litellm-mirror/litellm/llms/azure/chat/o_series_handler.py
Krish Dholakia 1105e35538
Complete o3 model support (#8183)
* fix(o_series_transformation.py): add 'reasoning_effort' as o series model param

Closes https://github.com/BerriAI/litellm/issues/8182

* fix(main.py): ensure `reasoning_effort` is a mapped openai param

* refactor(azure/): rename o1_[x] files to o_series_[x]

* refactor(base_llm_unit_tests.py): refactor testing for o series reasoning effort

* test(test_azure_o_series.py): have azure o series tests correctly inherit from base o series model tests

* feat(base_utils.py): support translating 'developer' role to 'system' role for non-openai providers

Makes it easy to switch from openai to anthropic

* fix: fix linting errors

* fix(base_llm_unit_tests.py): fix test

* fix(main.py): add missing param
2025-02-02 22:36:37 -08:00

53 lines
1.5 KiB
Python

"""
Handler file for calls to Azure OpenAI's o1/o3 family of models
Written separately to handle faking streaming for o1 and o3 models.
"""
from typing import Optional, Union
import httpx
from openai import AsyncAzureOpenAI, AsyncOpenAI, AzureOpenAI, OpenAI
from ...openai.openai import OpenAIChatCompletion
from ..common_utils import get_azure_openai_client
class AzureOpenAIO1ChatCompletion(OpenAIChatCompletion):
def _get_openai_client(
self,
is_async: bool,
api_key: Optional[str] = None,
api_base: Optional[str] = None,
api_version: Optional[str] = None,
timeout: Union[float, httpx.Timeout] = httpx.Timeout(None),
max_retries: Optional[int] = 2,
organization: Optional[str] = None,
client: Optional[
Union[OpenAI, AsyncOpenAI, AzureOpenAI, AsyncAzureOpenAI]
] = None,
) -> Optional[
Union[
OpenAI,
AsyncOpenAI,
AzureOpenAI,
AsyncAzureOpenAI,
]
]:
# Override to use Azure-specific client initialization
if not isinstance(client, AzureOpenAI) and not isinstance(
client, AsyncAzureOpenAI
):
client = None
return get_azure_openai_client(
api_key=api_key,
api_base=api_base,
timeout=timeout,
max_retries=max_retries,
organization=organization,
api_version=api_version,
client=client,
_is_async=is_async,
)