fix - test lowest cost routing

This commit is contained in:
Ishaan Jaff 2024-06-05 21:42:41 -07:00
parent 685d6e4400
commit 27db329621

View file

@ -106,14 +106,14 @@ async def test_lowest_cost_routing():
""" """
model_list = [ model_list = [
{ {
"model_name": "gpt-3.5-turbo", "model_name": "gpt-4",
"litellm_params": {"model": "gpt-4"}, "litellm_params": {"model": "gpt-4"},
"model_info": {"id": "openai-gpt-4"}, "model_info": {"id": "openai-gpt-4"},
}, },
{ {
"model_name": "gpt-3.5-turbo", "model_name": "gpt-3.5-turbo",
"litellm_params": {"model": "groq/llama3-8b-8192"}, "litellm_params": {"model": "gpt-3.5-turbo"},
"model_info": {"id": "groq-llama"}, "model_info": {"id": "gpt-3.5-turbo"},
}, },
] ]
@ -127,7 +127,7 @@ async def test_lowest_cost_routing():
print( print(
response._hidden_params["model_id"] response._hidden_params["model_id"]
) # expect groq-llama, since groq/llama has lowest cost ) # expect groq-llama, since groq/llama has lowest cost
assert "groq-llama" == response._hidden_params["model_id"] assert "gpt-3.5-turbo" == response._hidden_params["model_id"]
async def _deploy(lowest_cost_logger, deployment_id, tokens_used, duration): async def _deploy(lowest_cost_logger, deployment_id, tokens_used, duration):