mirror of
https://github.com/github/awesome-copilot.git
synced 2026-05-04 14:15:55 +00:00
chore: sync Arize skills from arize-skills@597d609bfe5f07fd7d24acfdb408a082911b18fc and phoenix@746247cbb07b0dc7803b87c69dd8c77811c33f59 (#1583)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
@@ -14,6 +14,10 @@ CI/CD evals vs production monitoring - complementary approaches.
|
||||
## CI/CD Evaluations
|
||||
|
||||
```python
|
||||
from phoenix.client import Client
|
||||
|
||||
client = Client()
|
||||
|
||||
# Fast, deterministic checks
|
||||
ci_evaluators = [
|
||||
has_required_format,
|
||||
@@ -23,7 +27,7 @@ ci_evaluators = [
|
||||
]
|
||||
|
||||
# Small but representative dataset (~100 examples)
|
||||
run_experiment(ci_dataset, task, ci_evaluators)
|
||||
client.experiments.run_experiment(dataset=ci_dataset, task=task, evaluators=ci_evaluators)
|
||||
```
|
||||
|
||||
Set thresholds: regression=0.95, safety=1.0, format=0.98.
|
||||
|
||||
Reference in New Issue
Block a user