* docs: Adding documentation for the new multi-turn eval metrics
* Update criteria.md
---------
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* docs: Add documentation for per_turn_user_simulator_quality_v1 evaluation criterion
* fixes typo
* Include documentation for User Personas
* Fix User Personas table formatting
---------
Co-authored-by: Sebastian Caldas <scaldas@google.com>
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* docs: Add documentation for per_turn_user_simulator_quality_v1 evaluation criterion
* fixes typo
* Include documentation for User Personas
---------
Co-authored-by: Sebastian Caldas <scaldas@google.com>
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* Mark rubric-based criteria as user sim compatible
* Add missing documentation for custom user sim instructions
---------
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* Update documentation to reflect recent changes made to Tool Trajecotry metrics
* Updated some typos
* Update criteria.md
---------
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* Add link to Colab user sim tutorial in ADK samples
* Add a tip admonition that links to sample notebook
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* Add documentation for User Simulation
* Update user-sim.md with version number
---------
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* docs: add language support tags to pages
- replace img.shield tags
- add language support tags where missing
* update Agents page with general tags
* update language and version tagging
- response to review comments
- rename css styles to avoid style name conflicts
* add tags to api-server page
* feat: Add detail documentation for all eval metrics supported by ADK
* Add path to criteria.md
---------
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* feat: modifying the Evaluate docs with the new features.
New features added:
1. Evaluation Configuration: users can now configure custom threshold for the metrics used for each eval run, allowing more control for the evaluation criteria
2. Evaluation Case view & edit: Each eval case added can now be viewed and edited. Right now we only support edit of text responses from Agent. This allows users to customize the response to fit their needs
3. New tracing: We have a new tab which contains all traces grouped by user messages. Each trace row is clickable and hoverable. Upon hover the corresponding message will be highlighted in the chat window. Upon click, the bottom panel will show up that contains Event detail, Request, Response, and Graph that corresponds to that trace row
* fix: modified the Step 2, and added the Trace View section
fix: modified the Step 2, and added the Trace View section
* fix: added gif animations
fix: added gif animations
* fix: inserted the gif animations
fix: inserted the gif animations
* fix: added an explanation for the blue rows
fix: added an explanation for the blue rows
* docs: Updates eval documentation to reflect recent eval schema updates.
* Addressed review comments.
* Added clarification on identifying when to use the migration.
ykchen-g