build(pyproject.toml): add new dev dependencies - for type checking

.github/workflows/test-linting.yml

@@ -0,0 +1,53 @@
+name: LiteLLM Linting
+
+on:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
+
+    - name: Install dependencies
+      run: |
+        poetry install --with dev
+
+    - name: Run Black formatting check
+      run: |
+        cd litellm
+        poetry run black . --check
+        cd ..
+
+    - name: Run Ruff linting
+      run: |
+        cd litellm
+        poetry run ruff check .
+        cd ..
+
+    - name: Run MyPy type checking
+      run: |
+        cd litellm
+        poetry run mypy . --ignore-missing-imports
+        cd ..
+
+    - name: Check for circular imports
+      run: |
+        cd litellm
+        poetry run python ../tests/documentation_tests/test_circular_imports.py
+        cd ..
+
+    - name: Check import safety
+      run: |
+        poetry run python -c "from litellm import *" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)

.github/workflows/test-litellm.yml

@@ -1,4 +1,4 @@
-name: LiteLLM Tests
+name: LiteLLM Mock Tests (folder - tests/litellm)
 
 on:
   pull_request:

.pre-commit-config.yaml

@@ -14,10 +14,10 @@ repos:
         types: [python]
         files: litellm/.*\.py
         exclude: ^litellm/__init__.py$
--   repo: https://github.com/psf/black
-    rev: 24.2.0
-    hooks:
-    - id: black
+# -   repo: https://github.com/psf/black
+#     rev: 24.2.0
+#     hooks:
+#     - id: black
 -   repo: https://github.com/pycqa/flake8
     rev: 7.0.0  # The version of flake8 to use
     hooks:

enterprise/enterprise_hooks/secret_detection.py

@@ -444,9 +444,7 @@ def scan_message_for_secrets(self, message_content: str):
 
         detected_secrets = []
         for file in secrets.files:
-
             for found_secret in secrets[file]:
-
                 if found_secret.secret_value is None:
                     continue
                 detected_secrets.append(
@@ -471,14 +469,12 @@ async def async_pre_call_hook(
         data: dict,
         call_type: str,  # "completion", "embeddings", "image_generation", "moderation"
     ):
-
         if await self.should_run_check(user_api_key_dict) is False:
             return
 
         if "messages" in data and isinstance(data["messages"], list):
             for message in data["messages"]:
                 if "content" in message and isinstance(message["content"], str):
-
                     detected_secrets = self.scan_message_for_secrets(message["content"])
 
                     for secret in detected_secrets:

litellm/__init__.py

@@ -122,38 +122,38 @@
 prometheus_initialize_budget_metrics: Optional[bool] = False
 argilla_batch_size: Optional[int] = None
 datadog_use_v1: Optional[bool] = False  # if you want to use v1 datadog logged payload
-gcs_pub_sub_use_v1: Optional[bool] = (
-    False  # if you want to use v1 gcs pubsub logged payload
-)
+gcs_pub_sub_use_v1: Optional[
+    bool
+] = False  # if you want to use v1 gcs pubsub logged payload
 argilla_transformation_object: Optional[Dict[str, Any]] = None
-_async_input_callback: List[Union[str, Callable, CustomLogger]] = (
-    []
-)  # internal variable - async custom callbacks are routed here.
-_async_success_callback: List[Union[str, Callable, CustomLogger]] = (
-    []
-)  # internal variable - async custom callbacks are routed here.
-_async_failure_callback: List[Union[str, Callable, CustomLogger]] = (
-    []
-)  # internal variable - async custom callbacks are routed here.
+_async_input_callback: List[
+    Union[str, Callable, CustomLogger]
+] = []  # internal variable - async custom callbacks are routed here.
+_async_success_callback: List[
+    Union[str, Callable, CustomLogger]
+] = []  # internal variable - async custom callbacks are routed here.
+_async_failure_callback: List[
+    Union[str, Callable, CustomLogger]
+] = []  # internal variable - async custom callbacks are routed here.
 pre_call_rules: List[Callable] = []
 post_call_rules: List[Callable] = []
 turn_off_message_logging: Optional[bool] = False
 log_raw_request_response: bool = False
 redact_messages_in_exceptions: Optional[bool] = False
 redact_user_api_key_info: Optional[bool] = False
 filter_invalid_headers: Optional[bool] = False
-add_user_information_to_llm_headers: Optional[bool] = (
-    None  # adds user_id, team_id, token hash (params from StandardLoggingMetadata) to request headers
-)
+add_user_information_to_llm_headers: Optional[
+    bool
+] = None  # adds user_id, team_id, token hash (params from StandardLoggingMetadata) to request headers
 store_audit_logs = False  # Enterprise feature, allow users to see audit logs
 ### end of callbacks #############
 
-email: Optional[str] = (
-    None  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
-)
-token: Optional[str] = (
-    None  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
-)
+email: Optional[
+    str
+] = None  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
+token: Optional[
+    str
+] = None  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
 telemetry = True
 max_tokens = 256  # OpenAI Defaults
 drop_params = bool(os.getenv("LITELLM_DROP_PARAMS", False))
@@ -229,24 +229,20 @@
 enable_caching_on_provider_specific_optional_params: bool = (
     False  # feature-flag for caching on optional params - e.g. 'top_k'
 )
-caching: bool = (
-    False  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
-)
-caching_with_models: bool = (
-    False  # # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
-)
-cache: Optional[Cache] = (
-    None  # cache object <- use this - https://docs.litellm.ai/docs/caching
-)
+caching: bool = False  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
+caching_with_models: bool = False  # # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
+cache: Optional[
+    Cache
+] = None  # cache object <- use this - https://docs.litellm.ai/docs/caching
 default_in_memory_ttl: Optional[float] = None
 default_redis_ttl: Optional[float] = None
 default_redis_batch_cache_expiry: Optional[float] = None
 model_alias_map: Dict[str, str] = {}
 model_group_alias_map: Dict[str, str] = {}
 max_budget: float = 0.0  # set the max budget across all providers
-budget_duration: Optional[str] = (
-    None  # proxy only - resets budget after fixed duration. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").
-)
+budget_duration: Optional[
+    str
+] = None  # proxy only - resets budget after fixed duration. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").
 default_soft_budget: float = (
     50.0  # by default all litellm proxy keys have a soft budget of 50.0
 )
@@ -255,15 +251,11 @@
 
 _current_cost = 0.0  # private variable, used if max budget is set
 error_logs: Dict = {}
-add_function_to_prompt: bool = (
-    False  # if function calling not supported by api, append function call details to system prompt
-)
+add_function_to_prompt: bool = False  # if function calling not supported by api, append function call details to system prompt
 client_session: Optional[httpx.Client] = None
 aclient_session: Optional[httpx.AsyncClient] = None
 model_fallbacks: Optional[List] = None  # Deprecated for 'litellm.fallbacks'
-model_cost_map_url: str = (
-    "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
-)
+model_cost_map_url: str = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
 suppress_debug_info = False
 dynamodb_table_name: Optional[str] = None
 s3_callback_params: Optional[Dict] = None
@@ -285,9 +277,7 @@
 custom_prometheus_metadata_labels: List[str] = []
 #### REQUEST PRIORITIZATION ####
 priority_reservation: Optional[Dict[str, float]] = None
-force_ipv4: bool = (
-    False  # when True, litellm will force ipv4 for all LLM requests. Some users have seen httpx ConnectionError when using ipv6.
-)
+force_ipv4: bool = False  # when True, litellm will force ipv4 for all LLM requests. Some users have seen httpx ConnectionError when using ipv6.
 module_level_aclient = AsyncHTTPHandler(
     timeout=request_timeout, client_alias="module level aclient"
 )
@@ -301,13 +291,13 @@
 context_window_fallbacks: Optional[List] = None
 content_policy_fallbacks: Optional[List] = None
 allowed_fails: int = 3
-num_retries_per_request: Optional[int] = (
-    None  # for the request overall (incl. fallbacks + model retries)
-)
+num_retries_per_request: Optional[
+    int
+] = None  # for the request overall (incl. fallbacks + model retries)
 ####### SECRET MANAGERS #####################
-secret_manager_client: Optional[Any] = (
-    None  # list of instantiated key management clients - e.g. azure kv, infisical, etc.
-)
+secret_manager_client: Optional[
+    Any
+] = None  # list of instantiated key management clients - e.g. azure kv, infisical, etc.
 _google_kms_resource_name: Optional[str] = None
 _key_management_system: Optional[KeyManagementSystem] = None
 _key_management_settings: KeyManagementSettings = KeyManagementSettings()
@@ -1056,10 +1046,10 @@ def add_known_models():
 from .types.utils import GenericStreamingChunk
 
 custom_provider_map: List[CustomLLMItem] = []
-_custom_providers: List[str] = (
-    []
-)  # internal helper util, used to track names of custom providers
-disable_hf_tokenizer_download: Optional[bool] = (
-    None  # disable huggingface tokenizer download. Defaults to openai clk100
-)
+_custom_providers: List[
+    str
+] = []  # internal helper util, used to track names of custom providers
+disable_hf_tokenizer_download: Optional[
+    bool
+] = None  # disable huggingface tokenizer download. Defaults to openai clk100
 global_disable_no_log_param: bool = False

litellm/batches/main.py

@@ -153,7 +153,6 @@ def create_batch(
         )
         api_base: Optional[str] = None
         if custom_llm_provider == "openai":
-
             # for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
             api_base = (
                 optional_params.api_base
@@ -358,7 +357,6 @@ def retrieve_batch(
         _is_async = kwargs.pop("aretrieve_batch", False) is True
         api_base: Optional[str] = None
         if custom_llm_provider == "openai":
-
             # for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
             api_base = (
                 optional_params.api_base

litellm/caching/caching_handler.py

@@ -66,9 +66,7 @@ class CachingHandlerResponse(BaseModel):
 
     cached_result: Optional[Any] = None
     final_embedding_cached_response: Optional[EmbeddingResponse] = None
-    embedding_all_elements_cache_hit: bool = (
-        False  # this is set to True when all elements in the list have a cache hit in the embedding cache, if true return the final_embedding_cached_response no need to make an API call
-    )
+    embedding_all_elements_cache_hit: bool = False  # this is set to True when all elements in the list have a cache hit in the embedding cache, if true return the final_embedding_cached_response no need to make an API call
 
 
 class LLMCachingHandler:
@@ -738,7 +736,6 @@ def sync_set_cache(
         if self._should_store_result_in_cache(
             original_function=self.original_function, kwargs=new_kwargs
         ):
-
             litellm.cache.add_cache(result, **new_kwargs)
 
         return
@@ -865,9 +862,9 @@ def _update_litellm_logging_obj_environment(
         }
 
         if litellm.cache is not None:
-            litellm_params["preset_cache_key"] = (
-                litellm.cache._get_preset_cache_key_from_kwargs(**kwargs)
-            )
+            litellm_params[
+                "preset_cache_key"
+            ] = litellm.cache._get_preset_cache_key_from_kwargs(**kwargs)
         else:
             litellm_params["preset_cache_key"] = None
 

litellm/caching/llm_caching_handler.py

@@ -8,7 +8,6 @@
 
 
 class LLMClientCache(InMemoryCache):
-
     def update_cache_key_with_event_loop(self, key):
         """
         Add the event loop to the cache key, to prevent event loop closed errors.

litellm/caching/redis_cache.py

@@ -57,7 +57,6 @@ def __init__(
         socket_timeout: Optional[float] = 5.0,  # default 5 second timeout
         **kwargs,
     ):
-
         from litellm._service_logger import ServiceLogging
 
         from .._redis import get_redis_client, get_redis_connection_pool