mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-06 08:16:43 +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
97 lines
3.1 KiB
Python
97 lines
3.1 KiB
Python
|
|
import os
|
|
|
|
|
|
import asyncio
|
|
import litellm
|
|
from litellm._logging import verbose_logger
|
|
import logging
|
|
import time
|
|
import pytest
|
|
|
|
|
|
def test_otel_logging_async():
|
|
try:
|
|
os.environ["OTEL_EXPORTER"] = "otlp_http"
|
|
os.environ["OTEL_ENDPOINT"] = (
|
|
"https://exampleopenaiendpoint-production.up.railway.app/traces"
|
|
)
|
|
os.environ["OTEL_HEADERS"] = "Authorization=K0BSwd"
|
|
|
|
def single_run():
|
|
litellm.callbacks = []
|
|
start_time_empty = asyncio.run(make_async_calls())
|
|
print(f"Time with empty callback: {start_time_empty}")
|
|
|
|
litellm.callbacks = ["otel"]
|
|
start_time_otel = asyncio.run(make_async_calls())
|
|
print(f"Time with otel callback: {start_time_otel}")
|
|
|
|
percent_diff = (
|
|
abs(start_time_otel - start_time_empty) / start_time_empty * 100
|
|
)
|
|
print(f"Run performance difference: {percent_diff:.2f}%")
|
|
return percent_diff
|
|
|
|
percent_diffs = [single_run() for _ in range(3)]
|
|
avg_percent_diff = sum(percent_diffs) / len(percent_diffs)
|
|
|
|
print(f"Percentage differences: {percent_diffs}")
|
|
print(f"Average performance difference: {avg_percent_diff:.2f}%")
|
|
|
|
assert (
|
|
avg_percent_diff < 30
|
|
), f"Average performance difference of {avg_percent_diff:.2f}% exceeds 30% threshold"
|
|
|
|
except litellm.Timeout as e:
|
|
pass
|
|
except Exception as e:
|
|
pytest.fail(f"An exception occurred - {e}")
|
|
|
|
|
|
async def make_async_calls(metadata=None, **completion_kwargs):
|
|
total_start_time = asyncio.get_event_loop().time()
|
|
tasks = []
|
|
|
|
async def create_and_run_task():
|
|
task = create_async_task(**completion_kwargs)
|
|
response = await task
|
|
print(f"Response: {response}")
|
|
|
|
for _ in range(3): # Run for 10 seconds
|
|
# Create 100 tasks
|
|
tasks = []
|
|
for _ in range(100):
|
|
tasks.append(asyncio.create_task(create_and_run_task()))
|
|
|
|
# Wait for any remaining tasks to complete
|
|
await asyncio.gather(*tasks)
|
|
|
|
await asyncio.sleep(1)
|
|
|
|
# Calculate the total time taken
|
|
total_time = asyncio.get_event_loop().time() - total_start_time
|
|
|
|
return total_time
|
|
|
|
|
|
def create_async_task(**completion_kwargs):
|
|
"""
|
|
Creates an async task for the litellm.acompletion function.
|
|
This is just the task, but it is not run here.
|
|
To run the task it must be awaited or used in other asyncio coroutine execution functions like asyncio.gather.
|
|
Any kwargs passed to this function will be passed to the litellm.acompletion function.
|
|
By default a standard set of arguments are used for the litellm.acompletion function.
|
|
"""
|
|
completion_args = {
|
|
"model": "openai/chatgpt-v-3",
|
|
"api_version": "2024-02-01",
|
|
"messages": [{"role": "user", "content": "This is a test" * 100}],
|
|
"max_tokens": 5,
|
|
"temperature": 0.7,
|
|
"timeout": 5,
|
|
"user": "langfuse_latency_test_user",
|
|
"mock_response": "Mock response",
|
|
}
|
|
completion_args.update(completion_kwargs)
|
|
return asyncio.create_task(litellm.acompletion(**completion_args))
|