phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor(sagemaker/): separate chat + completion routes + make them b… (#7151)

Browse source 
* refactor(sagemaker/): separate chat + completion routes + make them both use base llm config

Addresses https://github.com/andrewyng/aisuite/issues/113#issuecomment-2512369132

* fix(main.py): pass hf model name + custom prompt dict to litellm params
This commit is contained in:
Krish Dholakia 2024-12-10 19:40:05 -08:00 • committed by GitHub
parent df12f87a64
commit 61afdab228
14 changed files with 799 additions and 534 deletions
Download patch file Download diff file Expand all files Collapse all files

17
tests/local_testing/test_async_fn.py
View file

@ -246,23 +246,6 @@ async def test_hf_completion_tgi():
# test_get_cloudflare_response_streaming()
@pytest.mark.skip(reason="AWS Suspended Account")
@pytest.mark.asyncio
async def test_completion_sagemaker():
# litellm.set_verbose=True
try:
response = await acompletion(
model="sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4",
messages=[{"content": "Hello, how are you?", "role": "user"}],
)
# Add any assertions here to check the response
print(response)
except litellm.Timeout as e:
pass
except Exception as e:
pytest.fail(f"Error occurred: {e}")
def test_get_response_streaming():
import asyncio