phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix - undo local dev changes

Browse source
This commit is contained in:
Ishaan Jaff 2024-05-04 19:11:57 -07:00
parent 653d0cf512
commit 909e8470a7
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/router.py
View file

@ -1707,7 +1707,7 @@ class Router:
response = original_function(*args, **kwargs) response = original_function(*args, **kwargs)
return response return response
except Exception as most_recent_exception: except Exception as e:
## LOGGING ## LOGGING
kwargs = self.log_retry(kwargs=kwargs, e=e) kwargs = self.log_retry(kwargs=kwargs, e=e)
remaining_retries = num_retries - current_attempt remaining_retries = num_retries - current_attempt
@ -1717,7 +1717,7 @@ class Router:
num_retries=num_retries, num_retries=num_retries,
) )
time.sleep(_timeout) time.sleep(_timeout)
raise most_recent_exception raise original_exception
### HELPER FUNCTIONS ### HELPER FUNCTIONS
@ -1852,7 +1852,7 @@ class Router:
exception_status = 500 exception_status = 500
_should_retry = litellm._should_retry(status_code=exception_status) _should_retry = litellm._should_retry(status_code=exception_status)
if updated_fails > self.allowed_fails: if updated_fails > self.allowed_fails or _should_retry == False:
# get the current cooldown list for that minute # get the current cooldown list for that minute
cooldown_key = f"{current_minute}:cooldown_models" # group cooldown models by minute to reduce number of redis calls cooldown_key = f"{current_minute}:cooldown_models" # group cooldown models by minute to reduce number of redis calls
cached_value = self.cache.get_cache(key=cooldown_key) cached_value = self.cache.get_cache(key=cooldown_key)