Spaces:
Configuration error
Configuration error
File size: 12,815 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 |
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
from typing import Literal
import pytest
import litellm
import asyncio
import logging
from litellm._logging import verbose_logger
from prometheus_client import REGISTRY, CollectorRegistry
from litellm.integrations.lago import LagoLogger
from litellm.integrations.deepeval import DeepEvalLogger
from litellm.integrations.openmeter import OpenMeterLogger
from litellm.integrations.braintrust_logging import BraintrustLogger
from litellm.integrations.galileo import GalileoObserve
from litellm.integrations.langsmith import LangsmithLogger
from litellm.integrations.literal_ai import LiteralAILogger
from litellm.integrations.prometheus import PrometheusLogger
from litellm.integrations.datadog.datadog import DataDogLogger
from litellm.integrations.datadog.datadog_llm_obs import DataDogLLMObsLogger
from litellm.integrations.gcs_bucket.gcs_bucket import GCSBucketLogger
from litellm.integrations.gcs_pubsub.pub_sub import GcsPubSubLogger
from litellm.integrations.opik.opik import OpikLogger
from litellm.integrations.opentelemetry import OpenTelemetry
from litellm.integrations.mlflow import MlflowLogger
from litellm.integrations.argilla import ArgillaLogger
from litellm.integrations.deepeval.deepeval import DeepEvalLogger
from litellm.integrations.s3_v2 import S3Logger
from litellm.integrations.anthropic_cache_control_hook import AnthropicCacheControlHook
from litellm.integrations.vector_stores.bedrock_vector_store import BedrockVectorStore
from litellm.integrations.langfuse.langfuse_prompt_management import (
LangfusePromptManagement,
)
from litellm.integrations.azure_storage.azure_storage import AzureBlobStorageLogger
from litellm.integrations.agentops import AgentOps
from litellm.integrations.humanloop import HumanloopLogger
from litellm.proxy.hooks.dynamic_rate_limiter import _PROXY_DynamicRateLimitHandler
from litellm_enterprise.enterprise_callbacks.generic_api_callback import GenericAPILogger
from litellm_enterprise.enterprise_callbacks.send_emails.resend_email import ResendEmailLogger
from litellm_enterprise.enterprise_callbacks.send_emails.smtp_email import SMTPEmailLogger
from litellm_enterprise.enterprise_callbacks.pagerduty.pagerduty import PagerDutyAlerting
from unittest.mock import patch
# clear prometheus collectors / registry
collectors = list(REGISTRY._collector_to_names.keys())
for collector in collectors:
REGISTRY.unregister(collector)
######################################
callback_class_str_to_classType = {
"lago": LagoLogger,
"openmeter": OpenMeterLogger,
"braintrust": BraintrustLogger,
"galileo": GalileoObserve,
"langsmith": LangsmithLogger,
"literalai": LiteralAILogger,
"prometheus": PrometheusLogger,
"datadog": DataDogLogger,
"datadog_llm_observability": DataDogLLMObsLogger,
"gcs_bucket": GCSBucketLogger,
"opik": OpikLogger,
"argilla": ArgillaLogger,
"opentelemetry": OpenTelemetry,
"azure_storage": AzureBlobStorageLogger,
"humanloop": HumanloopLogger,
# OTEL compatible loggers
"logfire": OpenTelemetry,
"arize": OpenTelemetry,
"arize_phoenix": OpenTelemetry,
"langtrace": OpenTelemetry,
"mlflow": MlflowLogger,
"langfuse": LangfusePromptManagement,
"otel": OpenTelemetry,
"pagerduty": PagerDutyAlerting,
"gcs_pubsub": GcsPubSubLogger,
"anthropic_cache_control_hook": AnthropicCacheControlHook,
"agentops": AgentOps,
"bedrock_vector_store": BedrockVectorStore,
"generic_api": GenericAPILogger,
"resend_email": ResendEmailLogger,
"smtp_email": SMTPEmailLogger,
"deepeval": DeepEvalLogger,
"s3_v2": S3Logger,
}
expected_env_vars = {
"LAGO_API_KEY": "api_key",
"LAGO_API_BASE": "mock_base",
"LAGO_API_EVENT_CODE": "mock_event_code",
"OPENMETER_API_KEY": "openmeter_api_key",
"BRAINTRUST_API_KEY": "braintrust_api_key",
"GALILEO_API_KEY": "galileo_api_key",
"LITERAL_API_KEY": "literal_api_key",
"DD_API_KEY": "datadog_api_key",
"DD_SITE": "datadog_site",
"GOOGLE_APPLICATION_CREDENTIALS": "gcs_credentials",
"OPIK_API_KEY": "opik_api_key",
"LANGTRACE_API_KEY": "langtrace_api_key",
"LOGFIRE_TOKEN": "logfire_token",
"ARIZE_SPACE_KEY": "arize_space_key",
"ARIZE_API_KEY": "arize_api_key",
"PHOENIX_API_KEY": "phoenix_api_key",
"ARGILLA_API_KEY": "argilla_api_key",
"PAGERDUTY_API_KEY": "pagerduty_api_key",
"GCS_PUBSUB_TOPIC_ID": "gcs_pubsub_topic_id",
"GCS_PUBSUB_PROJECT_ID": "gcs_pubsub_project_id",
"CONFIDENT_API_KEY": "confident_api_key",
"LITELM_ENVIRONMENT": "development",
"AWS_BUCKET_NAME": "aws_bucket_name",
"AWS_SECRET_ACCESS_KEY": "aws_secret_access_key",
"AWS_ACCESS_KEY_ID": "aws_access_key_id",
"AWS_REGION": "aws_region",
}
def reset_all_callbacks():
litellm.callbacks = []
litellm.input_callback = []
litellm.success_callback = []
litellm.failure_callback = []
litellm._async_success_callback = []
litellm._async_failure_callback = []
initial_env_vars = {}
def init_env_vars():
for env_var, value in expected_env_vars.items():
if env_var not in os.environ:
os.environ[env_var] = value
else:
initial_env_vars[env_var] = os.environ[env_var]
def reset_env_vars():
for env_var, value in initial_env_vars.items():
os.environ[env_var] = value
all_callback_required_env_vars = []
async def use_callback_in_llm_call(
callback: str, used_in: Literal["callbacks", "success_callback"]
):
if callback == "dynamic_rate_limiter":
# internal CustomLogger class that expects internal_usage_cache passed to it, it always fails when tested in this way
return
elif callback == "argilla":
litellm.argilla_transformation_object = {}
elif callback == "openmeter":
# it's currently handled in jank way, TODO: fix openmete and then actually run it's test
return
elif callback == "prometheus":
# pytest teardown - clear existing prometheus collectors
collectors = list(REGISTRY._collector_to_names.keys())
for collector in collectors:
REGISTRY.unregister(collector)
# Mock the httpx call for Argilla dataset retrieval
if callback == "argilla":
import httpx
mock_response = httpx.Response(
status_code=200, json={"items": [{"id": "mocked_dataset_id"}]}
)
patch.object(
litellm.module_level_client, "get", return_value=mock_response
).start()
# Mock the httpx call for Argilla dataset retrieval
if callback == "argilla":
import httpx
mock_response = httpx.Response(
status_code=200, json={"items": [{"id": "mocked_dataset_id"}]}
)
patch.object(
litellm.module_level_client, "get", return_value=mock_response
).start()
if used_in == "callbacks":
litellm.callbacks = [callback]
elif used_in == "success_callback":
litellm.success_callback = [callback]
for _ in range(5):
await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "hi"}],
temperature=0.1,
mock_response="hello",
)
await asyncio.sleep(0.5)
expected_class = callback_class_str_to_classType[callback]
if used_in == "callbacks":
assert isinstance(litellm._async_success_callback[0], expected_class)
assert isinstance(litellm._async_failure_callback[0], expected_class)
assert isinstance(litellm.success_callback[0], expected_class)
assert isinstance(litellm.failure_callback[0], expected_class)
assert (
len(litellm._async_success_callback) == 1
), f"Got={litellm._async_success_callback}"
assert len(litellm._async_failure_callback) == 1
assert len(litellm.success_callback) == 1
assert len(litellm.failure_callback) == 1
assert len(litellm.callbacks) == 1
elif used_in == "success_callback":
print(f"litellm.success_callback: {litellm.success_callback}")
print(f"litellm._async_success_callback: {litellm._async_success_callback}")
assert isinstance(litellm.success_callback[0], expected_class)
assert len(litellm.success_callback) == 1 # ["lago", LagoLogger]
assert isinstance(litellm._async_success_callback[0], expected_class)
assert len(litellm._async_success_callback) == 1
# TODO also assert that it's not set for failure_callback
# As of Oct 21 2024, it's currently set
# 1st hoping to add test coverage for just setting in success_callback/_async_success_callback
if callback == "argilla":
patch.stopall()
if callback == "argilla":
patch.stopall()
@pytest.mark.asyncio
async def test_init_custom_logger_compatible_class_as_callback():
init_env_vars()
# used like litellm.callbacks = ["prometheus"]
for callback in litellm._known_custom_logger_compatible_callbacks:
print(f"Testing callback: {callback}")
reset_all_callbacks()
await use_callback_in_llm_call(callback, used_in="callbacks")
# used like this litellm.success_callback = ["prometheus"]
for callback in litellm._known_custom_logger_compatible_callbacks:
print(f"Testing callback: {callback}")
reset_all_callbacks()
await use_callback_in_llm_call(callback, used_in="success_callback")
reset_env_vars()
def test_dynamic_logging_global_callback():
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.integrations.custom_logger import CustomLogger
from litellm.types.utils import ModelResponse, Choices, Message, Usage
cl = CustomLogger()
litellm_logging = LiteLLMLoggingObj(
model="claude-3-opus-20240229",
messages=[{"role": "user", "content": "hi"}],
stream=False,
call_type="completion",
start_time=datetime.now(),
litellm_call_id="123",
function_id="456",
kwargs={
"langfuse_public_key": "my-mock-public-key",
"langfuse_secret_key": "my-mock-secret-key",
},
dynamic_success_callbacks=["langfuse"],
)
with patch.object(cl, "log_success_event") as mock_log_success_event:
cl.log_success_event = mock_log_success_event
litellm.success_callback = [cl]
try:
litellm_logging.success_handler(
result=ModelResponse(
id="chatcmpl-5418737b-ab14-420b-b9c5-b278b6681b70",
created=1732306261,
model="claude-3-opus-20240229",
object="chat.completion",
system_fingerprint=None,
choices=[
Choices(
finish_reason="stop",
index=0,
message=Message(
content="hello",
role="assistant",
tool_calls=None,
function_call=None,
),
)
],
usage=Usage(
completion_tokens=20,
prompt_tokens=10,
total_tokens=30,
completion_tokens_details=None,
prompt_tokens_details=None,
),
),
start_time=datetime.now(),
end_time=datetime.now(),
cache_hit=False,
)
except Exception as e:
print(f"Error: {e}")
mock_log_success_event.assert_called_once()
def test_get_combined_callback_list():
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
_logging = LiteLLMLoggingObj(
model="claude-3-opus-20240229",
messages=[{"role": "user", "content": "hi"}],
stream=False,
call_type="completion",
start_time=datetime.now(),
litellm_call_id="123",
function_id="456",
)
assert "langfuse" in _logging.get_combined_callback_list(
dynamic_success_callbacks=["langfuse"], global_callbacks=["lago"]
)
assert "lago" in _logging.get_combined_callback_list(
dynamic_success_callbacks=["langfuse"], global_callbacks=["lago"]
)
|