Spaces:
Configuration error
Configuration error
File size: 20,410 Bytes
447ebeb |
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 |
"""
Test HuggingFace LLM
"""
from base_llm_unit_tests import BaseLLMChatTest
import json
import os
import sys
from unittest.mock import patch, MagicMock, AsyncMock
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
import litellm
import pytest
from litellm.types.utils import ModelResponseStream, ModelResponse
MOCK_COMPLETION_RESPONSE = {
"id": "9115d3daeab10608",
"object": "chat.completion",
"created": 11111,
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
"prompt": [],
"choices": [
{
"finish_reason": "stop",
"seed": 3629048360264764400,
"logprobs": None,
"index": 0,
"message": {
"role": "assistant",
"content": "This is a test response from the mocked HuggingFace API.",
"tool_calls": [],
},
}
],
"usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30},
}
MOCK_STREAMING_CHUNKS = [
{
"id": "id1",
"object": "chat.completion.chunk",
"created": 1111,
"choices": [
{
"index": 0,
"text": "Deep",
"logprobs": None,
"finish_reason": None,
"seed": None,
"delta": {
"token_id": 34564,
"role": "assistant",
"content": "Deep",
"tool_calls": None,
},
}
],
"model": "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
"usage": None,
},
{
"id": "id2",
"object": "chat.completion.chunk",
"created": 1111,
"choices": [
{
"index": 0,
"text": " learning",
"logprobs": None,
"finish_reason": None,
"seed": None,
"delta": {
"token_id": 6975,
"role": "assistant",
"content": " learning",
"tool_calls": None,
},
}
],
"model": "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
"usage": None,
},
{
"id": "id3",
"object": "chat.completion.chunk",
"created": 1111,
"choices": [
{
"index": 0,
"text": " is",
"logprobs": None,
"finish_reason": None,
"seed": None,
"delta": {
"token_id": 374,
"role": "assistant",
"content": " is",
"tool_calls": None,
},
}
],
"model": "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
"usage": None,
},
{
"id": "sid4",
"object": "chat.completion.chunk",
"created": 1111,
"choices": [
{
"index": 0,
"text": " response",
"logprobs": None,
"finish_reason": "length",
"seed": 2853637492034609700,
"delta": {
"token_id": 323,
"role": "assistant",
"content": " response",
"tool_calls": None,
},
}
],
"model": "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
"usage": {"prompt_tokens": 26, "completion_tokens": 20, "total_tokens": 46},
},
]
PROVIDER_MAPPING_RESPONSE = {
"fireworks-ai": {
"status": "live",
"providerId": "accounts/fireworks/models/llama-v3-8b-instruct",
"task": "conversational",
},
"together": {
"status": "live",
"providerId": "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
"task": "conversational",
},
"hf-inference": {
"status": "live",
"providerId": "meta-llama/Meta-Llama-3-8B-Instruct",
"task": "conversational",
},
}
@pytest.fixture
def mock_provider_mapping():
with patch(
"litellm.llms.huggingface.chat.transformation._fetch_inference_provider_mapping"
) as mock:
mock.return_value = PROVIDER_MAPPING_RESPONSE
yield mock
@pytest.fixture(autouse=True)
def clear_lru_cache():
from litellm.llms.huggingface.common_utils import _fetch_inference_provider_mapping
_fetch_inference_provider_mapping.cache_clear()
yield
_fetch_inference_provider_mapping.cache_clear()
@pytest.fixture
def mock_http_handler():
"""Fixture to mock the HTTP handler"""
with patch("litellm.llms.custom_httpx.http_handler.HTTPHandler.post") as mock:
print(f"Creating mock HTTP handler: {mock}") # noqa: T201
mock_response = MagicMock()
mock_response.raise_for_status.return_value = None
mock_response.status_code = 200
def mock_side_effect(*args, **kwargs):
if kwargs.get("stream", True):
mock_response.iter_lines.return_value = iter(
[
f"data: {json.dumps(chunk)}".encode("utf-8")
for chunk in MOCK_STREAMING_CHUNKS
]
+ [b"data: [DONE]"]
)
else:
mock_response.json.return_value = MOCK_COMPLETION_RESPONSE
return mock_response
mock.side_effect = mock_side_effect
yield mock
@pytest.fixture
def mock_http_async_handler():
"""Fixture to mock the async HTTP handler"""
with patch(
"litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.post",
new_callable=AsyncMock,
) as mock:
print(f"Creating mock async HTTP handler: {mock}") # noqa: T201
mock_response = MagicMock()
mock_response.raise_for_status.return_value = None
mock_response.status_code = 200
mock_response.headers = {"content-type": "application/json"}
mock_response.json.return_value = MOCK_COMPLETION_RESPONSE
mock_response.text = json.dumps(MOCK_COMPLETION_RESPONSE)
async def mock_side_effect(*args, **kwargs):
if kwargs.get("stream", True):
async def mock_aiter():
for chunk in MOCK_STREAMING_CHUNKS:
yield f"data: {json.dumps(chunk)}".encode("utf-8")
yield b"data: [DONE]"
mock_response.aiter_lines = mock_aiter
return mock_response
mock.side_effect = mock_side_effect
yield mock
class TestHuggingFace(BaseLLMChatTest):
@pytest.fixture(autouse=True)
def setup(self, mock_provider_mapping, mock_http_handler, mock_http_async_handler):
self.mock_provider_mapping = mock_provider_mapping
self.mock_http = mock_http_handler
self.mock_http_async = mock_http_async_handler
self.model = "huggingface/together/meta-llama/Meta-Llama-3-8B-Instruct"
litellm.set_verbose = False
def get_base_completion_call_args(self) -> dict:
"""Implementation of abstract method from BaseLLMChatTest"""
return {"model": self.model}
def test_completion_non_streaming(self):
messages = [{"role": "user", "content": "This is a dummy message"}]
response = litellm.completion(model=self.model, messages=messages, stream=False)
assert isinstance(response, ModelResponse)
assert (
response.choices[0].message.content
== "This is a test response from the mocked HuggingFace API."
)
assert response.usage is not None
assert response.model == self.model.split("/", 2)[2]
def test_completion_streaming(self):
messages = [{"role": "user", "content": "This is a dummy message"}]
response = litellm.completion(model=self.model, messages=messages, stream=True)
chunks = list(response)
assert len(chunks) > 0
assert self.mock_http.called
call_args = self.mock_http.call_args
assert call_args is not None
kwargs = call_args[1]
data = json.loads(kwargs["data"])
assert data["stream"] is True
assert data["messages"] == messages
assert isinstance(chunks, list)
assert isinstance(chunks[0], ModelResponseStream)
assert isinstance(chunks[0].id, str)
assert chunks[0].model == self.model.split("/", 1)[1]
@pytest.mark.asyncio
async def test_async_completion_streaming(self):
"""Test async streaming completion"""
messages = [{"role": "user", "content": "This is a dummy message"}]
response = await litellm.acompletion(
model=self.model, messages=messages, stream=True
)
chunks = []
async for chunk in response:
chunks.append(chunk)
assert self.mock_http_async.called
assert len(chunks) > 0
assert isinstance(chunks[0], ModelResponseStream)
assert isinstance(chunks[0].id, str)
assert chunks[0].model == self.model.split("/", 1)[1]
@pytest.mark.asyncio
async def test_async_completion_non_streaming(self):
"""Test async non-streaming completion"""
messages = [{"role": "user", "content": "This is a dummy message"}]
response = await litellm.acompletion(
model=self.model, messages=messages, stream=False
)
assert self.mock_http_async.called
assert isinstance(response, ModelResponse)
assert (
response.choices[0].message.content
== "This is a test response from the mocked HuggingFace API."
)
assert response.usage is not None
assert response.model == self.model.split("/", 2)[2]
def test_tool_call_no_arguments(self, tool_call_no_arguments):
mock_tool_response = {
**MOCK_COMPLETION_RESPONSE,
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": tool_call_no_arguments,
}
],
}
with patch.object(
self.mock_http,
"side_effect",
lambda *args, **kwargs: MagicMock(
status_code=200,
json=lambda: mock_tool_response,
raise_for_status=lambda: None,
),
):
messages = [{"role": "user", "content": "Get the FAQ"}]
tools = [
{
"type": "function",
"function": {
"name": "Get-FAQ",
"description": "Get FAQ information",
"parameters": {
"type": "object",
"properties": {},
"required": [],
},
},
}
]
response = litellm.completion(
model=self.model, messages=messages, tools=tools, tool_choice="auto"
)
assert response.choices[0].message.tool_calls is not None
assert len(response.choices[0].message.tool_calls) == 1
assert (
response.choices[0].message.tool_calls[0].function.name
== tool_call_no_arguments["tool_calls"][0]["function"]["name"]
)
assert (
response.choices[0].message.tool_calls[0].function.arguments
== tool_call_no_arguments["tool_calls"][0]["function"]["arguments"]
)
@pytest.mark.parametrize(
"model, provider, expected_url",
[
(
"meta-llama/Llama-3-8B-Instruct",
None,
"https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3-8B-Instruct/v1/chat/completions",
),
(
"together/meta-llama/Llama-3-8B-Instruct",
None,
"https://router.huggingface.co/together/v1/chat/completions",
),
(
"novita/meta-llama/Llama-3-8B-Instruct",
None,
"https://router.huggingface.co/novita/v3/openai/chat/completions",
),
(
"http://custom-endpoint.com/v1/chat/completions",
None,
"http://custom-endpoint.com/v1/chat/completions",
),
],
)
def test_get_complete_url(self, model, provider, expected_url):
"""Test that the complete URL is constructed correctly for different providers"""
from litellm.llms.huggingface.chat.transformation import HuggingFaceChatConfig
config = HuggingFaceChatConfig()
url = config.get_complete_url(
api_base=None,
model=model,
optional_params={},
stream=False,
api_key="test_api_key",
litellm_params={},
)
assert url == expected_url
@pytest.mark.parametrize(
"api_base, model, expected_url",
[
(
"https://abcd123.us-east-1.aws.endpoints.huggingface.cloud",
"huggingface/tgi",
"https://abcd123.us-east-1.aws.endpoints.huggingface.cloud/v1/chat/completions",
),
(
"https://abcd123.us-east-1.aws.endpoints.huggingface.cloud/",
"huggingface/tgi",
"https://abcd123.us-east-1.aws.endpoints.huggingface.cloud/v1/chat/completions",
),
(
"https://abcd123.us-east-1.aws.endpoints.huggingface.cloud/v1/chat/completions",
"huggingface/tgi",
"https://abcd123.us-east-1.aws.endpoints.huggingface.cloud/v1/chat/completions",
),
(
"https://example.com/custom/path",
"huggingface/tgi",
"https://example.com/custom/path/v1/chat/completions",
),
(
"https://example.com/custom/path/v1/chat/completions",
"huggingface/tgi",
"https://example.com/custom/path/v1/chat/completions",
),
(
"https://example.com/v1",
"huggingface/tgi",
"https://example.com/v1/chat/completions",
),
],
)
def test_get_complete_url_inference_endpoints(self, api_base, model, expected_url):
from litellm.llms.huggingface.chat.transformation import HuggingFaceChatConfig
config = HuggingFaceChatConfig()
url = config.get_complete_url(
api_base=api_base,
model=model,
optional_params={},
stream=False,
api_key="test_api_key",
litellm_params={},
)
assert url == expected_url
def test_completion_with_api_base(self):
messages = [{"role": "user", "content": "This is a test message"}]
api_base = "https://abcd123.us-east-1.aws.endpoints.huggingface.cloud"
response = litellm.completion(
model="huggingface/tgi", messages=messages, api_base=api_base, stream=False
)
assert isinstance(response, ModelResponse)
assert (
response.choices[0].message.content
== "This is a test response from the mocked HuggingFace API."
)
assert self.mock_http.called
call_args = self.mock_http.call_args
assert call_args is not None
called_url = call_args[1]["url"]
assert called_url == f"{api_base}/v1/chat/completions"
@pytest.mark.asyncio
async def test_async_completion_with_api_base(self):
messages = [{"role": "user", "content": "This is a test message"}]
api_base = "https://abcd123.us-east-1.aws.endpoints.huggingface.cloud"
response = await litellm.acompletion(
model="huggingface/tgi", messages=messages, api_base=api_base, stream=False
)
assert isinstance(response, ModelResponse)
assert (
response.choices[0].message.content
== "This is a test response from the mocked HuggingFace API."
)
assert self.mock_http_async.called
call_args = self.mock_http_async.call_args
assert call_args is not None
called_url = call_args[1]["url"]
assert called_url == f"{api_base}/v1/chat/completions"
def test_completion_streaming_with_api_base(self):
"""Test streaming completion with api_base parameter"""
messages = [{"role": "user", "content": "This is a test message"}]
api_base = "https://abcd123.us-east-1.aws.endpoints.huggingface.cloud"
response = litellm.completion(
model="huggingface/tgi", messages=messages, api_base=api_base, stream=True
)
chunks = list(response)
assert len(chunks) > 0
assert isinstance(chunks[0], ModelResponseStream)
# Check that the correct URL was called
assert self.mock_http.called
call_args = self.mock_http.call_args
assert call_args is not None
called_url = call_args[1]["url"]
assert called_url == f"{api_base}/v1/chat/completions"
def test_build_chat_completion_url_function(self):
"""Test the _build_chat_completion_url helper function"""
from litellm.llms.huggingface.chat.transformation import (
_build_chat_completion_url,
)
test_cases = [
("https://example.com", "https://example.com/v1/chat/completions"),
("https://example.com/", "https://example.com/v1/chat/completions"),
("https://example.com/v1", "https://example.com/v1/chat/completions"),
("https://example.com/v1/", "https://example.com/v1/chat/completions"),
(
"https://example.com/v1/chat/completions",
"https://example.com/v1/chat/completions",
),
(
"https://example.com/custom/path",
"https://example.com/custom/path/v1/chat/completions",
),
(
"https://example.com/custom/path/",
"https://example.com/custom/path/v1/chat/completions",
),
]
for input_url, expected_url in test_cases:
result = _build_chat_completion_url(input_url)
assert (
result == expected_url
), f"Failed for input: {input_url}, expected: {expected_url}, got: {result}"
def test_validate_environment(self):
"""Test that the environment is validated correctly"""
from litellm.llms.huggingface.chat.transformation import HuggingFaceChatConfig
config = HuggingFaceChatConfig()
headers = config.validate_environment(
headers={},
model="huggingface/fireworks-ai/meta-llama/Meta-Llama-3-8B-Instruct",
messages=[{"role": "user", "content": "Hello"}],
optional_params={},
api_key="test_api_key",
litellm_params={},
)
assert headers["Authorization"] == "Bearer test_api_key"
assert headers["content-type"] == "application/json"
@pytest.mark.parametrize(
"model, expected_model",
[
(
"together/meta-llama/Llama-3-8B-Instruct",
"meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
),
(
"meta-llama/Meta-Llama-3-8B-Instruct",
"meta-llama/Meta-Llama-3-8B-Instruct",
),
],
)
def test_transform_request(self, model, expected_model):
from litellm.llms.huggingface.chat.transformation import HuggingFaceChatConfig
config = HuggingFaceChatConfig()
messages = [{"role": "user", "content": "Hello"}]
transformed_request = config.transform_request(
model=model,
messages=messages,
optional_params={},
litellm_params={},
headers={},
)
assert transformed_request["model"] == expected_model
assert transformed_request["messages"] == messages
@pytest.mark.asyncio
async def test_completion_cost(self):
pass
|