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(proxy_server.py): support max budget on proxy

Browse source
This commit is contained in:
Krrish Dholakia 2023-12-21 16:07:20 +05:30
parent 14115d0d60
commit 1a32228da5
5 changed files with 66 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/proxy/utils.py
View file

@ -4,6 +4,7 @@ import litellm, backoff
from litellm.proxy._types import UserAPIKeyAuth
from litellm.caching import DualCache
from litellm.proxy.hooks.parallel_request_limiter import MaxParallelRequestsHandler
from litellm.proxy.hooks.max_budget_limiter import MaxBudgetLimiter
from litellm.integrations.custom_logger import CustomLogger
def print_verbose(print_statement):
if litellm.set_verbose:
@ -23,11 +24,13 @@ class ProxyLogging:
self.call_details: dict = {}
self.call_details["user_api_key_cache"] = user_api_key_cache
self.max_parallel_request_limiter = MaxParallelRequestsHandler()
self.max_budget_limiter = MaxBudgetLimiter()
pass
def _init_litellm_callbacks(self):
print_verbose(f"INITIALIZING LITELLM CALLBACKS!")
litellm.callbacks.append(self.max_parallel_request_limiter)
litellm.callbacks.append(self.max_budget_limiter)
for callback in litellm.callbacks:
if callback not in litellm.input_callback:
litellm.input_callback.append(callback)
@ -203,7 +206,6 @@ class PrismaClient:
hashed_token = self.hash_token(token=token)
db_data = self.jsonify_object(data=data)
db_data["token"] = hashed_token
new_verification_token = await self.db.litellm_verificationtoken.upsert( # type: ignore
where={
'token': hashed_token,