mirror of
https://github.com/tiennm99/litellm.git
synced 2026-06-18 07:33:58 +00:00
Krish Dholakia
ba39f9e360
* fix(helicone.py): add helicone api base support Fixes https://github.com/BerriAI/litellm/issues/10825 * test: add unit test for cache hit response on embedding calls * fix(caching_handler.py): fix handling cache hit on embedding when input is string Fixes LIT-197 * docs(helicone_integration.md): document new helicone api base param
55 lines
1.4 KiB
Python
55 lines
1.4 KiB
Python
import asyncio
|
|
import json
|
|
import os
|
|
import sys
|
|
import time
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import httpx
|
|
import pytest
|
|
import respx
|
|
from fastapi.testclient import TestClient
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../../..")
|
|
) # Adds the parent directory to the system path
|
|
from datetime import datetime
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
from litellm.caching.caching_handler import LLMCachingHandler
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_process_async_embedding_cached_response():
|
|
llm_caching_handler = LLMCachingHandler(
|
|
original_function=MagicMock(),
|
|
request_kwargs={},
|
|
start_time=datetime.now(),
|
|
)
|
|
|
|
args = {
|
|
"cached_result": [
|
|
{
|
|
"embedding": [-0.025122925639152527, -0.019487135112285614],
|
|
"index": 0,
|
|
"object": "embedding",
|
|
}
|
|
]
|
|
}
|
|
|
|
mock_logging_obj = MagicMock()
|
|
mock_logging_obj.async_success_handler = AsyncMock()
|
|
response, cache_hit = llm_caching_handler._process_async_embedding_cached_response(
|
|
final_embedding_cached_response=None,
|
|
cached_result=args["cached_result"],
|
|
kwargs={"model": "text-embedding-ada-002", "input": "test"},
|
|
logging_obj=mock_logging_obj,
|
|
start_time=datetime.now(),
|
|
model="text-embedding-ada-002",
|
|
)
|
|
|
|
assert cache_hit
|
|
|
|
print(f"response: {response}")
|
|
assert len(response.data) == 1
|