mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-08 22:21:35 +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
135 lines
4.1 KiB
Python
135 lines
4.1 KiB
Python
import asyncio
|
|
import time
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
from typing import Dict, List, Optional, Union
|
|
|
|
import pytest
|
|
|
|
import litellm
|
|
from litellm import Router
|
|
from litellm.router import CustomRoutingStrategyBase
|
|
|
|
from tests.fake_openai_endpoint import FAKE_OPENAI_API_BASE
|
|
|
|
|
|
def _create_router():
|
|
return Router(
|
|
model_list=[
|
|
{
|
|
"model_name": "azure-model",
|
|
"litellm_params": {
|
|
"model": "openai/very-special-endpoint",
|
|
"api_base": FAKE_OPENAI_API_BASE,
|
|
"api_key": "fake-key",
|
|
},
|
|
"model_info": {"id": "very-special-endpoint"},
|
|
},
|
|
{
|
|
"model_name": "azure-model",
|
|
"litellm_params": {
|
|
"model": "openai/fast-endpoint",
|
|
"api_base": FAKE_OPENAI_API_BASE,
|
|
"api_key": "fake-key",
|
|
},
|
|
"model_info": {"id": "fast-endpoint"},
|
|
},
|
|
],
|
|
set_verbose=True,
|
|
debug_level="DEBUG",
|
|
)
|
|
|
|
|
|
class CustomRoutingStrategy(CustomRoutingStrategyBase):
|
|
def __init__(self, router_instance: Router):
|
|
self._router = router_instance
|
|
|
|
async def async_get_available_deployment(
|
|
self,
|
|
model: str,
|
|
messages: Optional[List[Dict[str, str]]] = None,
|
|
input: Optional[Union[str, List]] = None,
|
|
specific_deployment: Optional[bool] = False,
|
|
request_kwargs: Optional[Dict] = None,
|
|
):
|
|
print("In CUSTOM async get available deployment")
|
|
model_list = self._router.model_list
|
|
print("router model list=", model_list)
|
|
for model in model_list:
|
|
if isinstance(model, dict):
|
|
if model["litellm_params"]["model"] == "openai/very-special-endpoint":
|
|
return model
|
|
pass
|
|
|
|
def get_available_deployment(
|
|
self,
|
|
model: str,
|
|
messages: Optional[List[Dict[str, str]]] = None,
|
|
input: Optional[Union[str, List]] = None,
|
|
specific_deployment: Optional[bool] = False,
|
|
request_kwargs: Optional[Dict] = None,
|
|
):
|
|
pass
|
|
|
|
|
|
def test_reset_custom_routing_strategy():
|
|
"""
|
|
Setting a custom routing strategy installs instance-level overrides for
|
|
get_available_deployment / async_get_available_deployment. Re-initializing the
|
|
routing strategy must clear them so the class implementations are used again.
|
|
"""
|
|
router = _create_router()
|
|
router.set_custom_routing_strategy(CustomRoutingStrategy(router))
|
|
|
|
assert "get_available_deployment" in router.__dict__
|
|
assert "async_get_available_deployment" in router.__dict__
|
|
|
|
router._reset_custom_routing_strategy()
|
|
|
|
assert "get_available_deployment" not in router.__dict__
|
|
assert "async_get_available_deployment" not in router.__dict__
|
|
assert (
|
|
router.async_get_available_deployment.__func__
|
|
is Router.async_get_available_deployment
|
|
)
|
|
|
|
# idempotent: resetting again when nothing is overridden must not raise
|
|
router._reset_custom_routing_strategy()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_custom_routing():
|
|
litellm.set_verbose = True
|
|
|
|
router = _create_router()
|
|
router.set_custom_routing_strategy(CustomRoutingStrategy(router))
|
|
|
|
# make 4 requests
|
|
for _ in range(4):
|
|
try:
|
|
response = await router.acompletion(
|
|
model="azure-model", messages=[{"role": "user", "content": "hello"}]
|
|
)
|
|
print(response)
|
|
except Exception as e:
|
|
print("got exception", e)
|
|
|
|
await asyncio.sleep(1)
|
|
print("done sending initial requests to collect latency")
|
|
|
|
deployments = {}
|
|
# make 10 requests
|
|
for _ in range(10):
|
|
response = await router.acompletion(
|
|
model="azure-model", messages=[{"role": "user", "content": "hello"}]
|
|
)
|
|
print(response)
|
|
_picked_model_id = response._hidden_params["model_id"]
|
|
if _picked_model_id not in deployments:
|
|
deployments[_picked_model_id] = 1
|
|
else:
|
|
deployments[_picked_model_id] += 1
|
|
print("deployments", deployments)
|