Spaces:
Configuration error
Configuration error
File size: 6,605 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 |
import io
import os
import sys
sys.path.insert(0, os.path.abspath("../.."))
import asyncio
import json
import logging
import tempfile
import uuid
import json
from datetime import datetime, timedelta, timezone
from datetime import datetime
import pytest
import litellm
from litellm import completion
from litellm._logging import verbose_logger
from litellm.integrations.gcs_bucket.gcs_bucket import (
GCSBucketLogger,
StandardLoggingPayload,
)
from litellm.types.utils import StandardCallbackDynamicParams
# This is the response payload that GCS would return.
mock_response_data = {
"id": "chatcmpl-9870a859d6df402795f75dc5fca5b2e0",
"trace_id": None,
"call_type": "acompletion",
"cache_hit": None,
"stream": True,
"status": "success",
"custom_llm_provider": "openai",
"saved_cache_cost": 0.0,
"startTime": 1739235379.683053,
"endTime": 1739235379.84533,
"completionStartTime": 1739235379.84533,
"response_time": 0.1622769832611084,
"model": "my-fake-model",
"metadata": {
"user_api_key_hash": "88dc28d0f030c55ed4ab77ed8faf098196cb1c05df778539800c9f1243fe6b4b",
"user_api_key_alias": None,
"user_api_key_team_id": None,
"user_api_key_org_id": None,
"user_api_key_user_id": "default_user_id",
"user_api_key_team_alias": None,
"spend_logs_metadata": None,
"requester_ip_address": "127.0.0.1",
"requester_metadata": {},
"user_api_key_end_user_id": None,
"prompt_management_metadata": None,
},
"cache_key": None,
"response_cost": 3.7500000000000003e-05,
"total_tokens": 21,
"prompt_tokens": 9,
"completion_tokens": 12,
"request_tags": [],
"end_user": "",
"api_base": "https://exampleopenaiendpoint-production.up.railway.app",
"model_group": "fake-openai-endpoint",
"model_id": "b68d56d76b0c24ac9462ab69541e90886342508212210116e300441155f37865",
"requester_ip_address": "127.0.0.1",
"messages": [
{"role": "user", "content": [{"type": "text", "text": "very gm to u"}]}
],
"response": {
"id": "chatcmpl-9870a859d6df402795f75dc5fca5b2e0",
"created": 1677652288,
"model": "gpt-3.5-turbo-0301",
"object": "chat.completion",
"system_fingerprint": "fp_44709d6fcb",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "\n\nHello there, how may I assist you today?",
"role": "assistant",
"tool_calls": None,
"function_call": None,
"refusal": None,
},
}
],
"usage": {
"completion_tokens": 12,
"prompt_tokens": 9,
"total_tokens": 21,
"completion_tokens_details": None,
"prompt_tokens_details": None,
},
"service_tier": None,
},
"model_parameters": {"stream": False, "max_retries": 0, "extra_body": {}},
"hidden_params": {
"model_id": "b68d56d76b0c24ac9462ab69541e90886342508212210116e300441155f37865",
"cache_key": None,
"api_base": "https://exampleopenaiendpoint-production.up.railway.app/",
"response_cost": 3.7500000000000003e-05,
"additional_headers": {},
"litellm_overhead_time_ms": 2.126,
},
"model_map_information": {
"model_map_key": "gpt-3.5-turbo-0301",
"model_map_value": {},
},
"error_str": None,
"error_information": {"error_code": "", "error_class": "", "llm_provider": ""},
"response_cost_failure_debug_info": None,
"guardrail_information": None,
}
@pytest.mark.asyncio
async def test_get_payload_current_day():
"""
Verify that the payload is returned when it is found on the current day.
"""
gcs_logger = GCSBucketLogger()
# Use January 1, 2024 as the current day
start_time = datetime(2024, 1, 1, tzinfo=timezone.utc)
request_id = mock_response_data["id"]
async def fake_download(object_name: str, **kwargs) -> bytes | None:
if "2024-01-01" in object_name:
return json.dumps(mock_response_data).encode("utf-8")
return None
gcs_logger.download_gcs_object = fake_download
payload = await gcs_logger.get_request_response_payload(
request_id, start_time, None
)
assert payload is not None
assert payload["id"] == request_id
@pytest.mark.asyncio
async def test_get_payload_next_day():
"""
Verify that if the payload is not found on the current day,
but is available on the next day, it is returned.
"""
gcs_logger = GCSBucketLogger()
start_time = datetime(2024, 1, 1, tzinfo=timezone.utc)
request_id = mock_response_data["id"]
async def fake_download(object_name: str, **kwargs) -> bytes | None:
if "2024-01-02" in object_name:
return json.dumps(mock_response_data).encode("utf-8")
return None
gcs_logger.download_gcs_object = fake_download
payload = await gcs_logger.get_request_response_payload(
request_id, start_time, None
)
assert payload is not None
assert payload["id"] == request_id
@pytest.mark.asyncio
async def test_get_payload_previous_day():
"""
Verify that if the payload is not found on the current or next day,
but is available on the previous day, it is returned.
"""
gcs_logger = GCSBucketLogger()
start_time = datetime(2024, 1, 1, tzinfo=timezone.utc)
request_id = mock_response_data["id"]
async def fake_download(object_name: str, **kwargs) -> bytes | None:
if "2023-12-31" in object_name:
return json.dumps(mock_response_data).encode("utf-8")
return None
gcs_logger.download_gcs_object = fake_download
payload = await gcs_logger.get_request_response_payload(
request_id, start_time, None
)
assert payload is not None
assert payload["id"] == request_id
@pytest.mark.asyncio
async def test_get_payload_not_found():
"""
Verify that if none of the three days contain the payload, None is returned.
"""
gcs_logger = GCSBucketLogger()
start_time = datetime(2024, 1, 1, tzinfo=timezone.utc)
request_id = mock_response_data["id"]
async def fake_download(object_name: str, **kwargs) -> bytes | None:
return None
gcs_logger.download_gcs_object = fake_download
payload = await gcs_logger.get_request_response_payload(
request_id, start_time, None
)
assert payload is None
|