phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #5358 from BerriAI/litellm_fix_retry_after

Browse source 
fix retry after - cooldown individual models based on their specific 'retry-after' header
This commit is contained in:
Krish Dholakia 2024-08-27 11:50:14 -07:00 • committed by GitHub
commit 415abc86c6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 754 additions and 202 deletions
Download patch file Download diff file Expand all files Collapse all files

13
litellm/tests/test_completion.py
View file

@ -1635,18 +1635,19 @@ def test_completion_perplexity_api():
pydantic_obj = ChatCompletion(**response_object)
def _return_pydantic_obj(*args, **kwargs):
return pydantic_obj
new_response = MagicMock()
new_response.headers = {"hello": "world"}
print(f"pydantic_obj: {pydantic_obj}")
new_response.parse.return_value = pydantic_obj
return new_response
openai_client = OpenAI()
openai_client.chat.completions.create = MagicMock()
with patch.object(
openai_client.chat.completions, "create", side_effect=_return_pydantic_obj
openai_client.chat.completions.with_raw_response,
"create",
side_effect=_return_pydantic_obj,
) as mock_client:
pass
# litellm.set_verbose= True
messages = [
{"role": "system", "content": "You're a good bot"},