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

fix(main.py): fix retries being multiplied when using openai sdk (#7221)

Browse source 
* fix(main.py): fix retries being multiplied when using openai sdk

Closes https://github.com/BerriAI/litellm/pull/7130

* docs(prompt_management.md): add langfuse prompt management doc

* feat(team_endpoints.py): allow teams to add their own models

Enables teams to call their own finetuned models via the proxy

* test: add better enforcement check testing for `/model/new` now that teams can add their own models

* docs(team_model_add.md): tutorial for allowing teams to add their own models

* test: fix test
This commit is contained in:
Krish Dholakia 2024-12-14 11:56:55 -08:00 • committed by GitHub
parent 8060c5c698
commit ec36353b41
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 2439 additions and 1540 deletions
Download patch file Download diff file Expand all files Collapse all files

35
tests/local_testing/test_completion_with_retries.py
View file

@ -11,7 +11,7 @@ sys.path.insert(
import pytest
import openai
import litellm
from litellm import completion_with_retries, completion
from litellm import completion_with_retries, completion, acompletion_with_retries
from litellm import (
AuthenticationError,
BadRequestError,
@ -113,3 +113,36 @@ async def test_completion_with_retry_policy_no_error(sync_mode):
await completion(**data)
except Exception as e:
print(e)
@pytest.mark.parametrize("sync_mode", [True, False])
@pytest.mark.asyncio
async def test_completion_with_retries(sync_mode):
"""
If completion_with_retries is called with num_retries=3, and max_retries=0, then litellm.completion should receive num_retries , max_retries=0
"""
from unittest.mock import patch, MagicMock, AsyncMock
if sync_mode:
target_function = "completion"
else:
target_function = "acompletion"
with patch.object(litellm, target_function) as mock_completion:
if sync_mode:
completion_with_retries(
model="gpt-3.5-turbo",
messages=[{"gm": "vibe", "role": "user"}],
num_retries=3,
original_function=mock_completion,
)
else:
await acompletion_with_retries(
model="gpt-3.5-turbo",
messages=[{"gm": "vibe", "role": "user"}],
num_retries=3,
original_function=mock_completion,
)
mock_completion.assert_called_once()
assert mock_completion.call_args.kwargs["num_retries"] == 0
assert mock_completion.call_args.kwargs["max_retries"] == 0