 Joseph PagadoraandCopybara-Service
|
553e376718
|
feat: Remove overall_eval_status calculation from _CustomMetricEvaluator and add threshold to custom metric function expected signature
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 861268984
|
2026-01-26 11:01:32 -08:00 |
|
 Joseph PagadoraandCopybara-Service
|
ea0934b993
|
feat: Update adk eval cli to consume custom metrics by adding CustomMetricEvaluator
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 857229167
|
2026-01-16 11:05:52 -08:00 |
|
 Joseph PagadoraandCopybara-Service
|
6d2f33a59c
|
feat: Update EvalConfig and EvalMetric data models to support custom metrics
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 855517478
|
2026-01-12 21:37:21 -08:00 |
|
 Joseph PagadoraandCopybara-Service
|
da2c933b53
|
feat: Filter invocation and eval case rubrics by type when running rubric based evaluators
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 853841204
|
2026-01-08 12:23:33 -08:00 |
|
 Joseph PagadoraandCopybara-Service
|
8afb99a078
|
feat: Support per-eval case and per-invocation rubrics in rubric-based evaluators
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 853820099
|
2026-01-08 11:26:06 -08:00 |
|
 Joseph PagadoraandCopybara-Service
|
5b7c8c04d6
|
chore: Introduce MetricInfoProvider interface, and refactor metric evaluators to use this interface to provide MetricInfo
Co-authored-by: Joseph Pagadora <jcpagadora@google.com>
PiperOrigin-RevId: 851406110
|
2026-01-02 11:49:34 -08:00 |
|
 Joseph PagadoraandCopybara-Service
|
9fbed0b15a
|
fix: Overall eval status should be NOT_EVALUATED if no invocations were evaluated
PiperOrigin-RevId: 819322513
|
2025-10-14 11:36:33 -07:00 |
|
 Joseph PagadoraandCopybara-Service
|
8c73d29c75
|
feat: Add HallucinationsV1 evaluation metric
PiperOrigin-RevId: 813456369
|
2025-09-30 15:39:10 -07:00 |
|
 Joseph PagadoraandCopybara-Service
|
75699fbeca
|
feat: Implement auto rater-based evaluator for responses
PiperOrigin-RevId: 780654576
|
2025-07-08 11:49:26 -07:00 |
|
 Joseph PagadoraandCopybara-Service
|
9597a446fd
|
feat: Add rouge_score library to ADK eval dependencies, and implement RougeEvaluator that is computes ROUGE-1 for "response_match_score" metric
PiperOrigin-RevId: 774949712
|
2025-06-23 15:31:03 -07:00 |
|
 Joseph PagadoraandCopybara-Service
|
fa025d7559
|
feat: Add a new option eval_storage_uri in adk web & adk eval to specify GCS bucket to store eval data
PiperOrigin-RevId: 774947795
|
2025-06-23 15:24:57 -07:00 |
|