Litellm remove circular imports (#7232)

* fix(utils.py): initial commit to remove circular imports - moves llmproviders to utils.py

* fix(router.py): fix 'litellm.EmbeddingResponse' import from router.py

'

* refactor: fix litellm.ModelResponse import on pass through endpoints

* refactor(litellm_logging.py): fix circular import for custom callbacks literal

* fix(factory.py): fix circular imports inside prompt factory

* fix(cost_calculator.py): fix circular import for 'litellm.Usage'

* fix(proxy_server.py): fix potential circular import with `litellm.Router'

* fix(proxy/utils.py): fix potential circular import in `litellm.Router`

* fix: remove circular imports in 'auth_checks' and 'guardrails/'

* fix(prompt_injection_detection.py): fix router impor t

* fix(vertex_passthrough_logging_handler.py): fix potential circular imports in vertex pass through

* fix(anthropic_pass_through_logging_handler.py): fix potential circular imports

* fix(slack_alerting.py-+-ollama_chat.py): fix modelresponse import

* fix(base.py): fix potential circular import

* fix(handler.py): fix potential circular ref in codestral + cohere handler's

* fix(azure.py): fix potential circular imports

* fix(gpt_transformation.py): fix modelresponse import

* fix(litellm_logging.py): add logging base class - simplify typing

makes it easy for other files to type check the logging obj without introducing circular imports

* fix(azure_ai/embed): fix potential circular import on handler.py

* fix(databricks/): fix potential circular imports in databricks/

* fix(vertex_ai/): fix potential circular imports on vertex ai embeddings

* fix(vertex_ai/image_gen): fix import

* fix(watsonx-+-bedrock): cleanup imports

* refactor(anthropic-pass-through-+-petals): cleanup imports

* refactor(huggingface/): cleanup imports

* fix(ollama-+-clarifai): cleanup circular imports

* fix(openai_like/): fix impor t

* fix(openai_like/): fix embedding handler

cleanup imports

* refactor(openai.py): cleanup imports

* fix(sagemaker/transformation.py): fix import

* ci(config.yml): add circular import test to ci/cd

litellm/llms/azure/chat/gpt_transformation.py

@@ -4,7 +4,11 @@ from typing import TYPE_CHECKING, Any, List, Optional, Type, Union
 from httpx._models import Headers, Response
 
 import litellm
+from litellm.litellm_core_utils.prompt_templates.factory import (
+    convert_to_azure_openai_messages,
+)
 from litellm.llms.base_llm.transformation import BaseLLMException
+from litellm.types.utils import ModelResponse
 
 from ....exceptions import UnsupportedParamsError
 from ....types.llms.openai import (
@@ -14,9 +18,7 @@ from ....types.llms.openai import (
     ChatCompletionToolParam,
     ChatCompletionToolParamFunctionChunk,
 )
-
 from ...base_llm.transformation import BaseConfig
-from litellm.litellm_core_utils.prompt_templates.factory import convert_to_azure_openai_messages
 from ..common_utils import AzureOpenAIError
 
 if TYPE_CHECKING:
@@ -26,6 +28,7 @@ if TYPE_CHECKING:
 else:
     LoggingClass = Any
 
+
 class AzureOpenAIConfig(BaseConfig):
     """
     Reference: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions
@@ -221,7 +224,7 @@ class AzureOpenAIConfig(BaseConfig):
         self,
         model: str,
         raw_response: Response,
-        model_response: litellm.ModelResponse,
+        model_response: ModelResponse,
         logging_obj: LoggingClass,
         request_data: dict,
         messages: List[AllMessageValues],
@@ -230,7 +233,7 @@ class AzureOpenAIConfig(BaseConfig):
         encoding: Any,
         api_key: Optional[str] = None,
         json_mode: Optional[bool] = None,
-    ) -> litellm.ModelResponse:
+    ) -> ModelResponse:
         raise NotImplementedError(
             "Azure OpenAI handler.py has custom logic for transforming response, as it uses the OpenAI SDK."
         )