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

Squashed commit of the following: (#9709)

Browse source 
commit b12a9892b7
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Wed Apr 2 08:09:56 2025 -0700

    fix(utils.py): don't modify openai_token_counter

commit 294de31803
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 21:22:40 2025 -0700

    fix: fix linting error

commit cb6e9fbe40
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:52:45 2025 -0700

    refactor: complete migration

commit bfc159172d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:09:59 2025 -0700

    refactor: refactor more constants

commit 43ffb6a558
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:45:24 2025 -0700

    fix: test

commit 04dbe4310c
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:28:58 2025 -0700

    refactor: refactor: move more constants into constants.py

commit 3c26284aff
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:14:46 2025 -0700

    refactor: migrate hardcoded constants out of __init__.py

commit c11e0de69d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:11:21 2025 -0700

    build: migrate all constants into constants.py

commit 7882bdc787
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:07:37 2025 -0700

    build: initial test banning hardcoded numbers in repo
This commit is contained in:
Krish Dholakia 2025-04-02 21:24:54 -07:00 • committed by GitHub
parent 3911187129
commit 354a75fb59
51 changed files with 509 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

22
litellm/utils.py
View file

@ -62,6 +62,16 @@ import litellm.llms.gemini
from litellm.caching._internal_lru_cache import lru_cache_wrapper
from litellm.caching.caching import DualCache
from litellm.caching.caching_handler import CachingHandlerResponse, LLMCachingHandler
from litellm.constants import (
DEFAULT_MAX_LRU_CACHE_SIZE,
DEFAULT_TRIM_RATIO,
FUNCTION_DEFINITION_TOKEN_COUNT,
INITIAL_RETRY_DELAY,
JITTER,
MAX_RETRY_DELAY,
MINIMUM_PROMPT_CACHE_TOKEN_COUNT,
TOOL_CHOICE_OBJECT_TOKEN_COUNT,
)
from litellm.integrations.custom_guardrail import CustomGuardrail
from litellm.integrations.custom_logger import CustomLogger
from litellm.litellm_core_utils.core_helpers import (
@ -1520,7 +1530,7 @@ def _select_tokenizer(
return _select_tokenizer_helper(model=model)
@lru_cache(maxsize=128)
@lru_cache(maxsize=DEFAULT_MAX_LRU_CACHE_SIZE)
def _select_tokenizer_helper(model: str) -> SelectTokenizerResponse:
if litellm.disable_hf_tokenizer_download is True:
return _return_openai_tokenizer(model)
@ -5336,15 +5346,15 @@ def _calculate_retry_after(
if retry_after is not None and 0 < retry_after <= 60:
return retry_after
initial_retry_delay = 0.5
max_retry_delay = 8.0
initial_retry_delay = INITIAL_RETRY_DELAY
max_retry_delay = MAX_RETRY_DELAY
nb_retries = max_retries - remaining_retries
# Apply exponential backoff, but not more than the max.
sleep_seconds = min(initial_retry_delay * pow(2.0, nb_retries), max_retry_delay)
# Apply some jitter, plus-or-minus half a second.
jitter = 1 - 0.25 * random.random()
jitter = JITTER * random.random()
timeout = sleep_seconds * jitter
return timeout if timeout >= min_timeout else min_timeout
@ -5670,7 +5680,7 @@ def shorten_message_to_fit_limit(message, tokens_needed, model: Optional[str]):
def trim_messages(
messages,
model: Optional[str] = None,
trim_ratio: float = 0.75,
trim_ratio: float = DEFAULT_TRIM_RATIO,
return_response_tokens: bool = False,
max_tokens=None,
):
@ -6543,7 +6553,7 @@ def is_prompt_caching_valid_prompt(
model=model,
use_default_image_token_count=True,
)
return token_count >= 1024
return token_count >= MINIMUM_PROMPT_CACHE_TOKEN_COUNT
except Exception as e:
verbose_logger.error(f"Error in is_prompt_caching_valid_prompt: {e}")
return False