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

feat(router.py): add routing capabilities for multiple deployments

Browse source
This commit is contained in:
Krrish Dholakia 2023-10-17 22:28:17 -07:00
parent 0aa3563ccf
commit b20cf3171b
3 changed files with 251 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

50
litellm/tests/test_router.py Normal file
View file

@ -0,0 +1,50 @@
#### What this tests ####
# This tests calling batch_completions by running 100 messages together
import sys, os
import traceback
import pytest
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
from litellm import Router
from dotenv import load_dotenv
load_dotenv()
model_list = [{
"model_name": "gpt-3.5-turbo", # openai model name
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-v-2",
"api_key": os.getenv("AZURE_API_KEY"),
"api_version": os.getenv("AZURE_API_VERSION"),
"api_base": os.getenv("AZURE_API_BASE")
},
"tpm": 240000,
"rpm": 1800
}, {
"model_name": "gpt-3.5-turbo", # openai model name
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-functioncalling",
"api_key": os.getenv("AZURE_API_KEY"),
"api_version": os.getenv("AZURE_API_VERSION"),
"api_base": os.getenv("AZURE_API_BASE")
},
"tpm": 240000,
"rpm": 1800
}, {
"model_name": "gpt-3.5-turbo", # openai model name
"litellm_params": { # params for litellm completion/embedding call
"model": "gpt-3.5-turbo",
"api_key": os.getenv("OPENAI_API_KEY"),
},
"tpm": 1000000,
"rpm": 9000
}]
router = Router(model_list=model_list)
# openai.ChatCompletion.create replacement
response = router.completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hey, how's it going?"}])
print(response)