forked from phoenix/litellm-mirror
c73ce95c01
* use 1 file for duration_in_seconds * add to readme.md * re use duration_in_seconds * fix importing _extract_from_regex, get_last_day_of_month * fix import * update provider budget routing * fix - remove dup test * add support for using in multi instance environments * test_in_memory_redis_sync_e2e * test_in_memory_redis_sync_e2e * fix test_in_memory_redis_sync_e2e * fix code quality check * fix test provider budgets * working provider budget tests * add fixture for provider budget routing * fix router testing for provider budgets * add comments on provider budget routing * use RedisPipelineIncrementOperation * add redis async_increment_pipeline * use redis async_increment_pipeline * use lower value for testing * use redis async_increment_pipeline * use consistent key name for increment op * add handling for budget windows * fix typing async_increment_pipeline * fix set attr * add clear doc strings * unit testing for provider budgets * test_redis_increment_pipeline
35 lines
675 B
Python
35 lines
675 B
Python
from enum import Enum
|
|
from typing import Literal, Optional, TypedDict
|
|
|
|
|
|
class LiteLLMCacheType(str, Enum):
|
|
LOCAL = "local"
|
|
REDIS = "redis"
|
|
REDIS_SEMANTIC = "redis-semantic"
|
|
S3 = "s3"
|
|
DISK = "disk"
|
|
QDRANT_SEMANTIC = "qdrant-semantic"
|
|
|
|
|
|
CachingSupportedCallTypes = Literal[
|
|
"completion",
|
|
"acompletion",
|
|
"embedding",
|
|
"aembedding",
|
|
"atranscription",
|
|
"transcription",
|
|
"atext_completion",
|
|
"text_completion",
|
|
"arerank",
|
|
"rerank",
|
|
]
|
|
|
|
|
|
class RedisPipelineIncrementOperation(TypedDict):
|
|
"""
|
|
TypeDict for 1 Redis Pipeline Increment Operation
|
|
"""
|
|
|
|
key: str
|
|
increment_value: float
|
|
ttl: Optional[int]
|