phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

Merge pull request #1809 from BerriAI/litellm_embedding_caching_updates

Browse source 
Support caching individual items in embedding list (Async embedding only)
This commit is contained in:
Krish Dholakia 2024-02-03 21:04:23 -08:00 • committed by GitHub
commit 28df60b609
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 638 additions and 196 deletions
Download patch file Download diff file Expand all files Collapse all files

1
litellm/tests/test_completion.py
View file

@ -1994,6 +1994,7 @@ def test_completion_palm_stream():
def test_completion_together_ai_stream():
litellm.set_verbose = True
user_message = "Write 1pg about YC & litellm"
messages = [{"content": user_message, "role": "user"}]
try: