phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[Feat] Emit Key, Team Budget metrics on a cron job schedule (#9528)

Browse source 
* _initialize_remaining_budget_metrics

* initialize_budget_metrics_cron_job

* initialize_budget_metrics_cron_job

* initialize_budget_metrics_cron_job

* test_initialize_budget_metrics_cron_job

* LITELLM_PROXY_ADMIN_NAME

* fix code qa checks

* test_initialize_budget_metrics_cron_job

* test_initialize_budget_metrics_cron_job

* pod lock manager allow dynamic cron job ID

* fix pod lock manager

* require cronjobid for PodLockManager

* fix DB_SPEND_UPDATE_JOB_NAME acquire / release lock

* add comment on prometheus logger

* add debug statements for emitting key, team budget metrics

* test_pod_lock_manager.py

* test_initialize_budget_metrics_cron_job

* initialize_budget_metrics_cron_job

* initialize_remaining_budget_metrics

* remove outdated test
This commit is contained in:
Ishaan Jaff 2025-04-10 16:59:14 -07:00 • committed by GitHub
parent 557a2ca102
commit 4c85e13226
10 changed files with 346 additions and 142 deletions
Download patch file Download diff file Expand all files Collapse all files

29
litellm/proxy/proxy_server.py
View file

@ -803,9 +803,9 @@ model_max_budget_limiter = _PROXY_VirtualKeyModelMaxBudgetLimiter(
dual_cache=user_api_key_cache
)
litellm.logging_callback_manager.add_litellm_callback(model_max_budget_limiter)
redis_usage_cache: Optional[
RedisCache
] = None # redis cache used for tracking spend, tpm/rpm limits
redis_usage_cache: Optional[RedisCache] = (
None # redis cache used for tracking spend, tpm/rpm limits
)
user_custom_auth = None
user_custom_key_generate = None
user_custom_sso = None
@ -1131,9 +1131,9 @@ async def update_cache( # noqa: PLR0915
_id = "team_id:{}".format(team_id)
try:
# Fetch the existing cost for the given user
existing_spend_obj: Optional[
LiteLLM_TeamTable
] = await user_api_key_cache.async_get_cache(key=_id)
existing_spend_obj: Optional[LiteLLM_TeamTable] = (
await user_api_key_cache.async_get_cache(key=_id)
)
if existing_spend_obj is None:
# do nothing if team not in api key cache
return
@ -2812,9 +2812,9 @@ async def initialize( # noqa: PLR0915
user_api_base = api_base
dynamic_config[user_model]["api_base"] = api_base
if api_version:
os.environ[
"AZURE_API_VERSION"
] = api_version # set this for azure - litellm can read this from the env
os.environ["AZURE_API_VERSION"] = (
api_version # set this for azure - litellm can read this from the env
)
if max_tokens: # model-specific param
dynamic_config[user_model]["max_tokens"] = max_tokens
if temperature: # model-specific param
@ -3191,6 +3191,11 @@ class ProxyStartupEvent:
)
await proxy_logging_obj.slack_alerting_instance.send_fallback_stats_from_prometheus()
if litellm.prometheus_initialize_budget_metrics is True:
from litellm.integrations.prometheus import PrometheusLogger
PrometheusLogger.initialize_budget_metrics_cron_job(scheduler=scheduler)
scheduler.start()
@classmethod
@ -7753,9 +7758,9 @@ async def get_config_list(
hasattr(sub_field_info, "description")
and sub_field_info.description is not None
):
nested_fields[
idx
].field_description = sub_field_info.description
nested_fields[idx].field_description = (
sub_field_info.description
)
idx += 1
_stored_in_db = None