phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 10:49:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add new compact MetricInResponse type

Browse source
This commit is contained in:
Dinesh Yeduguru 2025-03-12 11:54:23 -07:00
parent 0fdb15bcc7
commit 8b63aba7a4
5 changed files with 21 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/distribution/routers/routers.py
View file

@ -48,7 +48,7 @@ from llama_stack.apis.scoring import (
ScoringFnParams,
)
from llama_stack.apis.shields import Shield
from llama_stack.apis.telemetry import MetricEvent, Telemetry
from llama_stack.apis.telemetry import MetricEvent, MetricInResponse, Telemetry
from llama_stack.apis.tools import (
RAGDocument,
RAGQueryConfig,
@ -206,12 +206,12 @@ class InferenceRouter(Inference):
completion_tokens: int,
total_tokens: int,
model: Model,
) -> List[MetricEvent]:
) -> List[MetricInResponse]:
metrics = self._construct_metrics(prompt_tokens, completion_tokens, total_tokens, model)
if self.telemetry:
for metric in metrics:
await self.telemetry.log_event(metric)
return metrics
return [MetricInResponse(metric=metric.metric, value=metric.value) for metric in metrics]
async def _count_tokens(
self,