phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat - refactor prometheus metrics

Browse source
This commit is contained in:
Ishaan Jaff 2024-08-10 09:14:38 -07:00
parent f4355d3e88
commit 05fba48cec
1 changed files with 132 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

50
litellm/integrations/prometheus.py
View file

@ -15,9 +15,10 @@ import requests # type: ignore
import litellm
from litellm._logging import print_verbose, verbose_logger
from litellm.integrations.custom_logger import CustomLogger
class PrometheusLogger:
class PrometheusLogger(CustomLogger):
# Class variables or attributes
def __init__(
self,
@ -147,22 +148,12 @@ class PrometheusLogger:
print_verbose(f"Got exception on init prometheus client {str(e)}")
raise e
async def _async_log_event(
self, kwargs, response_obj, start_time, end_time, print_verbose, user_id
):
self.log_event(
kwargs, response_obj, start_time, end_time, user_id, print_verbose
)
def log_event(
self, kwargs, response_obj, start_time, end_time, user_id, print_verbose
):
try:
async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
# Define prometheus client
from litellm.proxy.proxy_server import premium_user
verbose_logger.debug(
f"prometheus Logging - Enters logging function for model {kwargs}"
f"prometheus Logging - Enters success logging function for kwargs {kwargs}"
)
# unpack kwargs
@ -171,9 +162,7 @@ class PrometheusLogger:
litellm_params = kwargs.get("litellm_params", {}) or {}
proxy_server_request = litellm_params.get("proxy_server_request") or {}
end_user_id = proxy_server_request.get("body", {}).get("user", None)
user_id = litellm_params.get("metadata", {}).get(
"user_api_key_user_id", None
)
user_id = litellm_params.get("metadata", {}).get("user_api_key_user_id", None)
user_api_key = litellm_params.get("metadata", {}).get("user_api_key", None)
user_api_key_alias = litellm_params.get("metadata", {}).get(
"user_api_key_alias", None
@ -262,9 +251,33 @@ class PrometheusLogger:
# set x-ratelimit headers
if premium_user is True:
self.set_llm_deployment_success_metrics(kwargs)
pass
### FAILURE INCREMENT ###
if "exception" in kwargs:
async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time):
from litellm.proxy.proxy_server import premium_user
verbose_logger.debug(
f"prometheus Logging - Enters success logging function for kwargs {kwargs}"
)
# unpack kwargs
model = kwargs.get("model", "")
litellm_params = kwargs.get("litellm_params", {}) or {}
proxy_server_request = litellm_params.get("proxy_server_request") or {}
end_user_id = proxy_server_request.get("body", {}).get("user", None)
user_id = litellm_params.get("metadata", {}).get("user_api_key_user_id", None)
user_api_key = litellm_params.get("metadata", {}).get("user_api_key", None)
user_api_key_alias = litellm_params.get("metadata", {}).get(
"user_api_key_alias", None
)
user_api_team = litellm_params.get("metadata", {}).get(
"user_api_key_team_id", None
)
user_api_team_alias = litellm_params.get("metadata", {}).get(
"user_api_key_team_alias", None
)
try:
self.litellm_llm_api_failed_requests_metric.labels(
end_user_id,
user_api_key,
@ -282,6 +295,7 @@ class PrometheusLogger:
)
verbose_logger.debug(traceback.format_exc())
pass
pass
def set_llm_deployment_failure_metrics(self, request_kwargs: dict):
try: