diff --git a/litellm/main.py b/litellm/main.py index 69ec7985de4..3429cab4d2f 100644 --- a/litellm/main.py +++ b/litellm/main.py @@ -14,6 +14,7 @@ from functools import partial import dotenv, traceback, random, asyncio, time, contextvars from copy import deepcopy import httpx + import litellm from ._logging import verbose_logger from litellm import ( # type: ignore diff --git a/litellm/tests/test_token_counter.py b/litellm/tests/test_token_counter.py index 78e276a85ca..194dfb8af32 100644 --- a/litellm/tests/test_token_counter.py +++ b/litellm/tests/test_token_counter.py @@ -174,7 +174,6 @@ def test_load_test_token_counter(model): """ import tiktoken - enc = tiktoken.get_encoding("cl100k_base") messages = [{"role": "user", "content": text}] * 10 start_time = time.time() @@ -186,4 +185,4 @@ def test_load_test_token_counter(model): total_time = end_time - start_time print("model={}, total test time={}".format(model, total_time)) - assert total_time < 2, f"Total encoding time > 1.5s, {total_time}" + assert total_time < 10, f"Total encoding time > 10s, {total_time}"