File size: 12,771 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 |
import sys, os
import time
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
from litellm.caching import Cache
import random
# litellm.set_verbose=True
messages = [{"role": "user", "content": "who is ishaan Github? "}]
# comment
messages = [{"role": "user", "content": "who is ishaan 5222"}]
def test_caching_v2(): # test in memory cache
try:
litellm.cache = Cache()
response1 = completion(model="gpt-3.5-turbo", messages=messages, caching=True)
response2 = completion(model="gpt-3.5-turbo", messages=messages, caching=True)
print(f"response1: {response1}")
print(f"response2: {response2}")
litellm.cache = None # disable cache
if response2['choices'][0]['message']['content'] != response1['choices'][0]['message']['content']:
print(f"response1: {response1}")
print(f"response2: {response2}")
pytest.fail(f"Error occurred: {e}")
except Exception as e:
print(f"error occurred: {traceback.format_exc()}")
pytest.fail(f"Error occurred: {e}")
# test_caching_v2()
def test_caching_with_models_v2():
messages = [{"role": "user", "content": "who is ishaan CTO of litellm from litellm 2023"}]
litellm.cache = Cache()
print("test2 for caching")
response1 = completion(model="gpt-3.5-turbo", messages=messages, caching=True)
response2 = completion(model="gpt-3.5-turbo", messages=messages, caching=True)
response3 = completion(model="command-nightly", messages=messages, caching=True)
print(f"response1: {response1}")
print(f"response2: {response2}")
print(f"response3: {response3}")
litellm.cache = None
if response3['choices'][0]['message']['content'] == response2['choices'][0]['message']['content']:
# if models are different, it should not return cached response
print(f"response2: {response2}")
print(f"response3: {response3}")
pytest.fail(f"Error occurred:")
if response1['choices'][0]['message']['content'] != response2['choices'][0]['message']['content']:
print(f"response1: {response1}")
print(f"response2: {response2}")
pytest.fail(f"Error occurred:")
# test_caching_with_models_v2()
embedding_large_text = """
small text
""" * 5
# # test_caching_with_models()
def test_embedding_caching():
import time
litellm.cache = Cache()
text_to_embed = [embedding_large_text]
start_time = time.time()
embedding1 = embedding(model="text-embedding-ada-002", input=text_to_embed, caching=True)
end_time = time.time()
print(f"Embedding 1 response time: {end_time - start_time} seconds")
time.sleep(1)
start_time = time.time()
embedding2 = embedding(model="text-embedding-ada-002", input=text_to_embed, caching=True)
end_time = time.time()
print(f"embedding2: {embedding2}")
print(f"Embedding 2 response time: {end_time - start_time} seconds")
litellm.cache = None
assert end_time - start_time <= 0.1 # ensure 2nd response comes in in under 0.1 s
if embedding2['data'][0]['embedding'] != embedding1['data'][0]['embedding']:
print(f"embedding1: {embedding1}")
print(f"embedding2: {embedding2}")
pytest.fail("Error occurred: Embedding caching failed")
# test_embedding_caching()
def test_embedding_caching_azure():
print("Testing azure embedding caching")
import time
litellm.cache = Cache()
text_to_embed = [embedding_large_text]
api_key = os.environ['AZURE_API_KEY']
api_base = os.environ['AZURE_API_BASE']
api_version = os.environ['AZURE_API_VERSION']
os.environ['AZURE_API_VERSION'] = ""
os.environ['AZURE_API_BASE'] = ""
os.environ['AZURE_API_KEY'] = ""
start_time = time.time()
print("AZURE CONFIGS")
print(api_version)
print(api_key)
print(api_base)
embedding1 = embedding(
model="azure/azure-embedding-model",
input=["good morning from litellm", "this is another item"],
api_key=api_key,
api_base=api_base,
api_version=api_version,
caching=True
)
end_time = time.time()
print(f"Embedding 1 response time: {end_time - start_time} seconds")
time.sleep(1)
start_time = time.time()
embedding2 = embedding(
model="azure/azure-embedding-model",
input=["good morning from litellm", "this is another item"],
api_key=api_key,
api_base=api_base,
api_version=api_version,
caching=True
)
end_time = time.time()
print(f"Embedding 2 response time: {end_time - start_time} seconds")
litellm.cache = None
assert end_time - start_time <= 0.1 # ensure 2nd response comes in in under 0.1 s
if embedding2['data'][0]['embedding'] != embedding1['data'][0]['embedding']:
print(f"embedding1: {embedding1}")
print(f"embedding2: {embedding2}")
pytest.fail("Error occurred: Embedding caching failed")
os.environ['AZURE_API_VERSION'] = api_version
os.environ['AZURE_API_BASE'] = api_base
os.environ['AZURE_API_KEY'] = api_key
# test_embedding_caching_azure()
def test_redis_cache_completion():
litellm.set_verbose = False
random_number = random.randint(1, 100000) # add a random number to ensure it's always adding / reading from cache
messages = [{"role": "user", "content": f"write a one sentence poem about: {random_number}"}]
litellm.cache = Cache(type="redis", host=os.environ['REDIS_HOST'], port=os.environ['REDIS_PORT'], password=os.environ['REDIS_PASSWORD'])
print("test2 for caching")
response1 = completion(model="gpt-3.5-turbo", messages=messages, caching=True, max_tokens=10, seed=1222)
response2 = completion(model="gpt-3.5-turbo", messages=messages, caching=True, max_tokens=10, seed=1222)
response3 = completion(model="gpt-3.5-turbo", messages=messages, caching=True, temperature=1)
response4 = completion(model="command-nightly", messages=messages, caching=True)
print("\nresponse 1", response1)
print("\nresponse 2", response2)
print("\nresponse 3", response3)
print("\nresponse 4", response4)
litellm.cache = None
"""
1 & 2 should be exactly the same
1 & 3 should be different, since input params are diff
1 & 4 should be diff, since models are diff
"""
if response1['choices'][0]['message']['content'] != response2['choices'][0]['message']['content']: # 1 and 2 should be the same
# 1&2 have the exact same input params. This MUST Be a CACHE HIT
print(f"response1: {response1}")
print(f"response2: {response2}")
pytest.fail(f"Error occurred:")
if response1['choices'][0]['message']['content'] == response3['choices'][0]['message']['content']:
# if input params like seed, max_tokens are diff it should NOT be a cache hit
print(f"response1: {response1}")
print(f"response3: {response3}")
pytest.fail(f"Response 1 == response 3. Same model, diff params shoudl not cache Error occurred:")
if response1['choices'][0]['message']['content'] == response4['choices'][0]['message']['content']:
# if models are different, it should not return cached response
print(f"response1: {response1}")
print(f"response4: {response4}")
pytest.fail(f"Error occurred:")
# test_redis_cache_completion()
# redis cache with custom keys
def custom_get_cache_key(*args, **kwargs):
# return key to use for your cache:
key = kwargs.get("model", "") + str(kwargs.get("messages", "")) + str(kwargs.get("temperature", "")) + str(kwargs.get("logit_bias", ""))
return key
def test_custom_redis_cache_with_key():
messages = [{"role": "user", "content": "write a one line story"}]
litellm.cache = Cache(type="redis", host=os.environ['REDIS_HOST'], port=os.environ['REDIS_PORT'], password=os.environ['REDIS_PASSWORD'])
litellm.cache.get_cache_key = custom_get_cache_key
local_cache = {}
def set_cache(key, value):
local_cache[key] = value
def get_cache(key):
if key in local_cache:
return local_cache[key]
litellm.cache.cache.set_cache = set_cache
litellm.cache.cache.get_cache = get_cache
# patch this redis cache get and set call
response1 = completion(model="gpt-3.5-turbo", messages=messages, temperature=1, caching=True, num_retries=3)
response2 = completion(model="gpt-3.5-turbo", messages=messages, temperature=1, caching=True, num_retries=3)
response3 = completion(model="gpt-3.5-turbo", messages=messages, temperature=1, caching=False, num_retries=3)
print(f"response1: {response1}")
print(f"response2: {response2}")
print(f"response3: {response3}")
if response3['choices'][0]['message']['content'] == response2['choices'][0]['message']['content']:
pytest.fail(f"Error occurred:")
litellm.cache = None
# test_custom_redis_cache_with_key()
def test_custom_redis_cache_params():
# test if we can init redis with **kwargs
try:
litellm.cache = Cache(
type="redis",
host=os.environ['REDIS_HOST'],
port=os.environ['REDIS_PORT'],
password=os.environ['REDIS_PASSWORD'],
db = 0,
ssl=True,
ssl_certfile="./redis_user.crt",
ssl_keyfile="./redis_user_private.key",
ssl_ca_certs="./redis_ca.pem",
)
print(litellm.cache.cache.redis_client)
litellm.cache = None
except Exception as e:
pytest.fail(f"Error occurred:", e)
# test_custom_redis_cache_params()
# def test_redis_cache_with_ttl():
# cache = Cache(type="redis", host=os.environ['REDIS_HOST'], port=os.environ['REDIS_PORT'], password=os.environ['REDIS_PASSWORD'])
# sample_model_response_object_str = """{
# "choices": [
# {
# "finish_reason": "stop",
# "index": 0,
# "message": {
# "role": "assistant",
# "content": "I'm doing well, thank you for asking. I am Claude, an AI assistant created by Anthropic."
# }
# }
# ],
# "created": 1691429984.3852863,
# "model": "claude-instant-1",
# "usage": {
# "prompt_tokens": 18,
# "completion_tokens": 23,
# "total_tokens": 41
# }
# }"""
# sample_model_response_object = {
# "choices": [
# {
# "finish_reason": "stop",
# "index": 0,
# "message": {
# "role": "assistant",
# "content": "I'm doing well, thank you for asking. I am Claude, an AI assistant created by Anthropic."
# }
# }
# ],
# "created": 1691429984.3852863,
# "model": "claude-instant-1",
# "usage": {
# "prompt_tokens": 18,
# "completion_tokens": 23,
# "total_tokens": 41
# }
# }
# cache.add_cache(cache_key="test_key", result=sample_model_response_object_str, ttl=1)
# cached_value = cache.get_cache(cache_key="test_key")
# print(f"cached-value: {cached_value}")
# assert cached_value['choices'][0]['message']['content'] == sample_model_response_object['choices'][0]['message']['content']
# time.sleep(2)
# assert cache.get_cache(cache_key="test_key") is None
# # test_redis_cache_with_ttl()
# def test_in_memory_cache_with_ttl():
# cache = Cache(type="local")
# sample_model_response_object_str = """{
# "choices": [
# {
# "finish_reason": "stop",
# "index": 0,
# "message": {
# "role": "assistant",
# "content": "I'm doing well, thank you for asking. I am Claude, an AI assistant created by Anthropic."
# }
# }
# ],
# "created": 1691429984.3852863,
# "model": "claude-instant-1",
# "usage": {
# "prompt_tokens": 18,
# "completion_tokens": 23,
# "total_tokens": 41
# }
# }"""
# sample_model_response_object = {
# "choices": [
# {
# "finish_reason": "stop",
# "index": 0,
# "message": {
# "role": "assistant",
# "content": "I'm doing well, thank you for asking. I am Claude, an AI assistant created by Anthropic."
# }
# }
# ],
# "created": 1691429984.3852863,
# "model": "claude-instant-1",
# "usage": {
# "prompt_tokens": 18,
# "completion_tokens": 23,
# "total_tokens": 41
# }
# }
# cache.add_cache(cache_key="test_key", result=sample_model_response_object_str, ttl=1)
# cached_value = cache.get_cache(cache_key="test_key")
# assert cached_value['choices'][0]['message']['content'] == sample_model_response_object['choices'][0]['message']['content']
# time.sleep(2)
# assert cache.get_cache(cache_key="test_key") is None
# # test_in_memory_cache_with_ttl() |