mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-12 03:48:56 +00:00
dfe4df8c8a
* test: delete unconditionally skipped legacy tests * test: move whole-unit legacy test files into tests/unit * test: keep moved legacy tests free of import-time global state * test: keep the module-level invocation scan pointed at tests/local_testing * ci: drop the agent_testing CircleCI job emptied by the move * test: fix moved-test isolation and router coverage * test: add Tinyfish search package marker * test: isolate moved tests from logger state leaks * test: isolate Helicone logging fixture state * test: isolate Vertex pass-through credentials between moved tests * test: cancel S3 periodic flush tasks started by moved tests * ci: restore CircleCI assistant test selection after move * test: prevent Datadog datetime import shadowing * ci: drop the litellm_assistants_api_testing CircleCI job emptied by the move * test: deduplicate imports in rebased unit tests * test: remove duplicate passthrough router patch import * test: remove moved legacy source files after rebase * test: align moved tests with rebased main * test: carry main's legacy-file edits into moved destinations * test: make the moved cost map fallback tests assert the fetch and the backup The four fallback cases only checked the result was non-empty, so they still passed with integrity validation disabled. They now inject a mock client, assert one fetch happened, and assert the result is exactly the local backup with the fallback reason recorded. --------- Co-authored-by: yuneng <yuneng@berri.ai>
100 lines
3.2 KiB
Python
100 lines
3.2 KiB
Python
#### What this tests ####
|
|
# This tests using caching w/ litellm which requires SSL=True
|
|
|
|
import os
|
|
import sys
|
|
import time
|
|
import traceback
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
import pytest
|
|
|
|
import litellm
|
|
from litellm import Router, completion, embedding
|
|
from litellm.caching.caching import Cache
|
|
|
|
messages = [{"role": "user", "content": f"who is ishaan {time.time()}"}]
|
|
|
|
|
|
def test_caching_v2(): # test in memory cache
|
|
try:
|
|
litellm.cache = Cache(
|
|
type="redis",
|
|
host="os.environ/REDIS_HOST_2",
|
|
port="os.environ/REDIS_PORT_2",
|
|
password="os.environ/REDIS_PASSWORD_2",
|
|
ssl="os.environ/REDIS_SSL_2",
|
|
)
|
|
response1 = completion(model="gpt-3.5-turbo", messages=messages, caching=True)
|
|
response2 = completion(model="gpt-3.5-turbo", messages=messages, caching=True)
|
|
print(f"response1: {response1}")
|
|
print(f"response2: {response2}")
|
|
litellm.cache = None # disable cache
|
|
if (
|
|
response2["choices"][0]["message"]["content"]
|
|
!= response1["choices"][0]["message"]["content"]
|
|
):
|
|
print(f"response1: {response1}")
|
|
print(f"response2: {response2}")
|
|
raise Exception()
|
|
except Exception as e:
|
|
print(f"error occurred: {traceback.format_exc()}")
|
|
pytest.fail(f"Error occurred: {e}")
|
|
|
|
|
|
# test_caching_v2()
|
|
|
|
|
|
def test_caching_router():
|
|
"""
|
|
Test scenario where litellm.cache is set but kwargs("caching") is not. This should still return a cache hit.
|
|
"""
|
|
try:
|
|
model_list = [
|
|
{
|
|
"model_name": "gpt-3.5-turbo", # openai model name
|
|
"litellm_params": { # params for litellm completion/embedding call
|
|
"model": "azure/gpt-4.1-mini",
|
|
"api_key": os.getenv("AZURE_AI_API_KEY"),
|
|
"api_version": os.getenv("AZURE_API_VERSION"),
|
|
"api_base": os.getenv("AZURE_AI_API_BASE"),
|
|
},
|
|
"tpm": 240000,
|
|
"rpm": 1800,
|
|
}
|
|
]
|
|
litellm.cache = Cache(
|
|
type="redis",
|
|
host="os.environ/REDIS_HOST",
|
|
port="os.environ/REDIS_PORT",
|
|
password="os.environ/REDIS_PASSWORD",
|
|
ssl="os.environ/REDIS_SSL",
|
|
)
|
|
router = Router(
|
|
model_list=model_list,
|
|
routing_strategy="simple-shuffle",
|
|
set_verbose=False,
|
|
num_retries=1,
|
|
) # type: ignore
|
|
response1 = completion(model="gpt-3.5-turbo", messages=messages)
|
|
response2 = completion(model="gpt-3.5-turbo", messages=messages)
|
|
if (
|
|
response2["choices"][0]["message"]["content"]
|
|
!= response1["choices"][0]["message"]["content"]
|
|
):
|
|
print(f"response1: {response1}")
|
|
print(f"response2: {response2}")
|
|
litellm.cache = None # disable cache
|
|
assert (
|
|
response2["choices"][0]["message"]["content"]
|
|
== response1["choices"][0]["message"]["content"]
|
|
)
|
|
except Exception as e:
|
|
print(f"error occurred: {traceback.format_exc()}")
|
|
pytest.fail(f"Error occurred: {e}")
|
|
|
|
|
|
# test_caching_router()
|