diff --git a/litellm/tests/test_caching.py b/litellm/tests/test_caching.py index 4b47614cca..a1a42ff659 100644 --- a/litellm/tests/test_caching.py +++ b/litellm/tests/test_caching.py @@ -991,6 +991,9 @@ def test_cache_context_managers(): def test_redis_semantic_cache_completion(): litellm.set_verbose = True + import logging + + logging.basicConfig(level=logging.DEBUG) random_number = random.randint( 1, 100000 @@ -1021,3 +1024,38 @@ def test_redis_semantic_cache_completion(): # test_redis_cache_completion() + + +@pytest.mark.asyncio +async def test_redis_semantic_cache_acompletion(): + litellm.set_verbose = True + import logging + + logging.basicConfig(level=logging.DEBUG) + + random_number = random.randint( + 1, 100000 + ) # add a random number to ensure it's always adding / reading from cache + + print("testing semantic caching") + litellm.cache = Cache( + type="redis-semantic", + host=os.environ["REDIS_HOST"], + port=os.environ["REDIS_PORT"], + password=os.environ["REDIS_PASSWORD"], + similarity_threshold=0.8, + redis_semantic_cache_use_async=True, + ) + response1 = await litellm.acompletion( + model="gpt-3.5-turbo", + messages=[ + { + "role": "user", + "content": f"write a one sentence poem about: {random_number}", + } + ], + max_tokens=20, + ) + print(f"response1: {response1}") + + assert response1.id == "chatcmpl-8pI86yvT7fvgLDjngZSKULy1iP1o5"