phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

redis otel tracing + async support for latency routing (#6452)

Browse source 
* docs(exception_mapping.md): add missing exception types

Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183

* fix(main.py): register custom model pricing with specific key

Ensure custom model pricing is registered to the specific model+provider key combination

* test: make testing more robust for custom pricing

* fix(redis_cache.py): instrument otel logging for sync redis calls

ensures complete coverage for all redis cache calls

* refactor: pass parent_otel_span for redis caching calls in router

allows for more observability into what calls are causing latency issues

* test: update tests with new params

* refactor: ensure e2e otel tracing for router

* refactor(router.py): add more otel tracing acrosss router

catch all latency issues for router requests

* fix: fix linting error

* fix(router.py): fix linting error

* fix: fix test

* test: fix tests

* fix(dual_cache.py): pass ttl to redis cache

* fix: fix param
This commit is contained in:
Krish Dholakia 2024-10-28 21:52:12 -07:00 • committed by GitHub
parent d9e7818e6b
commit 4f8a3fd4cf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
25 changed files with 559 additions and 147 deletions
Download patch file Download diff file Expand all files Collapse all files

13
litellm/integrations/custom_logger.py
View file

@ -3,7 +3,7 @@
import os
import traceback
from datetime import datetime as datetimeObj
from typing import Any, Literal, Optional, Tuple, Union
from typing import TYPE_CHECKING, Any, Literal, Optional, Tuple, Union
import dotenv
from pydantic import BaseModel
@ -21,6 +21,13 @@ from litellm.types.utils import (
StandardLoggingPayload,
)
if TYPE_CHECKING:
from opentelemetry.trace import Span as _Span
Span = _Span
else:
Span = Any
class CustomLogger: # https://docs.litellm.ai/docs/observability/custom_callback#callback-class
# Class variables or attributes
@ -62,7 +69,9 @@ class CustomLogger: # https://docs.litellm.ai/docs/observability/custom_callbac
Allows usage-based-routing-v2 to run pre-call rpm checks within the picked deployment's semaphore (concurrency-safe tpm/rpm checks).
"""
async def async_pre_call_check(self, deployment: dict) -> Optional[dict]:
async def async_pre_call_check(
self, deployment: dict, parent_otel_span: Optional[Span]
) -> Optional[dict]:
pass
def pre_call_check(self, deployment: dict) -> Optional[dict]: