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

fix(pattern_match_deployments.py): default to user input if unable to… (#6632)

Browse source 
* fix(pattern_match_deployments.py): default to user input if unable to map based on wildcards

* test: fix test

* test: reset test name

* test: update conftest to reload proxy server module between tests

* ci(config.yml): move langfuse out of local_testing

reduce ci/cd time

* ci(config.yml): cleanup langfuse ci/cd tests

* fix: update test to not use global proxy_server app module

* ci: move caching to a separate test pipeline

speed up ci pipeline

* test: update conftest to check if proxy_server attr exists before reloading

* build(conftest.py): don't block on inability to reload proxy_server

* ci(config.yml): update caching unit test filter to work on 'cache' keyword as well

* fix(encrypt_decrypt_utils.py): use function to get salt key

* test: mark flaky test

* test: handle anthropic overloaded errors

* refactor: create separate ci/cd pipeline for proxy unit tests

make ci/cd faster

* ci(config.yml): add litellm_proxy_unit_testing to build_and_test jobs

* ci(config.yml): generate prisma binaries for proxy unit tests

* test: readd vertex_key.json

* ci(config.yml): remove `-s` from proxy_unit_test cmd

speed up test

* ci: remove any 'debug' logging flag

speed up ci pipeline

* test: fix test

* test(test_braintrust.py): rerun

* test: add delay for braintrust test
This commit is contained in:
Krish Dholakia 2024-11-08 00:55:57 +05:30 • committed by GitHub
parent 44840d615d
commit 27e18358ab
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
77 changed files with 2861 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

192
tests/local_testing/test_proxy_reject_logging.py
View file

@ -1,192 +0,0 @@
# What is this?
## Unit test that rejected requests are also logged as failures
# What is this?
## This tests the llm guard integration
import asyncio
import os
import random
# What is this?
## Unit test for presidio pii masking
import sys
import time
import traceback
from datetime import datetime
from dotenv import load_dotenv
load_dotenv()
import os
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
from typing import Literal
import pytest
from fastapi import Request, Response
from starlette.datastructures import URL
import litellm
from litellm import Router, mock_completion
from litellm.caching.caching import DualCache
from litellm.integrations.custom_logger import CustomLogger
from litellm.proxy._types import UserAPIKeyAuth
from litellm.proxy.enterprise.enterprise_hooks.secret_detection import (
_ENTERPRISE_SecretDetection,
)
from litellm.proxy.proxy_server import (
Depends,
HTTPException,
chat_completion,
completion,
embeddings,
)
from litellm.proxy.utils import ProxyLogging, hash_token
from litellm.router import Router
class testLogger(CustomLogger):
def __init__(self):
self.reaches_sync_failure_event = False
self.reaches_async_failure_event = False
async def async_pre_call_hook(
self,
user_api_key_dict: UserAPIKeyAuth,
cache: DualCache,
data: dict,
call_type: Literal[
"completion",
"text_completion",
"embeddings",
"image_generation",
"moderation",
"audio_transcription",
"pass_through_endpoint",
"rerank",
],
):
raise HTTPException(
status_code=429, detail={"error": "Max parallel request limit reached"}
)
async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time):
self.reaches_async_failure_event = True
def log_failure_event(self, kwargs, response_obj, start_time, end_time):
self.reaches_sync_failure_event = True
router = Router(
model_list=[
{
"model_name": "fake-model",
"litellm_params": {
"model": "openai/fake",
"api_base": "https://exampleopenaiendpoint-production.up.railway.app/",
"api_key": "sk-12345",
},
}
]
)
@pytest.mark.parametrize(
"route, body",
[
(
"/v1/chat/completions",
{
"model": "fake-model",
"messages": [
{
"role": "user",
"content": "Hello here is my OPENAI_API_KEY = sk-12345",
}
],
},
),
("/v1/completions", {"model": "fake-model", "prompt": "ping"}),
(
"/v1/embeddings",
{
"input": "The food was delicious and the waiter...",
"model": "text-embedding-ada-002",
"encoding_format": "float",
},
),
],
)
@pytest.mark.asyncio
async def test_chat_completion_request_with_redaction(route, body):
"""
IMPORTANT Enterprise Test - Do not delete it:
Makes a /chat/completions request on LiteLLM Proxy
Ensures that the secret is redacted EVEN on the callback
"""
from litellm.proxy import proxy_server
setattr(proxy_server, "llm_router", router)
_test_logger = testLogger()
litellm.callbacks = [_test_logger]
litellm.set_verbose = True
# Prepare the query string
query_params = "param1=value1&param2=value2"
# Create the Request object with query parameters
request = Request(
scope={
"type": "http",
"method": "POST",
"headers": [(b"content-type", b"application/json")],
"query_string": query_params.encode(),
}
)
request._url = URL(url=route)
async def return_body():
import json
return json.dumps(body).encode()
request.body = return_body
try:
if route == "/v1/chat/completions":
response = await chat_completion(
request=request,
user_api_key_dict=UserAPIKeyAuth(
api_key="sk-12345", token="hashed_sk-12345", rpm_limit=0
),
fastapi_response=Response(),
)
elif route == "/v1/completions":
response = await completion(
request=request,
user_api_key_dict=UserAPIKeyAuth(
api_key="sk-12345", token="hashed_sk-12345", rpm_limit=0
),
fastapi_response=Response(),
)
elif route == "/v1/embeddings":
response = await embeddings(
request=request,
user_api_key_dict=UserAPIKeyAuth(
api_key="sk-12345", token="hashed_sk-12345", rpm_limit=0
),
fastapi_response=Response(),
)
except Exception:
pass
await asyncio.sleep(3)
assert _test_logger.reaches_async_failure_event is True
assert _test_logger.reaches_sync_failure_event is True