gistfile1.txt

# HELP python_gc_objects_collected_total Objects collected during gc
# TYPE python_gc_objects_collected_total counter
python_gc_objects_collected_total{generation="0"} 4894.0
python_gc_objects_collected_total{generation="1"} 4412.0
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"} 1076.0
python_gc_collections_total{generation="1"} 97.0
python_gc_collections_total{generation="2"} 7.0
# HELP python_info Python platform information
# TYPE python_info gauge
python_info{implementation="CPython",major="3",minor="10",patchlevel="12",version="3.10.12"} 1.0
# HELP process_virtual_memory_bytes Virtual memory size in bytes.
# TYPE process_virtual_memory_bytes gauge
process_virtual_memory_bytes 6.677041152e+09
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 7.7479936e+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 1.72704844865e+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 149.74
# HELP process_open_fds Number of open file descriptors.
# TYPE process_open_fds gauge
process_open_fds 18.0
# HELP process_max_fds Maximum number of open file descriptors.
# TYPE process_max_fds gauge
process_max_fds 1.073741816e+09
# HELP http_requests_total Total number of requests by method, status and handler.
# TYPE http_requests_total counter
http_requests_total{handler="/health",method="GET",status="2xx"} 131.0
http_requests_total{handler="/metrics",method="GET",status="2xx"} 97.0
http_requests_total{handler="/v1/embeddings",method="POST",status="2xx"} 6.0
http_requests_total{handler="/",method="GET",status="3xx"} 1.0
http_requests_total{handler="none",method="GET",status="4xx"} 2.0
# HELP http_requests_created Total number of requests by method, status and handler.
# TYPE http_requests_created gauge
http_requests_created{handler="/health",method="GET",status="2xx"} 1.7270485140999904e+09
http_requests_created{handler="/metrics",method="GET",status="2xx"} 1.7270485191270738e+09
http_requests_created{handler="/v1/embeddings",method="POST",status="2xx"} 1.7270487580816634e+09
http_requests_created{handler="/",method="GET",status="3xx"} 1.7270494824645836e+09
http_requests_created{handler="none",method="GET",status="4xx"} 1.7270494824819798e+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="/health"} 131.0
http_request_size_bytes_sum{handler="/health"} 0.0
http_request_size_bytes_count{handler="/metrics"} 97.0
http_request_size_bytes_sum{handler="/metrics"} 0.0
http_request_size_bytes_count{handler="/v1/embeddings"} 6.0
http_request_size_bytes_sum{handler="/v1/embeddings"} 492.0
http_request_size_bytes_count{handler="/"} 1.0
http_request_size_bytes_sum{handler="/"} 0.0
http_request_size_bytes_count{handler="none"} 2.0
http_request_size_bytes_sum{handler="none"} 0.0
# 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="/health"} 1.7270485141000242e+09
http_request_size_bytes_created{handler="/metrics"} 1.7270485191270907e+09
http_request_size_bytes_created{handler="/v1/embeddings"} 1.7270487580816946e+09
http_request_size_bytes_created{handler="/"} 1.7270494824646134e+09
http_request_size_bytes_created{handler="none"} 1.7270494824820092e+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="/health"} 131.0
http_response_size_bytes_sum{handler="/health"} 3509.0
http_response_size_bytes_count{handler="/metrics"} 97.0
http_response_size_bytes_sum{handler="/metrics"} 813896.0
http_response_size_bytes_count{handler="/v1/embeddings"} 6.0
http_response_size_bytes_sum{handler="/v1/embeddings"} 13650.0
http_response_size_bytes_count{handler="/"} 1.0
http_response_size_bytes_sum{handler="/"} 0.0
http_response_size_bytes_count{handler="none"} 2.0
http_response_size_bytes_sum{handler="none"} 44.0
# 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="/health"} 1.7270485141000576e+09
http_response_size_bytes_created{handler="/metrics"} 1.7270485191271157e+09
http_response_size_bytes_created{handler="/v1/embeddings"} 1.7270487580817313e+09
http_response_size_bytes_created{handler="/"} 1.727049482464646e+09
http_response_size_bytes_created{handler="none"} 1.7270494824820526e+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"} 231.0
http_request_duration_highr_seconds_bucket{le="0.025"} 231.0
http_request_duration_highr_seconds_bucket{le="0.05"} 235.0
http_request_duration_highr_seconds_bucket{le="0.075"} 237.0
http_request_duration_highr_seconds_bucket{le="0.1"} 237.0
http_request_duration_highr_seconds_bucket{le="0.25"} 237.0
http_request_duration_highr_seconds_bucket{le="0.5"} 237.0
http_request_duration_highr_seconds_bucket{le="0.75"} 237.0
http_request_duration_highr_seconds_bucket{le="1.0"} 237.0
http_request_duration_highr_seconds_bucket{le="1.5"} 237.0
http_request_duration_highr_seconds_bucket{le="2.0"} 237.0
http_request_duration_highr_seconds_bucket{le="2.5"} 237.0
http_request_duration_highr_seconds_bucket{le="3.0"} 237.0
http_request_duration_highr_seconds_bucket{le="3.5"} 237.0
http_request_duration_highr_seconds_bucket{le="4.0"} 237.0
http_request_duration_highr_seconds_bucket{le="4.5"} 237.0
http_request_duration_highr_seconds_bucket{le="5.0"} 237.0
http_request_duration_highr_seconds_bucket{le="7.5"} 237.0
http_request_duration_highr_seconds_bucket{le="10.0"} 237.0
http_request_duration_highr_seconds_bucket{le="30.0"} 237.0
http_request_duration_highr_seconds_bucket{le="60.0"} 237.0
http_request_duration_highr_seconds_bucket{le="+Inf"} 237.0
http_request_duration_highr_seconds_count 237.0
http_request_duration_highr_seconds_sum 0.6785663773771375
# 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 1.72704845757815e+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="/health",le="0.1",method="GET"} 131.0
http_request_duration_seconds_bucket{handler="/health",le="0.5",method="GET"} 131.0
http_request_duration_seconds_bucket{handler="/health",le="1.0",method="GET"} 131.0
http_request_duration_seconds_bucket{handler="/health",le="+Inf",method="GET"} 131.0
http_request_duration_seconds_count{handler="/health",method="GET"} 131.0
http_request_duration_seconds_sum{handler="/health",method="GET"} 0.09874389204196632
http_request_duration_seconds_bucket{handler="/metrics",le="0.1",method="GET"} 97.0
http_request_duration_seconds_bucket{handler="/metrics",le="0.5",method="GET"} 97.0
http_request_duration_seconds_bucket{handler="/metrics",le="1.0",method="GET"} 97.0
http_request_duration_seconds_bucket{handler="/metrics",le="+Inf",method="GET"} 97.0
http_request_duration_seconds_count{handler="/metrics",method="GET"} 97.0
http_request_duration_seconds_sum{handler="/metrics",method="GET"} 0.3161639932077378
http_request_duration_seconds_bucket{handler="/v1/embeddings",le="0.1",method="POST"} 6.0
http_request_duration_seconds_bucket{handler="/v1/embeddings",le="0.5",method="POST"} 6.0
http_request_duration_seconds_bucket{handler="/v1/embeddings",le="1.0",method="POST"} 6.0
http_request_duration_seconds_bucket{handler="/v1/embeddings",le="+Inf",method="POST"} 6.0
http_request_duration_seconds_count{handler="/v1/embeddings",method="POST"} 6.0
http_request_duration_seconds_sum{handler="/v1/embeddings",method="POST"} 0.26152810524217784
http_request_duration_seconds_bucket{handler="/",le="0.1",method="GET"} 1.0
http_request_duration_seconds_bucket{handler="/",le="0.5",method="GET"} 1.0
http_request_duration_seconds_bucket{handler="/",le="1.0",method="GET"} 1.0
http_request_duration_seconds_bucket{handler="/",le="+Inf",method="GET"} 1.0
http_request_duration_seconds_count{handler="/",method="GET"} 1.0
http_request_duration_seconds_sum{handler="/",method="GET"} 0.0005076099187135696
http_request_duration_seconds_bucket{handler="none",le="0.1",method="GET"} 2.0
http_request_duration_seconds_bucket{handler="none",le="0.5",method="GET"} 2.0
http_request_duration_seconds_bucket{handler="none",le="1.0",method="GET"} 2.0
http_request_duration_seconds_bucket{handler="none",le="+Inf",method="GET"} 2.0
http_request_duration_seconds_count{handler="none",method="GET"} 2.0
http_request_duration_seconds_sum{handler="none",method="GET"} 0.0016227769665420055
# 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="/health",method="GET"} 1.7270485141001017e+09
http_request_duration_seconds_created{handler="/metrics",method="GET"} 1.727048519127144e+09
http_request_duration_seconds_created{handler="/v1/embeddings",method="POST"} 1.7270487580817761e+09
http_request_duration_seconds_created{handler="/",method="GET"} 1.7270494824646876e+09
http_request_duration_seconds_created{handler="none",method="GET"} 1.7270494824820902e+09