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

LiteLLM Minor Fixes & Improvements (09/21/2024) (#5819)

Browse source 
* fix(router.py): fix error message

* Litellm disable keys (#5814)

* build(schema.prisma): allow blocking/unblocking keys

Fixes https://github.com/BerriAI/litellm/issues/5328

* fix(key_management_endpoints.py): fix pop

* feat(auth_checks.py): allow admin to enable/disable virtual keys

Closes https://github.com/BerriAI/litellm/issues/5328

* docs(vertex.md): add auth section for vertex ai

Addresses - https://github.com/BerriAI/litellm/issues/5768#issuecomment-2365284223

* build(model_prices_and_context_window.json): show which models support prompt_caching

Closes https://github.com/BerriAI/litellm/issues/5776

* fix(router.py): allow setting default priority for requests

* fix(router.py): add 'retry-after' header for concurrent request limit errors

Fixes https://github.com/BerriAI/litellm/issues/5783

* fix(router.py): correctly raise and use retry-after header from azure+openai

Fixes https://github.com/BerriAI/litellm/issues/5783

* fix(user_api_key_auth.py): fix valid token being none

* fix(auth_checks.py): fix model dump for cache management object

* fix(user_api_key_auth.py): pass prisma_client to obj

* test(test_otel.py): update test for new key check

* test: fix test
This commit is contained in:
Krish Dholakia 2024-09-21 18:51:53 -07:00 • committed by GitHub
parent 1ca638973f
commit 8039b95aaf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
25 changed files with 1006 additions and 182 deletions
Download patch file Download diff file Expand all files Collapse all files

40
litellm/tests/test_exceptions.py
View file

@ -910,6 +910,7 @@ async def test_exception_with_headers(sync_mode, provider, model, call_type, str
{"message": "litellm.proxy.proxy_server.embeddings(): Exception occured - No deployments available for selected model, Try again in 60 seconds. Passed model=text-embedding-ada-002. pre-call-checks=False, allowed_model_region=n/a, cooldown_list=[('b49cbc9314273db7181fe69b1b19993f04efb88f2c1819947c538bac08097e4c', {'Exception Received': 'litellm.RateLimitError: AzureException RateLimitError - Requests to the Embeddings_Create Operation under Azure OpenAI API version 2023-09-01-preview have exceeded call rate limit of your current OpenAI S0 pricing tier. Please retry after 9 seconds. Please go here: https://aka.ms/oai/quotaincrease if you would like to further increase the default rate limit.', 'Status Code': '429'})]", "level": "ERROR", "timestamp": "2024-08-22T03:25:36.900476"}
```
"""
print(f"Received args: {locals()}")
import openai
if sync_mode:
@ -939,13 +940,38 @@ async def test_exception_with_headers(sync_mode, provider, model, call_type, str
cooldown_time = 30.0
def _return_exception(*args, **kwargs):
from fastapi import HTTPException
import datetime
raise HTTPException(
status_code=429,
detail="Rate Limited!",
headers={"retry-after": cooldown_time}, # type: ignore
)
from httpx import Headers, Request, Response
kwargs = {
"request": Request("POST", "https://www.google.com"),
"message": "Error code: 429 - Rate Limit Error!",
"body": {"detail": "Rate Limit Error!"},
"code": None,
"param": None,
"type": None,
"response": Response(
status_code=429,
headers=Headers(
{
"date": "Sat, 21 Sep 2024 22:56:53 GMT",
"server": "uvicorn",
"retry-after": "30",
"content-length": "30",
"content-type": "application/json",
}
),
request=Request("POST", "http://0.0.0.0:9000/chat/completions"),
),
"status_code": 429,
"request_id": None,
}
exception = Exception()
for k, v in kwargs.items():
setattr(exception, k, v)
raise exception
with patch.object(
mapped_target,
@ -975,7 +1001,7 @@ async def test_exception_with_headers(sync_mode, provider, model, call_type, str
except litellm.RateLimitError as e:
exception_raised = True
assert e.litellm_response_headers is not None
assert e.litellm_response_headers["retry-after"] == cooldown_time
assert int(e.litellm_response_headers["retry-after"]) == cooldown_time
if exception_raised is False:
print(resp)