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

Litellm dev 12 30 2024 p1 (#7480)

Browse source 
* test(azure_openai_o1.py): initial commit with testing for azure openai o1 preview model

* fix(base_llm_unit_tests.py): handle azure o1 preview response format tests

skip as o1 on azure doesn't support tool calling yet

* fix: initial commit of azure o1 handler using openai caller

simplifies calling + allows fake streaming logic alr. implemented for openai to just work

* feat(azure/o1_handler.py): fake o1 streaming for azure o1 models

azure does not currently support streaming for o1

* feat(o1_transformation.py): support overriding 'should_fake_stream' on azure/o1 via 'supports_native_streaming' param on model info

enables user to toggle on when azure allows o1 streaming without needing to bump versions

* style(router.py): remove 'give feedback/get help' messaging when router is used

Prevents noisy messaging

Closes https://github.com/BerriAI/litellm/issues/5942

* test: fix azure o1 test

* test: fix tests

* fix: fix test
This commit is contained in:
Krish Dholakia 2024-12-30 21:52:52 -08:00 • committed by GitHub
parent f0ed02d3ee
commit 0178e75cd9
17 changed files with 273 additions and 141 deletions
Download patch file Download diff file Expand all files Collapse all files

35
litellm/llms/azure/common_utils.py
View file

@ -1,7 +1,9 @@
from typing import Callable, Optional, Union
import httpx
from openai import AsyncAzureOpenAI, AzureOpenAI
import litellm
from litellm._logging import verbose_logger
from litellm.llms.base_llm.chat.transformation import BaseLLMException
from litellm.secret_managers.main import get_secret_str
@ -25,6 +27,39 @@ class AzureOpenAIError(BaseLLMException):
)
def get_azure_openai_client(
api_key: Optional[str],
api_base: Optional[str],
timeout: Union[float, httpx.Timeout],
max_retries: Optional[int],
api_version: Optional[str] = None,
organization: Optional[str] = None,
client: Optional[Union[AzureOpenAI, AsyncAzureOpenAI]] = None,
_is_async: bool = False,
) -> Optional[Union[AzureOpenAI, AsyncAzureOpenAI]]:
received_args = locals()
openai_client: Optional[Union[AzureOpenAI, AsyncAzureOpenAI]] = None
if client is None:
data = {}
for k, v in received_args.items():
if k == "self" or k == "client" or k == "_is_async":
pass
elif k == "api_base" and v is not None:
data["azure_endpoint"] = v
elif v is not None:
data[k] = v
if "api_version" not in data:
data["api_version"] = litellm.AZURE_DEFAULT_API_VERSION
if _is_async is True:
openai_client = AsyncAzureOpenAI(**data)
else:
openai_client = AzureOpenAI(**data) # type: ignore
else:
openai_client = client
return openai_client
def process_azure_headers(headers: Union[httpx.Headers, dict]) -> dict:
openai_headers = {}
if "x-ratelimit-limit-requests" in headers: