0bd05df471
feat: Add Safety evaluator metric
...
We add a new metric for evaluating safety of Agent's response to ADK Eval. We delegate the actual implementation to Vertex Gen AI Eval SDK, so using this metric will require GCP project.
As a part of this change, we created (refactored) a simple Facade for vertex gen ai eval sdk.
PiperOrigin-RevId: 778580406
2025-07-02 11:30:31 -07:00
04de3e197d
fix: Adding detailed information on each metric evaluation
...
Additionally, few other small changes.
* Updated a test fixture to support the latest eval data schema. Somehow I missed doing that previously.
* Updated the `evaluation_generator.py` to use `run_async`, instead of `run`.
* Also, raise an informed error when dependencies required eval are not installed.
* Also, changed the behavior of AgentEvaluator.evaluate method to run all the evals, instead of failing at the first eval metric failure.
PiperOrigin-RevId: 775919127
2025-06-25 18:32:02 -07:00
f33e0903b2
feat: Add ADK examples for litellm with add_function_to_prompt
...
Add examples for for https://github.com/google/adk-python/issues/1273
PiperOrigin-RevId: 775352677
2025-06-24 13:08:44 -07:00
e384fa4ad7
chore: fix previously skipped isort issue
...
PiperOrigin-RevId: 772224853
2025-06-16 16:57:46 -07:00
aafa80bd85
fix: stream in litellm + adk and add corresponding integration tests
...
Fixes https://github.com/google/adk-python/issues/1368
PiperOrigin-RevId: 772218385
2025-06-16 16:37:14 -07:00
8e285874da
feat: Add integration tests for litellm with and without turn on add_function_to_prompt
...
Add experiments for https://github.com/google/adk-python/issues/1273
PiperOrigin-RevId: 771145715
2025-06-13 10:37:09 -07:00
a09781142a
chore: Removes LlmAgent.examples field, which was already abandoned before 0.1 version
...
For context: tools/example_tool.py was created to replace LlmAgent.example
Also removes relevant usage in tests.
PiperOrigin-RevId: 768193042
2025-06-06 13:17:10 -07:00
41b33d4a0a
Move public_utils to utils in tests
...
Renamed conflicting utils.py as testing_utils.py
PiperOrigin-RevId: 761715808
2025-05-21 16:35:11 -07:00
3f117391a5
refactor: remote remote agent as there is no use case and it's not implemented properly
...
PiperOrigin-RevId: 760652423
2025-05-19 09:24:37 -07:00
729001fc0b
chore: logger = logging.getLogger(__name__) --> logger = logging.getLogger('google_adk.' + __name__)
...
PiperOrigin-RevId: 760019467
2025-05-17 09:47:55 -07:00
1c23556225
Updated test cases to use the new EvalSet schema to store test data. Also, added a utility to help migrate existing tests files to the new schema.
...
Also, migrated existing test files to the new schema and deleted test session files as they are no longer needed.
PiperOrigin-RevId: 759318735
2025-05-15 15:10:06 -07:00
4c6820e78c
Update AgentEvaluator to new new EvalSchema
...
PiperOrigin-RevId: 759293759
2025-05-15 14:09:23 -07:00
e7d9cf359a
make eval functions async
...
PiperOrigin-RevId: 756106627
2025-05-07 19:53:19 -07:00
794a70edcd
Support async agent and model callbacks
...
PiperOrigin-RevId: 755542756
2025-05-06 15:14:10 -07:00
e31cd0b5f8
No public description
...
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/243 from trandangtrungduc:fix_typos 6e317d69de
2025-04-18 12:07:52 -07:00
61d4be2d76
No public description
...
PiperOrigin-RevId: 748777998
2025-04-17 21:47:59 +00:00
Ankur Sharma
Genquan Duan
Liang Wu
Google Team Member
Wei Sun (Jack)
Selcuk Gun
Xiang (Sean) Zhou
Trần Đặng Trung Đức
Google ADK Member