mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
bd39e1ab5d
* add get_complete_url to base config * cloudflare - refactor to following existing pattern * migrate cloudflare chat completions to base llm http handler * fix unused import * fix fake stream in cloudflare * fix cloudflare transformation * fix naming for BaseModelResponseIterator * add async cloudflare streaming test * test cloudflare * add handler.py * add handler.py in cohere handler.py
42 lines
997 B
Python
42 lines
997 B
Python
import os
|
|
import sys
|
|
import traceback
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
import io
|
|
import os
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system path
|
|
import json
|
|
|
|
import pytest
|
|
|
|
import litellm
|
|
from litellm import RateLimitError, Timeout, completion, completion_cost, embedding
|
|
|
|
|
|
# Cloud flare AI test
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("stream", [True, False])
|
|
async def test_completion_cloudflare(stream):
|
|
try:
|
|
litellm.set_verbose = False
|
|
response = await litellm.acompletion(
|
|
model="cloudflare/@cf/meta/llama-2-7b-chat-int8",
|
|
messages=[{"content": "what llm are you", "role": "user"}],
|
|
max_tokens=15,
|
|
stream=stream,
|
|
)
|
|
print(response)
|
|
if stream is True:
|
|
async for chunk in response:
|
|
print(chunk)
|
|
else:
|
|
print(response)
|
|
|
|
except Exception as e:
|
|
pytest.fail(f"Error occurred: {e}")
|