phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 19:24:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(utils.py): async add to cache - for streaming

Browse source
This commit is contained in:
Krrish Dholakia 2024-03-15 18:25:40 -07:00
parent 4912ad5cf4
commit 909341c4f2
1 changed files with 6 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

7
litellm/utils.py
View file

@ -1795,7 +1795,12 @@ class Logging:
) )
result = kwargs["async_complete_streaming_response"] result = kwargs["async_complete_streaming_response"]
# only add to cache once we have a complete streaming response # only add to cache once we have a complete streaming response
litellm.cache.add_cache(result, **kwargs) if litellm.cache is not None and not isinstance(
litellm.cache.cache, S3Cache
):
await litellm.cache.async_add_cache(result, **kwargs)
else:
litellm.cache.add_cache(result, **kwargs)
if isinstance(callback, CustomLogger): # custom logger class if isinstance(callback, CustomLogger): # custom logger class
print_verbose( print_verbose(
f"Running Async success callback: {callback}; self.stream: {self.stream}; async_complete_streaming_response: {self.model_call_details.get('async_complete_streaming_response', None)} result={result}" f"Running Async success callback: {callback}; self.stream: {self.stream}; async_complete_streaming_response: {self.model_call_details.get('async_complete_streaming_response', None)} result={result}"