phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(fix) test-semantic caching

Browse source
This commit is contained in:
ishaan-jaff 2024-02-06 10:39:44 -08:00 • committed by Krrish Dholakia
parent f8248b2c79
commit f3de05cc54
1 changed files with 28 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

32
litellm/tests/test_caching.py
View file

@ -1019,8 +1019,20 @@ def test_redis_semantic_cache_completion():
)
print(f"response1: {response1}")
assert response1.id == "chatcmpl-8p5GejSWLJ1pDI1lfhc6Idhwd2bDJ"
# assert response1.choices[0].message == 1
random_number = random.randint(1, 100000)
response2 = completion(
model="gpt-3.5-turbo",
messages=[
{
"role": "user",
"content": f"write a one sentence poem about: {random_number}",
}
],
max_tokens=20,
)
print(f"response2: {response1}")
assert response1.id == response2.id
# test_redis_cache_completion()
@ -1054,8 +1066,20 @@ async def test_redis_semantic_cache_acompletion():
"content": f"write a one sentence poem about: {random_number}",
}
],
max_tokens=20,
max_tokens=5,
)
print(f"response1: {response1}")
assert response1.id == "chatcmpl-8pI86yvT7fvgLDjngZSKULy1iP1o5"
random_number = random.randint(1, 100000)
response2 = await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[
{
"role": "user",
"content": f"write a one sentence poem about: {random_number}",
}
],
max_tokens=5,
)
print(f"response2: {response2}")
assert response1.id == response2.id