litellm-mirror/litellm/integrations/custom_batch_logger.py
Krish Dholakia 11f9df923a
LiteLLM Minor Fixes & Improvements (10/10/2024) (#6158)
* refactor(vertex_ai_partner_models/anthropic): refactor anthropic to use partner model logic

* fix(vertex_ai/): support passing custom api base to partner models

Fixes https://github.com/BerriAI/litellm/issues/4317

* fix(proxy_server.py): Fix prometheus premium user check logic

* docs(prometheus.md): update quick start docs

* fix(custom_llm.py): support passing dynamic api key + api base

* fix(realtime_api/main.py): Add request/response logging for realtime api endpoints

Closes https://github.com/BerriAI/litellm/issues/6081

* feat(openai/realtime): add openai realtime api logging

Closes https://github.com/BerriAI/litellm/issues/6081

* fix(realtime_streaming.py): fix linting errors

* fix(realtime_streaming.py): fix linting errors

* fix: fix linting errors

* fix pattern match router

* Add literalai in the sidebar observability category (#6163)

* fix: add literalai in the sidebar

* fix: typo

* update (#6160)

* Feat: Add Langtrace integration (#5341)

* Feat: Add Langtrace integration

* add langtrace service name

* fix timestamps for traces

* add tests

* Discard Callback + use existing otel logger

* cleanup

* remove print statments

* remove callback

* add docs

* docs

* add logging docs

* format logging

* remove emoji and add litellm proxy example

* format logging

* format `logging.md`

* add langtrace docs to logging.md

* sync conflict

* docs fix

* (perf) move s3 logging to Batch logging + async [94% faster perf under 100 RPS on 1 litellm instance] (#6165)

* fix move s3 to use customLogger

* add basic s3 logging test

* add s3 to custom logger compatible

* use batch logger for s3

* s3 set flush interval and batch size

* fix s3 logging

* add notes on s3 logging

* fix s3 logging

* add basic s3 logging test

* fix s3 type errors

* add test for sync logging on s3

* fix: fix to debug log

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Willy Douhard <willy.douhard@gmail.com>
Co-authored-by: yujonglee <yujonglee.dev@gmail.com>
Co-authored-by: Ali Waleed <ali@scale3labs.com>
2024-10-11 23:04:36 -07:00

62 lines
1.9 KiB
Python

"""
Custom Logger that handles batching logic
Use this if you want your logs to be stored in memory and flushed periodically
"""
import asyncio
import time
from typing import List, Literal, Optional
from litellm._logging import verbose_logger
from litellm.integrations.custom_logger import CustomLogger
DEFAULT_BATCH_SIZE = 512
DEFAULT_FLUSH_INTERVAL_SECONDS = 5
class CustomBatchLogger(CustomLogger):
def __init__(
self,
flush_lock: Optional[asyncio.Lock] = None,
batch_size: Optional[int] = DEFAULT_BATCH_SIZE,
flush_interval: Optional[int] = DEFAULT_FLUSH_INTERVAL_SECONDS,
**kwargs,
) -> None:
"""
Args:
flush_lock (Optional[asyncio.Lock], optional): Lock to use when flushing the queue. Defaults to None. Only used for custom loggers that do batching
"""
self.log_queue: List = []
self.flush_interval = flush_interval or DEFAULT_FLUSH_INTERVAL_SECONDS
self.batch_size: int = batch_size or DEFAULT_BATCH_SIZE
self.last_flush_time = time.time()
self.flush_lock = flush_lock
super().__init__(**kwargs)
pass
async def periodic_flush(self):
while True:
await asyncio.sleep(self.flush_interval)
verbose_logger.debug(
f"CustomLogger periodic flush after {self.flush_interval} seconds"
)
await self.flush_queue()
async def flush_queue(self):
if self.flush_lock is None:
return
async with self.flush_lock:
if self.log_queue:
verbose_logger.debug(
"CustomLogger: Flushing batch of %s events", len(self.log_queue)
)
await self.async_send_batch()
self.log_queue.clear()
self.last_flush_time = time.time()
async def async_send_batch(self, *args, **kwargs):
pass