mirror of
https://github.com/tiennm99/litellm.git
synced 2026-06-17 18:48:36 +00:00
62 lines
1.6 KiB
Python
62 lines
1.6 KiB
Python
# What this tests ?
|
|
## Tests /models and /model/* endpoints
|
|
|
|
import pytest
|
|
import asyncio
|
|
import aiohttp
|
|
import os
|
|
import dotenv
|
|
from dotenv import load_dotenv
|
|
import pytest
|
|
|
|
load_dotenv()
|
|
|
|
|
|
async def generate_key(session, models=[], team_id=None):
|
|
url = "http://0.0.0.0:4000/key/generate"
|
|
headers = {"Authorization": "Bearer sk-1234", "Content-Type": "application/json"}
|
|
data = {
|
|
"models": models,
|
|
"duration": None,
|
|
"team_id": team_id,
|
|
}
|
|
|
|
async with session.post(url, headers=headers, json=data) as response:
|
|
status = response.status
|
|
response_text = await response.text()
|
|
|
|
print(response_text)
|
|
print()
|
|
|
|
if status != 200:
|
|
raise Exception(f"Request did not return a 200 status code: {status}")
|
|
return await response.json()
|
|
|
|
|
|
async def chat_completion(session, key, model="azure-gpt-3.5", request_metadata=None):
|
|
url = "http://0.0.0.0:4000/chat/completions"
|
|
headers = {
|
|
"Authorization": f"Bearer {key}",
|
|
"Content-Type": "application/json",
|
|
}
|
|
data = {
|
|
"model": model,
|
|
"messages": [
|
|
{"role": "system", "content": "You are a helpful assistant."},
|
|
{"role": "user", "content": "Hello!"},
|
|
],
|
|
"metadata": request_metadata,
|
|
}
|
|
|
|
print("data sent in test=", data)
|
|
|
|
async with session.post(url, headers=headers, json=data) as response:
|
|
status = response.status
|
|
response_text = await response.text()
|
|
|
|
print(response_text)
|
|
print()
|
|
|
|
if status != 200:
|
|
raise Exception(f"Request did not return a 200 status code: {status}")
|