phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(main.py): for health checks, don't use cached responses

Browse source
This commit is contained in:
Krrish Dholakia 2024-02-02 16:51:42 -08:00
parent d69edac11b
commit 62ad6f19b7
2 changed files with 22 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

3
litellm/main.py
View file

@ -3259,6 +3259,9 @@ async def ahealth_check(
organization=organization, organization=organization,
) )
else: else:
model_params["cache"] = {
"no-cache": True
} # don't used cached responses for making health check calls
if mode == "embedding": if mode == "embedding":
model_params.pop("messages", None) model_params.pop("messages", None)
model_params["input"] = input model_params["input"] = input

19
litellm/tests/test_completion.py
View file

@ -1694,6 +1694,25 @@ def test_completion_anyscale_api():
# test_completion_anyscale_api() # test_completion_anyscale_api()
def test_completion_cohere():
try:
# litellm.set_verbose=True
messages = [
{"role": "system", "content": "You're a good bot"},
{
"role": "user",
"content": "Hey",
},
]
response = completion(
model="command-nightly",
messages=messages,
)
print(response)
except Exception as e:
pytest.fail(f"Error occurred: {e}")
def test_azure_cloudflare_api(): def test_azure_cloudflare_api():
litellm.set_verbose = True litellm.set_verbose = True
try: try: