forked from phoenix/litellm-mirror
test(test_router.py): reintegrate router testing
This commit is contained in:
Krrish Dholakia
parent
c75e90663c
commit
3dcbf6197a
1 changed files with 277 additions and 277 deletions
|
|
@ -1,294 +1,294 @@
|
||||||
# #### What this tests ####
|
#### What this tests ####
|
||||||
# # This tests calling batch_completions by running 100 messages together
|
# This tests calling batch_completions by running 100 messages together
|
||||||
|
|
||||||
# import sys, os, time
|
import sys, os, time
|
||||||
# import traceback, asyncio
|
import traceback, asyncio
|
||||||
# import pytest
|
import pytest
|
||||||
# sys.path.insert(
|
sys.path.insert(
|
||||||
# 0, os.path.abspath("../..")
|
0, os.path.abspath("../..")
|
||||||
# ) # Adds the parent directory to the system path
|
) # Adds the parent directory to the system path
|
||||||
# import litellm
|
import litellm
|
||||||
# from litellm import Router
|
from litellm import Router
|
||||||
# from concurrent.futures import ThreadPoolExecutor
|
from concurrent.futures import ThreadPoolExecutor
|
||||||
# from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
# load_dotenv()
|
load_dotenv()
|
||||||
|
|
||||||
# def test_exception_raising():
|
def test_exception_raising():
|
||||||
# # this tests if the router raises an exception when invalid params are set
|
# this tests if the router raises an exception when invalid params are set
|
||||||
# # in this test both deployments have bad keys - Keep this test. It validates if the router raises the most recent exception
|
# in this test both deployments have bad keys - Keep this test. It validates if the router raises the most recent exception
|
||||||
# litellm.set_verbose=True
|
litellm.set_verbose=True
|
||||||
# import openai
|
import openai
|
||||||
# try:
|
try:
|
||||||
# print("testing if router raises an exception")
|
print("testing if router raises an exception")
|
||||||
# old_api_key = os.environ["AZURE_API_KEY"]
|
old_api_key = os.environ["AZURE_API_KEY"]
|
||||||
# os.environ["AZURE_API_KEY"] = ""
|
os.environ["AZURE_API_KEY"] = ""
|
||||||
# model_list = [
|
model_list = [
|
||||||
# {
|
{
|
||||||
# "model_name": "gpt-3.5-turbo", # openai model name
|
"model_name": "gpt-3.5-turbo", # openai model name
|
||||||
# "litellm_params": { # params for litellm completion/embedding call
|
"litellm_params": { # params for litellm completion/embedding call
|
||||||
# "model": "azure/chatgpt-v-2",
|
"model": "azure/chatgpt-v-2",
|
||||||
# "api_key": "bad-key",
|
"api_key": "bad-key",
|
||||||
# "api_version": os.getenv("AZURE_API_VERSION"),
|
"api_version": os.getenv("AZURE_API_VERSION"),
|
||||||
# "api_base": os.getenv("AZURE_API_BASE")
|
"api_base": os.getenv("AZURE_API_BASE")
|
||||||
# },
|
},
|
||||||
# "tpm": 240000,
|
"tpm": 240000,
|
||||||
# "rpm": 1800
|
"rpm": 1800
|
||||||
# },
|
},
|
||||||
# {
|
{
|
||||||
# "model_name": "gpt-3.5-turbo", # openai model name
|
"model_name": "gpt-3.5-turbo", # openai model name
|
||||||
# "litellm_params": { #
|
"litellm_params": { #
|
||||||
# "model": "gpt-3.5-turbo",
|
"model": "gpt-3.5-turbo",
|
||||||
# "api_key": "bad-key",
|
"api_key": "bad-key",
|
||||||
# },
|
},
|
||||||
# "tpm": 240000,
|
"tpm": 240000,
|
||||||
# "rpm": 1800
|
"rpm": 1800
|
||||||
# }
|
}
|
||||||
# ]
|
]
|
||||||
# router = Router(model_list=model_list,
|
router = Router(model_list=model_list,
|
||||||
# redis_host=os.getenv("REDIS_HOST"),
|
redis_host=os.getenv("REDIS_HOST"),
|
||||||
# redis_password=os.getenv("REDIS_PASSWORD"),
|
redis_password=os.getenv("REDIS_PASSWORD"),
|
||||||
# redis_port=int(os.getenv("REDIS_PORT")),
|
redis_port=int(os.getenv("REDIS_PORT")),
|
||||||
# routing_strategy="simple-shuffle",
|
routing_strategy="simple-shuffle",
|
||||||
# set_verbose=False,
|
set_verbose=False,
|
||||||
# num_retries=1) # type: ignore
|
num_retries=1) # type: ignore
|
||||||
# response = router.completion(
|
response = router.completion(
|
||||||
# model="gpt-3.5-turbo",
|
model="gpt-3.5-turbo",
|
||||||
# messages=[
|
messages=[
|
||||||
# {
|
{
|
||||||
# "role": "user",
|
"role": "user",
|
||||||
# "content": "hello this request will fail"
|
"content": "hello this request will fail"
|
||||||
# }
|
}
|
||||||
# ]
|
]
|
||||||
# )
|
)
|
||||||
# os.environ["AZURE_API_KEY"] = old_api_key
|
os.environ["AZURE_API_KEY"] = old_api_key
|
||||||
# pytest.fail(f"Should have raised an Auth Error")
|
pytest.fail(f"Should have raised an Auth Error")
|
||||||
# except openai.AuthenticationError:
|
except openai.AuthenticationError:
|
||||||
# print("Test Passed: Caught an OPENAI AUTH Error, Good job. This is what we needed!")
|
print("Test Passed: Caught an OPENAI AUTH Error, Good job. This is what we needed!")
|
||||||
# os.environ["AZURE_API_KEY"] = old_api_key
|
os.environ["AZURE_API_KEY"] = old_api_key
|
||||||
# router.flush_cache()
|
router.flush_cache()
|
||||||
# except Exception as e:
|
except Exception as e:
|
||||||
# os.environ["AZURE_API_KEY"] = old_api_key
|
os.environ["AZURE_API_KEY"] = old_api_key
|
||||||
# print("Got unexpected exception on router!", e)
|
print("Got unexpected exception on router!", e)
|
||||||
# # test_exception_raising()
|
# test_exception_raising()
|
||||||
|
|
||||||
|
|
||||||
# def test_reading_key_from_model_list():
|
def test_reading_key_from_model_list():
|
||||||
# # this tests if the router raises an exception when invalid params are set
|
# this tests if the router raises an exception when invalid params are set
|
||||||
# # DO NOT REMOVE THIS TEST. It's an IMP ONE. Speak to Ishaan, if you are tring to remove this
|
# DO NOT REMOVE THIS TEST. It's an IMP ONE. Speak to Ishaan, if you are tring to remove this
|
||||||
# litellm.set_verbose=False
|
litellm.set_verbose=False
|
||||||
# import openai
|
import openai
|
||||||
# try:
|
try:
|
||||||
# print("testing if router raises an exception")
|
print("testing if router raises an exception")
|
||||||
# old_api_key = os.environ["AZURE_API_KEY"]
|
old_api_key = os.environ["AZURE_API_KEY"]
|
||||||
# os.environ.pop("AZURE_API_KEY", None)
|
os.environ.pop("AZURE_API_KEY", None)
|
||||||
# model_list = [
|
model_list = [
|
||||||
# {
|
{
|
||||||
# "model_name": "gpt-3.5-turbo", # openai model name
|
"model_name": "gpt-3.5-turbo", # openai model name
|
||||||
# "litellm_params": { # params for litellm completion/embedding call
|
"litellm_params": { # params for litellm completion/embedding call
|
||||||
# "model": "azure/chatgpt-v-2",
|
"model": "azure/chatgpt-v-2",
|
||||||
# "api_key": old_api_key,
|
"api_key": old_api_key,
|
||||||
# "api_version": os.getenv("AZURE_API_VERSION"),
|
"api_version": os.getenv("AZURE_API_VERSION"),
|
||||||
# "api_base": os.getenv("AZURE_API_BASE")
|
"api_base": os.getenv("AZURE_API_BASE")
|
||||||
# },
|
},
|
||||||
# "tpm": 240000,
|
"tpm": 240000,
|
||||||
# "rpm": 1800
|
"rpm": 1800
|
||||||
# }
|
}
|
||||||
# ]
|
]
|
||||||
|
|
||||||
# router = Router(model_list=model_list,
|
router = Router(model_list=model_list,
|
||||||
# redis_host=os.getenv("REDIS_HOST"),
|
redis_host=os.getenv("REDIS_HOST"),
|
||||||
# redis_password=os.getenv("REDIS_PASSWORD"),
|
redis_password=os.getenv("REDIS_PASSWORD"),
|
||||||
# redis_port=int(os.getenv("REDIS_PORT")),
|
redis_port=int(os.getenv("REDIS_PORT")),
|
||||||
# routing_strategy="simple-shuffle",
|
routing_strategy="simple-shuffle",
|
||||||
# set_verbose=True,
|
set_verbose=True,
|
||||||
# num_retries=1) # type: ignore
|
num_retries=1) # type: ignore
|
||||||
# response = router.completion(
|
response = router.completion(
|
||||||
# model="gpt-3.5-turbo",
|
model="gpt-3.5-turbo",
|
||||||
# messages=[
|
messages=[
|
||||||
# {
|
{
|
||||||
# "role": "user",
|
"role": "user",
|
||||||
# "content": "hello this request will fail"
|
"content": "hello this request will fail"
|
||||||
# }
|
}
|
||||||
# ]
|
]
|
||||||
# )
|
)
|
||||||
# os.environ["AZURE_API_KEY"] = old_api_key
|
os.environ["AZURE_API_KEY"] = old_api_key
|
||||||
# router.flush_cache()
|
router.flush_cache()
|
||||||
# except Exception as e:
|
except Exception as e:
|
||||||
# os.environ["AZURE_API_KEY"] = old_api_key
|
os.environ["AZURE_API_KEY"] = old_api_key
|
||||||
# print(f"FAILED TEST")
|
print(f"FAILED TEST")
|
||||||
# pytest.fail("Got unexpected exception on router!", e)
|
pytest.fail("Got unexpected exception on router!", e)
|
||||||
# # test_reading_key_from_model_list()
|
# test_reading_key_from_model_list()
|
||||||
|
|
||||||
|
|
||||||
# ### FUNCTION CALLING
|
### FUNCTION CALLING
|
||||||
|
|
||||||
# def test_function_calling():
|
def test_function_calling():
|
||||||
# model_list = [
|
model_list = [
|
||||||
# {
|
{
|
||||||
# "model_name": "gpt-3.5-turbo-0613",
|
"model_name": "gpt-3.5-turbo-0613",
|
||||||
# "litellm_params": {
|
"litellm_params": {
|
||||||
# "model": "gpt-3.5-turbo-0613",
|
"model": "gpt-3.5-turbo-0613",
|
||||||
# "api_key": os.getenv("OPENAI_API_KEY"),
|
"api_key": os.getenv("OPENAI_API_KEY"),
|
||||||
# },
|
},
|
||||||
# "tpm": 100000,
|
"tpm": 100000,
|
||||||
# "rpm": 10000,
|
"rpm": 10000,
|
||||||
# },
|
},
|
||||||
# ]
|
]
|
||||||
|
|
||||||
# messages = [
|
messages = [
|
||||||
# {"role": "user", "content": "What is the weather like in Boston?"}
|
{"role": "user", "content": "What is the weather like in Boston?"}
|
||||||
# ]
|
]
|
||||||
# functions = [
|
functions = [
|
||||||
# {
|
{
|
||||||
# "name": "get_current_weather",
|
"name": "get_current_weather",
|
||||||
# "description": "Get the current weather in a given location",
|
"description": "Get the current weather in a given location",
|
||||||
# "parameters": {
|
"parameters": {
|
||||||
# "type": "object",
|
"type": "object",
|
||||||
# "properties": {
|
"properties": {
|
||||||
# "location": {
|
"location": {
|
||||||
# "type": "string",
|
"type": "string",
|
||||||
# "description": "The city and state, e.g. San Francisco, CA"
|
"description": "The city and state, e.g. San Francisco, CA"
|
||||||
# },
|
},
|
||||||
# "unit": {
|
"unit": {
|
||||||
# "type": "string",
|
"type": "string",
|
||||||
# "enum": ["celsius", "fahrenheit"]
|
"enum": ["celsius", "fahrenheit"]
|
||||||
# }
|
}
|
||||||
# },
|
},
|
||||||
# "required": ["location"]
|
"required": ["location"]
|
||||||
# }
|
}
|
||||||
# }
|
}
|
||||||
# ]
|
]
|
||||||
|
|
||||||
# router = Router(model_list=model_list, routing_strategy="latency-based-routing")
|
router = Router(model_list=model_list, routing_strategy="latency-based-routing")
|
||||||
# response = router.completion(model="gpt-3.5-turbo-0613", messages=messages, functions=functions)
|
response = router.completion(model="gpt-3.5-turbo-0613", messages=messages, functions=functions)
|
||||||
# print(response)
|
print(response)
|
||||||
|
|
||||||
# def test_acompletion_on_router():
|
def test_acompletion_on_router():
|
||||||
# try:
|
try:
|
||||||
# litellm.set_verbose = False
|
litellm.set_verbose = False
|
||||||
# model_list = [
|
model_list = [
|
||||||
# {
|
{
|
||||||
# "model_name": "gpt-3.5-turbo",
|
"model_name": "gpt-3.5-turbo",
|
||||||
# "litellm_params": {
|
"litellm_params": {
|
||||||
# "model": "gpt-3.5-turbo-0613",
|
"model": "gpt-3.5-turbo-0613",
|
||||||
# "api_key": os.getenv("OPENAI_API_KEY"),
|
"api_key": os.getenv("OPENAI_API_KEY"),
|
||||||
# },
|
},
|
||||||
# "tpm": 100000,
|
"tpm": 100000,
|
||||||
# "rpm": 10000,
|
"rpm": 10000,
|
||||||
# },
|
},
|
||||||
# {
|
{
|
||||||
# "model_name": "gpt-3.5-turbo",
|
"model_name": "gpt-3.5-turbo",
|
||||||
# "litellm_params": {
|
"litellm_params": {
|
||||||
# "model": "azure/chatgpt-v-2",
|
"model": "azure/chatgpt-v-2",
|
||||||
# "api_key": os.getenv("AZURE_API_KEY"),
|
"api_key": os.getenv("AZURE_API_KEY"),
|
||||||
# "api_base": os.getenv("AZURE_API_BASE"),
|
"api_base": os.getenv("AZURE_API_BASE"),
|
||||||
# "api_version": os.getenv("AZURE_API_VERSION")
|
"api_version": os.getenv("AZURE_API_VERSION")
|
||||||
# },
|
},
|
||||||
# "tpm": 100000,
|
"tpm": 100000,
|
||||||
# "rpm": 10000,
|
"rpm": 10000,
|
||||||
# }
|
}
|
||||||
# ]
|
]
|
||||||
|
|
||||||
# messages = [
|
messages = [
|
||||||
# {"role": "user", "content": f"write a one sentence poem {time.time()}?"}
|
{"role": "user", "content": f"write a one sentence poem {time.time()}?"}
|
||||||
# ]
|
]
|
||||||
# start_time = time.time()
|
start_time = time.time()
|
||||||
# router = Router(model_list=model_list,
|
router = Router(model_list=model_list,
|
||||||
# redis_host=os.environ["REDIS_HOST"],
|
redis_host=os.environ["REDIS_HOST"],
|
||||||
# redis_password=os.environ["REDIS_PASSWORD"],
|
redis_password=os.environ["REDIS_PASSWORD"],
|
||||||
# redis_port=os.environ["REDIS_PORT"],
|
redis_port=os.environ["REDIS_PORT"],
|
||||||
# cache_responses=True,
|
cache_responses=True,
|
||||||
# timeout=30,
|
timeout=30,
|
||||||
# routing_strategy="simple-shuffle")
|
routing_strategy="simple-shuffle")
|
||||||
# async def get_response():
|
async def get_response():
|
||||||
# response1 = await router.acompletion(model="gpt-3.5-turbo", messages=messages)
|
response1 = await router.acompletion(model="gpt-3.5-turbo", messages=messages)
|
||||||
# print(f"response1: {response1}")
|
print(f"response1: {response1}")
|
||||||
# response2 = await router.acompletion(model="gpt-3.5-turbo", messages=messages)
|
response2 = await router.acompletion(model="gpt-3.5-turbo", messages=messages)
|
||||||
# print(f"response2: {response2}")
|
print(f"response2: {response2}")
|
||||||
# assert response1.id == response2.id
|
assert response1.id == response2.id
|
||||||
# assert len(response1.choices[0].message.content) > 0
|
assert len(response1.choices[0].message.content) > 0
|
||||||
# assert response1.choices[0].message.content == response2.choices[0].message.content
|
assert response1.choices[0].message.content == response2.choices[0].message.content
|
||||||
# asyncio.run(get_response())
|
asyncio.run(get_response())
|
||||||
# except litellm.Timeout as e:
|
except litellm.Timeout as e:
|
||||||
# end_time = time.time()
|
end_time = time.time()
|
||||||
# print(f"timeout error occurred: {end_time - start_time}")
|
print(f"timeout error occurred: {end_time - start_time}")
|
||||||
# pass
|
pass
|
||||||
# except Exception as e:
|
except Exception as e:
|
||||||
# traceback.print_exc()
|
traceback.print_exc()
|
||||||
# pytest.fail(f"Error occurred: {e}")
|
pytest.fail(f"Error occurred: {e}")
|
||||||
|
|
||||||
# test_acompletion_on_router()
|
test_acompletion_on_router()
|
||||||
|
|
||||||
# def test_function_calling_on_router():
|
def test_function_calling_on_router():
|
||||||
# try:
|
try:
|
||||||
# litellm.set_verbose = True
|
litellm.set_verbose = True
|
||||||
# model_list = [
|
model_list = [
|
||||||
# {
|
{
|
||||||
# "model_name": "gpt-3.5-turbo",
|
"model_name": "gpt-3.5-turbo",
|
||||||
# "litellm_params": {
|
"litellm_params": {
|
||||||
# "model": "gpt-3.5-turbo-0613",
|
"model": "gpt-3.5-turbo-0613",
|
||||||
# "api_key": os.getenv("OPENAI_API_KEY"),
|
"api_key": os.getenv("OPENAI_API_KEY"),
|
||||||
# },
|
},
|
||||||
# },
|
},
|
||||||
# ]
|
]
|
||||||
# function1 = [
|
function1 = [
|
||||||
# {
|
{
|
||||||
# "name": "get_current_weather",
|
"name": "get_current_weather",
|
||||||
# "description": "Get the current weather in a given location",
|
"description": "Get the current weather in a given location",
|
||||||
# "parameters": {
|
"parameters": {
|
||||||
# "type": "object",
|
"type": "object",
|
||||||
# "properties": {
|
"properties": {
|
||||||
# "location": {
|
"location": {
|
||||||
# "type": "string",
|
"type": "string",
|
||||||
# "description": "The city and state, e.g. San Francisco, CA",
|
"description": "The city and state, e.g. San Francisco, CA",
|
||||||
# },
|
},
|
||||||
# "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
|
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
|
||||||
# },
|
},
|
||||||
# "required": ["location"],
|
"required": ["location"],
|
||||||
# },
|
},
|
||||||
# }
|
}
|
||||||
# ]
|
]
|
||||||
# router = Router(
|
router = Router(
|
||||||
# model_list=model_list,
|
model_list=model_list,
|
||||||
# redis_host=os.getenv("REDIS_HOST"),
|
redis_host=os.getenv("REDIS_HOST"),
|
||||||
# redis_password=os.getenv("REDIS_PASSWORD"),
|
redis_password=os.getenv("REDIS_PASSWORD"),
|
||||||
# redis_port=os.getenv("REDIS_PORT")
|
redis_port=os.getenv("REDIS_PORT")
|
||||||
# )
|
)
|
||||||
# messages=[
|
messages=[
|
||||||
# {
|
{
|
||||||
# "role": "user",
|
"role": "user",
|
||||||
# "content": "what's the weather in boston"
|
"content": "what's the weather in boston"
|
||||||
# }
|
}
|
||||||
# ]
|
]
|
||||||
# response = router.completion(model="gpt-3.5-turbo", messages=messages, functions=function1)
|
response = router.completion(model="gpt-3.5-turbo", messages=messages, functions=function1)
|
||||||
# print(f"final returned response: {response}")
|
print(f"final returned response: {response}")
|
||||||
# assert isinstance(response["choices"][0]["message"]["function_call"], dict)
|
assert isinstance(response["choices"][0]["message"]["function_call"], dict)
|
||||||
# except Exception as e:
|
except Exception as e:
|
||||||
# print(f"An exception occurred: {e}")
|
print(f"An exception occurred: {e}")
|
||||||
|
|
||||||
# # test_function_calling_on_router()
|
# test_function_calling_on_router()
|
||||||
|
|
||||||
# def test_aembedding_on_router():
|
def test_aembedding_on_router():
|
||||||
# try:
|
try:
|
||||||
# model_list = [
|
model_list = [
|
||||||
# {
|
{
|
||||||
# "model_name": "text-embedding-ada-002",
|
"model_name": "text-embedding-ada-002",
|
||||||
# "litellm_params": {
|
"litellm_params": {
|
||||||
# "model": "text-embedding-ada-002",
|
"model": "text-embedding-ada-002",
|
||||||
# },
|
},
|
||||||
# "tpm": 100000,
|
"tpm": 100000,
|
||||||
# "rpm": 10000,
|
"rpm": 10000,
|
||||||
# },
|
},
|
||||||
# ]
|
]
|
||||||
|
|
||||||
# async def embedding_call():
|
async def embedding_call():
|
||||||
# router = Router(model_list=model_list)
|
router = Router(model_list=model_list)
|
||||||
# response = await router.aembedding(
|
response = await router.aembedding(
|
||||||
# model="text-embedding-ada-002",
|
model="text-embedding-ada-002",
|
||||||
# input=["good morning from litellm", "this is another item"],
|
input=["good morning from litellm", "this is another item"],
|
||||||
# )
|
)
|
||||||
# print(response)
|
print(response)
|
||||||
# asyncio.run(embedding_call())
|
asyncio.run(embedding_call())
|
||||||
# except Exception as e:
|
except Exception as e:
|
||||||
# traceback.print_exc()
|
traceback.print_exc()
|
||||||
# pytest.fail(f"Error occurred: {e}")
|
pytest.fail(f"Error occurred: {e}")
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue