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

(chore) remove bloat caching tests

Browse source
This commit is contained in:
ishaan-jaff 2023-11-15 17:58:56 -08:00
parent a3d280baa3
commit 3945bfadb7
1 changed files with 0 additions and 122 deletions
Download patch file Download diff file Expand all files Collapse all files

122
litellm/tests/test_caching.py
View file

@ -19,52 +19,6 @@ messages = [{"role": "user", "content": "who is ishaan Github? "}]
# comment
def test_gpt_cache():
try:
# INIT GPT Cache #
from gptcache import cache
import gptcache
from gptcache.processor.pre import last_content_without_prompt
from litellm.gpt_cache import completion
from typing import Dict, Any
def pre_cache_func(data: Dict[str, Any], **params: Dict[str, Any]) -> Any:
# use this to set cache key
print("in do nothing")
last_content_without_prompt_val = last_content_without_prompt(data, **params)
print("last content without prompt", last_content_without_prompt_val)
print("model", data["model"])
cache_key = last_content_without_prompt_val + data["model"]
print("cache_key", cache_key)
return cache_key
cache.init(pre_func=pre_cache_func)
cache.set_openai_key()
messages = [{"role": "user", "content": "why should I use LiteLLM today"}]
response1 = completion(model="gpt-3.5-turbo", messages=messages)
response2 = completion(model="gpt-3.5-turbo", messages=messages)
response3 = completion(model="command-nightly", messages=messages)
if response1["choices"] != response2["choices"]: # same models should cache
print(f"response1: {response1}")
print(f"response2: {response2}")
pytest.fail(f"Error occurred:")
if response3["choices"] == response2["choices"]: # different models, don't cache
# if models are different, it should not return cached response
print(f"response2: {response2}")
print(f"response3: {response3}")
pytest.fail(f"Error occurred:")
except:
pass
# test_gpt_cache()
####### Updated Caching as of Aug 28, 2023 ###################
messages = [{"role": "user", "content": "who is ishaan 5222"}]
def test_caching_v2():
@ -198,82 +152,6 @@ def test_embedding_caching_azure():
# test_embedding_caching_azure()
# test caching with streaming
# flaky test on circle ci for some reason?
# def test_caching_v2_stream_basic():
# try:
# litellm.cache = Cache()
# messages = [{"role": "user", "content": "tell me a story in 2 sentences"}]
# response1 = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
# result_string = ""
# for chunk in response1:
# print(chunk)
# result_string+=chunk['choices'][0]['delta']['content']
# # response1_id = chunk['id']
# print("current cache")
# print(litellm.cache.cache.cache_dict)
# result2_string=""
# import time
# time.sleep(1)
# response2 = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
# for chunk in response2:
# print(chunk)
# result2_string+=chunk['choices'][0]['delta']['content']
# if result_string != result2_string:
# print(result_string)
# print(result2_string)
# pytest.fail(f"Error occurred: Caching with streaming failed, strings diff")
# litellm.cache = None
# except Exception as e:
# print(f"error occurred: {traceback.format_exc()}")
# pytest.fail(f"Error occurred: {e}")
# test_caching_v2_stream_basic()
# def test_caching_v2_stream():
# try:
# litellm.cache = Cache()
# # litellm.token="ishaan@berri.ai"
# messages = [{"role": "user", "content": "tell me a story in 2 sentences"}]
# response1 = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
# messages = [{"role": "user", "content": "tell me a chair"}]
# response7 = completion(model="command-nightly", messages=messages)
# messages = [{"role": "user", "content": "sing a song"}]
# response8 = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
# result_string = ""
# for chunk in response1:
# print(chunk)
# result_string+=chunk['choices'][0]['delta']['content']
# # response1_id = chunk['id']
# print("current cache")
# messages = [{"role": "user", "content": "tell me a story in 2 sentences"}]
# print(litellm.cache.cache.cache_dict)
# result2_string=""
# response2 = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
# for chunk in response2:
# print(chunk)
# result2_string+=chunk['choices'][0]['delta']['content']
# if result_string != result2_string:
# print(result_string)
# print(result2_string)
# pytest.fail(f"Error occurred: Caching with streaming failed, strings diff")
# litellm.cache = None
# except Exception as e:
# print(f"error occurred: {traceback.format_exc()}")
# pytest.fail(f"Error occurred: {e}")
# test_caching_v2_stream()
def test_redis_cache_completion():
litellm.set_verbose = True
messages = [{"role": "user", "content": "who is ishaan CTO of litellm from litellm 2023"}]