phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 18:42:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: implement query_metrics

Browse source 
query_metrics currently has no implementation, meaning once a metric is emitted there is no way in llama stack to query it from the store.

implement query_metrics for the meta_reference provider which follows a similar style to `query_traces`, using the trace_store to format an SQL query and execute it

in this case the parameters for the query are `metric.METRIC_NAME, start_time, and end_time`.

this required client side changes since the client had no `query_metrics` or any associated resources, so any tests here will fail but I will provider manual execution logs for the new tests I am adding

order the metrics by timestamp.

Additionally add `unit` to the `MetricDataPoint` class since this adds much more context to the metric being queried.

these metrics can also be aggregated via a `granularity` parameter. This was pre-defined as a string like: `1m, 1h, 1d` where metrics occuring in same timespan specified are aggregated together.

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-08-07 20:03:58 -04:00
parent 2ee898cc4c
commit fb553f3430
5 changed files with 237 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/apis/telemetry/telemetry.py
View file

@ -386,6 +386,7 @@ class MetricDataPoint(BaseModel):
timestamp: int
value: float
unit: str
@json_schema_type
@ -518,7 +519,7 @@ class Telemetry(Protocol):
metric_name: str,
start_time: int,
end_time: int | None = None,
granularity: str | None = "1d",
granularity: str | None = None,
query_type: MetricQueryType = MetricQueryType.RANGE,
label_matchers: list[MetricLabelMatcher] | None = None,
) -> QueryMetricsResponse: