File size: 29,568 Bytes
7db0ae4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 |
### What this tests ####
## This test asserts the type of data passed into each method of the custom callback handler
import sys, os, time, inspect, asyncio, traceback
from datetime import datetime
import pytest
sys.path.insert(0, os.path.abspath("../.."))
from typing import Optional, Literal, List, Union
from litellm import completion, embedding, Cache
import litellm
from litellm.integrations.custom_logger import CustomLogger
# 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
## 5. Caching
# Test models
## 1. OpenAI
## 2. Azure OpenAI
## 3. Non-OpenAI/Azure - e.g. Bedrock
# Test interfaces
## 1. litellm.completion() + litellm.embeddings()
## refer to test_custom_callback_input_router.py for the router + proxy tests
class CompletionCustomHandler(
CustomLogger
): # https://docs.litellm.ai/docs/observability/custom_callback#callback-class
"""
The set of expected inputs to a custom handler for a
"""
# Class variables or attributes
def __init__(self):
self.errors = []
self.states: Optional[
List[
Literal[
"sync_pre_api_call",
"async_pre_api_call",
"post_api_call",
"sync_stream",
"async_stream",
"sync_success",
"async_success",
"sync_failure",
"async_failure",
]
]
] = []
def log_pre_api_call(self, model, messages, kwargs):
try:
self.states.append("sync_pre_api_call")
## MODEL
assert isinstance(model, str)
## MESSAGES
assert isinstance(messages, list)
## KWARGS
assert isinstance(kwargs["model"], str)
assert isinstance(kwargs["messages"], list)
assert isinstance(kwargs["optional_params"], dict)
assert isinstance(kwargs["litellm_params"], dict)
assert isinstance(kwargs["start_time"], (datetime, type(None)))
assert isinstance(kwargs["stream"], bool)
assert isinstance(kwargs["user"], (str, type(None)))
except Exception as e:
print(f"Assertion Error: {traceback.format_exc()}")
self.errors.append(traceback.format_exc())
def log_post_api_call(self, kwargs, response_obj, start_time, end_time):
try:
self.states.append("post_api_call")
## START TIME
assert isinstance(start_time, datetime)
## END TIME
assert end_time == None
## RESPONSE OBJECT
assert response_obj == None
## KWARGS
assert isinstance(kwargs["model"], str)
assert isinstance(kwargs["messages"], list)
assert isinstance(kwargs["optional_params"], dict)
assert isinstance(kwargs["litellm_params"], dict)
assert isinstance(kwargs["start_time"], (datetime, type(None)))
assert isinstance(kwargs["stream"], bool)
assert isinstance(kwargs["user"], (str, type(None)))
assert isinstance(kwargs["input"], (list, dict, str))
assert isinstance(kwargs["api_key"], (str, type(None)))
assert (
isinstance(
kwargs["original_response"], (str, litellm.CustomStreamWrapper)
)
or inspect.iscoroutine(kwargs["original_response"])
or inspect.isasyncgen(kwargs["original_response"])
)
assert isinstance(kwargs["additional_args"], (dict, type(None)))
assert isinstance(kwargs["log_event_type"], str)
except:
print(f"Assertion Error: {traceback.format_exc()}")
self.errors.append(traceback.format_exc())
async def async_log_stream_event(self, kwargs, response_obj, start_time, end_time):
try:
self.states.append("async_stream")
## START TIME
assert isinstance(start_time, datetime)
## END TIME
assert isinstance(end_time, datetime)
## RESPONSE OBJECT
assert isinstance(response_obj, litellm.ModelResponse)
## KWARGS
assert isinstance(kwargs["model"], str)
assert isinstance(kwargs["messages"], list) and isinstance(
kwargs["messages"][0], dict
)
assert isinstance(kwargs["optional_params"], dict)
assert isinstance(kwargs["litellm_params"], dict)
assert isinstance(kwargs["start_time"], (datetime, type(None)))
assert isinstance(kwargs["stream"], bool)
assert isinstance(kwargs["user"], (str, type(None)))
assert (
isinstance(kwargs["input"], list)
and isinstance(kwargs["input"][0], dict)
) or isinstance(kwargs["input"], (dict, str))
assert isinstance(kwargs["api_key"], (str, type(None)))
assert (
isinstance(
kwargs["original_response"], (str, litellm.CustomStreamWrapper)
)
or inspect.isasyncgen(kwargs["original_response"])
or inspect.iscoroutine(kwargs["original_response"])
)
assert isinstance(kwargs["additional_args"], (dict, type(None)))
assert isinstance(kwargs["log_event_type"], str)
except:
print(f"Assertion Error: {traceback.format_exc()}")
self.errors.append(traceback.format_exc())
def log_success_event(self, kwargs, response_obj, start_time, end_time):
try:
self.states.append("sync_success")
## START TIME
assert isinstance(start_time, datetime)
## END TIME
assert isinstance(end_time, datetime)
## RESPONSE OBJECT
assert isinstance(response_obj, litellm.ModelResponse)
## KWARGS
assert isinstance(kwargs["model"], str)
assert isinstance(kwargs["messages"], list) and isinstance(
kwargs["messages"][0], dict
)
assert isinstance(kwargs["optional_params"], dict)
assert isinstance(kwargs["litellm_params"], dict)
assert isinstance(kwargs["start_time"], (datetime, type(None)))
assert isinstance(kwargs["stream"], bool)
assert isinstance(kwargs["user"], (str, type(None)))
assert (
isinstance(kwargs["input"], list)
and isinstance(kwargs["input"][0], dict)
) or isinstance(kwargs["input"], (dict, str))
assert isinstance(kwargs["api_key"], (str, type(None)))
assert isinstance(
kwargs["original_response"], (str, litellm.CustomStreamWrapper)
)
assert isinstance(kwargs["additional_args"], (dict, type(None)))
assert isinstance(kwargs["log_event_type"], str)
except:
print(f"Assertion Error: {traceback.format_exc()}")
self.errors.append(traceback.format_exc())
def log_failure_event(self, kwargs, response_obj, start_time, end_time):
try:
self.states.append("sync_failure")
## START TIME
assert isinstance(start_time, datetime)
## END TIME
assert isinstance(end_time, datetime)
## RESPONSE OBJECT
assert response_obj == None
## KWARGS
assert isinstance(kwargs["model"], str)
assert isinstance(kwargs["messages"], list) and isinstance(
kwargs["messages"][0], dict
)
assert isinstance(kwargs["optional_params"], dict)
assert isinstance(kwargs["litellm_params"], dict)
assert isinstance(kwargs["start_time"], (datetime, type(None)))
assert isinstance(kwargs["stream"], bool)
assert isinstance(kwargs["user"], (str, type(None)))
assert (
isinstance(kwargs["input"], list)
and isinstance(kwargs["input"][0], dict)
) or isinstance(kwargs["input"], (dict, str))
assert isinstance(kwargs["api_key"], (str, type(None)))
assert (
isinstance(
kwargs["original_response"], (str, litellm.CustomStreamWrapper)
)
or kwargs["original_response"] == None
)
assert isinstance(kwargs["additional_args"], (dict, type(None)))
assert isinstance(kwargs["log_event_type"], str)
except:
print(f"Assertion Error: {traceback.format_exc()}")
self.errors.append(traceback.format_exc())
async def async_log_pre_api_call(self, model, messages, kwargs):
try:
self.states.append("async_pre_api_call")
## MODEL
assert isinstance(model, str)
## MESSAGES
assert isinstance(messages, list) and isinstance(messages[0], dict)
## KWARGS
assert isinstance(kwargs["model"], str)
assert isinstance(kwargs["messages"], list) and isinstance(
kwargs["messages"][0], dict
)
assert isinstance(kwargs["optional_params"], dict)
assert isinstance(kwargs["litellm_params"], dict)
assert isinstance(kwargs["start_time"], (datetime, type(None)))
assert isinstance(kwargs["stream"], bool)
assert isinstance(kwargs["user"], (str, type(None)))
except Exception as e:
print(f"Assertion Error: {traceback.format_exc()}")
self.errors.append(traceback.format_exc())
async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
try:
self.states.append("async_success")
## START TIME
assert isinstance(start_time, datetime)
## END TIME
assert isinstance(end_time, datetime)
## RESPONSE OBJECT
assert isinstance(
response_obj, (litellm.ModelResponse, litellm.EmbeddingResponse)
)
## KWARGS
assert isinstance(kwargs["model"], str)
assert isinstance(kwargs["messages"], list)
assert isinstance(kwargs["optional_params"], dict)
assert isinstance(kwargs["litellm_params"], dict)
assert isinstance(kwargs["start_time"], (datetime, type(None)))
assert isinstance(kwargs["stream"], bool)
assert isinstance(kwargs["user"], (str, type(None)))
assert isinstance(kwargs["input"], (list, dict, str))
assert isinstance(kwargs["api_key"], (str, type(None)))
assert (
isinstance(
kwargs["original_response"], (str, litellm.CustomStreamWrapper)
)
or inspect.isasyncgen(kwargs["original_response"])
or inspect.iscoroutine(kwargs["original_response"])
)
assert isinstance(kwargs["additional_args"], (dict, type(None)))
assert isinstance(kwargs["log_event_type"], str)
assert kwargs["cache_hit"] is None or isinstance(kwargs["cache_hit"], bool)
except:
print(f"Assertion Error: {traceback.format_exc()}")
self.errors.append(traceback.format_exc())
async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time):
try:
self.states.append("async_failure")
## START TIME
assert isinstance(start_time, datetime)
## END TIME
assert isinstance(end_time, datetime)
## RESPONSE OBJECT
assert response_obj == None
## KWARGS
assert isinstance(kwargs["model"], str)
assert isinstance(kwargs["messages"], list)
assert isinstance(kwargs["optional_params"], dict)
assert isinstance(kwargs["litellm_params"], dict)
assert isinstance(kwargs["start_time"], (datetime, type(None)))
assert isinstance(kwargs["stream"], bool)
assert isinstance(kwargs["user"], (str, type(None)))
assert isinstance(kwargs["input"], (list, str, dict))
assert isinstance(kwargs["api_key"], (str, type(None)))
assert (
isinstance(
kwargs["original_response"], (str, litellm.CustomStreamWrapper)
)
or inspect.isasyncgen(kwargs["original_response"])
or inspect.iscoroutine(kwargs["original_response"])
or kwargs["original_response"] == None
)
assert isinstance(kwargs["additional_args"], (dict, type(None)))
assert isinstance(kwargs["log_event_type"], str)
except:
print(f"Assertion Error: {traceback.format_exc()}")
self.errors.append(traceback.format_exc())
# COMPLETION
## Test OpenAI + sync
def test_chat_openai_stream():
try:
customHandler = CompletionCustomHandler()
litellm.callbacks = [customHandler]
response = litellm.completion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync openai"}],
)
## test streaming
response = litellm.completion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
stream=True,
)
for chunk in response:
continue
## test failure callback
try:
response = litellm.completion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
api_key="my-bad-key",
stream=True,
)
for chunk in response:
continue
except:
pass
time.sleep(1)
print(f"customHandler.errors: {customHandler.errors}")
assert len(customHandler.errors) == 0
litellm.callbacks = []
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# test_chat_openai_stream()
## Test OpenAI + Async
@pytest.mark.asyncio
async def test_async_chat_openai_stream():
try:
customHandler = CompletionCustomHandler()
litellm.callbacks = [customHandler]
response = await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
)
## test streaming
response = await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
stream=True,
)
async for chunk in response:
continue
## test failure callback
try:
response = await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
api_key="my-bad-key",
stream=True,
)
async for chunk in response:
continue
except:
pass
time.sleep(1)
print(f"customHandler.errors: {customHandler.errors}")
assert len(customHandler.errors) == 0
litellm.callbacks = []
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# asyncio.run(test_async_chat_openai_stream())
## Test Azure + sync
def test_chat_azure_stream():
try:
customHandler = CompletionCustomHandler()
litellm.callbacks = [customHandler]
response = litellm.completion(
model="azure/chatgpt-v-2",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}],
)
# test streaming
response = litellm.completion(
model="azure/chatgpt-v-2",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}],
stream=True,
)
for chunk in response:
continue
# test failure callback
try:
response = litellm.completion(
model="azure/chatgpt-v-2",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}],
api_key="my-bad-key",
stream=True,
)
for chunk in response:
continue
except:
pass
time.sleep(1)
print(f"customHandler.errors: {customHandler.errors}")
assert len(customHandler.errors) == 0
litellm.callbacks = []
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# test_chat_azure_stream()
## Test Azure + Async
@pytest.mark.asyncio
async def test_async_chat_azure_stream():
try:
customHandler = CompletionCustomHandler()
litellm.callbacks = [customHandler]
response = await litellm.acompletion(
model="azure/chatgpt-v-2",
messages=[{"role": "user", "content": "Hi 👋 - i'm async azure"}],
)
## test streaming
response = await litellm.acompletion(
model="azure/chatgpt-v-2",
messages=[{"role": "user", "content": "Hi 👋 - i'm async azure"}],
stream=True,
)
async for chunk in response:
continue
# test failure callback
try:
response = await litellm.acompletion(
model="azure/chatgpt-v-2",
messages=[{"role": "user", "content": "Hi 👋 - i'm async azure"}],
api_key="my-bad-key",
stream=True,
)
async for chunk in response:
continue
except:
pass
await asyncio.sleep(1)
print(f"customHandler.errors: {customHandler.errors}")
assert len(customHandler.errors) == 0
litellm.callbacks = []
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
asyncio.run(test_async_chat_azure_stream())
## Test Bedrock + sync
def test_chat_bedrock_stream():
try:
customHandler = CompletionCustomHandler()
litellm.callbacks = [customHandler]
response = litellm.completion(
model="bedrock/anthropic.claude-v1",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync bedrock"}],
)
# test streaming
response = litellm.completion(
model="bedrock/anthropic.claude-v1",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync bedrock"}],
stream=True,
)
for chunk in response:
continue
# test failure callback
try:
response = litellm.completion(
model="bedrock/anthropic.claude-v1",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync bedrock"}],
aws_region_name="my-bad-region",
stream=True,
)
for chunk in response:
continue
except:
pass
time.sleep(1)
print(f"customHandler.errors: {customHandler.errors}")
assert len(customHandler.errors) == 0
litellm.callbacks = []
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# test_chat_bedrock_stream()
## Test Bedrock + Async
@pytest.mark.asyncio
async def test_async_chat_bedrock_stream():
try:
customHandler = CompletionCustomHandler()
litellm.callbacks = [customHandler]
response = await litellm.acompletion(
model="bedrock/anthropic.claude-v1",
messages=[{"role": "user", "content": "Hi 👋 - i'm async bedrock"}],
)
# test streaming
response = await litellm.acompletion(
model="bedrock/anthropic.claude-v1",
messages=[{"role": "user", "content": "Hi 👋 - i'm async bedrock"}],
stream=True,
)
print(f"response: {response}")
async for chunk in response:
print(f"chunk: {chunk}")
continue
## test failure callback
try:
response = await litellm.acompletion(
model="bedrock/anthropic.claude-v1",
messages=[{"role": "user", "content": "Hi 👋 - i'm async bedrock"}],
aws_region_name="my-bad-key",
stream=True,
)
async for chunk in response:
continue
except:
pass
time.sleep(1)
print(f"customHandler.errors: {customHandler.errors}")
assert len(customHandler.errors) == 0
litellm.callbacks = []
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# asyncio.run(test_async_chat_bedrock_stream())
# Text Completion
## Test OpenAI text completion + Async
@pytest.mark.asyncio
async def test_async_text_completion_openai_stream():
try:
customHandler = CompletionCustomHandler()
litellm.callbacks = [customHandler]
response = await litellm.atext_completion(
model="gpt-3.5-turbo",
prompt="Hi 👋 - i'm async text completion openai",
)
# test streaming
response = await litellm.atext_completion(
model="gpt-3.5-turbo",
prompt="Hi 👋 - i'm async text completion openai",
stream=True,
)
async for chunk in response:
print(f"chunk: {chunk}")
continue
## test failure callback
try:
response = await litellm.atext_completion(
model="gpt-3.5-turbo",
prompt="Hi 👋 - i'm async text completion openai",
stream=True,
api_key="my-bad-key",
)
async for chunk in response:
continue
except:
pass
time.sleep(1)
print(f"customHandler.errors: {customHandler.errors}")
assert len(customHandler.errors) == 0
litellm.callbacks = []
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# EMBEDDING
## Test OpenAI + Async
@pytest.mark.asyncio
async def test_async_embedding_openai():
try:
customHandler_success = CompletionCustomHandler()
customHandler_failure = CompletionCustomHandler()
litellm.callbacks = [customHandler_success]
response = await litellm.aembedding(
model="azure/azure-embedding-model", input=["good morning from litellm"]
)
await asyncio.sleep(1)
print(f"customHandler_success.errors: {customHandler_success.errors}")
print(f"customHandler_success.states: {customHandler_success.states}")
assert len(customHandler_success.errors) == 0
assert len(customHandler_success.states) == 3 # pre, post, success
# test failure callback
litellm.callbacks = [customHandler_failure]
try:
response = await litellm.aembedding(
model="text-embedding-ada-002",
input=["good morning from litellm"],
api_key="my-bad-key",
)
except:
pass
await asyncio.sleep(1)
print(f"customHandler_failure.errors: {customHandler_failure.errors}")
print(f"customHandler_failure.states: {customHandler_failure.states}")
assert len(customHandler_failure.errors) == 0
assert len(customHandler_failure.states) == 3 # pre, post, failure
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# asyncio.run(test_async_embedding_openai())
## Test Azure + Async
@pytest.mark.asyncio
async def test_async_embedding_azure():
try:
customHandler_success = CompletionCustomHandler()
customHandler_failure = CompletionCustomHandler()
litellm.callbacks = [customHandler_success]
response = await litellm.aembedding(
model="azure/azure-embedding-model", input=["good morning from litellm"]
)
await asyncio.sleep(1)
print(f"customHandler_success.errors: {customHandler_success.errors}")
print(f"customHandler_success.states: {customHandler_success.states}")
assert len(customHandler_success.errors) == 0
assert len(customHandler_success.states) == 3 # pre, post, success
# test failure callback
litellm.callbacks = [customHandler_failure]
try:
response = await litellm.aembedding(
model="azure/azure-embedding-model",
input=["good morning from litellm"],
api_key="my-bad-key",
)
except:
pass
await asyncio.sleep(1)
print(f"customHandler_failure.errors: {customHandler_failure.errors}")
print(f"customHandler_failure.states: {customHandler_failure.states}")
assert len(customHandler_failure.errors) == 0
assert len(customHandler_failure.states) == 3 # pre, post, success
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# asyncio.run(test_async_embedding_azure())
## Test Bedrock + Async
@pytest.mark.asyncio
async def test_async_embedding_bedrock():
try:
customHandler_success = CompletionCustomHandler()
customHandler_failure = CompletionCustomHandler()
litellm.callbacks = [customHandler_success]
litellm.set_verbose = True
response = await litellm.aembedding(
model="bedrock/cohere.embed-multilingual-v3",
input=["good morning from litellm"],
aws_region_name="os.environ/AWS_REGION_NAME_2",
)
await asyncio.sleep(1)
print(f"customHandler_success.errors: {customHandler_success.errors}")
print(f"customHandler_success.states: {customHandler_success.states}")
assert len(customHandler_success.errors) == 0
assert len(customHandler_success.states) == 3 # pre, post, success
# test failure callback
litellm.callbacks = [customHandler_failure]
try:
response = await litellm.aembedding(
model="bedrock/cohere.embed-multilingual-v3",
input=["good morning from litellm"],
aws_region_name="my-bad-region",
)
except:
pass
await asyncio.sleep(1)
print(f"customHandler_failure.errors: {customHandler_failure.errors}")
print(f"customHandler_failure.states: {customHandler_failure.states}")
assert len(customHandler_failure.errors) == 0
assert len(customHandler_failure.states) == 3 # pre, post, success
except Exception as e:
pytest.fail(f"An exception occurred: {str(e)}")
# asyncio.run(test_async_embedding_bedrock())
# CACHING
## Test Azure - completion, embedding
@pytest.mark.asyncio
async def test_async_completion_azure_caching():
customHandler_caching = CompletionCustomHandler()
litellm.cache = Cache(
type="redis",
host=os.environ["REDIS_HOST"],
port=os.environ["REDIS_PORT"],
password=os.environ["REDIS_PASSWORD"],
)
litellm.callbacks = [customHandler_caching]
unique_time = time.time()
response1 = await litellm.acompletion(
model="azure/chatgpt-v-2",
messages=[{"role": "user", "content": f"Hi 👋 - i'm async azure {unique_time}"}],
caching=True,
)
await asyncio.sleep(1)
print(f"customHandler_caching.states pre-cache hit: {customHandler_caching.states}")
response2 = await litellm.acompletion(
model="azure/chatgpt-v-2",
messages=[{"role": "user", "content": f"Hi 👋 - i'm async azure {unique_time}"}],
caching=True,
)
await asyncio.sleep(1) # success callbacks are done in parallel
print(
f"customHandler_caching.states post-cache hit: {customHandler_caching.states}"
)
assert len(customHandler_caching.errors) == 0
assert len(customHandler_caching.states) == 4 # pre, post, success, success
@pytest.mark.asyncio
async def test_async_embedding_azure_caching():
print("Testing custom callback input - Azure Caching")
customHandler_caching = CompletionCustomHandler()
litellm.cache = Cache(
type="redis",
host=os.environ["REDIS_HOST"],
port=os.environ["REDIS_PORT"],
password=os.environ["REDIS_PASSWORD"],
)
litellm.callbacks = [customHandler_caching]
unique_time = time.time()
response1 = await litellm.aembedding(
model="azure/azure-embedding-model",
input=[f"good morning from litellm1 {unique_time}"],
caching=True,
)
await asyncio.sleep(1) # set cache is async for aembedding()
response2 = await litellm.aembedding(
model="azure/azure-embedding-model",
input=[f"good morning from litellm1 {unique_time}"],
caching=True,
)
await asyncio.sleep(1) # success callbacks are done in parallel
print(customHandler_caching.states)
assert len(customHandler_caching.errors) == 0
assert len(customHandler_caching.states) == 4 # pre, post, success, success
# asyncio.run(
# test_async_embedding_azure_caching()
# )
|