File size: 9,399 Bytes
395201c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 |
#### What this tests ####
#This tests litellm router
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
load_dotenv()
def test_exception_raising():
# 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
litellm.set_verbose=True
import openai
try:
print("testing if router raises an exception")
old_api_key = os.environ["AZURE_API_KEY"]
os.environ["AZURE_API_KEY"] = ""
model_list = [
{
"model_name": "gpt-3.5-turbo", # openai model name
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-v-2",
"api_key": "bad-key",
"api_version": os.getenv("AZURE_API_VERSION"),
"api_base": os.getenv("AZURE_API_BASE")
},
"tpm": 240000,
"rpm": 1800
},
{
"model_name": "gpt-3.5-turbo", # openai model name
"litellm_params": { #
"model": "gpt-3.5-turbo",
"api_key": "bad-key",
},
"tpm": 240000,
"rpm": 1800
}
]
router = Router(model_list=model_list,
redis_host=os.getenv("REDIS_HOST"),
redis_password=os.getenv("REDIS_PASSWORD"),
redis_port=int(os.getenv("REDIS_PORT")),
routing_strategy="simple-shuffle",
set_verbose=False,
num_retries=1) # type: ignore
response = router.completion(
model="gpt-3.5-turbo",
messages=[
{
"role": "user",
"content": "hello this request will fail"
}
]
)
os.environ["AZURE_API_KEY"] = old_api_key
pytest.fail(f"Should have raised an Auth Error")
except openai.AuthenticationError:
print("Test Passed: Caught an OPENAI AUTH Error, Good job. This is what we needed!")
os.environ["AZURE_API_KEY"] = old_api_key
router.reset()
except Exception as e:
os.environ["AZURE_API_KEY"] = old_api_key
print("Got unexpected exception on router!", e)
# test_exception_raising()
def test_reading_key_from_model_list():
# 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
litellm.set_verbose=False
import openai
try:
print("testing if router raises an exception")
old_api_key = os.environ["AZURE_API_KEY"]
os.environ.pop("AZURE_API_KEY", None)
model_list = [
{
"model_name": "gpt-3.5-turbo", # openai model name
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-v-2",
"api_key": old_api_key,
"api_version": os.getenv("AZURE_API_VERSION"),
"api_base": os.getenv("AZURE_API_BASE")
},
"tpm": 240000,
"rpm": 1800
}
]
router = Router(model_list=model_list,
redis_host=os.getenv("REDIS_HOST"),
redis_password=os.getenv("REDIS_PASSWORD"),
redis_port=int(os.getenv("REDIS_PORT")),
routing_strategy="simple-shuffle",
set_verbose=True,
num_retries=1) # type: ignore
response = router.completion(
model="gpt-3.5-turbo",
messages=[
{
"role": "user",
"content": "hello this request will fail"
}
]
)
os.environ["AZURE_API_KEY"] = old_api_key
router.reset()
except Exception as e:
os.environ["AZURE_API_KEY"] = old_api_key
print(f"FAILED TEST")
pytest.fail(f"Got unexpected exception on router! - {e}")
# test_reading_key_from_model_list()
### FUNCTION CALLING
def test_function_calling():
model_list = [
{
"model_name": "gpt-3.5-turbo-0613",
"litellm_params": {
"model": "gpt-3.5-turbo-0613",
"api_key": os.getenv("OPENAI_API_KEY"),
},
"tpm": 100000,
"rpm": 10000,
},
]
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"]
}
}
]
router = Router(model_list=model_list, routing_strategy="latency-based-routing")
response = router.completion(model="gpt-3.5-turbo-0613", messages=messages, functions=functions)
router.reset()
print(response)
def test_acompletion_on_router():
try:
litellm.set_verbose = False
model_list = [
{
"model_name": "gpt-3.5-turbo",
"litellm_params": {
"model": "gpt-3.5-turbo-0613",
"api_key": os.getenv("OPENAI_API_KEY"),
},
"tpm": 100000,
"rpm": 10000,
},
{
"model_name": "gpt-3.5-turbo",
"litellm_params": {
"model": "azure/chatgpt-v-2",
"api_key": os.getenv("AZURE_API_KEY"),
"api_base": os.getenv("AZURE_API_BASE"),
"api_version": os.getenv("AZURE_API_VERSION")
},
"tpm": 100000,
"rpm": 10000,
}
]
messages = [
{"role": "user", "content": f"write a one sentence poem {time.time()}?"}
]
start_time = time.time()
router = Router(model_list=model_list,
redis_host=os.environ["REDIS_HOST"],
redis_password=os.environ["REDIS_PASSWORD"],
redis_port=os.environ["REDIS_PORT"],
cache_responses=True,
timeout=30,
routing_strategy="simple-shuffle")
async def get_response():
response1 = await router.acompletion(model="gpt-3.5-turbo", messages=messages)
print(f"response1: {response1}")
response2 = await router.acompletion(model="gpt-3.5-turbo", messages=messages)
print(f"response2: {response2}")
assert response1.id == response2.id
assert len(response1.choices[0].message.content) > 0
assert response1.choices[0].message.content == response2.choices[0].message.content
asyncio.run(get_response())
router.reset()
except litellm.Timeout as e:
end_time = time.time()
print(f"timeout error occurred: {end_time - start_time}")
pass
except Exception as e:
traceback.print_exc()
pytest.fail(f"Error occurred: {e}")
# test_acompletion_on_router()
def test_function_calling_on_router():
try:
litellm.set_verbose = True
model_list = [
{
"model_name": "gpt-3.5-turbo",
"litellm_params": {
"model": "gpt-3.5-turbo-0613",
"api_key": os.getenv("OPENAI_API_KEY"),
},
},
]
function1 = [
{
"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"],
},
}
]
router = Router(
model_list=model_list,
redis_host=os.getenv("REDIS_HOST"),
redis_password=os.getenv("REDIS_PASSWORD"),
redis_port=os.getenv("REDIS_PORT")
)
messages=[
{
"role": "user",
"content": "what's the weather in boston"
}
]
response = router.completion(model="gpt-3.5-turbo", messages=messages, functions=function1)
print(f"final returned response: {response}")
router.reset()
assert isinstance(response["choices"][0]["message"]["function_call"], dict)
except Exception as e:
print(f"An exception occurred: {e}")
# test_function_calling_on_router()
def test_aembedding_on_router():
litellm.set_verbose = True
try:
model_list = [
{
"model_name": "text-embedding-ada-002",
"litellm_params": {
"model": "text-embedding-ada-002",
},
"tpm": 100000,
"rpm": 10000,
},
]
async def embedding_call():
router = Router(model_list=model_list)
response = await router.aembedding(
model="text-embedding-ada-002",
input=["good morning from litellm", "this is another item"],
)
print(response)
router.reset()
asyncio.run(embedding_call())
except Exception as e:
traceback.print_exc()
pytest.fail(f"Error occurred: {e}")
# test_aembedding_on_router()
def test_azure_aembedding_on_router():
litellm.set_verbose = True
try:
model_list = [
{
"model_name": "text-embedding-ada-002",
"litellm_params": {
"model": "azure/azure-embedding-model",
"api_key":os.environ['AZURE_API_KEY'],
"api_base": os.environ['AZURE_API_BASE']
},
"tpm": 100000,
"rpm": 10000,
},
]
async def embedding_call():
router = Router(model_list=model_list)
response = await router.aembedding(
model="text-embedding-ada-002",
input=["good morning from litellm"]
)
print(response)
router.reset()
asyncio.run(embedding_call())
except Exception as e:
traceback.print_exc()
pytest.fail(f"Error occurred: {e}")
# test_azure_aembedding_on_router() |