phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Litellm dev 12 06 2024 (#7067)

Browse source 
* fix(edit_budget_modal.tsx): call `/budget/update` endpoint instead of `/budget/new`

allows updating existing budget on ui

* fix(user_api_key_auth.py): support cost tracking for end user via jwt field

* fix(presidio.py): support pii masking on sync logging callbacks

enables masking before logging to langfuse

* feat(utils.py): support retry policy logic inside '.completion()'

Fixes https://github.com/BerriAI/litellm/issues/6623

* fix(utils.py): support retry by retry policy on async logic as well

* fix(handle_jwt.py): set leeway default leeway value

* test: fix test to handle jwt audience claim
This commit is contained in:
Krish Dholakia 2024-12-06 22:44:18 -08:00 • committed by GitHub
parent ba1e6fe7b7
commit e4493248ae
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 498 additions and 498 deletions
Download patch file Download diff file Expand all files Collapse all files

19
litellm/utils.py
View file

@ -97,6 +97,10 @@ from litellm.litellm_core_utils.rules import Rules
from litellm.litellm_core_utils.streaming_handler import CustomStreamWrapper
from litellm.litellm_core_utils.token_counter import get_modified_max_tokens
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
from litellm.router_utils.get_retry_from_policy import (
get_num_retries_from_retry_policy,
reset_retry_policy,
)
from litellm.secret_managers.main import get_secret
from litellm.types.llms.openai import (
AllMessageValues,
@ -918,6 +922,14 @@ def client(original_function): # noqa: PLR0915
num_retries = (
kwargs.get("num_retries", None) or litellm.num_retries or None
)
if kwargs.get("retry_policy", None):
num_retries = get_num_retries_from_retry_policy(
exception=e,
retry_policy=kwargs.get("retry_policy"),
)
kwargs["retry_policy"] = (
reset_retry_policy()
) # prevent infinite loops
litellm.num_retries = (
None # set retries to None to prevent infinite loops
)
@ -1137,6 +1149,13 @@ def client(original_function): # noqa: PLR0915
num_retries = (
kwargs.get("num_retries", None) or litellm.num_retries or None
)
if kwargs.get("retry_policy", None):
num_retries = get_num_retries_from_retry_policy(
exception=e,
retry_policy=kwargs.get("retry_policy"),
)
kwargs["retry_policy"] = reset_retry_policy()
litellm.num_retries = (
None # set retries to None to prevent infinite loops
)