(code quality) add ruff check PLR0915 for too-many-statements (#6309)

* ruff add PLR0915

* add noqa for PLR0915

* fix noqa

* add # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* add # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

* # noqa: PLR0915

db_scripts/create_views.py

@@ -17,7 +17,7 @@ db = Prisma(
 )
 
 
-async def check_view_exists():
+async def check_view_exists():  # noqa: PLR0915
     """
     Checks if the LiteLLM_VerificationTokenView and MonthlyGlobalSpend exists in the user's db.
 

litellm/caching/caching.py

@@ -220,7 +220,7 @@ class Cache:
         if self.namespace is not None and isinstance(self.cache, RedisCache):
             self.cache.namespace = self.namespace
 
-    def get_cache_key(self, *args, **kwargs) -> str:
+    def get_cache_key(self, *args, **kwargs) -> str:  # noqa: PLR0915
         """
         Get the cache key for the given arguments.
 

litellm/caching/qdrant_semantic_cache.py

@@ -20,7 +20,7 @@ from .base_cache import BaseCache
 
 
 class QdrantSemanticCache(BaseCache):
-    def __init__(
+    def __init__(  # noqa: PLR0915
         self,
         qdrant_api_base=None,
         qdrant_api_key=None,

litellm/cost_calculator.py

@@ -79,7 +79,7 @@ def _cost_per_token_custom_pricing_helper(
     return None
 
 
-def cost_per_token(
+def cost_per_token(  # noqa: PLR0915
     model: str = "",
     prompt_tokens: int = 0,
     completion_tokens: int = 0,
@@ -474,7 +474,7 @@ def _select_model_name_for_cost_calc(
     return return_model
 
 
-def completion_cost(
+def completion_cost(  # noqa: PLR0915
     completion_response=None,
     model: Optional[str] = None,
     prompt="",

litellm/integrations/SlackAlerting/slack_alerting.py

@@ -287,7 +287,7 @@ class SlackAlerting(CustomBatchLogger):
         except Exception:
             return 0
 
-    async def send_daily_reports(self, router) -> bool:
+    async def send_daily_reports(self, router) -> bool:  # noqa: PLR0915
         """
         Send a daily report on:
         - Top 5 deployments with most failed requests
@@ -573,7 +573,7 @@ class SlackAlerting(CustomBatchLogger):
                 ttl=self.alerting_args.budget_alert_ttl,
             )
 
-    async def budget_alerts(
+    async def budget_alerts(  # noqa: PLR0915
         self,
         type: Literal[
             "token_budget",

litellm/integrations/braintrust_logging.py

@@ -125,7 +125,9 @@ class BraintrustLogger(CustomLogger):
 
         self.default_project_id = project_dict["id"]
 
-    def log_success_event(self, kwargs, response_obj, start_time, end_time):
+    def log_success_event(  # noqa: PLR0915
+        self, kwargs, response_obj, start_time, end_time
+    ):
         verbose_logger.debug("REACHES BRAINTRUST SUCCESS")
         try:
             litellm_call_id = kwargs.get("litellm_call_id")
@@ -237,7 +239,9 @@ class BraintrustLogger(CustomLogger):
         except Exception as e:
             raise e  # don't use verbose_logger.exception, if exception is raised
 
-    async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
+    async def async_log_success_event(  # noqa: PLR0915
+        self, kwargs, response_obj, start_time, end_time
+    ):
         verbose_logger.debug("REACHES BRAINTRUST SUCCESS")
         try:
             litellm_call_id = kwargs.get("litellm_call_id")

litellm/integrations/langfuse.py

@@ -143,7 +143,7 @@ class LangFuseLogger:
     #         level ="ERROR" # can be any of DEBUG, DEFAULT, WARNING or ERROR
     #         status_message='error' # can be any string (e.g. stringified stack trace or error body)
     #     )
-    def log_event(
+    def log_event(  # noqa: PLR0915
         self,
         kwargs,
         response_obj,
@@ -349,7 +349,7 @@ class LangFuseLogger:
             )
         )
 
-    def _log_langfuse_v2(
+    def _log_langfuse_v2(  # noqa: PLR0915
         self,
         user_id,
         metadata,

litellm/integrations/langsmith.py

@@ -132,7 +132,9 @@ class LangsmithLogger(CustomBatchLogger):
             LANGSMITH_PROJECT=_credentials_project,
         )
 
-    def _prepare_log_data(self, kwargs, response_obj, start_time, end_time):
+    def _prepare_log_data(  # noqa: PLR0915
+        self, kwargs, response_obj, start_time, end_time
+    ):
         import json
         from datetime import datetime as dt
 

litellm/integrations/opentelemetry.py

@@ -393,7 +393,7 @@ class OpenTelemetry(CustomLogger):
         except Exception:
             return ""
 
-    def set_attributes(self, span: Span, kwargs, response_obj):
+    def set_attributes(self, span: Span, kwargs, response_obj):  # noqa: PLR0915
         try:
             if self.callback_name == "arize":
                 from litellm.integrations.arize_ai import set_arize_ai_attributes

litellm/integrations/opik/opik.py

@@ -182,7 +182,7 @@ class OpikLogger(CustomBatchLogger):
                 url=self.span_url, headers=self.headers, batch={"spans": spans}
             )
 
-    def _create_opik_payload(
+    def _create_opik_payload(  # noqa: PLR0915
         self, kwargs, response_obj, start_time, end_time
     ) -> List[Dict]:
 

litellm/integrations/prometheus.py

@@ -321,7 +321,9 @@ class PrometheusLogger(CustomLogger):
             print_verbose(f"Got exception on init prometheus client {str(e)}")
             raise e
 
-    async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
+    async def async_log_success_event(  # noqa: PLR0915
+        self, kwargs, response_obj, start_time, end_time
+    ):
         # Define prometheus client
         from litellm.proxy.common_utils.callback_utils import (
             get_model_group_from_litellm_kwargs,

litellm/litellm_core_utils/exception_mapping_utils.py

@@ -89,7 +89,7 @@ def _get_response_headers(original_exception: Exception) -> Optional[httpx.Heade
     return _response_headers
 
 
-def exception_type(  # type: ignore
+def exception_type(  # type: ignore  # noqa: PLR0915
     model,
     original_exception,
     custom_llm_provider,

litellm/litellm_core_utils/get_llm_provider_logic.py

@@ -67,7 +67,7 @@ def handle_cohere_chat_model_custom_llm_provider(
     return model, custom_llm_provider
 
 
-def get_llm_provider(
+def get_llm_provider(  # noqa: PLR0915
     model: str,
     custom_llm_provider: Optional[str] = None,
     api_base: Optional[str] = None,

litellm/litellm_core_utils/litellm_logging.py

@@ -428,7 +428,7 @@ class Logging:
         ):  # if model name was changes pre-call, overwrite the initial model call name with the new one
             self.model_call_details["model"] = model
 
-    def pre_call(self, input, api_key, model=None, additional_args={}):
+    def pre_call(self, input, api_key, model=None, additional_args={}):  # noqa: PLR0915
         # Log the exact input to the LLM API
         litellm.error_logs["PRE_CALL"] = locals()
         try:
@@ -868,7 +868,7 @@ class Logging:
         except Exception as e:
             raise Exception(f"[Non-Blocking] LiteLLM.Success_Call Error: {str(e)}")
 
-    def success_handler(
+    def success_handler(  # noqa: PLR0915
         self, result=None, start_time=None, end_time=None, cache_hit=None, **kwargs
     ):
         print_verbose(f"Logging Details LiteLLM-Success Call: Cache_hit={cache_hit}")
@@ -1494,7 +1494,7 @@ class Logging:
                 ),
             )
 
-    async def async_success_handler(
+    async def async_success_handler(  # noqa: PLR0915
         self, result=None, start_time=None, end_time=None, cache_hit=None, **kwargs
     ):
         """
@@ -1833,7 +1833,7 @@ class Logging:
                     kwargs=self.model_call_details,
                 )  # type: ignore
 
-    def failure_handler(
+    def failure_handler(  # noqa: PLR0915
         self, exception, traceback_exception, start_time=None, end_time=None
     ):
         verbose_logger.debug(
@@ -2191,7 +2191,7 @@ class Logging:
         return None
 
 
-def set_callbacks(callback_list, function_id=None):
+def set_callbacks(callback_list, function_id=None):  # noqa: PLR0915
     """
     Globally sets the callback client
     """
@@ -2301,7 +2301,7 @@ def set_callbacks(callback_list, function_id=None):
         raise e
 
 
-def _init_custom_logger_compatible_class(
+def _init_custom_logger_compatible_class(  # noqa: PLR0915
     logging_integration: litellm._custom_logger_compatible_callbacks_literal,
     internal_usage_cache: Optional[DualCache],
     llm_router: Optional[
@@ -2629,7 +2629,7 @@ def is_valid_sha256_hash(value: str) -> bool:
     return bool(re.fullmatch(r"[a-fA-F0-9]{64}", value))
 
 
-def get_standard_logging_object_payload(
+def get_standard_logging_object_payload(  # noqa: PLR0915
     kwargs: Optional[dict],
     init_response_obj: Union[Any, BaseModel, dict],
     start_time: dt_object,

litellm/llms/AzureOpenAI/azure.py

@@ -344,7 +344,7 @@ class AzureChatCompletion(BaseLLM):
         except Exception as e:
             raise e
 
-    def completion(
+    def completion(  # noqa: PLR0915
         self,
         model: str,
         messages: list,

litellm/llms/OpenAI/openai.py

@@ -612,7 +612,7 @@ class OpenAIChatCompletion(BaseLLM):
             else:
                 raise e
 
-    def completion(  # type: ignore
+    def completion(  # type: ignore # noqa: PLR0915
         self,
         model_response: ModelResponse,
         timeout: Union[float, httpx.Timeout],

litellm/llms/anthropic/experimental_pass_through/transformation.py

@@ -73,7 +73,7 @@ class AnthropicExperimentalPassThroughConfig:
         """
         return ["messages", "metadata", "system", "tool_choice", "tools"]
 
-    def translate_anthropic_messages_to_openai(
+    def translate_anthropic_messages_to_openai(  # noqa: PLR0915
         self,
         messages: List[
             Union[

litellm/llms/azure_text.py

@@ -141,7 +141,7 @@ class AzureTextCompletion(BaseLLM):
             headers["Authorization"] = f"Bearer {azure_ad_token}"
         return headers
 
-    def completion(
+    def completion(  # noqa: PLR0915
         self,
         model: str,
         messages: list,

litellm/llms/base_aws_llm.py

@@ -38,7 +38,7 @@ class BaseAWSLLM(BaseLLM):
         credential_str = json.dumps(credential_args, sort_keys=True)
         return hashlib.sha256(credential_str.encode()).hexdigest()
 
-    def get_credentials(
+    def get_credentials(  # noqa: PLR0915
         self,
         aws_access_key_id: Optional[str] = None,
         aws_secret_access_key: Optional[str] = None,

litellm/llms/bedrock/chat/converse_handler.py

@@ -200,7 +200,7 @@ class BedrockConverseLLM(BaseAWSLLM):
             encoding=encoding,
         )
 
-    def completion(
+    def completion(  # noqa: PLR0915
         self,
         model: str,
         messages: list,

litellm/llms/bedrock/chat/invoke_handler.py

@@ -308,7 +308,7 @@ class BedrockLLM(BaseAWSLLM):
                     prompt += f"{message['content']}"
         return prompt, chat_history  # type: ignore
 
-    def process_response(
+    def process_response(  # noqa: PLR0915
         self,
         model: str,
         response: Union[requests.Response, httpx.Response],
@@ -574,7 +574,7 @@ class BedrockLLM(BaseAWSLLM):
         """
         return urllib.parse.quote(model_id, safe="")
 
-    def completion(
+    def completion(  # noqa: PLR0915
         self,
         model: str,
         messages: list,

litellm/llms/huggingface_restapi.py

@@ -333,7 +333,7 @@ class Huggingface(BaseLLM):
             headers = default_headers
         return headers
 
-    def convert_to_model_response_object(
+    def convert_to_model_response_object(  # noqa: PLR0915
         self,
         completion_response,
         model_response: litellm.ModelResponse,
@@ -447,7 +447,7 @@ class Huggingface(BaseLLM):
         model_response._hidden_params["original_response"] = completion_response
         return model_response
 
-    def completion(
+    def completion(  # noqa: PLR0915
         self,
         model: str,
         messages: list,

litellm/llms/ollama_chat.py

@@ -213,7 +213,7 @@ class OllamaChatConfig:
 
 
 # ollama implementation
-def get_ollama_response(
+def get_ollama_response(  # noqa: PLR0915
     model_response: litellm.ModelResponse,
     messages: list,
     optional_params: dict,

litellm/llms/predibase.py

@@ -240,7 +240,7 @@ class PredibaseChatCompletion(BaseLLM):
                 generated_text = generated_text[::-1].replace(token[::-1], "", 1)[::-1]
         return generated_text
 
-    def process_response(
+    def process_response(  # noqa: PLR0915
         self,
         model: str,
         response: Union[requests.Response, httpx.Response],

litellm/llms/prompt_templates/factory.py

@@ -385,7 +385,9 @@ known_tokenizer_config = {
 }
 
 
-def hf_chat_template(model: str, messages: list, chat_template: Optional[Any] = None):
+def hf_chat_template(  # noqa: PLR0915
+    model: str, messages: list, chat_template: Optional[Any] = None
+):
     # Define Jinja2 environment
     env = ImmutableSandboxedEnvironment()
 
@@ -1339,7 +1341,7 @@ def add_cache_control_to_content(
     return anthropic_content_element
 
 
-def anthropic_messages_pt(
+def anthropic_messages_pt(  # noqa: PLR0915
     messages: List[AllMessageValues],
     model: str,
     llm_provider: str,
@@ -1797,7 +1799,7 @@ def convert_to_cohere_tool_invoke(tool_calls: list) -> List[ToolCallObject]:
     return cohere_tool_invoke
 
 
-def cohere_messages_pt_v2(
+def cohere_messages_pt_v2(  # noqa: PLR0915
     messages: List,
     model: str,
     llm_provider: str,
@@ -2409,7 +2411,7 @@ def _insert_assistant_continue_message(
     return messages
 
 
-def _bedrock_converse_messages_pt(
+def _bedrock_converse_messages_pt(  # noqa: PLR0915
     messages: List,
     model: str,
     llm_provider: str,

litellm/llms/sagemaker/sagemaker.py

@@ -248,7 +248,7 @@ class SagemakerLLM(BaseAWSLLM):
 
         return prompt
 
-    def completion(
+    def completion(  # noqa: PLR0915
         self,
         model: str,
         messages: list,

litellm/llms/vertex_ai_and_google_ai_studio/gemini/vertex_and_google_ai_studio_gemini.py

@@ -742,7 +742,7 @@ class VertexLLM(VertexBase):
     def __init__(self) -> None:
         super().__init__()
 
-    def _process_response(
+    def _process_response(  # noqa: PLR0915
         self,
         model: str,
         response: httpx.Response,

litellm/llms/vertex_ai_and_google_ai_studio/vertex_ai_non_gemini.py

@@ -131,7 +131,7 @@ def _process_gemini_image(image_url: str) -> PartType:
         raise e
 
 
-def _gemini_convert_messages_with_history(
+def _gemini_convert_messages_with_history(  # noqa: PLR0915
     messages: List[AllMessageValues],
 ) -> List[ContentType]:
     """
@@ -279,7 +279,7 @@ def _set_client_in_cache(client_cache_key: str, vertex_llm_model: Any):
     litellm.in_memory_llm_clients_cache[client_cache_key] = vertex_llm_model
 
 
-def completion(
+def completion(  # noqa: PLR0915
     model: str,
     messages: list,
     model_response: ModelResponse,
@@ -770,7 +770,7 @@ def completion(
         )
 
 
-async def async_completion(
+async def async_completion(  # noqa: PLR0915
     llm_model,
     mode: str,
     prompt: str,
@@ -1010,7 +1010,7 @@ async def async_completion(
         raise VertexAIError(status_code=500, message=str(e))
 
 
-async def async_streaming(
+async def async_streaming(  # noqa: PLR0915
     llm_model,
     mode: str,
     prompt: str,

litellm/main.py

@@ -657,7 +657,7 @@ def mock_completion(
 
 
 @client
-def completion(  # type: ignore
+def completion(  # type: ignore # noqa: PLR0915
     model: str,
     # Optional OpenAI params: see https://platform.openai.com/docs/api-reference/chat/create
     messages: List = [],
@@ -3136,7 +3136,7 @@ async def aembedding(*args, **kwargs) -> EmbeddingResponse:
 
 
 @client
-def embedding(
+def embedding(  # noqa: PLR0915
     model,
     input=[],
     # Optional params
@@ -3911,7 +3911,7 @@ async def atext_completion(
 
 
 @client
-def text_completion(
+def text_completion(  # noqa: PLR0915
     prompt: Union[
         str, List[Union[str, List[Union[str, List[int]]]]]
     ],  # Required: The prompt(s) to generate completions for.
@@ -4378,7 +4378,7 @@ async def aimage_generation(*args, **kwargs) -> ImageResponse:
 
 
 @client
-def image_generation(
+def image_generation(  # noqa: PLR0915
     prompt: str,
     model: Optional[str] = None,
     n: Optional[int] = None,
@@ -5111,7 +5111,7 @@ def speech(
 ##### Health Endpoints #######################
 
 
-async def ahealth_check(
+async def ahealth_check(  # noqa: PLR0915
     model_params: dict,
     mode: Optional[
         Literal[
@@ -5374,7 +5374,7 @@ def stream_chunk_builder_text_completion(
     return TextCompletionResponse(**response)
 
 
-def stream_chunk_builder(
+def stream_chunk_builder(  # noqa: PLR0915
     chunks: list, messages: Optional[list] = None, start_time=None, end_time=None
 ) -> Optional[Union[ModelResponse, TextCompletionResponse]]:
     try:

litellm/proxy/auth/auth_checks.py

@@ -44,7 +44,7 @@ else:
 all_routes = LiteLLMRoutes.openai_routes.value + LiteLLMRoutes.management_routes.value
 
 
-def common_checks(
+def common_checks(  # noqa: PLR0915
     request_body: dict,
     team_object: Optional[LiteLLM_TeamTable],
     user_object: Optional[LiteLLM_UserTable],

litellm/proxy/auth/user_api_key_auth.py

@@ -105,7 +105,7 @@ def _get_bearer_token(
     return api_key
 
 
-async def user_api_key_auth(
+async def user_api_key_auth(  # noqa: PLR0915
     request: Request,
     api_key: str = fastapi.Security(api_key_header),
     azure_api_key_header: str = fastapi.Security(azure_api_key_header),

litellm/proxy/common_utils/callback_utils.py

@@ -11,7 +11,7 @@ blue_color_code = "\033[94m"
 reset_color_code = "\033[0m"
 
 
-def initialize_callbacks_on_proxy(
+def initialize_callbacks_on_proxy(  # noqa: PLR0915
     value: Any,
     premium_user: bool,
     config_file_path: str,

litellm/proxy/db/create_views.py

@@ -5,7 +5,7 @@ from litellm import verbose_logger
 _db = Any
 
 
-async def create_missing_views(db: _db):
+async def create_missing_views(db: _db):  # noqa: PLR0915
     """
     --------------------------------------------------
     NOTE: Copy of `litellm/db_scripts/create_views.py`.

litellm/proxy/guardrails/guardrail_hooks/lakera_ai.py

@@ -119,7 +119,7 @@ class lakeraAI_Moderation(CustomGuardrail):
 
         return None
 
-    async def _check(
+    async def _check(  # noqa: PLR0915
         self,
         data: dict,
         user_api_key_dict: UserAPIKeyAuth,

litellm/proxy/guardrails/init_guardrails.py

@@ -86,7 +86,7 @@ Map guardrail_name: <pre_call>, <post_call>, during_call
 """
 
 
-def init_guardrails_v2(
+def init_guardrails_v2(  # noqa: PLR0915
     all_guardrails: List[Dict],
     config_file_path: Optional[str] = None,
 ):

litellm/proxy/health_endpoints/_health_endpoints.py

@@ -53,7 +53,7 @@ async def test_endpoint(request: Request):
     dependencies=[Depends(user_api_key_auth)],
     include_in_schema=False,
 )
-async def health_services_endpoint(
+async def health_services_endpoint(  # noqa: PLR0915
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
     service: Union[
         Literal[

litellm/proxy/hooks/parallel_request_limiter.py

@@ -117,7 +117,7 @@ class _PROXY_MaxParallelRequestsHandler(CustomLogger):
             headers={"retry-after": str(self.time_to_next_minute())},
         )
 
-    async def async_pre_call_hook(
+    async def async_pre_call_hook(  # noqa: PLR0915
         self,
         user_api_key_dict: UserAPIKeyAuth,
         cache: DualCache,
@@ -411,7 +411,9 @@ class _PROXY_MaxParallelRequestsHandler(CustomLogger):
 
         return
 
-    async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
+    async def async_log_success_event(  # noqa: PLR0915
+        self, kwargs, response_obj, start_time, end_time
+    ):
         from litellm.proxy.common_utils.callback_utils import (
             get_model_group_from_litellm_kwargs,
         )

litellm/proxy/litellm_pre_call_utils.py

@@ -211,7 +211,7 @@ def add_litellm_data_for_backend_llm_call(
     return data
 
 
-async def add_litellm_data_to_request(
+async def add_litellm_data_to_request(  # noqa: PLR0915
     data: dict,
     request: Request,
     user_api_key_dict: UserAPIKeyAuth,

litellm/proxy/management_endpoints/internal_user_endpoints.py

@@ -308,7 +308,7 @@ def get_team_from_list(
     # response_model=UserInfoResponse,
 )
 @management_endpoint_wrapper
-async def user_info(
+async def user_info(  # noqa: PLR0915
     user_id: Optional[str] = fastapi.Query(
         default=None, description="User ID in the request parameters"
     ),

litellm/proxy/management_endpoints/key_management_endpoints.py

@@ -45,7 +45,7 @@ router = APIRouter()
     response_model=GenerateKeyResponse,
 )
 @management_endpoint_wrapper
-async def generate_key_fn(
+async def generate_key_fn(  # noqa: PLR0915
     data: GenerateKeyRequest,
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
     litellm_changed_by: Optional[str] = Header(
@@ -768,7 +768,7 @@ async def info_key_fn(
         )
 
 
-async def generate_key_helper_fn(
+async def generate_key_helper_fn(  # noqa: PLR0915
     request_type: Literal[
         "user", "key"
     ],  # identifies if this request is from /user/new or /key/generate

litellm/proxy/management_endpoints/team_endpoints.py

@@ -92,7 +92,7 @@ async def get_all_team_memberships(
     response_model=LiteLLM_TeamTable,
 )
 @management_endpoint_wrapper
-async def new_team(
+async def new_team(  # noqa: PLR0915
     data: NewTeamRequest,
     http_request: Request,
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),

litellm/proxy/management_endpoints/ui_sso.py

@@ -46,7 +46,7 @@ router = APIRouter()
 
 
 @router.get("/sso/key/generate", tags=["experimental"], include_in_schema=False)
-async def google_login(request: Request):
+async def google_login(request: Request):  # noqa: PLR0915
     """
     Create Proxy API Keys using Google Workspace SSO. Requires setting PROXY_BASE_URL in .env
     PROXY_BASE_URL should be the your deployed proxy endpoint, e.g. PROXY_BASE_URL="https://litellm-production-7002.up.railway.app/"
@@ -221,7 +221,7 @@ async def google_login(request: Request):
 
 
 @router.get("/sso/callback", tags=["experimental"], include_in_schema=False)
-async def auth_callback(request: Request):
+async def auth_callback(request: Request):  # noqa: PLR0915
     """Verify login"""
     from litellm.proxy.management_endpoints.key_management_endpoints import (
         generate_key_helper_fn,

litellm/proxy/pass_through_endpoints/pass_through_endpoints.py

@@ -105,7 +105,7 @@ async def set_env_variables_in_header(custom_headers: Optional[dict]) -> Optiona
     return headers
 
 
-async def chat_completion_pass_through_endpoint(
+async def chat_completion_pass_through_endpoint(  # noqa: PLR0915
     fastapi_response: Response,
     request: Request,
     adapter_id: str,
@@ -306,7 +306,7 @@ def get_endpoint_type(url: str) -> EndpointType:
     return EndpointType.GENERIC
 
 
-async def pass_through_request(
+async def pass_through_request(  # noqa: PLR0915
     request: Request,
     target: str,
     custom_headers: dict,

litellm/proxy/proxy_cli.py

@@ -216,7 +216,7 @@ def is_port_in_use(port):
     envvar="SSL_CERTFILE_PATH",
 )
 @click.option("--local", is_flag=True, default=False, help="for local debugging")
-def run_server(
+def run_server(  # noqa: PLR0915
     host,
     port,
     api_base,

litellm/proxy/proxy_server.py

@@ -881,7 +881,7 @@ def _set_spend_logs_payload(
     return prisma_client
 
 
-async def update_database(
+async def update_database(  # noqa: PLR0915
     token,
     response_cost,
     user_id=None,
@@ -1063,7 +1063,7 @@ async def update_database(
         )
 
 
-async def update_cache(
+async def update_cache(  # noqa: PLR0915
     token: Optional[str],
     user_id: Optional[str],
     end_user_id: Optional[str],
@@ -1492,7 +1492,7 @@ class ProxyConfig:
             ## INIT PROXY REDIS USAGE CLIENT ##
             redis_usage_cache = litellm.cache.cache
 
-    async def load_config(
+    async def load_config(  # noqa: PLR0915
         self, router: Optional[litellm.Router], config_file_path: str
     ):
         """
@@ -2144,7 +2144,7 @@ class ProxyConfig:
                 added_models += 1
         return added_models
 
-    async def _update_llm_router(
+    async def _update_llm_router(  # noqa: PLR0915
         self,
         new_models: list,
         proxy_logging_obj: ProxyLogging,
@@ -2387,7 +2387,7 @@ def save_worker_config(**data):
     os.environ["WORKER_CONFIG"] = json.dumps(data)
 
 
-async def initialize(
+async def initialize(  # noqa: PLR0915
     model=None,
     alias=None,
     api_base=None,
@@ -2728,7 +2728,7 @@ def giveup(e):
 
 
 @router.on_event("startup")
-async def startup_event():
+async def startup_event():  # noqa: PLR0915
     global prisma_client, master_key, use_background_health_checks, llm_router, llm_model_list, general_settings, proxy_budget_rescheduler_min_time, proxy_budget_rescheduler_max_time, litellm_proxy_admin_name, db_writer_client, store_model_in_db, premium_user, _license_check
     import json
 
@@ -3078,7 +3078,7 @@ async def model_list(
     giveup=giveup,
     logger=verbose_proxy_logger,
 )
-async def chat_completion(
+async def chat_completion(  # noqa: PLR0915
     request: Request,
     fastapi_response: Response,
     model: Optional[str] = None,
@@ -3357,7 +3357,7 @@ async def chat_completion(
     dependencies=[Depends(user_api_key_auth)],
     tags=["completions"],
 )
-async def completion(
+async def completion(  # noqa: PLR0915
     request: Request,
     fastapi_response: Response,
     model: Optional[str] = None,
@@ -3580,7 +3580,7 @@ async def completion(
     response_class=ORJSONResponse,
     tags=["embeddings"],
 )  # azure compatible endpoint
-async def embeddings(
+async def embeddings(  # noqa: PLR0915
     request: Request,
     fastapi_response: Response,
     model: Optional[str] = None,
@@ -5469,7 +5469,7 @@ async def moderations(
     dependencies=[Depends(user_api_key_auth)],
     response_model=AnthropicResponse,
 )
-async def anthropic_response(
+async def anthropic_response(  # noqa: PLR0915
     anthropic_data: AnthropicMessagesRequest,
     fastapi_response: Response,
     request: Request,
@@ -7278,7 +7278,7 @@ async def model_metrics_exceptions(
     tags=["model management"],
     dependencies=[Depends(user_api_key_auth)],
 )
-async def model_info_v1(
+async def model_info_v1(  # noqa: PLR0915
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
     litellm_model_id: Optional[str] = None,
 ):
@@ -7985,7 +7985,7 @@ async def fallback_login(request: Request):
 @router.post(
     "/login", include_in_schema=False
 )  # hidden since this is a helper for UI sso login
-async def login(request: Request):
+async def login(request: Request):  # noqa: PLR0915
     global premium_user, general_settings
     try:
         import multipart
@@ -8653,7 +8653,7 @@ async def invitation_delete(
     dependencies=[Depends(user_api_key_auth)],
     include_in_schema=False,
 )
-async def update_config(config_info: ConfigYAML):
+async def update_config(config_info: ConfigYAML):  # noqa: PLR0915
     """
     For Admin UI - allows admin to update config via UI
 
@@ -9156,7 +9156,7 @@ async def delete_config_general_settings(
     include_in_schema=False,
     dependencies=[Depends(user_api_key_auth)],
 )
-async def get_config():
+async def get_config():  # noqa: PLR0915
     """
     For Admin UI - allows admin to view config via UI
     # return the callbacks and the env variables for the callback

litellm/proxy/spend_tracking/spend_management_endpoints.py

@@ -1597,7 +1597,7 @@ async def calculate_spend(request: SpendCalculateRequest):
         200: {"model": List[LiteLLM_SpendLogs]},
     },
 )
-async def view_spend_logs(
+async def view_spend_logs(  # noqa: PLR0915
     api_key: Optional[str] = fastapi.Query(
         default=None,
         description="Get spend logs based on api key",

litellm/proxy/utils.py

@@ -1426,7 +1426,7 @@ class PrismaClient:
         on_backoff=on_backoff,  # specifying the function to call on backoff
     )
     @log_to_opentelemetry
-    async def get_data(
+    async def get_data(  # noqa: PLR0915
         self,
         token: Optional[Union[str, list]] = None,
         user_id: Optional[str] = None,
@@ -1780,7 +1780,7 @@ class PrismaClient:
         max_time=10,  # maximum total time to retry for
         on_backoff=on_backoff,  # specifying the function to call on backoff
     )
-    async def insert_data(
+    async def insert_data(  # noqa: PLR0915
         self,
         data: dict,
         table_name: Literal[
@@ -1928,7 +1928,7 @@ class PrismaClient:
         max_time=10,  # maximum total time to retry for
         on_backoff=on_backoff,  # specifying the function to call on backoff
     )
-    async def update_data(
+    async def update_data(  # noqa: PLR0915
         self,
         token: Optional[str] = None,
         data: dict = {},
@@ -2617,7 +2617,7 @@ async def reset_budget(prisma_client: PrismaClient):
             )
 
 
-async def update_spend(
+async def update_spend(  # noqa: PLR0915
     prisma_client: PrismaClient,
     db_writer_client: Optional[HTTPHandler],
     proxy_logging_obj: ProxyLogging,

litellm/router.py

@@ -156,7 +156,7 @@ class Router:
     leastbusy_logger: Optional[LeastBusyLoggingHandler] = None
     lowesttpm_logger: Optional[LowestTPMLoggingHandler] = None
 
-    def __init__(
+    def __init__(  # noqa: PLR0915
         self,
         model_list: Optional[
             Union[List[DeploymentTypedDict], List[Dict[str, Any]]]
@@ -2565,7 +2565,7 @@ class Router:
 
     #### [END] ASSISTANTS API ####
 
-    async def async_function_with_fallbacks(self, *args, **kwargs):
+    async def async_function_with_fallbacks(self, *args, **kwargs):  # noqa: PLR0915
         """
         Try calling the function_with_retries
         If it fails after num_retries, fall back to another model group
@@ -4170,7 +4170,7 @@ class Router:
         model_name = model_info["model_name"]
         return self.get_model_list(model_name=model_name)
 
-    def _set_model_group_info(
+    def _set_model_group_info(  # noqa: PLR0915
         self, model_group: str, user_facing_model_group_name: str
     ) -> Optional[ModelGroupInfo]:
         """
@@ -4696,7 +4696,7 @@ class Router:
                     client = self.cache.get_cache(key=cache_key)
                 return client
 
-    def _pre_call_checks(
+    def _pre_call_checks(  # noqa: PLR0915
         self,
         model: str,
         healthy_deployments: List,

litellm/router_strategy/lowest_cost.py

@@ -209,7 +209,7 @@ class LowestCostLoggingHandler(CustomLogger):
             )
             pass
 
-    async def async_get_available_deployments(
+    async def async_get_available_deployments(  # noqa: PLR0915
         self,
         model_group: str,
         healthy_deployments: list,

litellm/router_strategy/lowest_latency.py

@@ -44,7 +44,9 @@ class LowestLatencyLoggingHandler(CustomLogger):
         self.model_list = model_list
         self.routing_args = RoutingArgs(**routing_args)
 
-    def log_success_event(self, kwargs, response_obj, start_time, end_time):
+    def log_success_event(  # noqa: PLR0915
+        self, kwargs, response_obj, start_time, end_time
+    ):
         try:
             """
             Update latency usage on success
@@ -244,7 +246,9 @@ class LowestLatencyLoggingHandler(CustomLogger):
             )
             pass
 
-    async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
+    async def async_log_success_event(  # noqa: PLR0915
+        self, kwargs, response_obj, start_time, end_time
+    ):
         try:
             """
             Update latency usage on success
@@ -375,7 +379,7 @@ class LowestLatencyLoggingHandler(CustomLogger):
             )
             pass
 
-    def get_available_deployments(
+    def get_available_deployments(  # noqa: PLR0915
         self,
         model_group: str,
         healthy_deployments: list,

litellm/router_strategy/lowest_tpm_rpm.py

@@ -166,7 +166,7 @@ class LowestTPMLoggingHandler(CustomLogger):
             verbose_router_logger.debug(traceback.format_exc())
             pass
 
-    def get_available_deployments(
+    def get_available_deployments(  # noqa: PLR0915
         self,
         model_group: str,
         healthy_deployments: list,

litellm/router_strategy/lowest_tpm_rpm_v2.py

@@ -318,7 +318,7 @@ class LowestTPMLoggingHandler_v2(CustomLogger):
             )
             pass
 
-    def _common_checks_available_deployment(
+    def _common_checks_available_deployment(  # noqa: PLR0915
         self,
         model_group: str,
         healthy_deployments: list,

litellm/router_utils/client_initalization_utils.py

@@ -48,7 +48,7 @@ def should_initialize_sync_client(
     return True
 
 
-def set_client(litellm_router_instance: LitellmRouter, model: dict):
+def set_client(litellm_router_instance: LitellmRouter, model: dict):  # noqa: PLR0915
     """
     - Initializes Azure/OpenAI clients. Stores them in cache, b/c of this - https://github.com/BerriAI/litellm/issues/1278
     - Initializes Semaphore for client w/ rpm. Stores them in cache. b/c of this - https://github.com/BerriAI/litellm/issues/2994

litellm/secret_managers/main.py

@@ -67,7 +67,7 @@ def get_secret_str(
     return value
 
 
-def get_secret(
+def get_secret(  # noqa: PLR0915
     secret_name: str,
     default_value: Optional[Union[str, bool]] = None,
 ):

litellm/utils.py

@@ -328,7 +328,7 @@ def custom_llm_setup():
             litellm._custom_providers.append(custom_llm["provider"])
 
 
-def function_setup(
+def function_setup(  # noqa: PLR0915
     original_function: str, rules_obj, start_time, *args, **kwargs
 ):  # just run once to check if user wants to send their data anywhere - PostHog/Sentry/Slack/etc.
     ### NOTICES ###
@@ -605,7 +605,7 @@ def function_setup(
         raise e
 
 
-def client(original_function):
+def client(original_function):  # noqa: PLR0915
     global liteDebuggerClient
     rules_obj = Rules()
 
@@ -721,7 +721,7 @@ def client(original_function):
             raise e
 
     @wraps(original_function)
-    def wrapper(*args, **kwargs):
+    def wrapper(*args, **kwargs):  # noqa: PLR0915
         # DO NOT MOVE THIS. It always needs to run first
         # Check if this is an async function. If so only execute the async function
         if (
@@ -1007,7 +1007,7 @@ def client(original_function):
             raise e
 
     @wraps(original_function)
-    async def wrapper_async(*args, **kwargs):
+    async def wrapper_async(*args, **kwargs):  # noqa: PLR0915
         print_args_passed_to_litellm(original_function, args, kwargs)
         start_time = datetime.datetime.now()
         result = None
@@ -1289,7 +1289,7 @@ def decode(model="", tokens: List[int] = [], custom_tokenizer: Optional[dict] =
     return dec
 
 
-def openai_token_counter(
+def openai_token_counter(  # noqa: PLR0915
     messages: Optional[list] = None,
     model="gpt-3.5-turbo-0613",
     text: Optional[str] = None,
@@ -1930,7 +1930,7 @@ def _update_dictionary(existing_dict: Dict, new_dict: dict) -> dict:
     return existing_dict
 
 
-def register_model(model_cost: Union[str, dict]):
+def register_model(model_cost: Union[str, dict]):  # noqa: PLR0915
     """
     Register new / Override existing models (and their pricing) to specific providers.
     Provide EITHER a model cost dictionary or a url to a hosted json blob
@@ -2253,7 +2253,7 @@ def get_optional_params_image_gen(
     return optional_params
 
 
-def get_optional_params_embeddings(
+def get_optional_params_embeddings(  # noqa: PLR0915
     # 2 optional params
     model: str,
     user: Optional[str] = None,
@@ -2469,7 +2469,7 @@ def _remove_strict_from_schema(schema):
     return schema
 
 
-def get_optional_params(
+def get_optional_params(  # noqa: PLR0915
     # use the openai defaults
     # https://platform.openai.com/docs/api-reference/chat/create
     model: str,
@@ -4077,7 +4077,7 @@ def get_first_chars_messages(kwargs: dict) -> str:
         return ""
 
 
-def get_supported_openai_params(
+def get_supported_openai_params(  # noqa: PLR0915
     model: str,
     custom_llm_provider: Optional[str] = None,
     request_type: Literal["chat_completion", "embeddings"] = "chat_completion",
@@ -4573,7 +4573,9 @@ def _get_model_info_from_model_cost(key: str) -> dict:
     return litellm.model_cost[key]
 
 
-def get_model_info(model: str, custom_llm_provider: Optional[str] = None) -> ModelInfo:
+def get_model_info(  # noqa: PLR0915
+    model: str, custom_llm_provider: Optional[str] = None
+) -> ModelInfo:
     """
     Get a dict for the maximum tokens (context window), input_cost_per_token, output_cost_per_token  for a given model.
 
@@ -5116,7 +5118,7 @@ def create_proxy_transport_and_mounts():
     return sync_proxy_mounts, async_proxy_mounts
 
 
-def validate_environment(
+def validate_environment(  # noqa: PLR0915
     model: Optional[str] = None, api_key: Optional[str] = None
 ) -> dict:
     """
@@ -5605,7 +5607,7 @@ def _handle_invalid_parallel_tool_calls(
     return tool_calls
 
 
-def convert_to_model_response_object(
+def convert_to_model_response_object(  # noqa: PLR0915
     response_object: Optional[dict] = None,
     model_response_object: Optional[
         Union[
@@ -7170,7 +7172,7 @@ class CustomStreamWrapper:
             is_empty = False
         return is_empty
 
-    def chunk_creator(self, chunk):  # type: ignore
+    def chunk_creator(self, chunk):  # type: ignore  # noqa: PLR0915
         model_response = self.model_response_creator()
         response_obj = {}
         try:
@@ -7881,7 +7883,7 @@ class CustomStreamWrapper:
             model_response.choices[0].finish_reason = "tool_calls"
         return model_response
 
-    def __next__(self):
+    def __next__(self):  # noqa: PLR0915
         cache_hit = False
         if (
             self.custom_llm_provider is not None
@@ -8016,7 +8018,7 @@ class CustomStreamWrapper:
 
         return self.completion_stream
 
-    async def __anext__(self):
+    async def __anext__(self):  # noqa: PLR0915
         cache_hit = False
         if (
             self.custom_llm_provider is not None

ruff.toml

@@ -1,4 +1,4 @@
 ignore = ["F405", "E402", "F401", "E501", "F403"]
-extend-select = ["E501"]
+extend-select = ["E501", "PLR0915"]
 line-length = 120
 exclude = ["litellm/types/*", "litellm/__init__.py", "litellm/proxy/example_config_yaml/*"]