="GET"} 13340.0
http_request_duration_seconds_sum{handler="/metrics",method="GET"} 155.44167294366446
http_request_duration_seconds_bucket{handler="/",le="0.1",method="GET"} 4.0
http_request_duration_seconds_bucket{handler="/",le="0.5",method="GET"} 4.0
http_request_duration_seconds_bucket{handler="/",le="1.0",method="GET"} 4.0
http_request_duration_seconds_bucket{handler="/",le="+Inf",method="GET"} 4.0
http_request_duration_seconds_count{handler="/",method="GET"} 4.0
http_request_duration_seconds_sum{handler="/",method="GET"} 0.0032480249428772368
http_request_duration_seconds_bucket{handler="none",le="0.1",method="GET"} 112.0
http_request_duration_seconds_bucket{handler="none",le="0.5",method="GET"} 112.0
http_request_duration_seconds_bucket{handler="none",le="1.0",method="GET"} 112.0
http_request_duration_seconds_bucket{handler="none",le="+Inf",method="GET"} 112.0
http_request_duration_seconds_count{handler="none",method="GET"} 112.0
http_request_duration_seconds_sum{handler="none",method="GET"} 0.1606783292008913
http_request_duration_seconds_bucket{handler="/v1/logs",le="0.1",method="GET"} 15.0
http_request_duration_seconds_bucket{handler="/v1/logs",le="0.5",method="GET"} 15.0
http_request_duration_seconds_bucket{handler="/v1/logs",le="1.0",method="GET"} 15.0
http_request_duration_seconds_bucket{handler="/v1/logs",le="+Inf",method="GET"} 15.0
http_request_duration_seconds_count{handler="/v1/logs",method="GET"} 15.0
http_request_duration_seconds_sum{handler="/v1/logs",method="GET"} 0.11836145611596294
http_request_duration_seconds_bucket{handler="/v1/conversationQA",le="0.1",method="POST"} 15.0
http_request_duration_seconds_bucket{handler="/v1/conversationQA",le="0.5",method="POST"} 15.0
http_request_duration_seconds_bucket{handler="/v1/conversationQA",le="1.0",method="POST"} 17.0
http_request_duration_seconds_bucket{handler="/v1/conversationQA",le="+Inf",method="POST"} 136.0
http_request_duration_seconds_count{handler="/v1/conversationQA",method="POST"} 136.0
http_request_duration_seconds_sum{handler="/v1/conversationQA",method="POST"} 645.9823712696816
http_request_duration_seconds_bucket{handler="/v1/qa",le="0.1",method="POST"} 0.0
http_request_duration_seconds_bucket{handler="/v1/qa",le="0.5",method="POST"} 0.0
http_request_duration_seconds_bucket{handler="/v1/qa",le="1.0",method="POST"} 0.0
http_request_duration_seconds_bucket{handler="/v1/qa",le="+Inf",method="POST"} 3.0
http_request_duration_seconds_count{handler="/v1/qa",method="POST"} 3.0
http_request_duration_seconds_sum{handler="/v1/qa",method="POST"} 13.053628161782399
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"} 0.0
http_request_duration_seconds_bucket{handler="/v1/drafting",le="+Inf",method="POST"} 3.0
http_request_duration_seconds_count{handler="/v1/drafting",method="POST"} 3.0
http_request_duration_seconds_sum{handler="/v1/drafting",method="POST"} 11.353225073195063
# 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"} 1.791958074847313e+09
http_request_duration_seconds_created{handler="/",method="GET"} 1.7919651842019057e+09
http_request_duration_seconds_created{handler="none",method="GET"} 1.7919651842640553e+09
http_request_duration_seconds_created{handler="/v1/logs",method="GET"} 1.7919701387430747e+09
http_request_duration_seconds_created{handler="/v1/conversationQA",method="POST"} 1.7920283669288545e+09
http_request_duration_seconds_created{handler="/v1/qa",method="POST"} 1.7924715921153607e+09
http_request_duration_seconds_created{handler="/v1/drafting",method="POST"} 1.793000626704202e+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="6",version="3.14.6"} 1.0
# HELP process_virtual_memory_bytes Virtual memory size in bytes.
# TYPE process_virtual_memory_bytes gauge
process_virtual_memory_bytes 3.72998144e+08
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 4.982784e+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 1.79195798374e+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 187.94
# 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
# HELP values_qa EMA gauge for qa
# TYPE values_qa gauge
values_qa 0.0014955026501348569