phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

build(pyproject.toml): add new dev dependencies - for type checking (#9631)

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

* build: reformat files to fit black

* ci: reformat to fit black

* ci(test-litellm.yml): make tests run clear

* build(pyproject.toml): add ruff

* fix: fix ruff checks

* build(mypy/): fix mypy linting errors

* fix(hashicorp_secret_manager.py): fix passing cert for tls auth

* build(mypy/): resolve all mypy errors

* test: update test

* fix: fix black formatting

* build(pre-commit-config.yaml): use poetry run black

* fix(proxy_server.py): fix linting error

* fix: fix ruff safe representation error
This commit is contained in:
Krish Dholakia 2025-03-29 11:02:13 -07:00 • committed by GitHub
parent 72198737f8
commit d7b294dd0a
214 changed files with 1553 additions and 1433 deletions
Download patch file Download diff file Expand all files Collapse all files

36
litellm/proxy/proxy_server.py
View file

@ -18,6 +18,7 @@ from typing import (
List,
Optional,
Tuple,
Union,
cast,
get_args,
get_origin,
@ -36,7 +37,7 @@ if TYPE_CHECKING:
from litellm.integrations.opentelemetry import OpenTelemetry
Span = _Span
Span = Union[_Span, Any]
else:
Span = Any
OpenTelemetry = Any
@ -763,9 +764,9 @@ model_max_budget_limiter = _PROXY_VirtualKeyModelMaxBudgetLimiter(
dual_cache=user_api_key_cache
)
litellm.logging_callback_manager.add_litellm_callback(model_max_budget_limiter)
redis_usage_cache: Optional[RedisCache] = (
None # redis cache used for tracking spend, tpm/rpm limits
)
redis_usage_cache: Optional[
RedisCache
] = None # redis cache used for tracking spend, tpm/rpm limits
user_custom_auth = None
user_custom_key_generate = None
user_custom_sso = None
@ -818,7 +819,6 @@ async def check_request_disconnection(request: Request, llm_api_call_task):
while time.time() - start_time < 600:
await asyncio.sleep(1)
if await request.is_disconnected():
# cancel the LLM API Call task if any passed - this is passed from individual providers
# Example OpenAI, Azure, VertexAI etc
llm_api_call_task.cancel()
@ -1092,9 +1092,9 @@ async def update_cache( # noqa: PLR0915
_id = "team_id:{}".format(team_id)
try:
# Fetch the existing cost for the given user
existing_spend_obj: Optional[LiteLLM_TeamTable] = (
await user_api_key_cache.async_get_cache(key=_id)
)
existing_spend_obj: Optional[
LiteLLM_TeamTable
] = await user_api_key_cache.async_get_cache(key=_id)
if existing_spend_obj is None:
# do nothing if team not in api key cache
return
@ -1589,7 +1589,7 @@ class ProxyConfig:
# users can pass os.environ/ variables on the proxy - we should read them from the env
for key, value in cache_params.items():
if type(value) is str and value.startswith("os.environ/"):
if isinstance(value, str) and value.startswith("os.environ/"):
cache_params[key] = get_secret(value)
## to pass a complete url, or set ssl=True, etc. just set it as `os.environ[REDIS_URL] = <your-redis-url>`, _redis.py checks for REDIS specific environment variables
@ -1610,7 +1610,6 @@ class ProxyConfig:
litellm.guardrail_name_config_map = guardrail_name_config_map
elif key == "callbacks":
initialize_callbacks_on_proxy(
value=value,
premium_user=premium_user,
@ -2765,9 +2764,9 @@ async def initialize( # noqa: PLR0915
user_api_base = api_base
dynamic_config[user_model]["api_base"] = api_base
if api_version:
os.environ["AZURE_API_VERSION"] = (
api_version # set this for azure - litellm can read this from the env
)
os.environ[
"AZURE_API_VERSION"
] = api_version # set this for azure - litellm can read this from the env
if max_tokens: # model-specific param
dynamic_config[user_model]["max_tokens"] = max_tokens
if temperature: # model-specific param
@ -2810,7 +2809,6 @@ async def async_assistants_data_generator(
try:
time.time()
async with response as chunk:
### CALL HOOKS ### - modify outgoing data
chunk = await proxy_logging_obj.async_post_call_streaming_hook(
user_api_key_dict=user_api_key_dict, response=chunk
@ -4675,7 +4673,6 @@ async def get_thread(
global proxy_logging_obj
data: Dict = {}
try:
# Include original request and headers in the data
data = await add_litellm_data_to_request(
data=data,
@ -6385,7 +6382,6 @@ async def alerting_settings(
for field_name, field_info in SlackAlertingArgs.model_fields.items():
if field_name in allowed_args:
_stored_in_db: Optional[bool] = None
if field_name in alerting_args_dict:
_stored_in_db = True
@ -7333,7 +7329,6 @@ async def update_config(config_info: ConfigYAML): # noqa: PLR0915
"success_callback" in updated_litellm_settings
and "success_callback" in config["litellm_settings"]
):
# check both success callback are lists
if isinstance(
config["litellm_settings"]["success_callback"], list
@ -7588,7 +7583,6 @@ async def get_config_list(
for field_name, field_info in ConfigGeneralSettings.model_fields.items():
if field_name in allowed_args:
## HANDLE TYPED DICT
typed_dict_type = allowed_args[field_name]["type"]
@ -7621,9 +7615,9 @@ async def get_config_list(
hasattr(sub_field_info, "description")
and sub_field_info.description is not None
):
nested_fields[idx].field_description = (
sub_field_info.description
)
nested_fields[
idx
].field_description = sub_field_info.description
idx += 1
_stored_in_db = None