phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +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
tests/router_unit_tests/test_router_helper_utils.py
View file

@ -440,12 +440,12 @@ def test_update_usage(model_list):
)
deployment_id = deployment["model_info"]["id"]
request_count = router._update_usage(
deployment_id=deployment_id,
deployment_id=deployment_id, parent_otel_span=None
)
assert request_count == 1
request_count = router._update_usage(
deployment_id=deployment_id,
deployment_id=deployment_id, parent_otel_span=None
)
assert request_count == 2
@ -482,7 +482,9 @@ def test_should_raise_content_policy_error(model_list, finish_reason, expected_e
def test_get_healthy_deployments(model_list):
"""Test if the '_get_healthy_deployments' function is working correctly"""
router = Router(model_list=model_list)
deployments = router._get_healthy_deployments(model="gpt-3.5-turbo")
deployments = router._get_healthy_deployments(
model="gpt-3.5-turbo", parent_otel_span=None
)
assert len(deployments) > 0
@ -756,6 +758,7 @@ def test_track_deployment_metrics(model_list):
model="gpt-3.5-turbo",
usage={"total_tokens": 100},
),
parent_otel_span=None,
)