mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
* 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 * fix(types/utils.py): handle none logprobs Fixes https://github.com/BerriAI/litellm/issues/328 * fix(exception_mapping_utils.py): fix error str unbound error * refactor(azure_ai/): move to openai_like chat completion handler allows for easy swapping of api base url's (e.g. ai.services.com) Fixes https://github.com/BerriAI/litellm/issues/7275 * refactor(azure_ai/): move to base llm http handler * fix(azure_ai/): handle differing api endpoints * fix(azure_ai/): make sure all unit tests are passing * fix: fix linting errors * fix: fix linting errors * fix: fix linting error * fix: fix linting errors * fix(azure_ai/transformation.py): handle extra body param * fix(azure_ai/transformation.py): fix max retries param handling * fix: fix test * test(test_azure_o1.py): fix test * fix(llm_http_handler.py): support handling azure ai unprocessable entity error * fix(llm_http_handler.py): handle sync invalid param error for azure ai * fix(azure_ai/): streaming support with base_llm_http_handler * fix(llm_http_handler.py): working sync stream calls with unprocessable entity handling for azure ai * fix: fix linting errors * fix(llm_http_handler.py): fix linting error * fix(azure_ai/): handle cohere tool call invalid index param error
51 lines
1.5 KiB
Python
51 lines
1.5 KiB
Python
from typing import List, Optional, Union
|
|
|
|
from httpx import Headers
|
|
|
|
from litellm.secret_managers.main import get_secret_str
|
|
from litellm.types.llms.openai import AllMessageValues
|
|
|
|
from ..base_llm.chat.transformation import BaseLLMException
|
|
|
|
|
|
class FireworksAIException(BaseLLMException):
|
|
pass
|
|
|
|
|
|
class FireworksAIMixin:
|
|
"""
|
|
Common Base Config functions across Fireworks AI Endpoints
|
|
"""
|
|
|
|
def get_error_class(
|
|
self, error_message: str, status_code: int, headers: Union[dict, Headers]
|
|
) -> BaseLLMException:
|
|
return FireworksAIException(
|
|
status_code=status_code,
|
|
message=error_message,
|
|
headers=headers,
|
|
)
|
|
|
|
def _get_api_key(self, api_key: Optional[str]) -> Optional[str]:
|
|
dynamic_api_key = api_key or (
|
|
get_secret_str("FIREWORKS_API_KEY")
|
|
or get_secret_str("FIREWORKS_AI_API_KEY")
|
|
or get_secret_str("FIREWORKSAI_API_KEY")
|
|
or get_secret_str("FIREWORKS_AI_TOKEN")
|
|
)
|
|
return dynamic_api_key
|
|
|
|
def validate_environment(
|
|
self,
|
|
headers: dict,
|
|
model: str,
|
|
messages: List[AllMessageValues],
|
|
optional_params: dict,
|
|
api_key: Optional[str] = None,
|
|
api_base: Optional[str] = None,
|
|
) -> dict:
|
|
api_key = self._get_api_key(api_key)
|
|
if api_key is None:
|
|
raise ValueError("FIREWORKS_API_KEY is not set")
|
|
|
|
return {"Authorization": "Bearer {}".format(api_key), **headers}
|