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

9
litellm/proxy/utils.py
View file

@ -235,7 +235,7 @@ class InternalUsageCache:
return await self.dual_cache.async_get_cache(
key=key,
local_only=local_only,
litellm_parent_otel_span=litellm_parent_otel_span,
parent_otel_span=litellm_parent_otel_span,
**kwargs,
)
@ -281,7 +281,7 @@ class InternalUsageCache:
key=key,
value=value,
local_only=local_only,
litellm_parent_otel_span=litellm_parent_otel_span,
parent_otel_span=litellm_parent_otel_span,
**kwargs,
)
@ -367,7 +367,10 @@ class ProxyLogging:
llm_router=llm_router
) # INITIALIZE LITELLM CALLBACKS ON SERVER STARTUP <- do this to catch any logging errors on startup, not when calls are being made
if "daily_reports" in self.slack_alerting_instance.alert_types:
if (
self.slack_alerting_instance is not None
and "daily_reports" in self.slack_alerting_instance.alert_types
):
asyncio.create_task(
self.slack_alerting_instance._run_scheduled_daily_report(
llm_router=llm_router