Skip to content

README.md

Latest commit

 

History

History
58 lines (40 loc) · 11.8 KB

README.md

File metadata and controls

58 lines (40 loc) · 11.8 KB
Raw

Reporting

Overview

Available Operations

  • query - Query reporting metrics

query

Returns time-series, scalar, and top-list analytics for AI usage, cost, latency, evaluator results, and guardrail outcomes.

Example Usage

from orq_ai_sdk import Orq
from orq_ai_sdk.utils import parse_datetime
import os


with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.reporting.query(metric="genai.evaluator.score.avg", from_=parse_datetime("2026-12-14T22:21:09.964Z"), to=parse_datetime("2026-03-06T12:20:53.904Z"))

    # Handle response
    print(res)

Parameters

Parameter Type Required Description
metric models.Metric ✔️ Catalogue metric to query.
from_ date ✔️ Inclusive lower bound for the report window (RFC 3339, UTC).
to date ✔️ Exclusive upper bound for the report window (RFC 3339, UTC).
grain Optional[models.Grain] ➖ Requested bucket grain. Use auto or omit the field to let the server choose based on the requested range.
group_by List[models.GroupBy] ➖ Reporting dimensions to break down by. Valid dimensions depend on the selected metric.
filters List[models.Filter] ➖ Up to 20 allowlisted predicates combined with AND.
limit Optional[int] ➖ Maximum bucket rows returned. Defaults to 1000 and is capped at
5000.
time_zone Optional[str] ➖ IANA time zone applied to bucket boundaries, for example
America/New_York. Response timestamps remain UTC. Empty means UTC.
include_totals Optional[bool] ➖ When true, include a totals block aggregated across the full
report window.
mode Optional[models.QueryReportRequestMode] ➖ Value shaping. timeseries (default) buckets by time; scalar returns one aggregated row per group over the whole window, ordered by value (top list), or a single row when group_by is empty.
sort Optional[models.Sort] ➖ Value ordering for scalar rows. Defaults to desc. Ignored for timeseries.
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.

Response

models.QueryReportResponse

Errors

Error Type Status Code Content Type
models.APIDefaultError 4XX, 5XX */*