phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 18:24:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add litellm caching

Browse source
This commit is contained in:
ishaan-jaff 2023-08-26 16:08:47 -07:00
parent 9155ba068f
commit 77436cbcf4
3 changed files with 19 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

3
.circleci/requirements.txt
View file

@ -4,4 +4,5 @@ python-dotenv
openai
tiktoken
importlib_metadata
baseten
baseten
gptcache

BIN
litellm/tests/data_map.txt
View file

Binary file not shown.

33
litellm/tests/test_caching.py
View file

@ -48,22 +48,23 @@ def test_caching_with_models():
pytest.fail(f"Error occurred:")
# def test_gpt_cache():
# # INIT GPT Cache #
# from gptcache import cache
# cache.init()
# cache.set_openai_key()
def test_gpt_cache():
# INIT GPT Cache #
from gptcache import cache
from litellm.cache import completion
cache.init()
cache.set_openai_key()
# messages = [{"role": "user", "content": "what is litellm this morning? "}]
# response2 = litellm.cache.completion(model="gpt-3.5-turbo", messages=messages)
# response3 = litellm.cache.completion(model="command-nightly", messages=messages)
# print(f"response2: {response2}")
# print(f"response3: {response3}")
messages = [{"role": "user", "content": "what is litellm YC 22?"}]
response2 = completion(model="gpt-3.5-turbo", messages=messages)
response3 = completion(model="command-nightly", messages=messages)
print(f"response2: {response2}")
print(f"response3: {response3}")
if response3['choices'] != response2['choices']:
# if models are different, it should not return cached response
print(f"response2: {response2}")
print(f"response3: {response3}")
pytest.fail(f"Error occurred:")
# if response3 != response2:
# # if models are different, it should not return cached response
# print(f"response2: {response2}")
# print(f"response3: {response3}")
# pytest.fail(f"Error occurred:")
# test_gpt_cache()