Spaces:
Configuration error
Configuration error
File size: 12,141 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 |
"""
Testing for _assemble_complete_response_from_streaming_chunks
- Test 1 - ModelResponse with 1 list of streaming chunks. Assert chunks are added to the streaming_chunks, after final chunk sent assert complete_streaming_response is not None
- Test 2 - TextCompletionResponse with 1 list of streaming chunks. Assert chunks are added to the streaming_chunks, after final chunk sent assert complete_streaming_response is not None
- Test 3 - Have multiple lists of streaming chunks, Assert that chunks are added to the correct list and that complete_streaming_response is None. After final chunk sent assert complete_streaming_response is not None
- Test 4 - build a complete response when 1 chunk is poorly formatted
"""
import json
import os
import sys
from datetime import datetime
from unittest.mock import AsyncMock
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
import httpx
import pytest
from respx import MockRouter
import litellm
from litellm import (
Choices,
Message,
ModelResponse,
ModelResponseStream,
TextCompletionResponse,
TextChoices,
)
from litellm.litellm_core_utils.logging_utils import (
_assemble_complete_response_from_streaming_chunks,
)
@pytest.mark.parametrize("is_async", [True, False])
def test_assemble_complete_response_from_streaming_chunks_1(is_async):
"""
Test 1 - ModelResponse with 1 list of streaming chunks. Assert chunks are added to the streaming_chunks, after final chunk sent assert complete_streaming_response is not None
"""
request_kwargs = {
"model": "test_model",
"messages": [{"role": "user", "content": "Hello, world!"}],
}
list_streaming_chunks = []
chunk = {
"id": "chatcmpl-9mWtyDnikZZoB75DyfUzWUxiiE2Pi",
"choices": [
litellm.utils.StreamingChoices(
delta=litellm.utils.Delta(
content="hello in response",
function_call=None,
role=None,
tool_calls=None,
),
index=0,
logprobs=None,
)
],
"created": 1721353246,
"model": "gpt-3.5-turbo",
"object": "chat.completion.chunk",
"system_fingerprint": None,
"usage": None,
}
chunk = ModelResponseStream(**chunk)
complete_streaming_response = _assemble_complete_response_from_streaming_chunks(
result=chunk,
start_time=datetime.now(),
end_time=datetime.now(),
request_kwargs=request_kwargs,
streaming_chunks=list_streaming_chunks,
is_async=is_async,
)
# this is the 1st chunk - complete_streaming_response should be None
print("list_streaming_chunks", list_streaming_chunks)
print("complete_streaming_response", complete_streaming_response)
assert complete_streaming_response is None
assert len(list_streaming_chunks) == 1
assert list_streaming_chunks[0] == chunk
# Add final chunk
chunk = {
"id": "chatcmpl-9mWtyDnikZZoB75DyfUzWUxiiE2Pi",
"choices": [
litellm.utils.StreamingChoices(
finish_reason="stop",
delta=litellm.utils.Delta(
content="end of response",
function_call=None,
role=None,
tool_calls=None,
),
index=0,
logprobs=None,
)
],
"created": 1721353246,
"model": "gpt-3.5-turbo",
"object": "chat.completion.chunk",
"system_fingerprint": None,
"usage": None,
}
chunk = ModelResponseStream(**chunk)
complete_streaming_response = _assemble_complete_response_from_streaming_chunks(
result=chunk,
start_time=datetime.now(),
end_time=datetime.now(),
request_kwargs=request_kwargs,
streaming_chunks=list_streaming_chunks,
is_async=is_async,
)
print("list_streaming_chunks", list_streaming_chunks)
print("complete_streaming_response", complete_streaming_response)
# this is the 2nd chunk - complete_streaming_response should not be None
assert complete_streaming_response is not None
assert len(list_streaming_chunks) == 2
assert isinstance(complete_streaming_response, ModelResponse)
assert isinstance(complete_streaming_response.choices[0], Choices)
pass
@pytest.mark.parametrize("is_async", [True, False])
def test_assemble_complete_response_from_streaming_chunks_2(is_async):
"""
Test 2 - TextCompletionResponse with 1 list of streaming chunks. Assert chunks are added to the streaming_chunks, after final chunk sent assert complete_streaming_response is not None
"""
from litellm.utils import TextCompletionStreamWrapper
_text_completion_stream_wrapper = TextCompletionStreamWrapper(
completion_stream=None, model="test_model"
)
request_kwargs = {
"model": "test_model",
"messages": [{"role": "user", "content": "Hello, world!"}],
}
list_streaming_chunks = []
chunk = {
"id": "chatcmpl-9mWtyDnikZZoB75DyfUzWUxiiE2Pi",
"choices": [
litellm.utils.StreamingChoices(
delta=litellm.utils.Delta(
content="hello in response",
function_call=None,
role=None,
tool_calls=None,
),
index=0,
logprobs=None,
)
],
"created": 1721353246,
"model": "gpt-3.5-turbo",
"object": "chat.completion.chunk",
"system_fingerprint": None,
"usage": None,
}
chunk = ModelResponseStream(**chunk)
chunk = _text_completion_stream_wrapper.convert_to_text_completion_object(chunk)
complete_streaming_response = _assemble_complete_response_from_streaming_chunks(
result=chunk,
start_time=datetime.now(),
end_time=datetime.now(),
request_kwargs=request_kwargs,
streaming_chunks=list_streaming_chunks,
is_async=is_async,
)
# this is the 1st chunk - complete_streaming_response should be None
print("list_streaming_chunks", list_streaming_chunks)
print("complete_streaming_response", complete_streaming_response)
assert complete_streaming_response is None
assert len(list_streaming_chunks) == 1
assert list_streaming_chunks[0] == chunk
# Add final chunk
chunk = {
"id": "chatcmpl-9mWtyDnikZZoB75DyfUzWUxiiE2Pi",
"choices": [
litellm.utils.StreamingChoices(
finish_reason="stop",
delta=litellm.utils.Delta(
content="end of response",
function_call=None,
role=None,
tool_calls=None,
),
index=0,
logprobs=None,
)
],
"created": 1721353246,
"model": "gpt-3.5-turbo",
"object": "chat.completion.chunk",
"system_fingerprint": None,
"usage": None,
}
chunk = ModelResponseStream(**chunk)
chunk = _text_completion_stream_wrapper.convert_to_text_completion_object(chunk)
complete_streaming_response = _assemble_complete_response_from_streaming_chunks(
result=chunk,
start_time=datetime.now(),
end_time=datetime.now(),
request_kwargs=request_kwargs,
streaming_chunks=list_streaming_chunks,
is_async=is_async,
)
print("list_streaming_chunks", list_streaming_chunks)
print("complete_streaming_response", complete_streaming_response)
# this is the 2nd chunk - complete_streaming_response should not be None
assert complete_streaming_response is not None
assert len(list_streaming_chunks) == 2
assert isinstance(complete_streaming_response, TextCompletionResponse)
assert isinstance(complete_streaming_response.choices[0], TextChoices)
pass
@pytest.mark.parametrize("is_async", [True, False])
def test_assemble_complete_response_from_streaming_chunks_3(is_async):
request_kwargs = {
"model": "test_model",
"messages": [{"role": "user", "content": "Hello, world!"}],
}
list_streaming_chunks_1 = []
list_streaming_chunks_2 = []
chunk = {
"id": "chatcmpl-9mWtyDnikZZoB75DyfUzWUxiiE2Pi",
"choices": [
litellm.utils.StreamingChoices(
delta=litellm.utils.Delta(
content="hello in response",
function_call=None,
role=None,
tool_calls=None,
),
index=0,
logprobs=None,
)
],
"created": 1721353246,
"model": "gpt-3.5-turbo",
"object": "chat.completion.chunk",
"system_fingerprint": None,
"usage": None,
}
chunk = ModelResponseStream(**chunk)
complete_streaming_response = _assemble_complete_response_from_streaming_chunks(
result=chunk,
start_time=datetime.now(),
end_time=datetime.now(),
request_kwargs=request_kwargs,
streaming_chunks=list_streaming_chunks_1,
is_async=is_async,
)
# this is the 1st chunk - complete_streaming_response should be None
print("list_streaming_chunks_1", list_streaming_chunks_1)
print("complete_streaming_response", complete_streaming_response)
assert complete_streaming_response is None
assert len(list_streaming_chunks_1) == 1
assert list_streaming_chunks_1[0] == chunk
assert len(list_streaming_chunks_2) == 0
# now add a chunk to the 2nd list
complete_streaming_response = _assemble_complete_response_from_streaming_chunks(
result=chunk,
start_time=datetime.now(),
end_time=datetime.now(),
request_kwargs=request_kwargs,
streaming_chunks=list_streaming_chunks_2,
is_async=is_async,
)
print("list_streaming_chunks_2", list_streaming_chunks_2)
print("complete_streaming_response", complete_streaming_response)
assert complete_streaming_response is None
assert len(list_streaming_chunks_2) == 1
assert list_streaming_chunks_2[0] == chunk
assert len(list_streaming_chunks_1) == 1
# now add a chunk to the 1st list
@pytest.mark.parametrize("is_async", [True, False])
def test_assemble_complete_response_from_streaming_chunks_4(is_async):
"""
Test 4 - build a complete response when 1 chunk is poorly formatted
- Assert complete_streaming_response is None
- Assert list_streaming_chunks is not empty
"""
request_kwargs = {
"model": "test_model",
"messages": [{"role": "user", "content": "Hello, world!"}],
}
list_streaming_chunks = []
chunk = {
"id": "chatcmpl-9mWtyDnikZZoB75DyfUzWUxiiE2Pi",
"choices": [
litellm.utils.StreamingChoices(
finish_reason="stop",
delta=litellm.utils.Delta(
content="end of response",
function_call=None,
role=None,
tool_calls=None,
),
index=0,
logprobs=None,
)
],
"created": 1721353246,
"model": "gpt-3.5-turbo",
"object": "chat.completion.chunk",
"system_fingerprint": None,
"usage": None,
}
chunk = ModelResponseStream(**chunk)
# remove attribute id from chunk
del chunk.object
complete_streaming_response = _assemble_complete_response_from_streaming_chunks(
result=chunk,
start_time=datetime.now(),
end_time=datetime.now(),
request_kwargs=request_kwargs,
streaming_chunks=list_streaming_chunks,
is_async=is_async,
)
print("complete_streaming_response", complete_streaming_response)
assert complete_streaming_response is None
print("list_streaming_chunks", list_streaming_chunks)
assert len(list_streaming_chunks) == 1
|