From 349223fd8b32ad690a7a60deace6f91960c1bdef Mon Sep 17 00:00:00 2001 From: mateo Date: Thu, 17 Sep 2026 20:05:27 +0000 Subject: [PATCH] test: remove fully commented-out test files that collect no tests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- tests/image_gen_tests/test_image_variation.py | 87 ---- tests/local_testing/test_azure_perf.py | 128 ------ tests/local_testing/test_budget_manager.py | 130 ------ tests/local_testing/test_class.py | 124 ------ .../test_langchain_ChatLiteLLM.py | 90 ----- .../local_testing/test_load_test_router_s3.py | 94 ----- tests/local_testing/test_loadtest_router.py | 86 ---- tests/local_testing/test_logging.py | 382 ------------------ .../local_testing/test_max_tpm_rpm_limiter.py | 163 -------- tests/local_testing/test_mem_leak.py | 243 ----------- tests/local_testing/test_mem_usage.py | 153 ------- tests/local_testing/test_ollama_local.py | 336 --------------- tests/local_testing/test_ollama_local_chat.py | 334 --------------- tests/search_tests/test_google_pse_search.py | 20 - 14 files changed, 2370 deletions(-) delete mode 100644 tests/image_gen_tests/test_image_variation.py delete mode 100644 tests/local_testing/test_azure_perf.py delete mode 100644 tests/local_testing/test_budget_manager.py delete mode 100644 tests/local_testing/test_class.py delete mode 100644 tests/local_testing/test_langchain_ChatLiteLLM.py delete mode 100644 tests/local_testing/test_load_test_router_s3.py delete mode 100644 tests/local_testing/test_loadtest_router.py delete mode 100644 tests/local_testing/test_logging.py delete mode 100644 tests/local_testing/test_max_tpm_rpm_limiter.py delete mode 100644 tests/local_testing/test_mem_leak.py delete mode 100644 tests/local_testing/test_mem_usage.py delete mode 100644 tests/local_testing/test_ollama_local.py delete mode 100644 tests/local_testing/test_ollama_local_chat.py delete mode 100644 tests/search_tests/test_google_pse_search.py diff --git a/tests/image_gen_tests/test_image_variation.py b/tests/image_gen_tests/test_image_variation.py deleted file mode 100644 index b566385bb8a..00000000000 --- a/tests/image_gen_tests/test_image_variation.py +++ /dev/null @@ -1,87 +0,0 @@ -# What this tests? -## This tests the litellm support for the openai /generations endpoint - -import logging -import traceback - - - -from dotenv import load_dotenv -from openai.types.image import Image -from litellm.caching import InMemoryCache - -logging.basicConfig(level=logging.DEBUG) -load_dotenv() -import asyncio -import pytest - -import litellm -import json -import tempfile -from base_image_generation_test import BaseImageGenTest -import logging -from litellm._logging import verbose_logger -from io import BytesIO -from PIL import Image as PILImage - -verbose_logger.setLevel(logging.DEBUG) - - -@pytest.fixture -def image_url(): - # DALL-E 2 image variations require a square PNG (less than 4MB) - # Generate a 1024x1024 square PNG programmatically to avoid network dependency - # and the non-square aspect ratio of the old LiteLLM logo URL - img = PILImage.new("RGBA", (1024, 1024), color=(128, 128, 128, 255)) - image_file = BytesIO() - img.save(image_file, format="PNG") - image_file.seek(0) - # openai>=2.24.0 requires BytesIO to have .name for MIME type detection in multipart uploads - image_file.name = "litellm_logo.png" - - return image_file - - -# Commented out: OpenAI /images/variations endpoint deprecated (DALL-E 2 shutdown May 12, 2026) -# def test_openai_image_variation_openai_sdk(image_url): -# from openai import OpenAI -# -# client = OpenAI() -# response = client.images.create_variation(image=image_url, n=2, size="1024x1024") -# print(response) -# -# -# @pytest.mark.parametrize("sync_mode", [True, False]) -# @pytest.mark.asyncio -# async def test_openai_image_variation_litellm_sdk(image_url, sync_mode): -# from litellm import image_variation, aimage_variation -# -# if sync_mode: -# image_variation(image=image_url, n=2, size="1024x1024") -# else: -# await aimage_variation(image=image_url, n=2, size="1024x1024") -# -# -# def test_topaz_image_variation(image_url): -# from litellm import image_variation, aimage_variation -# from litellm.llms.custom_httpx.http_handler import HTTPHandler -# from unittest.mock import patch -# -# client = HTTPHandler() -# with patch.object(client, "post") as mock_post: -# try: -# image_variation( -# model="topaz/Standard V2", -# image=image_url, -# n=2, -# size="1024x1024", -# client=client, -# ) -# except Exception as e: -# print(e) -# mock_post.assert_called_once() - - -def test_image_variation_placeholder(): - """Placeholder: variation tests commented out - OpenAI /images/variations deprecated (DALL-E 2 shutdown May 12, 2026).""" - pass diff --git a/tests/local_testing/test_azure_perf.py b/tests/local_testing/test_azure_perf.py deleted file mode 100644 index 57d56a24a15..00000000000 --- a/tests/local_testing/test_azure_perf.py +++ /dev/null @@ -1,128 +0,0 @@ -# #### What this tests #### -# # This adds perf testing to the router, to ensure it's never > 50ms slower than the azure-openai sdk. -# import sys, os, time, inspect, asyncio, traceback -# from datetime import datetime -# import pytest - -# sys.path.insert(0, os.path.abspath("../..")) -# import openai, litellm, uuid -# from openai import AsyncAzureOpenAI - -# client = AsyncAzureOpenAI( -# api_key=os.getenv("AZURE_AI_API_KEY"), -# azure_endpoint=os.getenv("AZURE_AI_API_BASE"), # type: ignore -# api_version=os.getenv("AZURE_API_VERSION"), -# ) - -# model_list = [ -# { -# "model_name": "azure-test", -# "litellm_params": { -# "model": "azure/gpt-4.1-mini", -# "api_key": os.getenv("AZURE_AI_API_KEY"), -# "api_base": os.getenv("AZURE_AI_API_BASE"), -# "api_version": os.getenv("AZURE_API_VERSION"), -# }, -# } -# ] - -# router = litellm.Router(model_list=model_list) # type: ignore - - -# async def _openai_completion(): -# try: -# start_time = time.time() -# response = await client.chat.completions.create( -# model="chatgpt-v-3", -# messages=[{"role": "user", "content": f"This is a test: {uuid.uuid4()}"}], -# stream=True, -# ) -# time_to_first_token = None -# first_token_ts = None -# init_chunk = None -# async for chunk in response: -# if ( -# time_to_first_token is None -# and len(chunk.choices) > 0 -# and chunk.choices[0].delta.content is not None -# ): -# first_token_ts = time.time() -# time_to_first_token = first_token_ts - start_time -# init_chunk = chunk -# end_time = time.time() -# print( -# "OpenAI Call: ", -# init_chunk, -# start_time, -# first_token_ts, -# time_to_first_token, -# end_time, -# ) -# return time_to_first_token -# except Exception as e: -# print(e) -# return None - - -# async def _router_completion(): -# try: -# start_time = time.time() -# response = await router.acompletion( -# model="azure-test", -# messages=[{"role": "user", "content": f"This is a test: {uuid.uuid4()}"}], -# stream=True, -# ) -# time_to_first_token = None -# first_token_ts = None -# init_chunk = None -# async for chunk in response: -# if ( -# time_to_first_token is None -# and len(chunk.choices) > 0 -# and chunk.choices[0].delta.content is not None -# ): -# first_token_ts = time.time() -# time_to_first_token = first_token_ts - start_time -# init_chunk = chunk -# end_time = time.time() -# print( -# "Router Call: ", -# init_chunk, -# start_time, -# first_token_ts, -# time_to_first_token, -# end_time - first_token_ts, -# ) -# return time_to_first_token -# except Exception as e: -# print(e) -# return None - - -# async def test_azure_completion_streaming(): -# """ -# Test azure streaming call - measure on time to first (non-null) token. -# """ -# n = 3 # Number of concurrent tasks -# ## OPENAI AVG. TIME -# tasks = [_openai_completion() for _ in range(n)] -# chat_completions = await asyncio.gather(*tasks) -# successful_completions = [c for c in chat_completions if c is not None] -# total_time = 0 -# for item in successful_completions: -# total_time += item -# avg_openai_time = total_time / 3 -# ## ROUTER AVG. TIME -# tasks = [_router_completion() for _ in range(n)] -# chat_completions = await asyncio.gather(*tasks) -# successful_completions = [c for c in chat_completions if c is not None] -# total_time = 0 -# for item in successful_completions: -# total_time += item -# avg_router_time = total_time / 3 -# ## COMPARE -# print(f"avg_router_time: {avg_router_time}; avg_openai_time: {avg_openai_time}") -# assert avg_router_time < avg_openai_time + 0.5 - - -# # asyncio.run(test_azure_completion_streaming()) diff --git a/tests/local_testing/test_budget_manager.py b/tests/local_testing/test_budget_manager.py deleted file mode 100644 index 6ebd060876d..00000000000 --- a/tests/local_testing/test_budget_manager.py +++ /dev/null @@ -1,130 +0,0 @@ -# #### What this tests #### -# # This tests calling batch_completions by running 100 messages together - -# import sys, os, json -# import traceback -# import pytest - -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import litellm -# litellm.set_verbose = True -# from litellm import completion, BudgetManager - -# budget_manager = BudgetManager(project_name="test_project", client_type="hosted") - -# ## Scenario 1: User budget enough to make call -# def test_user_budget_enough(): -# try: -# user = "1234" -# # create a budget for a user -# budget_manager.create_budget(total_budget=10, user=user, duration="daily") - -# # check if a given call can be made -# data = { -# "model": "gpt-3.5-turbo", -# "messages": [{"role": "user", "content": "Hey, how's it going?"}] -# } -# if budget_manager.get_current_cost(user=user) <= budget_manager.get_total_budget(user): -# response = completion(**data) -# print(budget_manager.update_cost(completion_obj=response, user=user)) -# else: -# response = "Sorry - no budget!" - -# print(f"response: {response}") -# except Exception as e: -# pytest.fail(f"An error occurred - {str(e)}") - -# ## Scenario 2: User budget not enough to make call -# def test_user_budget_not_enough(): -# try: -# user = "12345" -# # create a budget for a user -# budget_manager.create_budget(total_budget=0, user=user, duration="daily") - -# # check if a given call can be made -# data = { -# "model": "gpt-3.5-turbo", -# "messages": [{"role": "user", "content": "Hey, how's it going?"}] -# } -# model = data["model"] -# messages = data["messages"] -# if budget_manager.get_current_cost(user=user) < budget_manager.get_total_budget(user=user): -# response = completion(**data) -# print(budget_manager.update_cost(completion_obj=response, user=user)) -# else: -# response = "Sorry - no budget!" - -# print(f"response: {response}") -# except Exception: -# pytest.fail(f"An error occurred") - -# ## Scenario 3: Saving budget to client -# def test_save_user_budget(): -# try: -# response = budget_manager.save_data() -# if response["status"] == "error": -# raise Exception(f"An error occurred - {json.dumps(response)}") -# print(response) -# except Exception as e: -# pytest.fail(f"An error occurred: {str(e)}") - -# test_save_user_budget() -# ## Scenario 4: Getting list of users -# def test_get_users(): -# try: -# response = budget_manager.get_users() -# print(response) -# except Exception: -# pytest.fail(f"An error occurred") - - -# ## Scenario 5: Reset budget at the end of duration -# def test_reset_on_duration(): -# try: -# # First, set a short duration budget for a user -# user = "123456" -# budget_manager.create_budget(total_budget=10, user=user, duration="daily") - -# # Use some of the budget -# data = { -# "model": "gpt-3.5-turbo", -# "messages": [{"role": "user", "content": "Hello!"}] -# } -# if budget_manager.get_current_cost(user=user) <= budget_manager.get_total_budget(user=user): -# response = litellm.completion(**data) -# print(budget_manager.update_cost(completion_obj=response, user=user)) - -# assert budget_manager.get_current_cost(user) > 0, f"Test setup failed: Budget did not decrease after completion" - -# # Now, we need to simulate the passing of time. Since we don't want our tests to actually take days, we're going -# # to cheat a little -- we'll manually adjust the "created_at" time so it seems like a day has passed. -# # In a real-world testing scenario, we might instead use something like the `freezegun` library to mock the system time. -# one_day_in_seconds = 24 * 60 * 60 -# budget_manager.user_dict[user]["last_updated_at"] -= one_day_in_seconds - -# # Now the duration should have expired, so our budget should reset -# budget_manager.update_budget_all_users() - -# # Make sure the budget was actually reset -# assert budget_manager.get_current_cost(user) == 0, "Budget didn't reset after duration expired" -# except Exception as e: -# pytest.fail(f"An error occurred - {str(e)}") - -# ## Scenario 6: passing in text: -# def test_input_text_on_completion(): -# try: -# user = "12345" -# budget_manager.create_budget(total_budget=10, user=user, duration="daily") - -# input_text = "hello world" -# output_text = "it's a sunny day in san francisco" -# model = "gpt-3.5-turbo" - -# budget_manager.update_cost(user=user, model=model, input_text=input_text, output_text=output_text) -# print(budget_manager.get_current_cost(user)) -# except Exception as e: -# pytest.fail(f"An error occurred - {str(e)}") - -# test_input_text_on_completion() diff --git a/tests/local_testing/test_class.py b/tests/local_testing/test_class.py deleted file mode 100644 index b4b4f85a9d0..00000000000 --- a/tests/local_testing/test_class.py +++ /dev/null @@ -1,124 +0,0 @@ -# # #### What this tests #### -# # # This tests the LiteLLM Class - -# import sys, os -# import traceback -# import pytest - -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import litellm -# import asyncio - -# # litellm.set_verbose = True -# # from litellm import Router -# import instructor - -# from litellm import completion -# from pydantic import BaseModel - - -# class User(BaseModel): -# name: str -# age: int - - -# client = instructor.from_litellm(completion) - -# litellm.set_verbose = True - -# resp = client.chat.completions.create( -# model="gpt-3.5-turbo", -# max_tokens=1024, -# messages=[ -# { -# "role": "user", -# "content": "Extract Jason is 25 years old.", -# } -# ], -# response_model=User, -# num_retries=10, -# ) - -# assert isinstance(resp, User) -# assert resp.name == "Jason" -# assert resp.age == 25 - -# # from pydantic import BaseModel - -# # # This enables response_model keyword -# # # from client.chat.completions.create -# # client = instructor.patch( -# # Router( -# # 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"), -# # }, -# # } -# # ] -# # ) -# # ) - - -# # class UserDetail(BaseModel): -# # name: str -# # age: int - - -# # user = client.chat.completions.create( -# # model="gpt-3.5-turbo", -# # response_model=UserDetail, -# # messages=[ -# # {"role": "user", "content": "Extract Jason is 25 years old"}, -# # ], -# # ) - -# # assert isinstance(user, UserDetail) -# # assert user.name == "Jason" -# # assert user.age == 25 - -# # print(f"user: {user}") -# # # import instructor -# # # from openai import AsyncOpenAI - -# # aclient = instructor.apatch( -# # Router( -# # 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"), -# # }, -# # } -# # ], -# # default_litellm_params={"acompletion": True}, -# # ) -# # ) - - -# # class UserExtract(BaseModel): -# # name: str -# # age: int - - -# # async def main(): -# # model = await aclient.chat.completions.create( -# # model="gpt-3.5-turbo", -# # response_model=UserExtract, -# # messages=[ -# # {"role": "user", "content": "Extract jason is 25 years old"}, -# # ], -# # ) -# # print(f"model: {model}") - - -# # asyncio.run(main()) diff --git a/tests/local_testing/test_langchain_ChatLiteLLM.py b/tests/local_testing/test_langchain_ChatLiteLLM.py deleted file mode 100644 index 9b306886c62..00000000000 --- a/tests/local_testing/test_langchain_ChatLiteLLM.py +++ /dev/null @@ -1,90 +0,0 @@ -# import os -# import sys, os -# import traceback -# from dotenv import load_dotenv - -# load_dotenv() -# import os, io - -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import pytest -# import litellm -# from litellm import embedding, completion, text_completion, completion_cost - -# from langchain.chat_models import ChatLiteLLM -# from langchain.prompts.chat import ( -# ChatPromptTemplate, -# SystemMessagePromptTemplate, -# AIMessagePromptTemplate, -# HumanMessagePromptTemplate, -# ) -# from langchain.schema import AIMessage, HumanMessage, SystemMessage - -# def test_chat_gpt(): -# try: -# chat = ChatLiteLLM(model="gpt-3.5-turbo", max_tokens=10) -# messages = [ -# HumanMessage( -# content="what model are you" -# ) -# ] -# resp = chat(messages) - -# print(resp) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# # test_chat_gpt() - - -# def test_claude(): -# try: -# chat = ChatLiteLLM(model="claude-2", max_tokens=10) -# messages = [ -# HumanMessage( -# content="what model are you" -# ) -# ] -# resp = chat(messages) - -# print(resp) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# # test_claude() - - -# # def test_openai_with_params(): -# # try: -# # api_key = os.environ["OPENAI_API_KEY"] -# # os.environ.pop("OPENAI_API_KEY") -# # print("testing openai with params") -# # llm = ChatLiteLLM( -# # model="gpt-3.5-turbo", -# # openai_api_key=api_key, -# # # Prefer using None which is the default value, endpoint could be empty string -# # openai_api_base= None, -# # max_tokens=20, -# # temperature=0.5, -# # request_timeout=10, -# # model_kwargs={ -# # "frequency_penalty": 0, -# # "presence_penalty": 0, -# # }, -# # verbose=True, -# # max_retries=0, -# # ) -# # messages = [ -# # HumanMessage( -# # content="what model are you" -# # ) -# # ] -# # resp = llm(messages) - -# # print(resp) -# # except Exception as e: -# # pytest.fail(f"Error occurred: {e}") - -# # test_openai_with_params() diff --git a/tests/local_testing/test_load_test_router_s3.py b/tests/local_testing/test_load_test_router_s3.py deleted file mode 100644 index 70a4e873b6c..00000000000 --- a/tests/local_testing/test_load_test_router_s3.py +++ /dev/null @@ -1,94 +0,0 @@ -# import sys, os -# import traceback -# from dotenv import load_dotenv -# import copy - -# load_dotenv() -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import asyncio -# from litellm import Router, Timeout -# import time -# from litellm.caching.caching import Cache -# import litellm - -# litellm.cache = Cache( -# type="s3", s3_bucket_name="litellm-my-test-bucket-2", s3_region_name="us-west-2" -# ) - -# ### Test calling router with s3 Cache - - -# async def call_acompletion(semaphore, router: Router, input_data): -# async with semaphore: -# try: -# # Use asyncio.wait_for to set a timeout for the task -# response = await router.acompletion(**input_data) -# # Handle the response as needed -# print(response) -# return response -# except Timeout: -# print(f"Task timed out: {input_data}") -# return None # You may choose to return something else or raise an exception - - -# async def main(): -# # Initialize the Router -# model_list = [ -# { -# "model_name": "gpt-3.5-turbo", -# "litellm_params": { -# "model": "gpt-3.5-turbo", -# "api_key": os.getenv("OPENAI_API_KEY"), -# }, -# }, -# { -# "model_name": "gpt-3.5-turbo", -# "litellm_params": { -# "model": "azure/gpt-4.1-mini", -# "api_key": os.getenv("AZURE_API_KEY"), -# "api_base": os.getenv("AZURE_API_BASE"), -# "api_version": os.getenv("AZURE_API_VERSION"), -# }, -# }, -# ] -# router = Router(model_list=model_list, num_retries=3, timeout=10) - -# # Create a semaphore with a capacity of 100 -# semaphore = asyncio.Semaphore(100) - -# # List to hold all task references -# tasks = [] -# start_time_all_tasks = time.time() -# # Launch 1000 tasks -# for _ in range(500): -# task = asyncio.create_task( -# call_acompletion( -# semaphore, -# router, -# { -# "model": "gpt-3.5-turbo", -# "messages": [{"role": "user", "content": "Hey, how's it going?"}], -# }, -# ) -# ) -# tasks.append(task) - -# # Wait for all tasks to complete -# responses = await asyncio.gather(*tasks) -# # Process responses as needed -# # Record the end time for all tasks -# end_time_all_tasks = time.time() -# # Calculate the total time for all tasks -# total_time_all_tasks = end_time_all_tasks - start_time_all_tasks -# print(f"Total time for all tasks: {total_time_all_tasks} seconds") - -# # Calculate the average time per response -# average_time_per_response = total_time_all_tasks / len(responses) -# print(f"Average time per response: {average_time_per_response} seconds") -# print(f"NUMBER OF COMPLETED TASKS: {len(responses)}") - - -# # Run the main function -# asyncio.run(main()) diff --git a/tests/local_testing/test_loadtest_router.py b/tests/local_testing/test_loadtest_router.py deleted file mode 100644 index 3d1062f0d26..00000000000 --- a/tests/local_testing/test_loadtest_router.py +++ /dev/null @@ -1,86 +0,0 @@ -# import sys, os -# import traceback -# from dotenv import load_dotenv -# import copy - -# load_dotenv() -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import asyncio -# from litellm import Router, Timeout -# import time - - -# async def call_acompletion(semaphore, router: Router, input_data): -# async with semaphore: -# try: -# # Use asyncio.wait_for to set a timeout for the task -# response = await router.acompletion(**input_data) -# # Handle the response as needed -# print(response) -# return response -# except Timeout: -# print(f"Task timed out: {input_data}") -# return None # You may choose to return something else or raise an exception - - -# async def main(): -# # Initialize the Router -# model_list = [ -# { -# "model_name": "gpt-3.5-turbo", -# "litellm_params": { -# "model": "gpt-3.5-turbo", -# "api_key": os.getenv("OPENAI_API_KEY"), -# }, -# }, -# { -# "model_name": "gpt-3.5-turbo", -# "litellm_params": { -# "model": "azure/gpt-4.1-mini", -# "api_key": os.getenv("AZURE_AI_API_KEY"), -# "api_base": os.getenv("AZURE_AI_API_BASE"), -# "api_version": os.getenv("AZURE_API_VERSION"), -# }, -# }, -# ] -# router = Router(model_list=model_list, num_retries=3, timeout=10) - -# # Create a semaphore with a capacity of 100 -# semaphore = asyncio.Semaphore(100) - -# # List to hold all task references -# tasks = [] -# start_time_all_tasks = time.time() -# # Launch 1000 tasks -# for _ in range(500): -# task = asyncio.create_task( -# call_acompletion( -# semaphore, -# router, -# { -# "model": "gpt-3.5-turbo", -# "messages": [{"role": "user", "content": "Hey, how's it going?"}], -# }, -# ) -# ) -# tasks.append(task) - -# # Wait for all tasks to complete -# responses = await asyncio.gather(*tasks) -# # Process responses as needed -# # Record the end time for all tasks -# end_time_all_tasks = time.time() -# # Calculate the total time for all tasks -# total_time_all_tasks = end_time_all_tasks - start_time_all_tasks -# print(f"Total time for all tasks: {total_time_all_tasks} seconds") - -# # Calculate the average time per response -# average_time_per_response = total_time_all_tasks / len(responses) -# print(f"Average time per response: {average_time_per_response} seconds") -# print(f"NUMBER OF COMPLETED TASKS: {len(responses)}") - - -# # Run the main function -# asyncio.run(main()) diff --git a/tests/local_testing/test_logging.py b/tests/local_testing/test_logging.py deleted file mode 100644 index 0140cbd5658..00000000000 --- a/tests/local_testing/test_logging.py +++ /dev/null @@ -1,382 +0,0 @@ -# #### What this tests #### -# # This tests error logging (with custom user functions) for the raw `completion` + `embedding` endpoints - -# # Test Scenarios (test across completion, streaming, embedding) -# ## 1: Pre-API-Call -# ## 2: Post-API-Call -# ## 3: On LiteLLM Call success -# ## 4: On LiteLLM Call failure - -# import sys, os, io -# import traceback, logging -# import pytest -# import dotenv -# dotenv.load_dotenv() - -# # Create logger -# logger = logging.getLogger(__name__) -# logger.setLevel(logging.DEBUG) - -# # Create a stream handler -# stream_handler = logging.StreamHandler(sys.stdout) -# logger.addHandler(stream_handler) - -# # Create a function to log information -# def logger_fn(message): -# logger.info(message) - -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import litellm -# from litellm import embedding, completion -# from openai.error import AuthenticationError -# litellm.set_verbose = True - -# score = 0 - -# user_message = "Hello, how are you?" -# messages = [{"content": user_message, "role": "user"}] - -# # 1. On Call Success -# # normal completion -# # test on openai completion call -# def test_logging_success_completion(): -# global score -# try: -# # Redirect stdout -# old_stdout = sys.stdout -# sys.stdout = new_stdout = io.StringIO() - -# response = completion(model="gpt-3.5-turbo", messages=messages) -# # Restore stdout -# sys.stdout = old_stdout -# output = new_stdout.getvalue().strip() - -# if "Logging Details Pre-API Call" not in output: -# raise Exception("Required log message not found!") -# elif "Logging Details Post-API Call" not in output: -# raise Exception("Required log message not found!") -# elif "Logging Details LiteLLM-Success Call" not in output: -# raise Exception("Required log message not found!") -# score += 1 -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") -# pass - -# # ## test on non-openai completion call -# # def test_logging_success_completion_non_openai(): -# # global score -# # try: -# # # Redirect stdout -# # old_stdout = sys.stdout -# # sys.stdout = new_stdout = io.StringIO() - -# # response = completion(model="claude-3-5-haiku-20241022", messages=messages) - -# # # Restore stdout -# # sys.stdout = old_stdout -# # output = new_stdout.getvalue().strip() - -# # if "Logging Details Pre-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details Post-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details LiteLLM-Success Call" not in output: -# # raise Exception("Required log message not found!") -# # score += 1 -# # except Exception as e: -# # pytest.fail(f"Error occurred: {e}") -# # pass - -# # streaming completion -# ## test on openai completion call -# def test_logging_success_streaming_openai(): -# global score -# try: -# # litellm.set_verbose = False -# def custom_callback( -# kwargs, # kwargs to completion -# completion_response, # response from completion -# start_time, end_time # start/end time -# ): -# if "complete_streaming_response" in kwargs: -# print(f"Complete Streaming Response: {kwargs['complete_streaming_response']}") - -# # Assign the custom callback function -# litellm.success_callback = [custom_callback] - -# # Redirect stdout -# old_stdout = sys.stdout -# sys.stdout = new_stdout = io.StringIO() - -# response = completion(model="gpt-3.5-turbo", messages=messages, stream=True) -# for chunk in response: -# pass - -# # Restore stdout -# sys.stdout = old_stdout -# output = new_stdout.getvalue().strip() - -# if "Logging Details Pre-API Call" not in output: -# raise Exception("Required log message not found!") -# elif "Logging Details Post-API Call" not in output: -# raise Exception("Required log message not found!") -# elif "Logging Details LiteLLM-Success Call" not in output: -# raise Exception("Required log message not found!") -# elif "Complete Streaming Response:" not in output: -# raise Exception("Required log message not found!") -# score += 1 -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") -# pass - -# # test_logging_success_streaming_openai() - -# ## test on non-openai completion call -# def test_logging_success_streaming_non_openai(): -# global score -# try: -# # litellm.set_verbose = False -# def custom_callback( -# kwargs, # kwargs to completion -# completion_response, # response from completion -# start_time, end_time # start/end time -# ): -# # print(f"streaming response: {completion_response}") -# if "complete_streaming_response" in kwargs: -# print(f"Complete Streaming Response: {kwargs['complete_streaming_response']}") - -# # Assign the custom callback function -# litellm.success_callback = [custom_callback] - -# # Redirect stdout -# old_stdout = sys.stdout -# sys.stdout = new_stdout = io.StringIO() - -# response = completion(model="claude-3-5-haiku-20241022", messages=messages, stream=True) -# for idx, chunk in enumerate(response): -# pass - -# # Restore stdout -# sys.stdout = old_stdout -# output = new_stdout.getvalue().strip() - -# if "Logging Details Pre-API Call" not in output: -# raise Exception("Required log message not found!") -# elif "Logging Details Post-API Call" not in output: -# raise Exception("Required log message not found!") -# elif "Logging Details LiteLLM-Success Call" not in output: -# raise Exception("Required log message not found!") -# elif "Complete Streaming Response:" not in output: -# raise Exception(f"Required log message not found! {output}") -# score += 1 -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") -# pass - -# # test_logging_success_streaming_non_openai() -# # embedding - -# def test_logging_success_embedding_openai(): -# try: -# # Redirect stdout -# old_stdout = sys.stdout -# sys.stdout = new_stdout = io.StringIO() - -# response = embedding(model="text-embedding-ada-002", input=["good morning from litellm"]) - -# # Restore stdout -# sys.stdout = old_stdout -# output = new_stdout.getvalue().strip() - -# if "Logging Details Pre-API Call" not in output: -# raise Exception("Required log message not found!") -# elif "Logging Details Post-API Call" not in output: -# raise Exception("Required log message not found!") -# elif "Logging Details LiteLLM-Success Call" not in output: -# raise Exception("Required log message not found!") -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# # ## 2. On LiteLLM Call failure -# # ## TEST BAD KEY - -# # # normal completion -# # ## test on openai completion call -# # try: -# # temporary_oai_key = os.environ["OPENAI_API_KEY"] -# # os.environ["OPENAI_API_KEY"] = "bad-key" - -# # temporary_anthropic_key = os.environ["ANTHROPIC_API_KEY"] -# # os.environ["ANTHROPIC_API_KEY"] = "bad-key" - - -# # # Redirect stdout -# # old_stdout = sys.stdout -# # sys.stdout = new_stdout = io.StringIO() - -# # try: -# # response = completion(model="gpt-3.5-turbo", messages=messages) -# # except AuthenticationError: -# # print(f"raised auth error") -# # pass -# # # Restore stdout -# # sys.stdout = old_stdout -# # output = new_stdout.getvalue().strip() - -# # print(output) - -# # if "Logging Details Pre-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details Post-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details LiteLLM-Failure Call" not in output: -# # raise Exception("Required log message not found!") - -# # os.environ["OPENAI_API_KEY"] = temporary_oai_key -# # os.environ["ANTHROPIC_API_KEY"] = temporary_anthropic_key - -# # score += 1 -# # except Exception as e: -# # print(f"exception type: {type(e).__name__}") -# # pytest.fail(f"Error occurred: {e}") -# # pass - -# # ## test on non-openai completion call -# # try: -# # temporary_oai_key = os.environ["OPENAI_API_KEY"] -# # os.environ["OPENAI_API_KEY"] = "bad-key" - -# # temporary_anthropic_key = os.environ["ANTHROPIC_API_KEY"] -# # os.environ["ANTHROPIC_API_KEY"] = "bad-key" -# # # Redirect stdout -# # old_stdout = sys.stdout -# # sys.stdout = new_stdout = io.StringIO() - -# # try: -# # response = completion(model="claude-3-5-haiku-20241022", messages=messages) -# # except AuthenticationError: -# # pass - -# # if "Logging Details Pre-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details Post-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details LiteLLM-Failure Call" not in output: -# # raise Exception("Required log message not found!") -# # os.environ["OPENAI_API_KEY"] = temporary_oai_key -# # os.environ["ANTHROPIC_API_KEY"] = temporary_anthropic_key -# # score += 1 -# # except Exception as e: -# # print(f"exception type: {type(e).__name__}") -# # # Restore stdout -# # sys.stdout = old_stdout -# # output = new_stdout.getvalue().strip() - -# # print(output) -# # pytest.fail(f"Error occurred: {e}") - - -# # # streaming completion -# # ## test on openai completion call -# # try: -# # temporary_oai_key = os.environ["OPENAI_API_KEY"] -# # os.environ["OPENAI_API_KEY"] = "bad-key" - -# # temporary_anthropic_key = os.environ["ANTHROPIC_API_KEY"] -# # os.environ["ANTHROPIC_API_KEY"] = "bad-key" -# # # Redirect stdout -# # old_stdout = sys.stdout -# # sys.stdout = new_stdout = io.StringIO() - -# # try: -# # response = completion(model="gpt-3.5-turbo", messages=messages) -# # except AuthenticationError: -# # pass - -# # # Restore stdout -# # sys.stdout = old_stdout -# # output = new_stdout.getvalue().strip() - -# # print(output) - -# # if "Logging Details Pre-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details Post-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details LiteLLM-Failure Call" not in output: -# # raise Exception("Required log message not found!") - -# # os.environ["OPENAI_API_KEY"] = temporary_oai_key -# # os.environ["ANTHROPIC_API_KEY"] = temporary_anthropic_key -# # score += 1 -# # except Exception as e: -# # print(f"exception type: {type(e).__name__}") -# # pytest.fail(f"Error occurred: {e}") - -# # ## test on non-openai completion call -# # try: -# # temporary_oai_key = os.environ["OPENAI_API_KEY"] -# # os.environ["OPENAI_API_KEY"] = "bad-key" - -# # temporary_anthropic_key = os.environ["ANTHROPIC_API_KEY"] -# # os.environ["ANTHROPIC_API_KEY"] = "bad-key" -# # # Redirect stdout -# # old_stdout = sys.stdout -# # sys.stdout = new_stdout = io.StringIO() - -# # try: -# # response = completion(model="claude-3-5-haiku-20241022", messages=messages) -# # except AuthenticationError: -# # pass - -# # # Restore stdout -# # sys.stdout = old_stdout -# # output = new_stdout.getvalue().strip() - -# # print(output) - -# # if "Logging Details Pre-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details Post-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details LiteLLM-Failure Call" not in output: -# # raise Exception("Required log message not found!") -# # score += 1 -# # except Exception as e: -# # print(f"exception type: {type(e).__name__}") -# # pytest.fail(f"Error occurred: {e}") - -# # # embedding - -# # try: -# # temporary_oai_key = os.environ["OPENAI_API_KEY"] -# # os.environ["OPENAI_API_KEY"] = "bad-key" - -# # temporary_anthropic_key = os.environ["ANTHROPIC_API_KEY"] -# # os.environ["ANTHROPIC_API_KEY"] = "bad-key" -# # # Redirect stdout -# # old_stdout = sys.stdout -# # sys.stdout = new_stdout = io.StringIO() - -# # try: -# # response = embedding(model="text-embedding-ada-002", input=["good morning from litellm"]) -# # except AuthenticationError: -# # pass - -# # # Restore stdout -# # sys.stdout = old_stdout -# # output = new_stdout.getvalue().strip() - -# # print(output) - -# # if "Logging Details Pre-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details Post-API Call" not in output: -# # raise Exception("Required log message not found!") -# # elif "Logging Details LiteLLM-Failure Call" not in output: -# # raise Exception("Required log message not found!") -# # except Exception as e: -# # print(f"exception type: {type(e).__name__}") -# # pytest.fail(f"Error occurred: {e}") diff --git a/tests/local_testing/test_max_tpm_rpm_limiter.py b/tests/local_testing/test_max_tpm_rpm_limiter.py deleted file mode 100644 index 29f9a85c4d5..00000000000 --- a/tests/local_testing/test_max_tpm_rpm_limiter.py +++ /dev/null @@ -1,163 +0,0 @@ -### REPLACED BY 'test_parallel_request_limiter.py' ### -# What is this? -## Unit tests for the max tpm / rpm limiter hook for proxy - -# import sys, os, asyncio, time, random -# from datetime import datetime -# import traceback -# from dotenv import load_dotenv -# from typing import Optional - -# load_dotenv() -# import os - -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import pytest -# import litellm -# from litellm import Router -# from litellm.proxy.utils import ProxyLogging, hash_token -# from litellm.proxy._types import UserAPIKeyAuth -# from litellm.caching.caching import DualCache, RedisCache -# from litellm.proxy.hooks.tpm_rpm_limiter import _PROXY_MaxTPMRPMLimiter -# from datetime import datetime - - -# @pytest.mark.asyncio -# async def test_pre_call_hook_rpm_limits(): -# """ -# Test if error raised on hitting rpm limits -# """ -# litellm.set_verbose = True -# _api_key = hash_token("sk-12345") -# user_api_key_dict = UserAPIKeyAuth(api_key=_api_key, tpm_limit=9, rpm_limit=1) -# local_cache = DualCache() -# # redis_usage_cache = RedisCache() - -# local_cache.set_cache( -# key=_api_key, value={"api_key": _api_key, "tpm_limit": 9, "rpm_limit": 1} -# ) - -# tpm_rpm_limiter = _PROXY_MaxTPMRPMLimiter(internal_cache=DualCache()) - -# await tpm_rpm_limiter.async_pre_call_hook( -# user_api_key_dict=user_api_key_dict, cache=local_cache, data={}, call_type="" -# ) - -# kwargs = {"litellm_params": {"metadata": {"user_api_key": _api_key}}} - -# await tpm_rpm_limiter.async_log_success_event( -# kwargs=kwargs, -# response_obj="", -# start_time="", -# end_time="", -# ) - -# ## Expected cache val: {"current_requests": 0, "current_tpm": 0, "current_rpm": 1} - -# try: -# await tpm_rpm_limiter.async_pre_call_hook( -# user_api_key_dict=user_api_key_dict, -# cache=local_cache, -# data={}, -# call_type="", -# ) - -# pytest.fail(f"Expected call to fail") -# except Exception as e: -# assert e.status_code == 429 - - -# @pytest.mark.asyncio -# async def test_pre_call_hook_team_rpm_limits( -# _redis_usage_cache: Optional[RedisCache] = None, -# ): -# """ -# Test if error raised on hitting team rpm limits -# """ -# litellm.set_verbose = True -# _api_key = "sk-12345" -# _team_id = "unique-team-id" -# _user_api_key_dict = { -# "api_key": _api_key, -# "max_parallel_requests": 1, -# "tpm_limit": 9, -# "rpm_limit": 10, -# "team_rpm_limit": 1, -# "team_id": _team_id, -# } -# user_api_key_dict = UserAPIKeyAuth(**_user_api_key_dict) # type: ignore -# _api_key = hash_token(_api_key) -# local_cache = DualCache() -# local_cache.set_cache(key=_api_key, value=_user_api_key_dict) -# internal_cache = DualCache(redis_cache=_redis_usage_cache) -# tpm_rpm_limiter = _PROXY_MaxTPMRPMLimiter(internal_cache=internal_cache) -# await tpm_rpm_limiter.async_pre_call_hook( -# user_api_key_dict=user_api_key_dict, cache=local_cache, data={}, call_type="" -# ) - -# kwargs = { -# "litellm_params": { -# "metadata": {"user_api_key": _api_key, "user_api_key_team_id": _team_id} -# } -# } - -# await tpm_rpm_limiter.async_log_success_event( -# kwargs=kwargs, -# response_obj="", -# start_time="", -# end_time="", -# ) - -# print(f"local_cache: {local_cache}") - -# ## Expected cache val: {"current_requests": 0, "current_tpm": 0, "current_rpm": 1} - -# try: -# await tpm_rpm_limiter.async_pre_call_hook( -# user_api_key_dict=user_api_key_dict, -# cache=local_cache, -# data={}, -# call_type="", -# ) - -# pytest.fail(f"Expected call to fail") -# except Exception as e: -# assert e.status_code == 429 # type: ignore - - -# @pytest.mark.asyncio -# async def test_namespace(): -# """ -# - test if default namespace set via `proxyconfig._init_cache` -# - respected for tpm/rpm caching -# """ -# from litellm.proxy.proxy_server import ProxyConfig - -# redis_usage_cache: Optional[RedisCache] = None -# cache_params = {"type": "redis", "namespace": "litellm_default"} - -# ## INIT CACHE ## -# proxy_config = ProxyConfig() -# setattr(litellm.proxy.proxy_server, "proxy_config", proxy_config) - -# proxy_config._init_cache(cache_params=cache_params) - -# redis_cache: Optional[RedisCache] = getattr( -# litellm.proxy.proxy_server, "redis_usage_cache" -# ) - -# ## CHECK IF NAMESPACE SET ## -# assert redis_cache.namespace == "litellm_default" - -# ## CHECK IF TPM/RPM RATE LIMITING WORKS ## -# await test_pre_call_hook_team_rpm_limits(_redis_usage_cache=redis_cache) -# current_date = datetime.now().strftime("%Y-%m-%d") -# current_hour = datetime.now().strftime("%H") -# current_minute = datetime.now().strftime("%M") -# precise_minute = f"{current_date}-{current_hour}-{current_minute}" - -# cache_key = "litellm_default:usage:{}".format(precise_minute) -# value = await redis_cache.async_get_cache(key=cache_key) -# assert value is not None diff --git a/tests/local_testing/test_mem_leak.py b/tests/local_testing/test_mem_leak.py deleted file mode 100644 index 60f228f1e57..00000000000 --- a/tests/local_testing/test_mem_leak.py +++ /dev/null @@ -1,243 +0,0 @@ -# import io -# import os -# import sys - -# sys.path.insert(0, os.path.abspath("../..")) - -# import litellm -# from memory_profiler import profile -# from litellm.utils import ( -# ModelResponseIterator, -# ModelResponseListIterator, -# CustomStreamWrapper, -# ) -# from litellm.types.utils import ModelResponse, Choices, Message -# import time -# import pytest - - -# # @app.post("/debug") -# # async def debug(body: ExampleRequest) -> str: -# # return await main_logic(body.query) -# def model_response_list_factory(): -# chunks = [ -# { -# "id": "chatcmpl-9SQxdH5hODqkWyJopWlaVOOUnFwlj", -# "choices": [ -# { -# "delta": {"content": "", "role": "assistant"}, -# "finish_reason": None, -# "index": 0, -# } -# ], -# "created": 1716563849, -# "model": "gpt-4o-2024-05-13", -# "object": "chat.completion.chunk", -# "system_fingerprint": "fp_5f4bad809a", -# }, -# { -# "id": "chatcmpl-9SQxdH5hODqkWyJopWlaVOOUnFwlj", -# "choices": [ -# {"delta": {"content": "This"}, "finish_reason": None, "index": 0} -# ], -# "created": 1716563849, -# "model": "gpt-4o-2024-05-13", -# "object": "chat.completion.chunk", -# "system_fingerprint": "fp_5f4bad809a", -# }, -# { -# "id": "chatcmpl-9SQxdH5hODqkWyJopWlaVOOUnFwlj", -# "choices": [ -# {"delta": {"content": " is"}, "finish_reason": None, "index": 0} -# ], -# "created": 1716563849, -# "model": "gpt-4o-2024-05-13", -# "object": "chat.completion.chunk", -# "system_fingerprint": "fp_5f4bad809a", -# }, -# { -# "id": "chatcmpl-9SQxdH5hODqkWyJopWlaVOOUnFwlj", -# "choices": [ -# {"delta": {"content": " a"}, "finish_reason": None, "index": 0} -# ], -# "created": 1716563849, -# "model": "gpt-4o-2024-05-13", -# "object": "chat.completion.chunk", -# "system_fingerprint": "fp_5f4bad809a", -# }, -# { -# "id": "chatcmpl-9SQxdH5hODqkWyJopWlaVOOUnFwlj", -# "choices": [ -# {"delta": {"content": " dummy"}, "finish_reason": None, "index": 0} -# ], -# "created": 1716563849, -# "model": "gpt-4o-2024-05-13", -# "object": "chat.completion.chunk", -# "system_fingerprint": "fp_5f4bad809a", -# }, -# { -# "id": "chatcmpl-9SQxdH5hODqkWyJopWlaVOOUnFwlj", -# "choices": [ -# { -# "delta": {"content": " response"}, -# "finish_reason": None, -# "index": 0, -# } -# ], -# "created": 1716563849, -# "model": "gpt-4o-2024-05-13", -# "object": "chat.completion.chunk", -# "system_fingerprint": "fp_5f4bad809a", -# }, -# { -# "id": "", -# "choices": [ -# { -# "finish_reason": None, -# "index": 0, -# "content_filter_offsets": { -# "check_offset": 35159, -# "start_offset": 35159, -# "end_offset": 36150, -# }, -# "content_filter_results": { -# "hate": {"filtered": False, "severity": "safe"}, -# "self_harm": {"filtered": False, "severity": "safe"}, -# "sexual": {"filtered": False, "severity": "safe"}, -# "violence": {"filtered": False, "severity": "safe"}, -# }, -# } -# ], -# "created": 0, -# "model": "", -# "object": "", -# }, -# { -# "id": "chatcmpl-9SQxdH5hODqkWyJopWlaVOOUnFwlj", -# "choices": [{"delta": {"content": "."}, "finish_reason": None, "index": 0}], -# "created": 1716563849, -# "model": "gpt-4o-2024-05-13", -# "object": "chat.completion.chunk", -# "system_fingerprint": "fp_5f4bad809a", -# }, -# { -# "id": "chatcmpl-9SQxdH5hODqkWyJopWlaVOOUnFwlj", -# "choices": [{"delta": {}, "finish_reason": "stop", "index": 0}], -# "created": 1716563849, -# "model": "gpt-4o-2024-05-13", -# "object": "chat.completion.chunk", -# "system_fingerprint": "fp_5f4bad809a", -# }, -# { -# "id": "", -# "choices": [ -# { -# "finish_reason": None, -# "index": 0, -# "content_filter_offsets": { -# "check_offset": 36150, -# "start_offset": 36060, -# "end_offset": 37029, -# }, -# "content_filter_results": { -# "hate": {"filtered": False, "severity": "safe"}, -# "self_harm": {"filtered": False, "severity": "safe"}, -# "sexual": {"filtered": False, "severity": "safe"}, -# "violence": {"filtered": False, "severity": "safe"}, -# }, -# } -# ], -# "created": 0, -# "model": "", -# "object": "", -# }, -# ] - -# chunk_list = [] -# for chunk in chunks: -# new_chunk = litellm.ModelResponse(stream=True, id=chunk["id"]) -# if "choices" in chunk and isinstance(chunk["choices"], list): -# new_choices = [] -# for choice in chunk["choices"]: -# if isinstance(choice, litellm.utils.StreamingChoices): -# _new_choice = choice -# elif isinstance(choice, dict): -# _new_choice = litellm.utils.StreamingChoices(**choice) -# new_choices.append(_new_choice) -# new_chunk.choices = new_choices -# chunk_list.append(new_chunk) - -# return ModelResponseListIterator(model_responses=chunk_list) - - -# async def mock_completion(*args, **kwargs): -# completion_stream = model_response_list_factory() -# return litellm.CustomStreamWrapper( -# completion_stream=completion_stream, -# model="gpt-4-0613", -# custom_llm_provider="cached_response", -# logging_obj=litellm.Logging( -# model="gpt-4-0613", -# messages=[{"role": "user", "content": "Hey"}], -# stream=True, -# call_type="completion", -# start_time=time.time(), -# litellm_call_id="12345", -# function_id="1245", -# ), -# ) - - -# @profile -# async def main_logic() -> str: -# stream = await mock_completion() -# result = "" -# async for chunk in stream: -# result += chunk.choices[0].delta.content or "" -# return result - - -# import asyncio - -# for _ in range(100): -# asyncio.run(main_logic()) - - -# # @pytest.mark.asyncio -# # def test_memory_profile(capsys): -# # # Run the async function -# # result = asyncio.run(main_logic()) - -# # # Verify the result -# # assert result == "This is a dummy response." - -# # # Capture the output -# # captured = capsys.readouterr() - -# # # Print memory output for debugging -# # print("Memory Profiler Output:") -# # print(f"captured out: {captured.out}") - -# # # Basic memory leak checks -# # for idx, line in enumerate(captured.out.split("\n")): -# # if idx % 2 == 0 and "MiB" in line: -# # print(f"line: {line}") - -# # # mem_lines = [line for line in captured.out.split("\n") if "MiB" in line] - -# # print(mem_lines) - -# # # Ensure we have some memory lines -# # assert len(mem_lines) > 0, "No memory profiler output found" - -# # # Optional: Add more specific memory leak detection -# # for line in mem_lines: -# # # Extract memory increment -# # parts = line.split() -# # if len(parts) >= 3: -# # try: -# # mem_increment = float(parts[2].replace("MiB", "")) -# # # Assert that memory increment is below a reasonable threshold -# # assert mem_increment < 1.0, f"Potential memory leak detected: {line}" -# # except (ValueError, IndexError): -# # pass # Skip lines that don't match expected format diff --git a/tests/local_testing/test_mem_usage.py b/tests/local_testing/test_mem_usage.py deleted file mode 100644 index 927ebc4ae40..00000000000 --- a/tests/local_testing/test_mem_usage.py +++ /dev/null @@ -1,153 +0,0 @@ -# #### What this tests #### - -# from memory_profiler import profile, memory_usage -# import sys, os, time -# import traceback, asyncio -# import pytest - -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import litellm -# from litellm import Router -# from concurrent.futures import ThreadPoolExecutor -# from collections import defaultdict -# from dotenv import load_dotenv -# from litellm._uuid import uuid -# import tracemalloc -# import objgraph - -# objgraph.growth(shortnames=True) -# objgraph.show_most_common_types(limit=10) - -# from mem_top import mem_top - -# load_dotenv() - - -# 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_API_KEY"), -# "api_version": os.getenv("AZURE_API_VERSION"), -# "api_base": os.getenv("AZURE_API_BASE"), -# }, -# "tpm": 240000, -# "rpm": 1800, -# }, -# { -# "model_name": "bad-model", # openai model name -# "litellm_params": { # params for litellm completion/embedding call -# "model": "azure/gpt-4.1-mini", -# "api_key": "bad-key", -# "api_version": os.getenv("AZURE_API_VERSION"), -# "api_base": os.getenv("AZURE_API_BASE"), -# }, -# "tpm": 240000, -# "rpm": 1800, -# }, -# { -# "model_name": "text-embedding-ada-002", -# "litellm_params": { -# "model": "azure/text-embedding-ada-002", -# "api_key": os.environ["AZURE_API_KEY"], -# "api_base": os.environ["AZURE_API_BASE"], -# }, -# "tpm": 100000, -# "rpm": 10000, -# }, -# ] -# litellm.set_verbose = True -# litellm.cache = litellm.Cache( -# type="s3", s3_bucket_name="litellm-my-test-bucket-2", s3_region_name="us-east-1" -# ) -# router = Router( -# model_list=model_list, -# fallbacks=[ -# {"bad-model": ["gpt-3.5-turbo"]}, -# ], -# ) # type: ignore - - -# async def router_acompletion(): -# # embedding call -# question = f"This is a test: {uuid.uuid4()}" * 1 - -# response = await router.acompletion( -# model="bad-model", messages=[{"role": "user", "content": question}] -# ) -# print("completion-resp", response) -# return response - - -# async def main(): -# for i in range(1): -# start = time.time() -# n = 15 # Number of concurrent tasks -# tasks = [router_acompletion() for _ in range(n)] - -# chat_completions = await asyncio.gather(*tasks) - -# successful_completions = [c for c in chat_completions if c is not None] - -# # Write errors to error_log.txt -# with open("error_log.txt", "a") as error_log: -# for completion in chat_completions: -# if isinstance(completion, str): -# error_log.write(completion + "\n") - -# print(n, time.time() - start, len(successful_completions)) -# print() -# print(vars(router)) -# prev_models = router.previous_models - -# print("vars in prev_models") -# print(prev_models[0].keys()) - - -# if __name__ == "__main__": -# # Blank out contents of error_log.txt -# open("error_log.txt", "w").close() - -# import tracemalloc - -# tracemalloc.start(25) - -# # ... run your application ... - -# asyncio.run(main()) -# print(mem_top()) - -# snapshot = tracemalloc.take_snapshot() -# # top_stats = snapshot.statistics('lineno') - -# # print("[ Top 10 ]") -# # for stat in top_stats[:50]: -# # print(stat) - -# top_stats = snapshot.statistics("traceback") - -# # pick the biggest memory block -# stat = top_stats[0] -# print("%s memory blocks: %.1f KiB" % (stat.count, stat.size / 1024)) -# for line in stat.traceback.format(): -# print(line) -# print() -# stat = top_stats[1] -# print("%s memory blocks: %.1f KiB" % (stat.count, stat.size / 1024)) -# for line in stat.traceback.format(): -# print(line) - -# print() -# stat = top_stats[2] -# print("%s memory blocks: %.1f KiB" % (stat.count, stat.size / 1024)) -# for line in stat.traceback.format(): -# print(line) -# print() - -# stat = top_stats[3] -# print("%s memory blocks: %.1f KiB" % (stat.count, stat.size / 1024)) -# for line in stat.traceback.format(): -# print(line) diff --git a/tests/local_testing/test_ollama_local.py b/tests/local_testing/test_ollama_local.py deleted file mode 100644 index f5d629140e4..00000000000 --- a/tests/local_testing/test_ollama_local.py +++ /dev/null @@ -1,336 +0,0 @@ -# ##### THESE TESTS CAN ONLY RUN LOCALLY WITH THE OLLAMA SERVER RUNNING ###### -# # https://ollama.ai/ - -# import sys, os -# import traceback -# from dotenv import load_dotenv -# load_dotenv() -# import os -# sys.path.insert(0, os.path.abspath('../..')) # Adds the parent directory to the system path -# import pytest -# import litellm -# from litellm import embedding, completion -# import asyncio - - -# user_message = "respond in 20 words. who are you?" -# messages = [{ "content": user_message,"role": "user"}] - -# async def test_ollama_aembeddings(): -# litellm.set_verbose = True -# input = "The food was delicious and the waiter..." -# response = await litellm.aembedding(model="ollama/mistral", input=input) -# print(response) - -# asyncio.run(test_ollama_aembeddings()) - -# def test_ollama_embeddings(): -# litellm.set_verbose = True -# input = "The food was delicious and the waiter..." -# response = litellm.embedding(model="ollama/mistral", input=input) -# print(response) - -# test_ollama_embeddings() - -# def test_ollama_streaming(): -# try: -# litellm.set_verbose = False -# messages = [ -# {"role": "user", "content": "What is the weather like in Boston?"} -# ] -# functions = [ -# { -# "name": "get_current_weather", -# "description": "Get the current weather in a given location", -# "parameters": { -# "type": "object", -# "properties": { -# "location": { -# "type": "string", -# "description": "The city and state, e.g. San Francisco, CA" -# }, -# "unit": { -# "type": "string", -# "enum": ["celsius", "fahrenheit"] -# } -# }, -# "required": ["location"] -# } -# } -# ] -# response = litellm.completion(model="ollama/mistral", -# messages=messages, -# functions=functions, -# stream=True) -# for chunk in response: -# print(f"CHUNK: {chunk}") -# except Exception as e: -# print(e) - -# # test_ollama_streaming() - -# async def test_async_ollama_streaming(): -# try: -# litellm.set_verbose = False -# response = await litellm.acompletion(model="ollama/mistral-openorca", -# messages=[{"role": "user", "content": "Hey, how's it going?"}], -# stream=True) -# async for chunk in response: -# print(f"CHUNK: {chunk}") -# except Exception as e: -# print(e) - -# # asyncio.run(test_async_ollama_streaming()) - -# def test_completion_ollama(): -# try: -# litellm.set_verbose = True -# response = completion( -# model="ollama/mistral", -# messages=[{"role": "user", "content": "Hey, how's it going?"}], -# max_tokens=200, -# request_timeout = 10, -# stream=True -# ) -# for chunk in response: -# print(chunk) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# # test_completion_ollama() - -# def test_completion_ollama_function_calling(): -# try: -# litellm.set_verbose = True -# messages = [ -# {"role": "user", "content": "What is the weather like in Boston?"} -# ] -# functions = [ -# { -# "name": "get_current_weather", -# "description": "Get the current weather in a given location", -# "parameters": { -# "type": "object", -# "properties": { -# "location": { -# "type": "string", -# "description": "The city and state, e.g. San Francisco, CA" -# }, -# "unit": { -# "type": "string", -# "enum": ["celsius", "fahrenheit"] -# } -# }, -# "required": ["location"] -# } -# } -# ] -# response = completion( -# model="ollama/mistral", -# messages=messages, -# functions=functions, -# max_tokens=200, -# request_timeout = 10, -# ) -# for chunk in response: -# print(chunk) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") -# # test_completion_ollama_function_calling() - -# async def async_test_completion_ollama_function_calling(): -# try: -# litellm.set_verbose = True -# messages = [ -# {"role": "user", "content": "What is the weather like in Boston?"} -# ] -# functions = [ -# { -# "name": "get_current_weather", -# "description": "Get the current weather in a given location", -# "parameters": { -# "type": "object", -# "properties": { -# "location": { -# "type": "string", -# "description": "The city and state, e.g. San Francisco, CA" -# }, -# "unit": { -# "type": "string", -# "enum": ["celsius", "fahrenheit"] -# } -# }, -# "required": ["location"] -# } -# } -# ] -# response = await litellm.acompletion( -# model="ollama/mistral", -# messages=messages, -# functions=functions, -# max_tokens=200, -# request_timeout = 10, -# ) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# # asyncio.run(async_test_completion_ollama_function_calling()) - - -# def test_completion_ollama_with_api_base(): -# try: -# response = completion( -# model="ollama/llama2", -# messages=messages, -# api_base="http://localhost:11434" -# ) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# # test_completion_ollama_with_api_base() - - -# def test_completion_ollama_custom_prompt_template(): -# user_message = "what is litellm?" -# litellm.register_prompt_template( -# model="ollama/llama2", -# roles={ -# "system": {"pre_message": "System: "}, -# "user": {"pre_message": "User: "}, -# "assistant": {"pre_message": "Assistant: "} -# } -# ) -# messages = [{ "content": user_message,"role": "user"}] -# litellm.set_verbose = True -# try: -# response = completion( -# model="ollama/llama2", -# messages=messages, -# stream=True -# ) -# print(response) -# for chunk in response: -# print(chunk) -# # print(chunk['choices'][0]['delta']) - -# except Exception as e: -# traceback.print_exc() -# pytest.fail(f"Error occurred: {e}") - -# # test_completion_ollama_custom_prompt_template() - -# async def test_completion_ollama_async_stream(): -# user_message = "what is the weather" -# messages = [{ "content": user_message,"role": "user"}] -# try: -# response = await litellm.acompletion( -# model="ollama/llama2", -# messages=messages, -# api_base="http://localhost:11434", -# stream=True -# ) -# async for chunk in response: -# print(chunk['choices'][0]['delta']) - - -# print("TEST ASYNC NON Stream") -# response = await litellm.acompletion( -# model="ollama/llama2", -# messages=messages, -# api_base="http://localhost:11434", -# ) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# # import asyncio -# # asyncio.run(test_completion_ollama_async_stream()) - - -# def prepare_messages_for_chat(text: str) -> list: -# messages = [ -# {"role": "user", "content": text}, -# ] -# return messages - - -# async def ask_question(): -# params = { -# "messages": prepare_messages_for_chat("What is litellm? tell me 10 things about it who is sihaan.write an essay"), -# "api_base": "http://localhost:11434", -# "model": "ollama/llama2", -# "stream": True, -# } -# response = await litellm.acompletion(**params) -# return response - -# async def main(): -# response = await ask_question() -# async for chunk in response: -# print(chunk) - -# print("test async completion without streaming") -# response = await litellm.acompletion( -# model="ollama/llama2", -# messages=prepare_messages_for_chat("What is litellm? respond in 2 words"), -# ) -# print("response", response) - - -# def test_completion_expect_error(): -# # this tests if we can exception map correctly for ollama -# print("making ollama request") -# # litellm.set_verbose=True -# user_message = "what is litellm?" -# messages = [{ "content": user_message,"role": "user"}] -# try: -# response = completion( -# model="ollama/invalid", -# messages=messages, -# stream=True -# ) -# print(response) -# for chunk in response: -# print(chunk) -# # print(chunk['choices'][0]['delta']) - -# except Exception as e: -# pass -# pytest.fail(f"Error occurred: {e}") - -# # test_completion_expect_error() - - -# def test_ollama_llava(): -# litellm.set_verbose=True -# # same params as gpt-4 vision -# response = completion( -# model = "ollama/llava", -# messages=[ -# { -# "role": "user", -# "content": [ -# { -# "type": "text", -# "text": "What is in this picture" -# }, -# { -# "type": "image_url", -# "image_url": { -# "url": "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" -# } -# } -# ] -# } -# ], -# ) -# print("Response from ollama/llava") -# print(response) -# # test_ollama_llava() - - -# # PROCESSED CHUNK PRE CHUNK CREATOR diff --git a/tests/local_testing/test_ollama_local_chat.py b/tests/local_testing/test_ollama_local_chat.py deleted file mode 100644 index cca31942812..00000000000 --- a/tests/local_testing/test_ollama_local_chat.py +++ /dev/null @@ -1,334 +0,0 @@ -# ##### THESE TESTS CAN ONLY RUN LOCALLY WITH THE OLLAMA SERVER RUNNING ###### -# # https://ollama.ai/ - -# import sys, os -# import traceback -# from dotenv import load_dotenv - -# load_dotenv() -# import os - -# sys.path.insert( -# 0, os.path.abspath("../..") -# ) # Adds the parent directory to the system path -# import pytest -# import litellm -# from litellm import embedding, completion -# import asyncio - - -# user_message = "respond in 20 words. who are you?" -# messages = [{"content": user_message, "role": "user"}] - - -# def test_ollama_streaming(): -# try: -# litellm.set_verbose = False -# messages = [{"role": "user", "content": "What is the weather like in Boston?"}] -# functions = [ -# { -# "name": "get_current_weather", -# "description": "Get the current weather in a given location", -# "parameters": { -# "type": "object", -# "properties": { -# "location": { -# "type": "string", -# "description": "The city and state, e.g. San Francisco, CA", -# }, -# "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, -# }, -# "required": ["location"], -# }, -# } -# ] -# response = litellm.completion( -# model="ollama_chat/mistral", -# messages=messages, -# functions=functions, -# stream=True, -# ) -# for chunk in response: -# print(f"CHUNK: {chunk}") -# except Exception as e: -# print(e) - - -# # test_ollama_streaming() - - -# async def test_async_ollama_streaming(): -# try: -# litellm.set_verbose = True -# response = await litellm.acompletion( -# model="ollama_chat/llama2", -# messages=[{"role": "user", "content": "Hey, how's it going?"}], -# stream=True, -# ) -# async for chunk in response: -# print(f"CHUNK: {chunk}") -# except Exception as e: -# print(e) - - -# # asyncio.run(test_async_ollama_streaming()) - -# async def test_async_ollama(): -# try: -# litellm.set_verbose = True -# response = await litellm.acompletion( -# model="ollama_chat/llama2", -# messages=[{"role": "user", "content": "Hey, how's it going?"}], -# ) -# print("\n response", response) -# except Exception as e: -# print(e) - - -# # asyncio.run(test_async_ollama()) - - -# def test_completion_ollama(): -# try: -# litellm.set_verbose = True -# response = completion( -# model="ollama_chat/mistral", -# messages=[{"role": "user", "content": "Hey, how's it going?"}], -# max_tokens=200, -# request_timeout=10, -# stream=True, -# ) -# for chunk in response: -# print(chunk) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - - -# # test_completion_ollama() - - -# def test_completion_ollama_function_calling(): -# try: -# litellm.set_verbose = True -# messages = [{"role": "user", "content": "What is the weather like in Boston?"}] -# functions = [ -# { -# "name": "get_current_weather", -# "description": "Get the current weather in a given location", -# "parameters": { -# "type": "object", -# "properties": { -# "location": { -# "type": "string", -# "description": "The city and state, e.g. San Francisco, CA", -# }, -# "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, -# }, -# "required": ["location"], -# }, -# } -# ] -# response = completion( -# model="ollama_chat/mistral", -# messages=messages, -# functions=functions, -# max_tokens=200, -# request_timeout=10, -# ) -# for chunk in response: -# print(chunk) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - - -# test_completion_ollama_function_calling() - - -# async def async_test_completion_ollama_function_calling(): -# try: -# litellm.set_verbose = True -# messages = [{"role": "user", "content": "What is the weather like in Boston?"}] -# functions = [ -# { -# "name": "get_current_weather", -# "description": "Get the current weather in a given location", -# "parameters": { -# "type": "object", -# "properties": { -# "location": { -# "type": "string", -# "description": "The city and state, e.g. San Francisco, CA", -# }, -# "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, -# }, -# "required": ["location"], -# }, -# } -# ] -# response = await litellm.acompletion( -# model="ollama/mistral", -# messages=messages, -# functions=functions, -# max_tokens=200, -# request_timeout=10, -# ) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - - -# # asyncio.run(async_test_completion_ollama_function_calling()) - - -# def test_completion_ollama_with_api_base(): -# try: -# response = completion( -# model="ollama/llama2", messages=messages, api_base="http://localhost:11434" -# ) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - - -# # test_completion_ollama_with_api_base() - - -# def test_completion_ollama_custom_prompt_template(): -# user_message = "what is litellm?" -# litellm.register_prompt_template( -# model="ollama/llama2", -# roles={ -# "system": {"pre_message": "System: "}, -# "user": {"pre_message": "User: "}, -# "assistant": {"pre_message": "Assistant: "}, -# }, -# ) -# messages = [{"content": user_message, "role": "user"}] -# litellm.set_verbose = True -# try: -# response = completion(model="ollama/llama2", messages=messages, stream=True) -# print(response) -# for chunk in response: -# print(chunk) -# # print(chunk['choices'][0]['delta']) - -# except Exception as e: -# traceback.print_exc() -# pytest.fail(f"Error occurred: {e}") - - -# # test_completion_ollama_custom_prompt_template() - - -# async def test_completion_ollama_async_stream(): -# user_message = "what is the weather" -# messages = [{"content": user_message, "role": "user"}] -# try: -# response = await litellm.acompletion( -# model="ollama/llama2", -# messages=messages, -# api_base="http://localhost:11434", -# stream=True, -# ) -# async for chunk in response: -# print(chunk["choices"][0]["delta"]) - -# print("TEST ASYNC NON Stream") -# response = await litellm.acompletion( -# model="ollama/llama2", -# messages=messages, -# api_base="http://localhost:11434", -# ) -# print(response) -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - - -# # import asyncio -# # asyncio.run(test_completion_ollama_async_stream()) - - -# def prepare_messages_for_chat(text: str) -> list: -# messages = [ -# {"role": "user", "content": text}, -# ] -# return messages - - -# async def ask_question(): -# params = { -# "messages": prepare_messages_for_chat( -# "What is litellm? tell me 10 things about it who is sihaan.write an essay" -# ), -# "api_base": "http://localhost:11434", -# "model": "ollama/llama2", -# "stream": True, -# } -# response = await litellm.acompletion(**params) -# return response - - -# async def main(): -# response = await ask_question() -# async for chunk in response: -# print(chunk) - -# print("test async completion without streaming") -# response = await litellm.acompletion( -# model="ollama/llama2", -# messages=prepare_messages_for_chat("What is litellm? respond in 2 words"), -# ) -# print("response", response) - - -# def test_completion_expect_error(): -# # this tests if we can exception map correctly for ollama -# print("making ollama request") -# # litellm.set_verbose=True -# user_message = "what is litellm?" -# messages = [{"content": user_message, "role": "user"}] -# try: -# response = completion(model="ollama/invalid", messages=messages, stream=True) -# print(response) -# for chunk in response: -# print(chunk) -# # print(chunk['choices'][0]['delta']) - -# except Exception as e: -# pass -# pytest.fail(f"Error occurred: {e}") - - -# # test_completion_expect_error() - - -# def test_ollama_llava(): -# litellm.set_verbose = True -# # same params as gpt-4 vision -# response = completion( -# model="ollama/llava", -# messages=[ -# { -# "role": "user", -# "content": [ -# {"type": "text", "text": "What is in this picture"}, -# { -# "type": "image_url", -# "image_url": { -# "url": "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" -# }, -# }, -# ], -# } -# ], -# ) -# print("Response from ollama/llava") -# print(response) - - -# # test_ollama_llava() - - -# # PROCESSED CHUNK PRE CHUNK CREATOR diff --git a/tests/search_tests/test_google_pse_search.py b/tests/search_tests/test_google_pse_search.py deleted file mode 100644 index 12b1a714709..00000000000 --- a/tests/search_tests/test_google_pse_search.py +++ /dev/null @@ -1,20 +0,0 @@ -""" -Tests for Google Programmable Search Engine (PSE) API integration. -""" - -import pytest - - -from tests.search_tests.base_search_unit_tests import BaseSearchTest - - -# class TestGooglePSESearch(BaseSearchTest): -# """ -# Tests for Google PSE Search functionality. -# """ - -# def get_search_provider(self) -> str: -# """ -# Return search_provider for Google PSE Search. -# """ -# return "google_pse"