Spaces:
Configuration error
Configuration error
File size: 10,803 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 |
# test that the proxy actually does exception mapping to the OpenAI format
import json
import os
import sys
from unittest import mock
from dotenv import load_dotenv
load_dotenv()
import asyncio
import io
import os
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
import openai
import pytest
from fastapi import Response
from fastapi.testclient import TestClient
import litellm
from litellm.proxy.proxy_server import ( # Replace with the actual module where your FastAPI router is defined
initialize,
router,
save_worker_config,
)
invalid_authentication_error_response = Response(
status_code=401,
content=json.dumps({"error": "Invalid Authentication"}),
)
context_length_exceeded_error_response_dict = {
"error": {
"message": "AzureException - Error code: 400 - {'error': {'message': \"This model's maximum context length is 4096 tokens. However, your messages resulted in 10007 tokens. Please reduce the length of the messages.\", 'type': 'invalid_request_error', 'param': 'messages', 'code': 'context_length_exceeded'}}",
"type": None,
"param": None,
"code": 400,
},
}
context_length_exceeded_error_response = Response(
status_code=400,
content=json.dumps(context_length_exceeded_error_response_dict),
)
@pytest.fixture
def client():
filepath = os.path.dirname(os.path.abspath(__file__))
config_fp = f"{filepath}/test_configs/test_bad_config.yaml"
asyncio.run(initialize(config=config_fp))
from litellm.proxy.proxy_server import app
return TestClient(app)
# raise openai.AuthenticationError
def test_chat_completion_exception(client):
try:
# Your test data
test_data = {
"model": "gpt-3.5-turbo",
"messages": [
{"role": "user", "content": "hi"},
],
"max_tokens": 10,
}
response = client.post("/chat/completions", json=test_data)
json_response = response.json()
print("keys in json response", json_response.keys())
assert json_response.keys() == {"error"}
print("ERROR=", json_response["error"])
assert isinstance(json_response["error"]["message"], str)
assert (
"litellm.AuthenticationError: AuthenticationError"
in json_response["error"]["message"]
)
code_in_error = json_response["error"]["code"]
# OpenAI SDK required code to be STR, https://github.com/BerriAI/litellm/issues/4970
# If we look on official python OpenAI lib, the code should be a string:
# https://github.com/openai/openai-python/blob/195c05a64d39c87b2dfdf1eca2d339597f1fce03/src/openai/types/shared/error_object.py#L11
# Related LiteLLM issue: https://github.com/BerriAI/litellm/discussions/4834
assert type(code_in_error) == str
# make an openai client to call _make_status_error_from_response
openai_client = openai.OpenAI(api_key="anything")
openai_exception = openai_client._make_status_error_from_response(
response=response
)
assert isinstance(openai_exception, openai.AuthenticationError)
except Exception as e:
pytest.fail(f"LiteLLM Proxy test failed. Exception {str(e)}")
# raise openai.AuthenticationError
@mock.patch(
"litellm.proxy.proxy_server.llm_router.acompletion",
return_value=invalid_authentication_error_response,
)
def test_chat_completion_exception_azure(mock_acompletion, client):
try:
# Your test data
test_data = {
"model": "azure-gpt-3.5-turbo",
"messages": [
{"role": "user", "content": "hi"},
],
"max_tokens": 10,
}
response = client.post("/chat/completions", json=test_data)
mock_acompletion.assert_called_once_with(
**test_data,
litellm_call_id=mock.ANY,
litellm_logging_obj=mock.ANY,
request_timeout=mock.ANY,
metadata=mock.ANY,
proxy_server_request=mock.ANY,
)
json_response = response.json()
print("keys in json response", json_response.keys())
assert json_response.keys() == {"error"}
# make an openai client to call _make_status_error_from_response
openai_client = openai.OpenAI(api_key="anything")
openai_exception = openai_client._make_status_error_from_response(
response=response
)
print(openai_exception)
assert isinstance(openai_exception, openai.AuthenticationError)
except Exception as e:
pytest.fail(f"LiteLLM Proxy test failed. Exception {str(e)}")
# raise openai.AuthenticationError
@mock.patch(
"litellm.proxy.proxy_server.llm_router.aembedding",
return_value=invalid_authentication_error_response,
)
def test_embedding_auth_exception_azure(mock_aembedding, client):
try:
# Your test data
test_data = {"model": "azure-embedding", "input": ["hi"]}
response = client.post("/embeddings", json=test_data)
mock_aembedding.assert_called_once_with(
**test_data,
metadata=mock.ANY,
proxy_server_request=mock.ANY,
)
print("Response from proxy=", response)
json_response = response.json()
print("keys in json response", json_response.keys())
assert json_response.keys() == {"error"}
# make an openai client to call _make_status_error_from_response
openai_client = openai.OpenAI(api_key="anything")
openai_exception = openai_client._make_status_error_from_response(
response=response
)
print("Exception raised=", openai_exception)
assert isinstance(openai_exception, openai.AuthenticationError)
except Exception as e:
pytest.fail(f"LiteLLM Proxy test failed. Exception {str(e)}")
# raise openai.BadRequestError
# chat/completions openai
def test_exception_openai_bad_model(client):
try:
# Your test data
test_data = {
"model": "azure/GPT-12",
"messages": [
{"role": "user", "content": "hi"},
],
"max_tokens": 10,
}
response = client.post("/chat/completions", json=test_data)
json_response = response.json()
print("keys in json response", json_response.keys())
assert json_response.keys() == {"error"}
# make an openai client to call _make_status_error_from_response
openai_client = openai.OpenAI(api_key="anything")
openai_exception = openai_client._make_status_error_from_response(
response=response
)
print("Type of exception=", type(openai_exception))
assert isinstance(openai_exception, openai.BadRequestError)
except Exception as e:
pytest.fail(f"LiteLLM Proxy test failed. Exception {str(e)}")
# chat/completions any model
def test_chat_completion_exception_any_model(client):
try:
# Your test data
test_data = {
"model": "Lite-GPT-12",
"messages": [
{"role": "user", "content": "hi"},
],
"max_tokens": 10,
}
response = client.post("/chat/completions", json=test_data)
json_response = response.json()
assert json_response.keys() == {"error"}
# make an openai client to call _make_status_error_from_response
openai_client = openai.OpenAI(api_key="anything")
openai_exception = openai_client._make_status_error_from_response(
response=response
)
assert isinstance(openai_exception, openai.BadRequestError)
_error_message = openai_exception.message
assert (
"/chat/completions: Invalid model name passed in model=Lite-GPT-12"
in str(_error_message)
)
except Exception as e:
pytest.fail(f"LiteLLM Proxy test failed. Exception {str(e)}")
# embeddings any model
def test_embedding_exception_any_model(client):
try:
# Your test data
test_data = {"model": "Lite-GPT-12", "input": ["hi"]}
response = client.post("/embeddings", json=test_data)
print("Response from proxy=", response)
print(response.json())
json_response = response.json()
print("keys in json response", json_response.keys())
assert json_response.keys() == {"error"}
# make an openai client to call _make_status_error_from_response
openai_client = openai.OpenAI(api_key="anything")
openai_exception = openai_client._make_status_error_from_response(
response=response
)
print("Exception raised=", openai_exception)
assert isinstance(openai_exception, openai.BadRequestError)
_error_message = openai_exception.message
assert "/embeddings: Invalid model name passed in model=Lite-GPT-12" in str(
_error_message
)
except Exception as e:
pytest.fail(f"LiteLLM Proxy test failed. Exception {str(e)}")
# raise openai.BadRequestError
@mock.patch(
"litellm.proxy.proxy_server.llm_router.acompletion",
return_value=context_length_exceeded_error_response,
)
def test_chat_completion_exception_azure_context_window(mock_acompletion, client):
try:
# Your test data
test_data = {
"model": "working-azure-gpt-3.5-turbo",
"messages": [
{"role": "user", "content": "hi" * 10000},
],
"max_tokens": 10,
}
response = None
response = client.post("/chat/completions", json=test_data)
print("got response from server", response)
mock_acompletion.assert_called_once_with(
**test_data,
litellm_call_id=mock.ANY,
litellm_logging_obj=mock.ANY,
request_timeout=mock.ANY,
metadata=mock.ANY,
proxy_server_request=mock.ANY,
)
json_response = response.json()
print("keys in json response", json_response.keys())
assert json_response.keys() == {"error"}
assert json_response == context_length_exceeded_error_response_dict
# make an openai client to call _make_status_error_from_response
openai_client = openai.OpenAI(api_key="anything")
openai_exception = openai_client._make_status_error_from_response(
response=response
)
print("exception from proxy", openai_exception)
assert isinstance(openai_exception, openai.BadRequestError)
print("passed exception is of type BadRequestError")
except Exception as e:
pytest.fail(f"LiteLLM Proxy test failed. Exception {str(e)}")
|