mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 11:14:04 +00:00
0178e75cd9
* 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
51 lines
1.5 KiB
Python
51 lines
1.5 KiB
Python
"""
|
|
Handler file for calls to Azure OpenAI's o1 family of models
|
|
|
|
Written separately to handle faking streaming for o1 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 isinstance(client, OpenAI) or isinstance(client, AsyncOpenAI):
|
|
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,
|
|
)
|