scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

fix(prometheus.py): fix metrics

Browse source
This commit is contained in:
Krrish Dholakia 2025-06-19 15:30:06 -07:00
parent 649636b26b
commit b05742e814
2 changed files with 15 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
litellm/integrations/prometheus.py
View file

@ -215,40 +215,25 @@ class PrometheusLogger(CustomLogger):
self.litellm_remaining_requests_metric = self._gauge_factory(
"litellm_remaining_requests",
"LLM Deployment Analytics - remaining requests for model, returned from LLM API Provider",
labelnames=[
"model_group",
"api_provider",
"api_base",
"litellm_model_name",
"hashed_api_key",
"api_key_alias",
],
labelnames=self.get_labels_for_metric(
"litellm_remaining_requests_metric"
),
)
self.litellm_remaining_tokens_metric = self._gauge_factory(
"litellm_remaining_tokens",
"remaining tokens for model, returned from LLM API Provider",
labelnames=[
"model_group",
"api_provider",
"api_base",
"litellm_model_name",
"hashed_api_key",
"api_key_alias",
],
labelnames=self.get_labels_for_metric(
"litellm_remaining_tokens_metric"
),
)
self.litellm_overhead_latency_metric = self._histogram_factory(
"litellm_overhead_latency_metric",
"Latency overhead (milliseconds) added by LiteLLM processing",
labelnames=[
"model_group",
"api_provider",
"api_base",
"litellm_model_name",
"hashed_api_key",
"api_key_alias",
],
labelnames=self.get_labels_for_metric(
"litellm_overhead_latency_metric"
),
buckets=LATENCY_BUCKETS,
)
# llm api provider budget metrics
@ -1160,6 +1145,7 @@ class PrometheusLogger(CustomLogger):
enum_values: UserAPIKeyLabelValues,
output_tokens: float = 1.0,
):
try:
verbose_logger.debug("setting remaining tokens requests metric")
standard_logging_payload: Optional[StandardLoggingPayload] = (
@ -1292,7 +1278,7 @@ class PrometheusLogger(CustomLogger):
).observe(latency_per_token)
except Exception as e:
verbose_logger.error(
verbose_logger.exception(
"Prometheus Error: set_llm_deployment_success_metrics. Exception occured - {}".format(
str(e)
)

7
litellm/types/integrations/prometheus.py
View file

@ -71,6 +71,7 @@ class UserAPIKeyLabelNames(Enum):
STATUS_CODE = "status_code"
FALLBACK_MODEL = "fallback_model"
ROUTE = "route"
MODEL_GROUP = "model_group"
DEFINED_PROMETHEUS_METRICS = Literal[
@ -161,7 +162,7 @@ class PrometheusMetricLabels:
]
litellm_overhead_latency_metric = [
UserAPIKeyLabelNames.REQUESTED_MODEL.value,
UserAPIKeyLabelNames.MODEL_GROUP.value,
UserAPIKeyLabelNames.API_PROVIDER.value,
UserAPIKeyLabelNames.API_BASE.value,
UserAPIKeyLabelNames.v2_LITELLM_MODEL_NAME.value,
@ -170,7 +171,7 @@ class PrometheusMetricLabels:
]
litellm_remaining_requests_metric = [
UserAPIKeyLabelNames.REQUESTED_MODEL.value,
UserAPIKeyLabelNames.MODEL_GROUP.value,
UserAPIKeyLabelNames.API_PROVIDER.value,
UserAPIKeyLabelNames.API_BASE.value,
UserAPIKeyLabelNames.v2_LITELLM_MODEL_NAME.value,
@ -179,7 +180,7 @@ class PrometheusMetricLabels:
]
litellm_remaining_tokens_metric = [
UserAPIKeyLabelNames.REQUESTED_MODEL.value,
UserAPIKeyLabelNames.MODEL_GROUP.value,
UserAPIKeyLabelNames.API_PROVIDER.value,
UserAPIKeyLabelNames.API_BASE.value,
UserAPIKeyLabelNames.v2_LITELLM_MODEL_NAME.value,