mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-09 22:31:41 +00:00
6a0d03914c
* test: drop the cwd-relative sys.path.insert calls from the test suite
TQ003 stands at 1,077 across 1,058 files, and 1,015 of them are the same shape:
sys.path.insert(0, os.path.abspath("../..")) and its deeper siblings. The
argument resolves against the working directory rather than the file, so from
the repo root, where every job runs pytest, it inserts the directory two levels
above the checkout. It has never pointed at litellm. The package is installed
into the environment anyway, which is what actually makes the import work, and
what the rule's message has said all along.
Removing them leaves 1,634 imports of sys and os with no remaining reference,
and those go too, except where another test module imports the name back out of
the file. The rest of TQ003 is 62 call sites that resolve against __file__ or a
variable, which are a different question and are left alone.
Collection is identical either way: 45,871 tests and the same 51 pre-existing
collection errors before and after, and ruff reports no new undefined name.
* test: drop the duplicate imports the sys.path sweep exposed to F811
* test(pre-call-utils): restore the os import the new bedrock tests need
136 lines
3.6 KiB
Python
136 lines
3.6 KiB
Python
|
|
import pytest
|
|
from dotenv import load_dotenv
|
|
from fastapi import Request
|
|
from fastapi.routing import APIRoute
|
|
|
|
import litellm
|
|
from litellm.proxy._types import SpendCalculateRequest
|
|
from litellm.proxy.spend_tracking.spend_management_endpoints import calculate_spend
|
|
from litellm.router import Router
|
|
|
|
# this file is to test litellm/proxy
|
|
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_spend_calc_model_messages():
|
|
cost_obj = await calculate_spend(
|
|
request=SpendCalculateRequest(
|
|
model="gpt-3.5-turbo",
|
|
messages=[
|
|
{"role": "user", "content": "What is the capital of France?"},
|
|
],
|
|
)
|
|
)
|
|
|
|
print("calculated cost", cost_obj)
|
|
cost = cost_obj["cost"]
|
|
assert cost > 0.0
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_spend_calc_model_on_router_messages():
|
|
from litellm.proxy.proxy_server import llm_router as init_llm_router
|
|
|
|
temp_llm_router = Router(
|
|
model_list=[
|
|
{
|
|
"model_name": "special-llama-model",
|
|
"litellm_params": {
|
|
"model": "groq/llama-3.1-8b-instant",
|
|
},
|
|
}
|
|
]
|
|
)
|
|
|
|
setattr(litellm.proxy.proxy_server, "llm_router", temp_llm_router)
|
|
|
|
cost_obj = await calculate_spend(
|
|
request=SpendCalculateRequest(
|
|
model="special-llama-model",
|
|
messages=[
|
|
{"role": "user", "content": "What is the capital of France?"},
|
|
],
|
|
)
|
|
)
|
|
|
|
print("calculated cost", cost_obj)
|
|
_cost = cost_obj["cost"]
|
|
|
|
assert _cost > 0.0
|
|
|
|
# set router to init value
|
|
setattr(litellm.proxy.proxy_server, "llm_router", init_llm_router)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_spend_calc_using_response():
|
|
cost_obj = await calculate_spend(
|
|
request=SpendCalculateRequest(
|
|
completion_response={
|
|
"id": "chatcmpl-3bc7abcd-f70b-48ab-a16c-dfba0b286c86",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"message": {
|
|
"content": "Yooo! What's good?",
|
|
"role": "assistant",
|
|
},
|
|
}
|
|
],
|
|
"created": "1677652288",
|
|
"model": "groq/llama-3.1-8b-instant",
|
|
"object": "chat.completion",
|
|
"system_fingerprint": "fp_873a560973",
|
|
"usage": {
|
|
"completion_tokens": 8,
|
|
"prompt_tokens": 12,
|
|
"total_tokens": 20,
|
|
},
|
|
}
|
|
)
|
|
)
|
|
|
|
print("calculated cost", cost_obj)
|
|
cost = cost_obj["cost"]
|
|
assert cost > 0.0
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_spend_calc_model_alias_on_router_messages():
|
|
from litellm.proxy.proxy_server import llm_router as init_llm_router
|
|
|
|
temp_llm_router = Router(
|
|
model_list=[
|
|
{
|
|
"model_name": "gpt-4o",
|
|
"litellm_params": {
|
|
"model": "gpt-4o",
|
|
},
|
|
}
|
|
],
|
|
model_group_alias={
|
|
"gpt4o": "gpt-4o",
|
|
},
|
|
)
|
|
|
|
setattr(litellm.proxy.proxy_server, "llm_router", temp_llm_router)
|
|
|
|
cost_obj = await calculate_spend(
|
|
request=SpendCalculateRequest(
|
|
model="gpt4o",
|
|
messages=[
|
|
{"role": "user", "content": "What is the capital of France?"},
|
|
],
|
|
)
|
|
)
|
|
|
|
print("calculated cost", cost_obj)
|
|
_cost = cost_obj["cost"]
|
|
|
|
assert _cost > 0.0
|
|
|
|
# set router to init value
|
|
setattr(litellm.proxy.proxy_server, "llm_router", init_llm_router)
|