mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
9160d80fa5
* fix(caching): convert arg to equivalent kwargs in llm caching handler prevent unexpected errors * fix(caching_handler.py): don't pass args to caching * fix(caching): remove all *args from caching.py * fix(caching): consistent function signatures + abc method * test(caching_unit_tests.py): add unit tests for llm caching ensures coverage for common caching scenarios across different implementations * refactor(litellm_logging.py): move to using cache key from hidden params instead of regenerating one * fix(router.py): drop redis password requirement * fix(proxy_server.py): fix faulty slack alerting check * fix(langfuse.py): avoid copying functions/thread lock objects in metadata fixes metadata copy error when parent otel span in metadata * test: update test
55 lines
1.4 KiB
Python
55 lines
1.4 KiB
Python
"""
|
|
Base Cache implementation. All cache implementations should inherit from this class.
|
|
|
|
Has 4 methods:
|
|
- set_cache
|
|
- get_cache
|
|
- async_set_cache
|
|
- async_get_cache
|
|
"""
|
|
|
|
from abc import ABC, abstractmethod
|
|
from typing import TYPE_CHECKING, Any, Optional
|
|
|
|
if TYPE_CHECKING:
|
|
from opentelemetry.trace import Span as _Span
|
|
|
|
Span = _Span
|
|
else:
|
|
Span = Any
|
|
|
|
|
|
class BaseCache(ABC):
|
|
def __init__(self, default_ttl: int = 60):
|
|
self.default_ttl = default_ttl
|
|
|
|
def get_ttl(self, **kwargs) -> Optional[int]:
|
|
kwargs_ttl: Optional[int] = kwargs.get("ttl")
|
|
if kwargs_ttl is not None:
|
|
try:
|
|
return int(kwargs_ttl)
|
|
except ValueError:
|
|
return self.default_ttl
|
|
return self.default_ttl
|
|
|
|
def set_cache(self, key, value, **kwargs):
|
|
raise NotImplementedError
|
|
|
|
async def async_set_cache(self, key, value, **kwargs):
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
async def async_set_cache_pipeline(self, cache_list, **kwargs):
|
|
pass
|
|
|
|
def get_cache(self, key, **kwargs):
|
|
raise NotImplementedError
|
|
|
|
async def async_get_cache(self, key, **kwargs):
|
|
raise NotImplementedError
|
|
|
|
async def batch_cache_write(self, key, value, **kwargs):
|
|
raise NotImplementedError
|
|
|
|
async def disconnect(self):
|
|
raise NotImplementedError
|