mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
e9d40a8f73
A name bound twice keeps only the second binding. In `tests/` that is nearly always a repeated import, harmless but misleading, and the same rule is what catches the cases that are not harmless: a local that shadows an import the module still calls, and a second `def test_x` that quietly replaces the first. 311 of the 344 sites were repeated imports and came out with ruff's own fix. The remaining 33 needed a decision. Four modules imported a name they never used because a local definition below already shadowed it. Two comprehensions bound `call` over `unittest.mock.call`, which those modules import and use. One test rebound the two module handles its nested reload closure had captured. One class attribute shadowed an unused `status` import. The load-test fixtures move to a conftest, which is how pytest is meant to share them, so the test module no longer imports three fixture names it never calls. The nine `prisma_client` parameters keep a narrow `noqa`: pytest resolves that fixture by name before the body runs, so the parameter never shadows anything.
60 lines
1.6 KiB
Python
60 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
|
|
|
|
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}")
|