eval-studio-client 1.0.1__py3-none-any.whl → 1.1.0a5__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (527) hide show
  1. eval_studio_client/api/__init__.py +36 -1
  2. eval_studio_client/api/api/__init__.py +4 -0
  3. eval_studio_client/api/api/adversarial_inputs_service_api.py +321 -0
  4. eval_studio_client/api/api/dashboard_service_api.py +1 -1
  5. eval_studio_client/api/api/document_service_api.py +1 -1
  6. eval_studio_client/api/api/evaluation_service_api.py +1 -1
  7. eval_studio_client/api/api/evaluator_service_api.py +1 -1
  8. eval_studio_client/api/api/generated_questions_validation_service_api.py +321 -0
  9. eval_studio_client/api/api/human_calibration_service_api.py +1 -1
  10. eval_studio_client/api/api/info_service_api.py +1 -1
  11. eval_studio_client/api/api/leaderboard_report_service_api.py +292 -0
  12. eval_studio_client/api/api/leaderboard_service_api.py +17 -17
  13. eval_studio_client/api/api/model_service_api.py +17 -17
  14. eval_studio_client/api/api/operation_progress_service_api.py +1 -1
  15. eval_studio_client/api/api/operation_service_api.py +272 -17
  16. eval_studio_client/api/api/perturbation_service_api.py +1 -1
  17. eval_studio_client/api/api/perturbator_service_api.py +17 -17
  18. eval_studio_client/api/api/prompt_generation_service_api.py +1 -1
  19. eval_studio_client/api/api/prompt_library_service_api.py +1 -1
  20. eval_studio_client/api/api/test_case_relationship_service_api.py +292 -0
  21. eval_studio_client/api/api/test_case_service_api.py +17 -17
  22. eval_studio_client/api/api/test_class_service_api.py +17 -17
  23. eval_studio_client/api/api/test_lab_service_api.py +1 -1
  24. eval_studio_client/api/api/test_service_api.py +585 -17
  25. eval_studio_client/api/api/who_am_i_service_api.py +1 -1
  26. eval_studio_client/api/api/workflow_edge_service_api.py +541 -2
  27. eval_studio_client/api/api/workflow_node_service_api.py +923 -126
  28. eval_studio_client/api/api/workflow_service_api.py +317 -33
  29. eval_studio_client/api/api_client.py +1 -1
  30. eval_studio_client/api/configuration.py +1 -1
  31. eval_studio_client/api/docs/AdversarialInputsServiceApi.md +78 -0
  32. eval_studio_client/api/docs/AdversarialInputsServiceTestAdversarialInputsRobustnessRequest.md +45 -0
  33. eval_studio_client/api/docs/GeneratedQuestionsValidationServiceApi.md +78 -0
  34. eval_studio_client/api/docs/GeneratedQuestionsValidationServiceValidateGeneratedQuestionsRequest.md +30 -0
  35. eval_studio_client/api/docs/LeaderboardReportServiceApi.md +75 -0
  36. eval_studio_client/api/docs/LeaderboardServiceApi.md +5 -5
  37. eval_studio_client/api/docs/ModelServiceApi.md +5 -5
  38. eval_studio_client/api/docs/OperationServiceApi.md +72 -5
  39. eval_studio_client/api/docs/PerturbatorServiceApi.md +5 -5
  40. eval_studio_client/api/docs/PromptGenerationServiceAutoGeneratePromptsRequest.md +2 -1
  41. eval_studio_client/api/docs/RequiredTheTestCaseToUpdate.md +2 -0
  42. eval_studio_client/api/docs/RequiredTheUpdatedWorkflow.md +3 -0
  43. eval_studio_client/api/docs/TestCaseRelationshipServiceApi.md +75 -0
  44. eval_studio_client/api/docs/TestCaseServiceApi.md +5 -5
  45. eval_studio_client/api/docs/TestClassServiceApi.md +5 -5
  46. eval_studio_client/api/docs/TestServiceApi.md +145 -5
  47. eval_studio_client/api/docs/TestServiceCloneTestRequest.md +30 -0
  48. eval_studio_client/api/docs/TestServiceGenerateTestCasesRequest.md +3 -2
  49. eval_studio_client/api/docs/TestServicePerturbTestInPlaceRequest.md +30 -0
  50. eval_studio_client/api/docs/V1AbortOperationResponse.md +29 -0
  51. eval_studio_client/api/docs/V1CloneTestResponse.md +29 -0
  52. eval_studio_client/api/docs/V1CloneWorkflowResponse.md +29 -0
  53. eval_studio_client/api/docs/V1Context.md +32 -0
  54. eval_studio_client/api/docs/V1CreateWorkflowEdgeResponse.md +29 -0
  55. eval_studio_client/api/docs/V1CreateWorkflowNodeResponse.md +29 -0
  56. eval_studio_client/api/docs/V1DeleteWorkflowEdgeResponse.md +29 -0
  57. eval_studio_client/api/docs/V1GeneratedTestCase.md +30 -0
  58. eval_studio_client/api/docs/V1GetLeaderboardReportResponse.md +29 -0
  59. eval_studio_client/api/docs/V1Info.md +3 -0
  60. eval_studio_client/api/docs/V1InitWorkflowNodeResponse.md +29 -0
  61. eval_studio_client/api/docs/V1LeaderboardReport.md +32 -0
  62. eval_studio_client/api/docs/V1LeaderboardReportActualOutputData.md +31 -0
  63. eval_studio_client/api/docs/V1LeaderboardReportActualOutputMeta.md +31 -0
  64. eval_studio_client/api/docs/V1LeaderboardReportEvaluator.md +42 -0
  65. eval_studio_client/api/docs/V1LeaderboardReportEvaluatorParameter.md +38 -0
  66. eval_studio_client/api/docs/V1LeaderboardReportExplanation.md +34 -0
  67. eval_studio_client/api/docs/V1LeaderboardReportMetricsMetaEntry.md +41 -0
  68. eval_studio_client/api/docs/V1LeaderboardReportModel.md +39 -0
  69. eval_studio_client/api/docs/V1LeaderboardReportResult.md +45 -0
  70. eval_studio_client/api/docs/V1LeaderboardReportResultRelationship.md +32 -0
  71. eval_studio_client/api/docs/V1ListTestCaseRelationshipsResponse.md +29 -0
  72. eval_studio_client/api/docs/V1MetricScore.md +31 -0
  73. eval_studio_client/api/docs/V1MetricScores.md +29 -0
  74. eval_studio_client/api/docs/V1PerturbTestInPlaceResponse.md +29 -0
  75. eval_studio_client/api/docs/V1RepeatedString.md +29 -0
  76. eval_studio_client/api/docs/V1ResetWorkflowNodeResponse.md +29 -0
  77. eval_studio_client/api/docs/V1TestCase.md +2 -0
  78. eval_studio_client/api/docs/V1Workflow.md +3 -0
  79. eval_studio_client/api/docs/WorkflowEdgeServiceApi.md +139 -0
  80. eval_studio_client/api/docs/WorkflowNodeServiceApi.md +221 -12
  81. eval_studio_client/api/docs/WorkflowServiceApi.md +81 -10
  82. eval_studio_client/api/docs/WorkflowServiceCloneWorkflowRequest.md +33 -0
  83. eval_studio_client/api/exceptions.py +1 -1
  84. eval_studio_client/api/models/__init__.py +32 -1
  85. eval_studio_client/api/models/adversarial_inputs_service_test_adversarial_inputs_robustness_request.py +143 -0
  86. eval_studio_client/api/models/generated_questions_validation_service_validate_generated_questions_request.py +97 -0
  87. eval_studio_client/api/models/perturbation_service_create_perturbation_request.py +1 -1
  88. eval_studio_client/api/models/prompt_generation_service_auto_generate_prompts_request.py +13 -4
  89. eval_studio_client/api/models/protobuf_any.py +1 -1
  90. eval_studio_client/api/models/protobuf_null_value.py +1 -1
  91. eval_studio_client/api/models/required_the_dashboard_to_update.py +1 -1
  92. eval_studio_client/api/models/required_the_document_to_update.py +1 -1
  93. eval_studio_client/api/models/required_the_leaderboard_to_update.py +1 -1
  94. eval_studio_client/api/models/required_the_model_to_update.py +1 -1
  95. eval_studio_client/api/models/required_the_operation_to_finalize.py +1 -1
  96. eval_studio_client/api/models/required_the_operation_to_update.py +1 -1
  97. eval_studio_client/api/models/required_the_test_case_to_update.py +10 -3
  98. eval_studio_client/api/models/required_the_test_to_update.py +1 -1
  99. eval_studio_client/api/models/required_the_updated_workflow.py +11 -3
  100. eval_studio_client/api/models/required_the_updated_workflow_node.py +1 -1
  101. eval_studio_client/api/models/rpc_status.py +1 -1
  102. eval_studio_client/api/models/test_case_service_batch_delete_test_cases_request.py +1 -1
  103. eval_studio_client/api/models/test_service_clone_test_request.py +89 -0
  104. eval_studio_client/api/models/test_service_generate_test_cases_request.py +7 -5
  105. eval_studio_client/api/models/test_service_import_test_cases_from_library_request.py +1 -1
  106. eval_studio_client/api/models/test_service_list_test_case_library_items_request.py +1 -1
  107. eval_studio_client/api/models/test_service_perturb_test_in_place_request.py +97 -0
  108. eval_studio_client/api/models/test_service_perturb_test_request.py +1 -1
  109. eval_studio_client/api/models/v1_abort_operation_response.py +91 -0
  110. eval_studio_client/api/models/v1_batch_create_leaderboards_request.py +1 -1
  111. eval_studio_client/api/models/v1_batch_create_leaderboards_response.py +1 -1
  112. eval_studio_client/api/models/v1_batch_delete_dashboards_request.py +1 -1
  113. eval_studio_client/api/models/v1_batch_delete_dashboards_response.py +1 -1
  114. eval_studio_client/api/models/v1_batch_delete_documents_request.py +1 -1
  115. eval_studio_client/api/models/v1_batch_delete_documents_response.py +1 -1
  116. eval_studio_client/api/models/v1_batch_delete_evaluators_request.py +1 -1
  117. eval_studio_client/api/models/v1_batch_delete_evaluators_response.py +1 -1
  118. eval_studio_client/api/models/v1_batch_delete_leaderboards_request.py +1 -1
  119. eval_studio_client/api/models/v1_batch_delete_leaderboards_response.py +1 -1
  120. eval_studio_client/api/models/v1_batch_delete_models_request.py +1 -1
  121. eval_studio_client/api/models/v1_batch_delete_models_response.py +1 -1
  122. eval_studio_client/api/models/v1_batch_delete_test_cases_response.py +1 -1
  123. eval_studio_client/api/models/v1_batch_delete_tests_request.py +1 -1
  124. eval_studio_client/api/models/v1_batch_delete_tests_response.py +1 -1
  125. eval_studio_client/api/models/v1_batch_delete_workflows_request.py +1 -1
  126. eval_studio_client/api/models/v1_batch_delete_workflows_response.py +1 -1
  127. eval_studio_client/api/models/v1_batch_get_dashboards_response.py +1 -1
  128. eval_studio_client/api/models/v1_batch_get_documents_response.py +1 -1
  129. eval_studio_client/api/models/v1_batch_get_leaderboards_response.py +1 -1
  130. eval_studio_client/api/models/v1_batch_get_models_response.py +1 -1
  131. eval_studio_client/api/models/v1_batch_get_operations_response.py +1 -1
  132. eval_studio_client/api/models/v1_batch_get_tests_response.py +1 -1
  133. eval_studio_client/api/models/v1_batch_get_workflow_edges_response.py +1 -1
  134. eval_studio_client/api/models/v1_batch_get_workflow_nodes_response.py +1 -1
  135. eval_studio_client/api/models/v1_batch_import_leaderboard_request.py +1 -1
  136. eval_studio_client/api/models/v1_batch_import_leaderboard_response.py +1 -1
  137. eval_studio_client/api/models/v1_batch_import_tests_request.py +1 -1
  138. eval_studio_client/api/models/v1_batch_import_tests_response.py +1 -1
  139. eval_studio_client/api/models/v1_check_base_models_response.py +1 -1
  140. eval_studio_client/api/models/v1_clone_test_response.py +91 -0
  141. eval_studio_client/api/models/v1_clone_workflow_response.py +91 -0
  142. eval_studio_client/api/models/v1_collection_info.py +1 -1
  143. eval_studio_client/api/models/v1_context.py +93 -0
  144. eval_studio_client/api/models/v1_create_dashboard_response.py +1 -1
  145. eval_studio_client/api/models/v1_create_document_response.py +1 -1
  146. eval_studio_client/api/models/v1_create_evaluation_request.py +1 -1
  147. eval_studio_client/api/models/v1_create_evaluator_response.py +1 -1
  148. eval_studio_client/api/models/v1_create_leaderboard_request.py +1 -1
  149. eval_studio_client/api/models/v1_create_leaderboard_response.py +1 -1
  150. eval_studio_client/api/models/v1_create_leaderboard_without_cache_response.py +1 -1
  151. eval_studio_client/api/models/v1_create_model_response.py +1 -1
  152. eval_studio_client/api/models/v1_create_perturbation_response.py +1 -1
  153. eval_studio_client/api/models/v1_create_test_case_response.py +1 -1
  154. eval_studio_client/api/models/v1_create_test_lab_response.py +1 -1
  155. eval_studio_client/api/models/v1_create_test_response.py +1 -1
  156. eval_studio_client/api/models/v1_create_workflow_edge_response.py +91 -0
  157. eval_studio_client/api/models/v1_create_workflow_node_response.py +91 -0
  158. eval_studio_client/api/models/v1_create_workflow_response.py +1 -1
  159. eval_studio_client/api/models/v1_dashboard.py +1 -1
  160. eval_studio_client/api/models/v1_dashboard_status.py +1 -1
  161. eval_studio_client/api/models/v1_delete_dashboard_response.py +1 -1
  162. eval_studio_client/api/models/v1_delete_document_response.py +1 -1
  163. eval_studio_client/api/models/v1_delete_evaluator_response.py +1 -1
  164. eval_studio_client/api/models/v1_delete_leaderboard_response.py +1 -1
  165. eval_studio_client/api/models/v1_delete_model_response.py +1 -1
  166. eval_studio_client/api/models/v1_delete_test_case_response.py +1 -1
  167. eval_studio_client/api/models/v1_delete_test_response.py +1 -1
  168. eval_studio_client/api/models/v1_delete_workflow_edge_response.py +91 -0
  169. eval_studio_client/api/models/v1_delete_workflow_node_response.py +1 -1
  170. eval_studio_client/api/models/v1_delete_workflow_response.py +1 -1
  171. eval_studio_client/api/models/v1_document.py +1 -1
  172. eval_studio_client/api/models/v1_estimate_threshold_request.py +1 -1
  173. eval_studio_client/api/models/v1_evaluation_test.py +1 -1
  174. eval_studio_client/api/models/v1_evaluator.py +1 -1
  175. eval_studio_client/api/models/v1_evaluator_param_type.py +1 -1
  176. eval_studio_client/api/models/v1_evaluator_parameter.py +1 -1
  177. eval_studio_client/api/models/v1_evaluator_view.py +1 -1
  178. eval_studio_client/api/models/v1_finalize_operation_response.py +1 -1
  179. eval_studio_client/api/models/v1_find_all_test_cases_by_id_response.py +1 -1
  180. eval_studio_client/api/models/v1_find_test_lab_response.py +1 -1
  181. eval_studio_client/api/models/v1_generate_test_cases_response.py +1 -1
  182. eval_studio_client/api/models/v1_generated_test_case.py +101 -0
  183. eval_studio_client/api/models/v1_get_dashboard_response.py +1 -1
  184. eval_studio_client/api/models/v1_get_document_response.py +1 -1
  185. eval_studio_client/api/models/v1_get_evaluator_response.py +1 -1
  186. eval_studio_client/api/models/v1_get_info_response.py +1 -1
  187. eval_studio_client/api/models/v1_get_leaderboard_report_response.py +91 -0
  188. eval_studio_client/api/models/v1_get_leaderboard_response.py +1 -1
  189. eval_studio_client/api/models/v1_get_model_response.py +1 -1
  190. eval_studio_client/api/models/v1_get_operation_progress_by_parent_response.py +1 -1
  191. eval_studio_client/api/models/v1_get_operation_response.py +1 -1
  192. eval_studio_client/api/models/v1_get_perturbator_response.py +1 -1
  193. eval_studio_client/api/models/v1_get_test_case_response.py +1 -1
  194. eval_studio_client/api/models/v1_get_test_class_response.py +1 -1
  195. eval_studio_client/api/models/v1_get_test_response.py +1 -1
  196. eval_studio_client/api/models/v1_get_workflow_node_prerequisites_response.py +1 -1
  197. eval_studio_client/api/models/v1_get_workflow_node_response.py +1 -1
  198. eval_studio_client/api/models/v1_get_workflow_response.py +1 -1
  199. eval_studio_client/api/models/v1_import_evaluation_request.py +1 -1
  200. eval_studio_client/api/models/v1_import_leaderboard_request.py +1 -1
  201. eval_studio_client/api/models/v1_import_leaderboard_response.py +1 -1
  202. eval_studio_client/api/models/v1_import_test_cases_from_library_response.py +1 -1
  203. eval_studio_client/api/models/v1_import_test_cases_request.py +1 -1
  204. eval_studio_client/api/models/v1_info.py +10 -4
  205. eval_studio_client/api/models/v1_init_workflow_node_response.py +91 -0
  206. eval_studio_client/api/models/v1_insight.py +1 -1
  207. eval_studio_client/api/models/v1_labeled_test_case.py +1 -1
  208. eval_studio_client/api/models/v1_leaderboard.py +1 -1
  209. eval_studio_client/api/models/v1_leaderboard_report.py +115 -0
  210. eval_studio_client/api/models/v1_leaderboard_report_actual_output_data.py +93 -0
  211. eval_studio_client/api/models/v1_leaderboard_report_actual_output_meta.py +101 -0
  212. eval_studio_client/api/models/v1_leaderboard_report_evaluator.py +155 -0
  213. eval_studio_client/api/models/v1_leaderboard_report_evaluator_parameter.py +109 -0
  214. eval_studio_client/api/models/v1_leaderboard_report_explanation.py +103 -0
  215. eval_studio_client/api/models/v1_leaderboard_report_metrics_meta_entry.py +129 -0
  216. eval_studio_client/api/models/v1_leaderboard_report_model.py +121 -0
  217. eval_studio_client/api/models/v1_leaderboard_report_result.py +175 -0
  218. eval_studio_client/api/models/v1_leaderboard_report_result_relationship.py +97 -0
  219. eval_studio_client/api/models/v1_leaderboard_status.py +1 -1
  220. eval_studio_client/api/models/v1_leaderboard_type.py +1 -1
  221. eval_studio_client/api/models/v1_leaderboard_view.py +1 -1
  222. eval_studio_client/api/models/v1_list_base_models_response.py +1 -1
  223. eval_studio_client/api/models/v1_list_dashboards_response.py +1 -1
  224. eval_studio_client/api/models/v1_list_documents_response.py +1 -1
  225. eval_studio_client/api/models/v1_list_evaluators_response.py +1 -1
  226. eval_studio_client/api/models/v1_list_leaderboards_response.py +1 -1
  227. eval_studio_client/api/models/v1_list_llm_models_response.py +1 -1
  228. eval_studio_client/api/models/v1_list_model_collections_response.py +1 -1
  229. eval_studio_client/api/models/v1_list_models_response.py +1 -1
  230. eval_studio_client/api/models/v1_list_most_recent_dashboards_response.py +1 -1
  231. eval_studio_client/api/models/v1_list_most_recent_leaderboards_response.py +1 -1
  232. eval_studio_client/api/models/v1_list_most_recent_models_response.py +1 -1
  233. eval_studio_client/api/models/v1_list_most_recent_tests_response.py +1 -1
  234. eval_studio_client/api/models/v1_list_operations_response.py +1 -1
  235. eval_studio_client/api/models/v1_list_perturbators_response.py +1 -1
  236. eval_studio_client/api/models/v1_list_prompt_library_items_response.py +1 -1
  237. eval_studio_client/api/models/v1_list_rag_collections_response.py +1 -1
  238. eval_studio_client/api/models/v1_list_test_case_library_items_response.py +1 -1
  239. eval_studio_client/api/models/v1_list_test_case_relationships_response.py +95 -0
  240. eval_studio_client/api/models/v1_list_test_cases_response.py +1 -1
  241. eval_studio_client/api/models/v1_list_test_classes_response.py +1 -1
  242. eval_studio_client/api/models/v1_list_tests_response.py +1 -1
  243. eval_studio_client/api/models/v1_list_workflows_response.py +1 -1
  244. eval_studio_client/api/models/v1_metric_score.py +89 -0
  245. eval_studio_client/api/models/v1_metric_scores.py +95 -0
  246. eval_studio_client/api/models/v1_model.py +1 -1
  247. eval_studio_client/api/models/v1_model_type.py +1 -1
  248. eval_studio_client/api/models/v1_operation.py +1 -1
  249. eval_studio_client/api/models/v1_operation_progress.py +1 -1
  250. eval_studio_client/api/models/v1_perturb_test_in_place_response.py +91 -0
  251. eval_studio_client/api/models/v1_perturb_test_response.py +1 -1
  252. eval_studio_client/api/models/v1_perturbator.py +1 -1
  253. eval_studio_client/api/models/v1_perturbator_configuration.py +1 -1
  254. eval_studio_client/api/models/v1_perturbator_intensity.py +1 -1
  255. eval_studio_client/api/models/v1_problem_and_action.py +1 -1
  256. eval_studio_client/api/models/v1_process_workflow_node_response.py +1 -1
  257. eval_studio_client/api/models/v1_prompt_library_item.py +1 -1
  258. eval_studio_client/api/models/v1_repeated_string.py +87 -0
  259. eval_studio_client/api/models/v1_reset_workflow_node_response.py +91 -0
  260. eval_studio_client/api/models/v1_test.py +1 -1
  261. eval_studio_client/api/models/v1_test_case.py +10 -3
  262. eval_studio_client/api/models/v1_test_case_relationship.py +1 -1
  263. eval_studio_client/api/models/v1_test_cases_generator.py +1 -1
  264. eval_studio_client/api/models/v1_test_class.py +1 -1
  265. eval_studio_client/api/models/v1_test_class_type.py +1 -1
  266. eval_studio_client/api/models/v1_test_lab.py +1 -1
  267. eval_studio_client/api/models/v1_test_suite_evaluates.py +1 -1
  268. eval_studio_client/api/models/v1_update_dashboard_response.py +1 -1
  269. eval_studio_client/api/models/v1_update_document_response.py +1 -1
  270. eval_studio_client/api/models/v1_update_leaderboard_response.py +1 -1
  271. eval_studio_client/api/models/v1_update_model_response.py +1 -1
  272. eval_studio_client/api/models/v1_update_operation_response.py +1 -1
  273. eval_studio_client/api/models/v1_update_test_case_response.py +1 -1
  274. eval_studio_client/api/models/v1_update_test_response.py +1 -1
  275. eval_studio_client/api/models/v1_update_workflow_node_response.py +1 -1
  276. eval_studio_client/api/models/v1_update_workflow_response.py +1 -1
  277. eval_studio_client/api/models/v1_who_am_i_response.py +1 -1
  278. eval_studio_client/api/models/v1_workflow.py +11 -3
  279. eval_studio_client/api/models/v1_workflow_edge.py +1 -1
  280. eval_studio_client/api/models/v1_workflow_edge_type.py +1 -1
  281. eval_studio_client/api/models/v1_workflow_node.py +1 -1
  282. eval_studio_client/api/models/v1_workflow_node_artifact.py +1 -1
  283. eval_studio_client/api/models/v1_workflow_node_artifacts.py +1 -1
  284. eval_studio_client/api/models/v1_workflow_node_attributes.py +1 -1
  285. eval_studio_client/api/models/v1_workflow_node_status.py +1 -1
  286. eval_studio_client/api/models/v1_workflow_node_type.py +4 -1
  287. eval_studio_client/api/models/v1_workflow_node_view.py +1 -1
  288. eval_studio_client/api/models/v1_workflow_type.py +1 -1
  289. eval_studio_client/api/models/workflow_service_clone_workflow_request.py +95 -0
  290. eval_studio_client/api/rest.py +1 -1
  291. eval_studio_client/api/test/test_adversarial_inputs_service_api.py +37 -0
  292. eval_studio_client/api/test/test_adversarial_inputs_service_test_adversarial_inputs_robustness_request.py +128 -0
  293. eval_studio_client/api/test/test_dashboard_service_api.py +1 -1
  294. eval_studio_client/api/test/test_document_service_api.py +1 -1
  295. eval_studio_client/api/test/test_evaluation_service_api.py +1 -1
  296. eval_studio_client/api/test/test_evaluator_service_api.py +1 -1
  297. eval_studio_client/api/test/test_generated_questions_validation_service_api.py +37 -0
  298. eval_studio_client/api/test/test_generated_questions_validation_service_validate_generated_questions_request.py +83 -0
  299. eval_studio_client/api/test/test_human_calibration_service_api.py +1 -1
  300. eval_studio_client/api/test/test_info_service_api.py +1 -1
  301. eval_studio_client/api/test/test_leaderboard_report_service_api.py +37 -0
  302. eval_studio_client/api/test/test_leaderboard_service_api.py +1 -1
  303. eval_studio_client/api/test/test_model_service_api.py +1 -1
  304. eval_studio_client/api/test/test_operation_progress_service_api.py +1 -1
  305. eval_studio_client/api/test/test_operation_service_api.py +7 -1
  306. eval_studio_client/api/test/test_perturbation_service_api.py +1 -1
  307. eval_studio_client/api/test/test_perturbation_service_create_perturbation_request.py +6 -2
  308. eval_studio_client/api/test/test_perturbator_service_api.py +1 -1
  309. eval_studio_client/api/test/test_prompt_generation_service_api.py +1 -1
  310. eval_studio_client/api/test/test_prompt_generation_service_auto_generate_prompts_request.py +9 -4
  311. eval_studio_client/api/test/test_prompt_library_service_api.py +1 -1
  312. eval_studio_client/api/test/test_protobuf_any.py +1 -1
  313. eval_studio_client/api/test/test_protobuf_null_value.py +1 -1
  314. eval_studio_client/api/test/test_required_the_dashboard_to_update.py +1 -1
  315. eval_studio_client/api/test/test_required_the_document_to_update.py +1 -1
  316. eval_studio_client/api/test/test_required_the_leaderboard_to_update.py +1 -1
  317. eval_studio_client/api/test/test_required_the_model_to_update.py +1 -1
  318. eval_studio_client/api/test/test_required_the_operation_to_finalize.py +1 -1
  319. eval_studio_client/api/test/test_required_the_operation_to_update.py +1 -1
  320. eval_studio_client/api/test/test_required_the_test_case_to_update.py +6 -2
  321. eval_studio_client/api/test/test_required_the_test_to_update.py +1 -1
  322. eval_studio_client/api/test/test_required_the_updated_workflow.py +5 -2
  323. eval_studio_client/api/test/test_required_the_updated_workflow_node.py +1 -1
  324. eval_studio_client/api/test/test_rpc_status.py +1 -1
  325. eval_studio_client/api/test/test_test_case_relationship_service_api.py +37 -0
  326. eval_studio_client/api/test/test_test_case_service_api.py +1 -1
  327. eval_studio_client/api/test/test_test_case_service_batch_delete_test_cases_request.py +1 -1
  328. eval_studio_client/api/test/test_test_class_service_api.py +1 -1
  329. eval_studio_client/api/test/test_test_lab_service_api.py +1 -1
  330. eval_studio_client/api/test/test_test_service_api.py +13 -1
  331. eval_studio_client/api/test/test_test_service_clone_test_request.py +52 -0
  332. eval_studio_client/api/test/test_test_service_generate_test_cases_request.py +4 -1
  333. eval_studio_client/api/test/test_test_service_import_test_cases_from_library_request.py +1 -1
  334. eval_studio_client/api/test/test_test_service_list_test_case_library_items_request.py +1 -1
  335. eval_studio_client/api/test/test_test_service_perturb_test_in_place_request.py +59 -0
  336. eval_studio_client/api/test/test_test_service_perturb_test_request.py +1 -1
  337. eval_studio_client/api/test/test_v1_abort_operation_response.py +71 -0
  338. eval_studio_client/api/test/test_v1_batch_create_leaderboards_request.py +1 -1
  339. eval_studio_client/api/test/test_v1_batch_create_leaderboards_response.py +1 -1
  340. eval_studio_client/api/test/test_v1_batch_delete_dashboards_request.py +1 -1
  341. eval_studio_client/api/test/test_v1_batch_delete_dashboards_response.py +1 -1
  342. eval_studio_client/api/test/test_v1_batch_delete_documents_request.py +1 -1
  343. eval_studio_client/api/test/test_v1_batch_delete_documents_response.py +1 -1
  344. eval_studio_client/api/test/test_v1_batch_delete_evaluators_request.py +1 -1
  345. eval_studio_client/api/test/test_v1_batch_delete_evaluators_response.py +1 -1
  346. eval_studio_client/api/test/test_v1_batch_delete_leaderboards_request.py +1 -1
  347. eval_studio_client/api/test/test_v1_batch_delete_leaderboards_response.py +1 -1
  348. eval_studio_client/api/test/test_v1_batch_delete_models_request.py +1 -1
  349. eval_studio_client/api/test/test_v1_batch_delete_models_response.py +1 -1
  350. eval_studio_client/api/test/test_v1_batch_delete_test_cases_response.py +6 -2
  351. eval_studio_client/api/test/test_v1_batch_delete_tests_request.py +1 -1
  352. eval_studio_client/api/test/test_v1_batch_delete_tests_response.py +1 -1
  353. eval_studio_client/api/test/test_v1_batch_delete_workflows_request.py +1 -1
  354. eval_studio_client/api/test/test_v1_batch_delete_workflows_response.py +5 -2
  355. eval_studio_client/api/test/test_v1_batch_get_dashboards_response.py +1 -1
  356. eval_studio_client/api/test/test_v1_batch_get_documents_response.py +1 -1
  357. eval_studio_client/api/test/test_v1_batch_get_leaderboards_response.py +1 -1
  358. eval_studio_client/api/test/test_v1_batch_get_models_response.py +1 -1
  359. eval_studio_client/api/test/test_v1_batch_get_operations_response.py +1 -1
  360. eval_studio_client/api/test/test_v1_batch_get_tests_response.py +1 -1
  361. eval_studio_client/api/test/test_v1_batch_get_workflow_edges_response.py +1 -1
  362. eval_studio_client/api/test/test_v1_batch_get_workflow_nodes_response.py +1 -1
  363. eval_studio_client/api/test/test_v1_batch_import_leaderboard_request.py +1 -1
  364. eval_studio_client/api/test/test_v1_batch_import_leaderboard_response.py +1 -1
  365. eval_studio_client/api/test/test_v1_batch_import_tests_request.py +1 -1
  366. eval_studio_client/api/test/test_v1_batch_import_tests_response.py +1 -1
  367. eval_studio_client/api/test/test_v1_check_base_models_response.py +1 -1
  368. eval_studio_client/api/test/test_v1_clone_test_response.py +67 -0
  369. eval_studio_client/api/test/test_v1_clone_workflow_response.py +93 -0
  370. eval_studio_client/api/test/test_v1_collection_info.py +1 -1
  371. eval_studio_client/api/test/test_v1_context.py +54 -0
  372. eval_studio_client/api/test/test_v1_create_dashboard_response.py +1 -1
  373. eval_studio_client/api/test/test_v1_create_document_response.py +1 -1
  374. eval_studio_client/api/test/test_v1_create_evaluation_request.py +6 -2
  375. eval_studio_client/api/test/test_v1_create_evaluator_response.py +1 -1
  376. eval_studio_client/api/test/test_v1_create_leaderboard_request.py +1 -1
  377. eval_studio_client/api/test/test_v1_create_leaderboard_response.py +1 -1
  378. eval_studio_client/api/test/test_v1_create_leaderboard_without_cache_response.py +1 -1
  379. eval_studio_client/api/test/test_v1_create_model_response.py +1 -1
  380. eval_studio_client/api/test/test_v1_create_perturbation_response.py +1 -1
  381. eval_studio_client/api/test/test_v1_create_test_case_response.py +6 -2
  382. eval_studio_client/api/test/test_v1_create_test_lab_response.py +1 -1
  383. eval_studio_client/api/test/test_v1_create_test_response.py +1 -1
  384. eval_studio_client/api/test/test_v1_create_workflow_edge_response.py +62 -0
  385. eval_studio_client/api/test/test_v1_create_workflow_node_response.py +82 -0
  386. eval_studio_client/api/test/test_v1_create_workflow_response.py +5 -2
  387. eval_studio_client/api/test/test_v1_dashboard.py +1 -1
  388. eval_studio_client/api/test/test_v1_dashboard_status.py +1 -1
  389. eval_studio_client/api/test/test_v1_delete_dashboard_response.py +1 -1
  390. eval_studio_client/api/test/test_v1_delete_document_response.py +1 -1
  391. eval_studio_client/api/test/test_v1_delete_evaluator_response.py +1 -1
  392. eval_studio_client/api/test/test_v1_delete_leaderboard_response.py +1 -1
  393. eval_studio_client/api/test/test_v1_delete_model_response.py +1 -1
  394. eval_studio_client/api/test/test_v1_delete_test_case_response.py +6 -2
  395. eval_studio_client/api/test/test_v1_delete_test_response.py +1 -1
  396. eval_studio_client/api/test/test_v1_delete_workflow_edge_response.py +62 -0
  397. eval_studio_client/api/test/test_v1_delete_workflow_node_response.py +1 -1
  398. eval_studio_client/api/test/test_v1_delete_workflow_response.py +5 -2
  399. eval_studio_client/api/test/test_v1_document.py +1 -1
  400. eval_studio_client/api/test/test_v1_estimate_threshold_request.py +1 -1
  401. eval_studio_client/api/test/test_v1_evaluation_test.py +6 -2
  402. eval_studio_client/api/test/test_v1_evaluator.py +1 -1
  403. eval_studio_client/api/test/test_v1_evaluator_param_type.py +1 -1
  404. eval_studio_client/api/test/test_v1_evaluator_parameter.py +1 -1
  405. eval_studio_client/api/test/test_v1_evaluator_view.py +1 -1
  406. eval_studio_client/api/test/test_v1_finalize_operation_response.py +1 -1
  407. eval_studio_client/api/test/test_v1_find_all_test_cases_by_id_response.py +6 -2
  408. eval_studio_client/api/test/test_v1_find_test_lab_response.py +1 -1
  409. eval_studio_client/api/test/test_v1_generate_test_cases_response.py +1 -1
  410. eval_studio_client/api/test/test_v1_generated_test_case.py +79 -0
  411. eval_studio_client/api/test/test_v1_get_dashboard_response.py +1 -1
  412. eval_studio_client/api/test/test_v1_get_document_response.py +1 -1
  413. eval_studio_client/api/test/test_v1_get_evaluator_response.py +1 -1
  414. eval_studio_client/api/test/test_v1_get_info_response.py +7 -2
  415. eval_studio_client/api/test/test_v1_get_leaderboard_report_response.py +175 -0
  416. eval_studio_client/api/test/test_v1_get_leaderboard_response.py +1 -1
  417. eval_studio_client/api/test/test_v1_get_model_response.py +1 -1
  418. eval_studio_client/api/test/test_v1_get_operation_progress_by_parent_response.py +1 -1
  419. eval_studio_client/api/test/test_v1_get_operation_response.py +1 -1
  420. eval_studio_client/api/test/test_v1_get_perturbator_response.py +1 -1
  421. eval_studio_client/api/test/test_v1_get_test_case_response.py +6 -2
  422. eval_studio_client/api/test/test_v1_get_test_class_response.py +1 -1
  423. eval_studio_client/api/test/test_v1_get_test_response.py +1 -1
  424. eval_studio_client/api/test/test_v1_get_workflow_node_prerequisites_response.py +1 -1
  425. eval_studio_client/api/test/test_v1_get_workflow_node_response.py +1 -1
  426. eval_studio_client/api/test/test_v1_get_workflow_response.py +5 -2
  427. eval_studio_client/api/test/test_v1_import_evaluation_request.py +1 -1
  428. eval_studio_client/api/test/test_v1_import_leaderboard_request.py +1 -1
  429. eval_studio_client/api/test/test_v1_import_leaderboard_response.py +1 -1
  430. eval_studio_client/api/test/test_v1_import_test_cases_from_library_response.py +1 -1
  431. eval_studio_client/api/test/test_v1_import_test_cases_request.py +1 -1
  432. eval_studio_client/api/test/test_v1_info.py +7 -2
  433. eval_studio_client/api/test/test_v1_init_workflow_node_response.py +82 -0
  434. eval_studio_client/api/test/test_v1_insight.py +1 -1
  435. eval_studio_client/api/test/test_v1_labeled_test_case.py +1 -1
  436. eval_studio_client/api/test/test_v1_leaderboard.py +1 -1
  437. eval_studio_client/api/test/test_v1_leaderboard_report.py +174 -0
  438. eval_studio_client/api/test/test_v1_leaderboard_report_actual_output_data.py +52 -0
  439. eval_studio_client/api/test/test_v1_leaderboard_report_actual_output_meta.py +56 -0
  440. eval_studio_client/api/test/test_v1_leaderboard_report_evaluator.py +114 -0
  441. eval_studio_client/api/test/test_v1_leaderboard_report_evaluator_parameter.py +63 -0
  442. eval_studio_client/api/test/test_v1_leaderboard_report_explanation.py +58 -0
  443. eval_studio_client/api/test/test_v1_leaderboard_report_metrics_meta_entry.py +66 -0
  444. eval_studio_client/api/test/test_v1_leaderboard_report_model.py +62 -0
  445. eval_studio_client/api/test/test_v1_leaderboard_report_result.py +92 -0
  446. eval_studio_client/api/test/test_v1_leaderboard_report_result_relationship.py +53 -0
  447. eval_studio_client/api/test/test_v1_leaderboard_status.py +1 -1
  448. eval_studio_client/api/test/test_v1_leaderboard_type.py +1 -1
  449. eval_studio_client/api/test/test_v1_leaderboard_view.py +1 -1
  450. eval_studio_client/api/test/test_v1_list_base_models_response.py +1 -1
  451. eval_studio_client/api/test/test_v1_list_dashboards_response.py +1 -1
  452. eval_studio_client/api/test/test_v1_list_documents_response.py +1 -1
  453. eval_studio_client/api/test/test_v1_list_evaluators_response.py +1 -1
  454. eval_studio_client/api/test/test_v1_list_leaderboards_response.py +1 -1
  455. eval_studio_client/api/test/test_v1_list_llm_models_response.py +1 -1
  456. eval_studio_client/api/test/test_v1_list_model_collections_response.py +1 -1
  457. eval_studio_client/api/test/test_v1_list_models_response.py +1 -1
  458. eval_studio_client/api/test/test_v1_list_most_recent_dashboards_response.py +1 -1
  459. eval_studio_client/api/test/test_v1_list_most_recent_leaderboards_response.py +1 -1
  460. eval_studio_client/api/test/test_v1_list_most_recent_models_response.py +1 -1
  461. eval_studio_client/api/test/test_v1_list_most_recent_tests_response.py +1 -1
  462. eval_studio_client/api/test/test_v1_list_operations_response.py +1 -1
  463. eval_studio_client/api/test/test_v1_list_perturbators_response.py +1 -1
  464. eval_studio_client/api/test/test_v1_list_prompt_library_items_response.py +1 -1
  465. eval_studio_client/api/test/test_v1_list_rag_collections_response.py +1 -1
  466. eval_studio_client/api/test/test_v1_list_test_case_library_items_response.py +1 -1
  467. eval_studio_client/api/test/test_v1_list_test_case_relationships_response.py +56 -0
  468. eval_studio_client/api/test/test_v1_list_test_cases_response.py +6 -2
  469. eval_studio_client/api/test/test_v1_list_test_classes_response.py +1 -1
  470. eval_studio_client/api/test/test_v1_list_tests_response.py +1 -1
  471. eval_studio_client/api/test/test_v1_list_workflows_response.py +5 -2
  472. eval_studio_client/api/test/test_v1_metric_score.py +52 -0
  473. eval_studio_client/api/test/test_v1_metric_scores.py +55 -0
  474. eval_studio_client/api/test/test_v1_model.py +1 -1
  475. eval_studio_client/api/test/test_v1_model_type.py +1 -1
  476. eval_studio_client/api/test/test_v1_operation.py +1 -1
  477. eval_studio_client/api/test/test_v1_operation_progress.py +1 -1
  478. eval_studio_client/api/test/test_v1_perturb_test_in_place_response.py +67 -0
  479. eval_studio_client/api/test/test_v1_perturb_test_response.py +1 -1
  480. eval_studio_client/api/test/test_v1_perturbator.py +1 -1
  481. eval_studio_client/api/test/test_v1_perturbator_configuration.py +1 -1
  482. eval_studio_client/api/test/test_v1_perturbator_intensity.py +1 -1
  483. eval_studio_client/api/test/test_v1_problem_and_action.py +1 -1
  484. eval_studio_client/api/test/test_v1_process_workflow_node_response.py +1 -1
  485. eval_studio_client/api/test/test_v1_prompt_library_item.py +1 -1
  486. eval_studio_client/api/test/test_v1_repeated_string.py +53 -0
  487. eval_studio_client/api/test/test_v1_reset_workflow_node_response.py +82 -0
  488. eval_studio_client/api/test/test_v1_test.py +1 -1
  489. eval_studio_client/api/test/test_v1_test_case.py +6 -2
  490. eval_studio_client/api/test/test_v1_test_case_relationship.py +1 -1
  491. eval_studio_client/api/test/test_v1_test_cases_generator.py +1 -1
  492. eval_studio_client/api/test/test_v1_test_class.py +1 -1
  493. eval_studio_client/api/test/test_v1_test_class_type.py +1 -1
  494. eval_studio_client/api/test/test_v1_test_lab.py +1 -1
  495. eval_studio_client/api/test/test_v1_test_suite_evaluates.py +1 -1
  496. eval_studio_client/api/test/test_v1_update_dashboard_response.py +1 -1
  497. eval_studio_client/api/test/test_v1_update_document_response.py +1 -1
  498. eval_studio_client/api/test/test_v1_update_leaderboard_response.py +1 -1
  499. eval_studio_client/api/test/test_v1_update_model_response.py +1 -1
  500. eval_studio_client/api/test/test_v1_update_operation_response.py +1 -1
  501. eval_studio_client/api/test/test_v1_update_test_case_response.py +6 -2
  502. eval_studio_client/api/test/test_v1_update_test_response.py +1 -1
  503. eval_studio_client/api/test/test_v1_update_workflow_node_response.py +1 -1
  504. eval_studio_client/api/test/test_v1_update_workflow_response.py +5 -2
  505. eval_studio_client/api/test/test_v1_who_am_i_response.py +1 -1
  506. eval_studio_client/api/test/test_v1_workflow.py +5 -2
  507. eval_studio_client/api/test/test_v1_workflow_edge.py +1 -1
  508. eval_studio_client/api/test/test_v1_workflow_edge_type.py +1 -1
  509. eval_studio_client/api/test/test_v1_workflow_node.py +1 -1
  510. eval_studio_client/api/test/test_v1_workflow_node_artifact.py +1 -1
  511. eval_studio_client/api/test/test_v1_workflow_node_artifacts.py +1 -1
  512. eval_studio_client/api/test/test_v1_workflow_node_attributes.py +1 -1
  513. eval_studio_client/api/test/test_v1_workflow_node_status.py +1 -1
  514. eval_studio_client/api/test/test_v1_workflow_node_type.py +1 -1
  515. eval_studio_client/api/test/test_v1_workflow_node_view.py +1 -1
  516. eval_studio_client/api/test/test_v1_workflow_type.py +1 -1
  517. eval_studio_client/api/test/test_who_am_i_service_api.py +1 -1
  518. eval_studio_client/api/test/test_workflow_edge_service_api.py +15 -1
  519. eval_studio_client/api/test/test_workflow_node_service_api.py +23 -2
  520. eval_studio_client/api/test/test_workflow_service_api.py +8 -1
  521. eval_studio_client/api/test/test_workflow_service_clone_workflow_request.py +55 -0
  522. eval_studio_client/gen/openapiv2/eval_studio.swagger.json +1633 -219
  523. eval_studio_client/tests.py +103 -8
  524. {eval_studio_client-1.0.1.dist-info → eval_studio_client-1.1.0a5.dist-info}/METADATA +2 -2
  525. eval_studio_client-1.1.0a5.dist-info/RECORD +720 -0
  526. {eval_studio_client-1.0.1.dist-info → eval_studio_client-1.1.0a5.dist-info}/WHEEL +1 -1
  527. eval_studio_client-1.0.1.dist-info/RECORD +0 -615
@@ -1,10 +1,13 @@
1
1
  {
2
2
  "swagger": "2.0",
3
3
  "info": {
4
- "title": "ai/h2o/eval_studio/v1/collection.proto",
4
+ "title": "ai/h2o/eval_studio/v1/insight.proto",
5
5
  "version": "version not set"
6
6
  },
7
7
  "tags": [
8
+ {
9
+ "name": "AdversarialInputsService"
10
+ },
8
11
  {
9
12
  "name": "DashboardService"
10
13
  },
@@ -17,12 +20,18 @@
17
20
  {
18
21
  "name": "EvaluatorService"
19
22
  },
23
+ {
24
+ "name": "GeneratedQuestionsValidationService"
25
+ },
20
26
  {
21
27
  "name": "HumanCalibrationService"
22
28
  },
23
29
  {
24
30
  "name": "InfoService"
25
31
  },
32
+ {
33
+ "name": "LeaderboardReportService"
34
+ },
26
35
  {
27
36
  "name": "LeaderboardService"
28
37
  },
@@ -47,6 +56,9 @@
47
56
  {
48
57
  "name": "PromptLibraryService"
49
58
  },
59
+ {
60
+ "name": "TestCaseRelationshipService"
61
+ },
50
62
  {
51
63
  "name": "TestCaseService"
52
64
  },
@@ -2788,6 +2800,38 @@
2788
2800
  }
2789
2801
  },
2790
2802
  "/v1/{name_10}": {
2803
+ "get": {
2804
+ "operationId": "TestService_GetTest",
2805
+ "responses": {
2806
+ "200": {
2807
+ "description": "A successful response.",
2808
+ "schema": {
2809
+ "$ref": "#/definitions/v1GetTestResponse"
2810
+ }
2811
+ },
2812
+ "default": {
2813
+ "description": "An unexpected error response.",
2814
+ "schema": {
2815
+ "$ref": "#/definitions/rpcStatus"
2816
+ }
2817
+ }
2818
+ },
2819
+ "parameters": [
2820
+ {
2821
+ "name": "name_10",
2822
+ "description": "Required. The name of the Test to retrieve.",
2823
+ "in": "path",
2824
+ "required": true,
2825
+ "type": "string",
2826
+ "pattern": "tests/[^/]+"
2827
+ }
2828
+ ],
2829
+ "tags": [
2830
+ "TestService"
2831
+ ]
2832
+ }
2833
+ },
2834
+ "/v1/{name_11}": {
2791
2835
  "get": {
2792
2836
  "summary": "GetWorkflowNode retrieves a WorkflowNode by name. Deleted WorkflowNode is returned without\nerror, it has a delete_time and deleter fields set.",
2793
2837
  "operationId": "WorkflowNodeService_GetWorkflowNode",
@@ -2807,7 +2851,7 @@
2807
2851
  },
2808
2852
  "parameters": [
2809
2853
  {
2810
- "name": "name_10",
2854
+ "name": "name_11",
2811
2855
  "description": "Required. The name of the WorkflowNode to retrieve.",
2812
2856
  "in": "path",
2813
2857
  "required": true,
@@ -2833,7 +2877,7 @@
2833
2877
  ]
2834
2878
  }
2835
2879
  },
2836
- "/v1/{name_11}": {
2880
+ "/v1/{name_12}": {
2837
2881
  "get": {
2838
2882
  "summary": "GetWorkflow retrieves a Workflow by name. Deleted Workflow is returned without error, it has a\ndelete_time and deleter fields set.",
2839
2883
  "operationId": "WorkflowService_GetWorkflow",
@@ -2853,7 +2897,7 @@
2853
2897
  },
2854
2898
  "parameters": [
2855
2899
  {
2856
- "name": "name_11",
2900
+ "name": "name_12",
2857
2901
  "description": "Required. The name of the Workflow to retrieve.",
2858
2902
  "in": "path",
2859
2903
  "required": true,
@@ -2928,6 +2972,69 @@
2928
2972
  ]
2929
2973
  }
2930
2974
  },
2975
+ "/v1/{name_1}:clone": {
2976
+ "post": {
2977
+ "summary": "CloneWorkflow clones an existing Workflow.",
2978
+ "operationId": "WorkflowService_CloneWorkflow",
2979
+ "responses": {
2980
+ "200": {
2981
+ "description": "A successful response.",
2982
+ "schema": {
2983
+ "$ref": "#/definitions/v1CloneWorkflowResponse"
2984
+ }
2985
+ },
2986
+ "default": {
2987
+ "description": "An unexpected error response.",
2988
+ "schema": {
2989
+ "$ref": "#/definitions/rpcStatus"
2990
+ }
2991
+ }
2992
+ },
2993
+ "parameters": [
2994
+ {
2995
+ "name": "name_1",
2996
+ "description": "Required. The name of the Workflow to clone.",
2997
+ "in": "path",
2998
+ "required": true,
2999
+ "type": "string",
3000
+ "pattern": "workflows/[^/]+"
3001
+ },
3002
+ {
3003
+ "name": "body",
3004
+ "in": "body",
3005
+ "required": true,
3006
+ "schema": {
3007
+ "type": "object",
3008
+ "properties": {
3009
+ "displayNameOverride": {
3010
+ "type": "string",
3011
+ "description": "Optional. The display name of the cloned Workflow. If not specified, the display name from the\noriginal Workflow is used with \" Clone\" suffix added."
3012
+ },
3013
+ "descriptionOverride": {
3014
+ "type": "string",
3015
+ "description": "Optional. The description of the cloned Workflow. If not specified, the description from the\noriginal Workflow is used."
3016
+ },
3017
+ "modelOverride": {
3018
+ "type": "string",
3019
+ "description": "Optional. The name of the model to use in the cloned Workflow. If not specified, the model from\nthe original Workflow is used."
3020
+ },
3021
+ "llmModelOverride": {
3022
+ "type": "string",
3023
+ "description": "Optional. The name of the base LLM model to use in the cloned workflow. If not specified, the\nbase LLM model from the original Workflow is used. Required if model_override is set."
3024
+ },
3025
+ "modelParametersOverride": {
3026
+ "type": "string",
3027
+ "description": "Optional. Model specific parameters in JSON format. If not specified, the parameters from the\noriginal Workflow are used."
3028
+ }
3029
+ }
3030
+ }
3031
+ }
3032
+ ],
3033
+ "tags": [
3034
+ "WorkflowService"
3035
+ ]
3036
+ }
3037
+ },
2931
3038
  "/v1/{name_2}": {
2932
3039
  "get": {
2933
3040
  "operationId": "EvaluatorService_GetEvaluator",
@@ -2992,12 +3099,12 @@
2992
3099
  },
2993
3100
  "/v1/{name_3}": {
2994
3101
  "get": {
2995
- "operationId": "LeaderboardService_GetLeaderboard",
3102
+ "operationId": "LeaderboardReportService_GetLeaderboardReport",
2996
3103
  "responses": {
2997
3104
  "200": {
2998
3105
  "description": "A successful response.",
2999
3106
  "schema": {
3000
- "$ref": "#/definitions/v1GetLeaderboardResponse"
3107
+ "$ref": "#/definitions/v1GetLeaderboardReportResponse"
3001
3108
  }
3002
3109
  },
3003
3110
  "default": {
@@ -3014,11 +3121,11 @@
3014
3121
  "in": "path",
3015
3122
  "required": true,
3016
3123
  "type": "string",
3017
- "pattern": "leaderboards/[^/]+"
3124
+ "pattern": "leaderboardReports/[^/]+"
3018
3125
  }
3019
3126
  ],
3020
3127
  "tags": [
3021
- "LeaderboardService"
3128
+ "LeaderboardReportService"
3022
3129
  ]
3023
3130
  },
3024
3131
  "delete": {
@@ -3054,12 +3161,12 @@
3054
3161
  },
3055
3162
  "/v1/{name_4}": {
3056
3163
  "get": {
3057
- "operationId": "ModelService_GetModel",
3164
+ "operationId": "LeaderboardService_GetLeaderboard",
3058
3165
  "responses": {
3059
3166
  "200": {
3060
3167
  "description": "A successful response.",
3061
3168
  "schema": {
3062
- "$ref": "#/definitions/v1GetModelResponse"
3169
+ "$ref": "#/definitions/v1GetLeaderboardResponse"
3063
3170
  }
3064
3171
  },
3065
3172
  "default": {
@@ -3072,15 +3179,15 @@
3072
3179
  "parameters": [
3073
3180
  {
3074
3181
  "name": "name_4",
3075
- "description": "Required. The name of the Model to retrieve.",
3182
+ "description": "Required. The name of the Leaderboard to retrieve.",
3076
3183
  "in": "path",
3077
3184
  "required": true,
3078
3185
  "type": "string",
3079
- "pattern": "models/[^/]+"
3186
+ "pattern": "leaderboards/[^/]+"
3080
3187
  }
3081
3188
  ],
3082
3189
  "tags": [
3083
- "ModelService"
3190
+ "LeaderboardService"
3084
3191
  ]
3085
3192
  },
3086
3193
  "delete": {
@@ -3116,12 +3223,12 @@
3116
3223
  },
3117
3224
  "/v1/{name_5}": {
3118
3225
  "get": {
3119
- "operationId": "OperationService_GetOperation",
3226
+ "operationId": "ModelService_GetModel",
3120
3227
  "responses": {
3121
3228
  "200": {
3122
3229
  "description": "A successful response.",
3123
3230
  "schema": {
3124
- "$ref": "#/definitions/v1GetOperationResponse"
3231
+ "$ref": "#/definitions/v1GetModelResponse"
3125
3232
  }
3126
3233
  },
3127
3234
  "default": {
@@ -3134,15 +3241,15 @@
3134
3241
  "parameters": [
3135
3242
  {
3136
3243
  "name": "name_5",
3137
- "description": "Required. The name of the Operation to retrieve.",
3244
+ "description": "Required. The name of the Model to retrieve.",
3138
3245
  "in": "path",
3139
3246
  "required": true,
3140
3247
  "type": "string",
3141
- "pattern": "operations/[^/]+"
3248
+ "pattern": "models/[^/]+"
3142
3249
  }
3143
3250
  ],
3144
3251
  "tags": [
3145
- "OperationService"
3252
+ "ModelService"
3146
3253
  ]
3147
3254
  },
3148
3255
  "delete": {
@@ -3178,12 +3285,12 @@
3178
3285
  },
3179
3286
  "/v1/{name_6}": {
3180
3287
  "get": {
3181
- "operationId": "PerturbatorService_GetPerturbator",
3288
+ "operationId": "OperationService_GetOperation",
3182
3289
  "responses": {
3183
3290
  "200": {
3184
3291
  "description": "A successful response.",
3185
3292
  "schema": {
3186
- "$ref": "#/definitions/v1GetPerturbatorResponse"
3293
+ "$ref": "#/definitions/v1GetOperationResponse"
3187
3294
  }
3188
3295
  },
3189
3296
  "default": {
@@ -3196,15 +3303,15 @@
3196
3303
  "parameters": [
3197
3304
  {
3198
3305
  "name": "name_6",
3199
- "description": "Required. The name of the Perturbator to retrieve.",
3306
+ "description": "Required. The name of the Operation to retrieve.",
3200
3307
  "in": "path",
3201
3308
  "required": true,
3202
3309
  "type": "string",
3203
- "pattern": "perturbators/[^/]+"
3310
+ "pattern": "operations/[^/]+"
3204
3311
  }
3205
3312
  ],
3206
3313
  "tags": [
3207
- "PerturbatorService"
3314
+ "OperationService"
3208
3315
  ]
3209
3316
  },
3210
3317
  "delete": {
@@ -3247,12 +3354,12 @@
3247
3354
  },
3248
3355
  "/v1/{name_7}": {
3249
3356
  "get": {
3250
- "operationId": "TestCaseService_GetTestCase",
3357
+ "operationId": "PerturbatorService_GetPerturbator",
3251
3358
  "responses": {
3252
3359
  "200": {
3253
3360
  "description": "A successful response.",
3254
3361
  "schema": {
3255
- "$ref": "#/definitions/v1GetTestCaseResponse"
3362
+ "$ref": "#/definitions/v1GetPerturbatorResponse"
3256
3363
  }
3257
3364
  },
3258
3365
  "default": {
@@ -3265,25 +3372,25 @@
3265
3372
  "parameters": [
3266
3373
  {
3267
3374
  "name": "name_7",
3268
- "description": "The name of the TestCase to retrieve.\nFormat: tests/\u003cUUID\u003e/testCases/\u003cUUID\u003e",
3375
+ "description": "Required. The name of the Perturbator to retrieve.",
3269
3376
  "in": "path",
3270
3377
  "required": true,
3271
3378
  "type": "string",
3272
- "pattern": "tests/[^/]+/testCases/[^/]+"
3379
+ "pattern": "perturbators/[^/]+"
3273
3380
  }
3274
3381
  ],
3275
3382
  "tags": [
3276
- "TestCaseService"
3383
+ "PerturbatorService"
3277
3384
  ]
3278
3385
  },
3279
3386
  "delete": {
3280
- "summary": "DeleteWorkflowNode deletes a WorkflowNode by name. If the WorkflowNode does not exist an error\nis returned.",
3281
- "operationId": "WorkflowNodeService_DeleteWorkflowNode",
3387
+ "summary": "DeleteWorkflowEdge deletes a WorkflowEdge. If the WorkflowEdge does not exist an error is\nreturned",
3388
+ "operationId": "WorkflowEdgeService_DeleteWorkflowEdge",
3282
3389
  "responses": {
3283
3390
  "200": {
3284
3391
  "description": "A successful response.",
3285
3392
  "schema": {
3286
- "$ref": "#/definitions/v1DeleteWorkflowNodeResponse"
3393
+ "$ref": "#/definitions/v1DeleteWorkflowEdgeResponse"
3287
3394
  }
3288
3395
  },
3289
3396
  "default": {
@@ -3296,26 +3403,26 @@
3296
3403
  "parameters": [
3297
3404
  {
3298
3405
  "name": "name_7",
3299
- "description": "Required. The name of the WorkflowNode to delete.",
3406
+ "description": "Required. The name of the WorkflowEdge to delete.",
3300
3407
  "in": "path",
3301
3408
  "required": true,
3302
3409
  "type": "string",
3303
- "pattern": "workflows/[^/]+/nodes/[^/]+"
3410
+ "pattern": "workflows/[^/]+/edges/[^/]+"
3304
3411
  }
3305
3412
  ],
3306
3413
  "tags": [
3307
- "WorkflowNodeService"
3414
+ "WorkflowEdgeService"
3308
3415
  ]
3309
3416
  }
3310
3417
  },
3311
3418
  "/v1/{name_8}": {
3312
3419
  "get": {
3313
- "operationId": "TestClassService_GetTestClass",
3420
+ "operationId": "TestCaseService_GetTestCase",
3314
3421
  "responses": {
3315
3422
  "200": {
3316
3423
  "description": "A successful response.",
3317
3424
  "schema": {
3318
- "$ref": "#/definitions/v1GetTestClassResponse"
3425
+ "$ref": "#/definitions/v1GetTestCaseResponse"
3319
3426
  }
3320
3427
  },
3321
3428
  "default": {
@@ -3328,25 +3435,26 @@
3328
3435
  "parameters": [
3329
3436
  {
3330
3437
  "name": "name_8",
3331
- "description": "The name of the TestClass to retrieve.\nFormat: testClasses/\u003cUUID\u003e",
3438
+ "description": "The name of the TestCase to retrieve.\nFormat: tests/\u003cUUID\u003e/testCases/\u003cUUID\u003e",
3332
3439
  "in": "path",
3333
3440
  "required": true,
3334
3441
  "type": "string",
3335
- "pattern": "testClasses/[^/]+"
3442
+ "pattern": "tests/[^/]+/testCases/[^/]+"
3336
3443
  }
3337
3444
  ],
3338
3445
  "tags": [
3339
- "TestClassService"
3446
+ "TestCaseService"
3340
3447
  ]
3341
3448
  },
3342
3449
  "delete": {
3343
- "summary": "DeleteWorkflow deletes a Workflow by name. If the Workflow does not exist an error is returned.",
3344
- "operationId": "WorkflowService_DeleteWorkflow",
3450
+ "summary": "DeleteWorkflowNode deletes a WorkflowNode by name. If the WorkflowNode does not exist an error\nis returned. The edges are handled in a following way:",
3451
+ "description": "- inbound edges are deleted\n- for every outbound edge a new edge is created for every inbound node and the given\n outbound node\n\nFor example, deleting node D in the following graph:\n A ⇾ B ⇾ D ⇾ E\n ↘ ↗\n C\nwould create the following:\n A ⇾ B ⇾ E\n ↘ ↗\n C\nDeleting node B in the same graph, would create:\n A ⇾ D ⇾ E\n ↘ ↗\n C",
3452
+ "operationId": "WorkflowNodeService_DeleteWorkflowNode",
3345
3453
  "responses": {
3346
3454
  "200": {
3347
3455
  "description": "A successful response.",
3348
3456
  "schema": {
3349
- "$ref": "#/definitions/v1DeleteWorkflowResponse"
3457
+ "$ref": "#/definitions/v1DeleteWorkflowNodeResponse"
3350
3458
  }
3351
3459
  },
3352
3460
  "default": {
@@ -3359,26 +3467,26 @@
3359
3467
  "parameters": [
3360
3468
  {
3361
3469
  "name": "name_8",
3362
- "description": "Required. The name of the Workflow to delete.",
3470
+ "description": "Required. The name of the WorkflowNode to delete.",
3363
3471
  "in": "path",
3364
3472
  "required": true,
3365
3473
  "type": "string",
3366
- "pattern": "workflows/[^/]+"
3474
+ "pattern": "workflows/[^/]+/nodes/[^/]+"
3367
3475
  }
3368
3476
  ],
3369
3477
  "tags": [
3370
- "WorkflowService"
3478
+ "WorkflowNodeService"
3371
3479
  ]
3372
3480
  }
3373
3481
  },
3374
3482
  "/v1/{name_9}": {
3375
3483
  "get": {
3376
- "operationId": "TestService_GetTest",
3484
+ "operationId": "TestClassService_GetTestClass",
3377
3485
  "responses": {
3378
3486
  "200": {
3379
3487
  "description": "A successful response.",
3380
3488
  "schema": {
3381
- "$ref": "#/definitions/v1GetTestResponse"
3489
+ "$ref": "#/definitions/v1GetTestClassResponse"
3382
3490
  }
3383
3491
  },
3384
3492
  "default": {
@@ -3391,15 +3499,46 @@
3391
3499
  "parameters": [
3392
3500
  {
3393
3501
  "name": "name_9",
3394
- "description": "Required. The name of the Test to retrieve.",
3502
+ "description": "The name of the TestClass to retrieve.\nFormat: testClasses/\u003cUUID\u003e",
3395
3503
  "in": "path",
3396
3504
  "required": true,
3397
3505
  "type": "string",
3398
- "pattern": "tests/[^/]+"
3506
+ "pattern": "testClasses/[^/]+"
3399
3507
  }
3400
3508
  ],
3401
3509
  "tags": [
3402
- "TestService"
3510
+ "TestClassService"
3511
+ ]
3512
+ },
3513
+ "delete": {
3514
+ "summary": "DeleteWorkflow deletes a Workflow by name. If the Workflow does not exist an error is returned.",
3515
+ "operationId": "WorkflowService_DeleteWorkflow",
3516
+ "responses": {
3517
+ "200": {
3518
+ "description": "A successful response.",
3519
+ "schema": {
3520
+ "$ref": "#/definitions/v1DeleteWorkflowResponse"
3521
+ }
3522
+ },
3523
+ "default": {
3524
+ "description": "An unexpected error response.",
3525
+ "schema": {
3526
+ "$ref": "#/definitions/rpcStatus"
3527
+ }
3528
+ }
3529
+ },
3530
+ "parameters": [
3531
+ {
3532
+ "name": "name_9",
3533
+ "description": "Required. The name of the Workflow to delete.",
3534
+ "in": "path",
3535
+ "required": true,
3536
+ "type": "string",
3537
+ "pattern": "workflows/[^/]+"
3538
+ }
3539
+ ],
3540
+ "tags": [
3541
+ "WorkflowService"
3403
3542
  ]
3404
3543
  }
3405
3544
  },
@@ -3465,6 +3604,38 @@
3465
3604
  ]
3466
3605
  }
3467
3606
  },
3607
+ "/v1/{name}:abort": {
3608
+ "post": {
3609
+ "operationId": "OperationService_AbortOperation",
3610
+ "responses": {
3611
+ "200": {
3612
+ "description": "A successful response.",
3613
+ "schema": {
3614
+ "$ref": "#/definitions/v1AbortOperationResponse"
3615
+ }
3616
+ },
3617
+ "default": {
3618
+ "description": "An unexpected error response.",
3619
+ "schema": {
3620
+ "$ref": "#/definitions/rpcStatus"
3621
+ }
3622
+ }
3623
+ },
3624
+ "parameters": [
3625
+ {
3626
+ "name": "name",
3627
+ "description": "Required. The name of the Operation to abort.",
3628
+ "in": "path",
3629
+ "required": true,
3630
+ "type": "string",
3631
+ "pattern": "operations/[^/]+"
3632
+ }
3633
+ ],
3634
+ "tags": [
3635
+ "OperationService"
3636
+ ]
3637
+ }
3638
+ },
3468
3639
  "/v1/{name}:autoGeneratePrompts": {
3469
3640
  "post": {
3470
3641
  "operationId": "PromptGenerationService_AutoGeneratePrompts",
@@ -3516,11 +3687,12 @@
3516
3687
  "description": "Required. Base LLM model to use for generating the prompts."
3517
3688
  },
3518
3689
  "documentUrls": {
3519
- "type": "array",
3520
- "items": {
3521
- "type": "string"
3522
- },
3523
- "description": "Optional. The list of document URLs. The document URL might be a managed document URL or a\npublic URL."
3690
+ "$ref": "#/definitions/v1RepeatedString",
3691
+ "description": "The list of document URLs. The document URL might be a managed document URL or a\npublic URL."
3692
+ },
3693
+ "chunks": {
3694
+ "$ref": "#/definitions/v1RepeatedString",
3695
+ "title": "Chunks of text used instead of documents"
3524
3696
  },
3525
3697
  "generators": {
3526
3698
  "type": "array",
@@ -3549,14 +3721,14 @@
3549
3721
  ]
3550
3722
  }
3551
3723
  },
3552
- "/v1/{name}:generateTestCases": {
3724
+ "/v1/{name}:clone": {
3553
3725
  "post": {
3554
- "operationId": "TestService_GenerateTestCases",
3726
+ "operationId": "TestService_CloneTest",
3555
3727
  "responses": {
3556
3728
  "200": {
3557
3729
  "description": "A successful response.",
3558
3730
  "schema": {
3559
- "$ref": "#/definitions/v1GenerateTestCasesResponse"
3731
+ "$ref": "#/definitions/v1CloneTestResponse"
3560
3732
  }
3561
3733
  },
3562
3734
  "default": {
@@ -3569,7 +3741,7 @@
3569
3741
  "parameters": [
3570
3742
  {
3571
3743
  "name": "name",
3572
- "description": "Required. The Test for which to generate TestCases.",
3744
+ "description": "Required. The name of the Test to clone.",
3573
3745
  "in": "path",
3574
3746
  "required": true,
3575
3747
  "type": "string",
@@ -3582,36 +3754,93 @@
3582
3754
  "schema": {
3583
3755
  "type": "object",
3584
3756
  "properties": {
3585
- "count": {
3586
- "type": "integer",
3587
- "format": "int64",
3588
- "description": "Required. The number of TestCases to generate."
3589
- },
3590
- "model": {
3757
+ "newTestDisplayName": {
3591
3758
  "type": "string",
3592
- "description": "Optional. The Model to use for generating TestCases. If not specified, the default RAG h2oGPTe\nwill be used. Error is returned, if no default model is specified and this field is not set."
3759
+ "description": "Optional. Name of the newly created test."
3593
3760
  },
3594
- "baseLlmModel": {
3761
+ "newTestDescription": {
3595
3762
  "type": "string",
3596
- "description": "Optional. The base LLM model to use for generating the prompts. Selected automatically if not\nspecified."
3597
- },
3598
- "generators": {
3599
- "type": "array",
3600
- "items": {
3763
+ "description": "Optional. Description of the newly created Test."
3764
+ }
3765
+ }
3766
+ }
3767
+ }
3768
+ ],
3769
+ "tags": [
3770
+ "TestService"
3771
+ ]
3772
+ }
3773
+ },
3774
+ "/v1/{name}:generateTestCases": {
3775
+ "post": {
3776
+ "operationId": "TestService_GenerateTestCases",
3777
+ "responses": {
3778
+ "200": {
3779
+ "description": "A successful response.",
3780
+ "schema": {
3781
+ "$ref": "#/definitions/v1GenerateTestCasesResponse"
3782
+ }
3783
+ },
3784
+ "default": {
3785
+ "description": "An unexpected error response.",
3786
+ "schema": {
3787
+ "$ref": "#/definitions/rpcStatus"
3788
+ }
3789
+ }
3790
+ },
3791
+ "parameters": [
3792
+ {
3793
+ "name": "name",
3794
+ "description": "Required. The Test for which to generate TestCases.",
3795
+ "in": "path",
3796
+ "required": true,
3797
+ "type": "string",
3798
+ "pattern": "tests/[^/]+"
3799
+ },
3800
+ {
3801
+ "name": "body",
3802
+ "in": "body",
3803
+ "required": true,
3804
+ "schema": {
3805
+ "type": "object",
3806
+ "properties": {
3807
+ "count": {
3808
+ "type": "integer",
3809
+ "format": "int64",
3810
+ "description": "Required. The number of TestCases to generate."
3811
+ },
3812
+ "model": {
3813
+ "type": "string",
3814
+ "description": "Optional. The Model to use for generating TestCases. If not specified, the default RAG h2oGPTe\nwill be used. Error is returned, if no default model is specified and this field is not set."
3815
+ },
3816
+ "baseLlmModel": {
3817
+ "type": "string",
3818
+ "description": "Optional. The base LLM model to use for generating the prompts. Selected automatically if not\nspecified."
3819
+ },
3820
+ "generators": {
3821
+ "type": "array",
3822
+ "items": {
3601
3823
  "$ref": "#/definitions/v1TestCasesGenerator"
3602
3824
  },
3603
3825
  "description": "Optional. Generators to use for generation. If not specified, all generators are selected."
3604
3826
  },
3605
3827
  "h2ogpteCollectionId": {
3606
3828
  "type": "string",
3607
- "description": "Optional. The ID of the h2oGPTe collection to use. If empty, new temporary collection will be\ncreated."
3829
+ "description": "Optional. ID of the h2oGPTe collection to use. If provided, documents referenced by\nTest and any specified chunks are ignored. This field is required if Test does not\nreference any documents and no chunks are provided. If this field is left empty, a\ntemporary collection will be created."
3608
3830
  },
3609
3831
  "topics": {
3610
3832
  "type": "array",
3611
3833
  "items": {
3612
3834
  "type": "string"
3613
3835
  },
3614
- "description": "Optional. Optional. Topics to generate questions for. If not specified, use document summarization as topic generation."
3836
+ "description": "Optional. Topics to generate questions for. If not specified, use document summarization as\ntopic generation."
3837
+ },
3838
+ "chunks": {
3839
+ "type": "array",
3840
+ "items": {
3841
+ "type": "string"
3842
+ },
3843
+ "description": "Optional. The list of chunks to use for generation. If set, the Documents assigned to the Test\nand h2ogpte_collection_id are ignored."
3615
3844
  }
3616
3845
  }
3617
3846
  }
@@ -3717,6 +3946,39 @@
3717
3946
  ]
3718
3947
  }
3719
3948
  },
3949
+ "/v1/{name}:init": {
3950
+ "post": {
3951
+ "summary": "InitWorkflowNode initializes a WorkflowNode on first access.",
3952
+ "operationId": "WorkflowNodeService_InitWorkflowNode",
3953
+ "responses": {
3954
+ "200": {
3955
+ "description": "A successful response.",
3956
+ "schema": {
3957
+ "$ref": "#/definitions/v1InitWorkflowNodeResponse"
3958
+ }
3959
+ },
3960
+ "default": {
3961
+ "description": "An unexpected error response.",
3962
+ "schema": {
3963
+ "$ref": "#/definitions/rpcStatus"
3964
+ }
3965
+ }
3966
+ },
3967
+ "parameters": [
3968
+ {
3969
+ "name": "name",
3970
+ "description": "Required. The name of the WorkflowNode to initialize.",
3971
+ "in": "path",
3972
+ "required": true,
3973
+ "type": "string",
3974
+ "pattern": "workflows/[^/]+/nodes/[^/]+"
3975
+ }
3976
+ ],
3977
+ "tags": [
3978
+ "WorkflowNodeService"
3979
+ ]
3980
+ }
3981
+ },
3720
3982
  "/v1/{name}:listTestCaseLibraryItems": {
3721
3983
  "post": {
3722
3984
  "operationId": "TestService_ListTestCaseLibraryItems",
@@ -3863,6 +4125,63 @@
3863
4125
  ]
3864
4126
  }
3865
4127
  },
4128
+ "/v1/{name}:perturbInPlace": {
4129
+ "post": {
4130
+ "operationId": "TestService_PerturbTestInPlace",
4131
+ "responses": {
4132
+ "200": {
4133
+ "description": "A successful response.",
4134
+ "schema": {
4135
+ "$ref": "#/definitions/v1PerturbTestInPlaceResponse"
4136
+ }
4137
+ },
4138
+ "default": {
4139
+ "description": "An unexpected error response.",
4140
+ "schema": {
4141
+ "$ref": "#/definitions/rpcStatus"
4142
+ }
4143
+ }
4144
+ },
4145
+ "parameters": [
4146
+ {
4147
+ "name": "name",
4148
+ "description": "Required. The name of the Test to perturb.",
4149
+ "in": "path",
4150
+ "required": true,
4151
+ "type": "string",
4152
+ "pattern": "tests/[^/]+"
4153
+ },
4154
+ {
4155
+ "name": "body",
4156
+ "in": "body",
4157
+ "required": true,
4158
+ "schema": {
4159
+ "type": "object",
4160
+ "properties": {
4161
+ "perturbatorConfigurations": {
4162
+ "type": "array",
4163
+ "items": {
4164
+ "type": "object",
4165
+ "$ref": "#/definitions/v1PerturbatorConfiguration"
4166
+ },
4167
+ "description": "Required. PerturbatorConfigurations to apply to the Test."
4168
+ },
4169
+ "testCaseNames": {
4170
+ "type": "array",
4171
+ "items": {
4172
+ "type": "string"
4173
+ },
4174
+ "description": "Optional. Perturbation apply only to selected testCases."
4175
+ }
4176
+ }
4177
+ }
4178
+ }
4179
+ ],
4180
+ "tags": [
4181
+ "TestService"
4182
+ ]
4183
+ }
4184
+ },
3866
4185
  "/v1/{name}:process": {
3867
4186
  "post": {
3868
4187
  "summary": "ProcessWorkflowNode processes a WorkflowNode.",
@@ -3896,6 +4215,93 @@
3896
4215
  ]
3897
4216
  }
3898
4217
  },
4218
+ "/v1/{name}:reset": {
4219
+ "post": {
4220
+ "summary": "ResetWorkflowNode resets a WorkflowNode.",
4221
+ "operationId": "WorkflowNodeService_ResetWorkflowNode",
4222
+ "responses": {
4223
+ "200": {
4224
+ "description": "A successful response.",
4225
+ "schema": {
4226
+ "$ref": "#/definitions/v1ResetWorkflowNodeResponse"
4227
+ }
4228
+ },
4229
+ "default": {
4230
+ "description": "An unexpected error response.",
4231
+ "schema": {
4232
+ "$ref": "#/definitions/rpcStatus"
4233
+ }
4234
+ }
4235
+ },
4236
+ "parameters": [
4237
+ {
4238
+ "name": "name",
4239
+ "description": "Required. The name of the WorkflowNode to reset.",
4240
+ "in": "path",
4241
+ "required": true,
4242
+ "type": "string",
4243
+ "pattern": "workflows/[^/]+/nodes/[^/]+"
4244
+ }
4245
+ ],
4246
+ "tags": [
4247
+ "WorkflowNodeService"
4248
+ ]
4249
+ }
4250
+ },
4251
+ "/v1/{name}:validateGeneratedQuestions": {
4252
+ "post": {
4253
+ "operationId": "GeneratedQuestionsValidationService_ValidateGeneratedQuestions",
4254
+ "responses": {
4255
+ "200": {
4256
+ "description": "A successful response.",
4257
+ "schema": {
4258
+ "$ref": "#/definitions/v1Operation"
4259
+ }
4260
+ },
4261
+ "default": {
4262
+ "description": "An unexpected error response.",
4263
+ "schema": {
4264
+ "$ref": "#/definitions/rpcStatus"
4265
+ }
4266
+ }
4267
+ },
4268
+ "parameters": [
4269
+ {
4270
+ "name": "name",
4271
+ "description": "Required. The Test for which to generate TestCases.",
4272
+ "in": "path",
4273
+ "required": true,
4274
+ "type": "string",
4275
+ "pattern": "tests/[^/]+"
4276
+ },
4277
+ {
4278
+ "name": "body",
4279
+ "in": "body",
4280
+ "required": true,
4281
+ "schema": {
4282
+ "type": "object",
4283
+ "properties": {
4284
+ "operation": {
4285
+ "type": "string",
4286
+ "description": "Required. The Operation processing this question validation process."
4287
+ },
4288
+ "testCases": {
4289
+ "type": "array",
4290
+ "items": {
4291
+ "type": "object",
4292
+ "$ref": "#/definitions/v1GeneratedTestCase"
4293
+ },
4294
+ "description": "Required. Generated Test Cases, i.e., Test cases with context that was used for their generation."
4295
+ }
4296
+ }
4297
+ }
4298
+ }
4299
+ ],
4300
+ "tags": [
4301
+ "GeneratedQuestionsValidationService"
4302
+ ]
4303
+ }
4304
+ },
3899
4305
  "/v1/{node.name}": {
3900
4306
  "patch": {
3901
4307
  "summary": "UpdateWorkflowNode updates a WorkflowNode. The update_mask is used to specify the fields to be\nupdated.",
@@ -4211,14 +4617,15 @@
4211
4617
  ]
4212
4618
  }
4213
4619
  },
4214
- "/v1/{parent}/perturbations": {
4620
+ "/v1/{parent}/edges": {
4215
4621
  "post": {
4216
- "operationId": "PerturbationService_CreatePerturbation",
4622
+ "summary": "CreateWorkflowEdge creates a new WorkflowEdge.",
4623
+ "operationId": "WorkflowEdgeService_CreateWorkflowEdge",
4217
4624
  "responses": {
4218
4625
  "200": {
4219
4626
  "description": "A successful response.",
4220
4627
  "schema": {
4221
- "$ref": "#/definitions/v1CreatePerturbationResponse"
4628
+ "$ref": "#/definitions/v1CreateWorkflowEdgeResponse"
4222
4629
  }
4223
4630
  },
4224
4631
  "default": {
@@ -4231,42 +4638,125 @@
4231
4638
  "parameters": [
4232
4639
  {
4233
4640
  "name": "parent",
4234
- "description": "Required. The Test being perturbed.",
4641
+ "description": "Required. The parent Workflow in format of `workflow/{workflow_id}`.",
4235
4642
  "in": "path",
4236
4643
  "required": true,
4237
4644
  "type": "string",
4238
- "pattern": "tests/[^/]+"
4645
+ "pattern": "workflows/[^/]+"
4239
4646
  },
4240
4647
  {
4241
- "name": "body",
4648
+ "name": "edge",
4649
+ "description": "Required. The WorkflowEdge to create.",
4242
4650
  "in": "body",
4243
4651
  "required": true,
4244
4652
  "schema": {
4245
- "type": "object",
4246
- "properties": {
4247
- "perturbatorConfigurations": {
4248
- "type": "array",
4249
- "items": {
4250
- "type": "object",
4251
- "$ref": "#/definitions/v1PerturbatorConfiguration"
4252
- },
4253
- "description": "Required. PerturbatorConfiguration to apply to the parent Test."
4254
- },
4255
- "testCases": {
4256
- "type": "array",
4257
- "items": {
4258
- "type": "object",
4259
- "$ref": "#/definitions/v1TestCase"
4260
- },
4261
- "description": "Required. List of test cases to perturbate. These are the test cases from the parent test.\n\nTODO: breaks https://google.aip.dev/144"
4262
- },
4263
- "testCaseRelationships": {
4264
- "type": "array",
4265
- "items": {
4266
- "type": "object",
4267
- "$ref": "#/definitions/v1TestCaseRelationship"
4268
- },
4269
- "description": "Optional. List of relationships between test cases."
4653
+ "$ref": "#/definitions/v1WorkflowEdge"
4654
+ }
4655
+ }
4656
+ ],
4657
+ "tags": [
4658
+ "WorkflowEdgeService"
4659
+ ]
4660
+ }
4661
+ },
4662
+ "/v1/{parent}/nodes": {
4663
+ "post": {
4664
+ "summary": "CreateWorkflowNode creates a new WorkflowNode.",
4665
+ "operationId": "WorkflowNodeService_CreateWorkflowNode",
4666
+ "responses": {
4667
+ "200": {
4668
+ "description": "A successful response.",
4669
+ "schema": {
4670
+ "$ref": "#/definitions/v1CreateWorkflowNodeResponse"
4671
+ }
4672
+ },
4673
+ "default": {
4674
+ "description": "An unexpected error response.",
4675
+ "schema": {
4676
+ "$ref": "#/definitions/rpcStatus"
4677
+ }
4678
+ }
4679
+ },
4680
+ "parameters": [
4681
+ {
4682
+ "name": "parent",
4683
+ "description": "Required. The parent Workflow in format of `workflow/{workflow_id}`.",
4684
+ "in": "path",
4685
+ "required": true,
4686
+ "type": "string",
4687
+ "pattern": "workflows/[^/]+"
4688
+ },
4689
+ {
4690
+ "name": "node",
4691
+ "description": "Required. The WorkflowNode to create.",
4692
+ "in": "body",
4693
+ "required": true,
4694
+ "schema": {
4695
+ "$ref": "#/definitions/v1WorkflowNode"
4696
+ }
4697
+ }
4698
+ ],
4699
+ "tags": [
4700
+ "WorkflowNodeService"
4701
+ ]
4702
+ }
4703
+ },
4704
+ "/v1/{parent}/perturbations": {
4705
+ "post": {
4706
+ "operationId": "PerturbationService_CreatePerturbation",
4707
+ "responses": {
4708
+ "200": {
4709
+ "description": "A successful response.",
4710
+ "schema": {
4711
+ "$ref": "#/definitions/v1CreatePerturbationResponse"
4712
+ }
4713
+ },
4714
+ "default": {
4715
+ "description": "An unexpected error response.",
4716
+ "schema": {
4717
+ "$ref": "#/definitions/rpcStatus"
4718
+ }
4719
+ }
4720
+ },
4721
+ "parameters": [
4722
+ {
4723
+ "name": "parent",
4724
+ "description": "Required. The Test being perturbed.",
4725
+ "in": "path",
4726
+ "required": true,
4727
+ "type": "string",
4728
+ "pattern": "tests/[^/]+"
4729
+ },
4730
+ {
4731
+ "name": "body",
4732
+ "in": "body",
4733
+ "required": true,
4734
+ "schema": {
4735
+ "type": "object",
4736
+ "properties": {
4737
+ "perturbatorConfigurations": {
4738
+ "type": "array",
4739
+ "items": {
4740
+ "type": "object",
4741
+ "$ref": "#/definitions/v1PerturbatorConfiguration"
4742
+ },
4743
+ "description": "Required. PerturbatorConfiguration to apply to the parent Test."
4744
+ },
4745
+ "testCases": {
4746
+ "type": "array",
4747
+ "items": {
4748
+ "type": "object",
4749
+ "$ref": "#/definitions/v1TestCase"
4750
+ },
4751
+ "description": "Required. List of test cases to perturbate. These are the test cases from the parent test.\n\nTODO: breaks https://google.aip.dev/144"
4752
+ },
4753
+ "testCaseRelationships": {
4754
+ "type": "array",
4755
+ "items": {
4756
+ "type": "object",
4757
+ "$ref": "#/definitions/v1TestCaseRelationship"
4758
+ },
4759
+ "description": "Optional. List of relationships between test cases."
4270
4760
  },
4271
4761
  "defaultH2ogpteModel": {
4272
4762
  "$ref": "#/definitions/v1Model",
@@ -4313,6 +4803,38 @@
4313
4803
  ]
4314
4804
  }
4315
4805
  },
4806
+ "/v1/{parent}/testCaseRelationships": {
4807
+ "get": {
4808
+ "operationId": "TestCaseRelationshipService_ListTestCaseRelationships",
4809
+ "responses": {
4810
+ "200": {
4811
+ "description": "A successful response.",
4812
+ "schema": {
4813
+ "$ref": "#/definitions/v1ListTestCaseRelationshipsResponse"
4814
+ }
4815
+ },
4816
+ "default": {
4817
+ "description": "An unexpected error response.",
4818
+ "schema": {
4819
+ "$ref": "#/definitions/rpcStatus"
4820
+ }
4821
+ }
4822
+ },
4823
+ "parameters": [
4824
+ {
4825
+ "name": "parent",
4826
+ "description": "The name of the Test whose TestCaseRelationships to retrieve.",
4827
+ "in": "path",
4828
+ "required": true,
4829
+ "type": "string",
4830
+ "pattern": "tests/[^/]+"
4831
+ }
4832
+ ],
4833
+ "tags": [
4834
+ "TestCaseRelationshipService"
4835
+ ]
4836
+ }
4837
+ },
4316
4838
  "/v1/{parent}/testCases": {
4317
4839
  "get": {
4318
4840
  "operationId": "TestCaseService_ListTestCases",
@@ -4634,6 +5156,19 @@
4634
5156
  },
4635
5157
  "description": "Output only. The list of perturbators applied to this test case.",
4636
5158
  "readOnly": true
5159
+ },
5160
+ "topics": {
5161
+ "type": "array",
5162
+ "items": {
5163
+ "type": "string"
5164
+ },
5165
+ "description": "Output only. The list of topics used to generate this test case.",
5166
+ "readOnly": true
5167
+ },
5168
+ "generator": {
5169
+ "$ref": "#/definitions/v1TestCasesGenerator",
5170
+ "description": "Output only. Optional. Test case generator that was used to generate this test case.",
5171
+ "readOnly": true
4637
5172
  }
4638
5173
  },
4639
5174
  "title": "Required. The TestCase to update."
@@ -4645,6 +5180,138 @@
4645
5180
  ]
4646
5181
  }
4647
5182
  },
5183
+ "/v1/{test}:testAdversarialInputsRobustness": {
5184
+ "post": {
5185
+ "operationId": "AdversarialInputsService_TestAdversarialInputsRobustness",
5186
+ "responses": {
5187
+ "200": {
5188
+ "description": "A successful response.",
5189
+ "schema": {
5190
+ "$ref": "#/definitions/v1Operation"
5191
+ }
5192
+ },
5193
+ "default": {
5194
+ "description": "An unexpected error response.",
5195
+ "schema": {
5196
+ "$ref": "#/definitions/rpcStatus"
5197
+ }
5198
+ }
5199
+ },
5200
+ "parameters": [
5201
+ {
5202
+ "name": "test",
5203
+ "description": "Required. The Test to which the adversarial inputs TestCases will be added.",
5204
+ "in": "path",
5205
+ "required": true,
5206
+ "type": "string",
5207
+ "pattern": "tests/[^/]+"
5208
+ },
5209
+ {
5210
+ "name": "body",
5211
+ "in": "body",
5212
+ "required": true,
5213
+ "schema": {
5214
+ "type": "object",
5215
+ "properties": {
5216
+ "operation": {
5217
+ "type": "string",
5218
+ "description": "Required. The Operation processing adversarial inputs robustness testing."
5219
+ },
5220
+ "generatorInputTypes": {
5221
+ "type": "array",
5222
+ "items": {
5223
+ "$ref": "#/definitions/v1TestCasesGenerator"
5224
+ },
5225
+ "description": "Optional. The list of adversarial input types to generate."
5226
+ },
5227
+ "generatorDocumentUrls": {
5228
+ "type": "array",
5229
+ "items": {
5230
+ "type": "string"
5231
+ },
5232
+ "description": "Required. The document URLs which were used to generate the baseline TestCases."
5233
+ },
5234
+ "generatorModel": {
5235
+ "$ref": "#/definitions/v1Model",
5236
+ "description": "Required. The Model host to use for the generation of the adversarial TestCases. Currently only h2oGPTe is supported."
5237
+ },
5238
+ "generatorBaseLlmModel": {
5239
+ "type": "string",
5240
+ "description": "Required. Base LLM model to use for generation of adversarial the prompts."
5241
+ },
5242
+ "generatorCount": {
5243
+ "type": "integer",
5244
+ "format": "int64",
5245
+ "description": "Required. The number of adversarial TestCases to generate."
5246
+ },
5247
+ "generatorTopics": {
5248
+ "type": "array",
5249
+ "items": {
5250
+ "type": "string"
5251
+ },
5252
+ "description": "Optional. Topics to generate questions for. If not specified, use document summarization as\ntopic generation."
5253
+ },
5254
+ "generatorChunks": {
5255
+ "type": "array",
5256
+ "items": {
5257
+ "type": "string"
5258
+ },
5259
+ "description": "Optional. The list of chunks to use for generation. If set, the Documents assigned to the Test\nand h2ogpte_collection_id are ignored."
5260
+ },
5261
+ "generatorH2ogpteCollectionId": {
5262
+ "type": "string",
5263
+ "description": "Optional. ID of the h2oGPTe collection to use. If provided, documents referenced by\nTest and any specified chunks are ignored. This field is required if Test does not\nreference any documents and no chunks are provided. If this field is left empty, a\ntemporary collection will be created."
5264
+ },
5265
+ "evaluatorIdentifiers": {
5266
+ "type": "array",
5267
+ "items": {
5268
+ "type": "string"
5269
+ },
5270
+ "description": "Required. Evaluator identifiers to use for the model evaluation using the adversarial inputs."
5271
+ },
5272
+ "evaluatorsParameters": {
5273
+ "type": "object",
5274
+ "additionalProperties": {
5275
+ "type": "string"
5276
+ },
5277
+ "description": "Optional. Additional evaluators configuration, for all the evaluators used in the evaluation.\nKey is the evaluator identifier, and the value is a JSON string containing the configuration dictionary."
5278
+ },
5279
+ "model": {
5280
+ "$ref": "#/definitions/v1Model",
5281
+ "description": "Required. The Model host of the LLM model to be evaluated using the the adversarial inputs."
5282
+ },
5283
+ "baseLlmModel": {
5284
+ "type": "string",
5285
+ "description": "Required. Base LLM model to be evaluated using the adversarial inputs."
5286
+ },
5287
+ "modelParameters": {
5288
+ "type": "string",
5289
+ "description": "Optional. Parameters overrides for the Model host in JSON format."
5290
+ },
5291
+ "defaultH2ogpteModel": {
5292
+ "$ref": "#/definitions/v1Model",
5293
+ "description": "Optional. The default h2oGPTe Model host to be used for the evaluation e.g. by judge or agent based evaluators."
5294
+ },
5295
+ "baselineEval": {
5296
+ "type": "string",
5297
+ "description": "Required. Baseline evaluation name."
5298
+ },
5299
+ "baselineMetrics": {
5300
+ "type": "object",
5301
+ "additionalProperties": {
5302
+ "$ref": "#/definitions/v1MetricScores"
5303
+ },
5304
+ "description": "Required. Map of baseline metrics from the evaluator to the metric scores for the evaluator."
5305
+ }
5306
+ }
5307
+ }
5308
+ }
5309
+ ],
5310
+ "tags": [
5311
+ "AdversarialInputsService"
5312
+ ]
5313
+ }
5314
+ },
4648
5315
  "/v1/{workflow.name}": {
4649
5316
  "patch": {
4650
5317
  "summary": "UpdateWorkflow updates a Workflow. The update_mask is used to specify the fields to be updated.",
@@ -4768,6 +5435,19 @@
4768
5435
  "modelParameters": {
4769
5436
  "type": "string",
4770
5437
  "description": "Optional. Immutable. Model parameter overrides in JSON format."
5438
+ },
5439
+ "document": {
5440
+ "type": "string",
5441
+ "description": "The resource name of a Document."
5442
+ },
5443
+ "h2ogpteCollection": {
5444
+ "type": "string",
5445
+ "description": "Existing h2oGPTe collection."
5446
+ },
5447
+ "clonedFromWorkflow": {
5448
+ "type": "string",
5449
+ "description": "Optional. Output only. The Workflow that this Workflow was cloned from.",
5450
+ "readOnly": true
4771
5451
  }
4772
5452
  },
4773
5453
  "title": "Required. The updated Workflow."
@@ -4856,6 +5536,15 @@
4856
5536
  },
4857
5537
  "description": "The `Status` type defines a logical error model that is suitable for\ndifferent programming environments, including REST APIs and RPC APIs. It is\nused by [gRPC](https://github.com/grpc). Each `Status` message contains\nthree pieces of data: error code, error message, and error details.\n\nYou can find out more about this error model and how to work with it in the\n[API Design Guide](https://cloud.google.com/apis/design/errors)."
4858
5538
  },
5539
+ "v1AbortOperationResponse": {
5540
+ "type": "object",
5541
+ "properties": {
5542
+ "operation": {
5543
+ "$ref": "#/definitions/v1Operation",
5544
+ "description": "The updated Operation."
5545
+ }
5546
+ }
5547
+ },
4859
5548
  "v1BatchCreateLeaderboardsRequest": {
4860
5549
  "type": "object",
4861
5550
  "properties": {
@@ -5288,15 +5977,33 @@
5288
5977
  }
5289
5978
  }
5290
5979
  },
5291
- "v1CollectionInfo": {
5980
+ "v1CloneTestResponse": {
5292
5981
  "type": "object",
5293
5982
  "properties": {
5294
- "id": {
5295
- "type": "string",
5296
- "description": "Required. Collection ID."
5297
- },
5298
- "displayName": {
5299
- "type": "string",
5983
+ "test": {
5984
+ "$ref": "#/definitions/v1Test",
5985
+ "description": "The cloned Test."
5986
+ }
5987
+ }
5988
+ },
5989
+ "v1CloneWorkflowResponse": {
5990
+ "type": "object",
5991
+ "properties": {
5992
+ "workflow": {
5993
+ "$ref": "#/definitions/v1Workflow",
5994
+ "description": "The cloned Workflow."
5995
+ }
5996
+ }
5997
+ },
5998
+ "v1CollectionInfo": {
5999
+ "type": "object",
6000
+ "properties": {
6001
+ "id": {
6002
+ "type": "string",
6003
+ "description": "Required. Collection ID."
6004
+ },
6005
+ "displayName": {
6006
+ "type": "string",
5300
6007
  "description": "Required. Collection display name."
5301
6008
  },
5302
6009
  "description": {
@@ -5311,6 +6018,29 @@
5311
6018
  },
5312
6019
  "description": "CollectionInfo represents the information about a collection in the H2OGPTE."
5313
6020
  },
6021
+ "v1Context": {
6022
+ "type": "object",
6023
+ "properties": {
6024
+ "collectionId": {
6025
+ "type": "string",
6026
+ "description": "Collection Id."
6027
+ },
6028
+ "chunkId": {
6029
+ "type": "integer",
6030
+ "format": "int32",
6031
+ "description": "Chunk Id."
6032
+ },
6033
+ "score": {
6034
+ "type": "number",
6035
+ "format": "float",
6036
+ "description": "Chunk score."
6037
+ },
6038
+ "content": {
6039
+ "type": "string",
6040
+ "description": "Content."
6041
+ }
6042
+ }
6043
+ },
5314
6044
  "v1CreateDashboardResponse": {
5315
6045
  "type": "object",
5316
6046
  "properties": {
@@ -5468,6 +6198,24 @@
5468
6198
  }
5469
6199
  }
5470
6200
  },
6201
+ "v1CreateWorkflowEdgeResponse": {
6202
+ "type": "object",
6203
+ "properties": {
6204
+ "edge": {
6205
+ "$ref": "#/definitions/v1WorkflowEdge",
6206
+ "description": "The created WorkflowEdge."
6207
+ }
6208
+ }
6209
+ },
6210
+ "v1CreateWorkflowNodeResponse": {
6211
+ "type": "object",
6212
+ "properties": {
6213
+ "node": {
6214
+ "$ref": "#/definitions/v1WorkflowNode",
6215
+ "description": "The created WorkflowNode."
6216
+ }
6217
+ }
6218
+ },
5471
6219
  "v1CreateWorkflowResponse": {
5472
6220
  "type": "object",
5473
6221
  "properties": {
@@ -5624,6 +6372,15 @@
5624
6372
  }
5625
6373
  }
5626
6374
  },
6375
+ "v1DeleteWorkflowEdgeResponse": {
6376
+ "type": "object",
6377
+ "properties": {
6378
+ "edge": {
6379
+ "$ref": "#/definitions/v1WorkflowEdge",
6380
+ "description": "The deleted WorkflowEdge."
6381
+ }
6382
+ }
6383
+ },
5627
6384
  "v1DeleteWorkflowNodeResponse": {
5628
6385
  "type": "object",
5629
6386
  "properties": {
@@ -5990,6 +6747,23 @@
5990
6747
  }
5991
6748
  }
5992
6749
  },
6750
+ "v1GeneratedTestCase": {
6751
+ "type": "object",
6752
+ "properties": {
6753
+ "testCase": {
6754
+ "$ref": "#/definitions/v1TestCase",
6755
+ "description": "Test Case."
6756
+ },
6757
+ "context": {
6758
+ "type": "array",
6759
+ "items": {
6760
+ "type": "object",
6761
+ "$ref": "#/definitions/v1Context"
6762
+ },
6763
+ "description": "Context used for test_case generation."
6764
+ }
6765
+ }
6766
+ },
5993
6767
  "v1GetDashboardResponse": {
5994
6768
  "type": "object",
5995
6769
  "properties": {
@@ -6025,6 +6799,15 @@
6025
6799
  }
6026
6800
  }
6027
6801
  },
6802
+ "v1GetLeaderboardReportResponse": {
6803
+ "type": "object",
6804
+ "properties": {
6805
+ "leaderboardReport": {
6806
+ "$ref": "#/definitions/v1LeaderboardReport",
6807
+ "description": "The requested Leaderboard."
6808
+ }
6809
+ }
6810
+ },
6028
6811
  "v1GetLeaderboardResponse": {
6029
6812
  "type": "object",
6030
6813
  "properties": {
@@ -6290,6 +7073,30 @@
6290
7073
  "h2oSonarVersion": {
6291
7074
  "type": "string",
6292
7075
  "description": "The version of H2O Sonar used by the workers."
7076
+ },
7077
+ "preferredLlmsForTestGeneration": {
7078
+ "type": "array",
7079
+ "items": {
7080
+ "type": "string"
7081
+ },
7082
+ "description": "Ordered list of LLMs preferred for test generation. The value might be a regular expression."
7083
+ },
7084
+ "h2oCloudUrl": {
7085
+ "type": "string",
7086
+ "description": "The URL for the H2O Cloud host."
7087
+ },
7088
+ "publicInstance": {
7089
+ "type": "boolean",
7090
+ "description": "If the Eval Studio instance is public."
7091
+ }
7092
+ }
7093
+ },
7094
+ "v1InitWorkflowNodeResponse": {
7095
+ "type": "object",
7096
+ "properties": {
7097
+ "node": {
7098
+ "$ref": "#/definitions/v1WorkflowNode",
7099
+ "description": "The WorkflowNode that was initialized."
6293
7100
  }
6294
7101
  }
6295
7102
  },
@@ -6321,194 +7128,702 @@
6321
7128
  },
6322
7129
  "explanationType": {
6323
7130
  "type": "string",
6324
- "description": "Type of the explanation."
7131
+ "description": "Type of the explanation."
7132
+ },
7133
+ "explanationName": {
7134
+ "type": "string",
7135
+ "description": "Name of the explanation."
7136
+ },
7137
+ "explanationMime": {
7138
+ "type": "string",
7139
+ "description": "MIME type of the explanation."
7140
+ },
7141
+ "resources": {
7142
+ "type": "array",
7143
+ "items": {
7144
+ "type": "string"
7145
+ },
7146
+ "description": "List of resources that can be used to take actions based on the insight."
7147
+ },
7148
+ "insightType": {
7149
+ "type": "string",
7150
+ "description": "Type of the insight."
7151
+ },
7152
+ "insightAttrs": {
7153
+ "type": "object",
7154
+ "additionalProperties": {
7155
+ "type": "string"
7156
+ },
7157
+ "description": "Attributes of the insight."
7158
+ }
7159
+ },
7160
+ "description": "Insight represents additional information about the evaluation."
7161
+ },
7162
+ "v1LabeledTestCase": {
7163
+ "type": "object",
7164
+ "properties": {
7165
+ "name": {
7166
+ "type": "string",
7167
+ "description": "Required. The test case resource name."
7168
+ },
7169
+ "metricValue": {
7170
+ "type": "number",
7171
+ "format": "float",
7172
+ "description": "Required. The metric value."
7173
+ },
7174
+ "label": {
7175
+ "type": "boolean",
7176
+ "description": "Required. Human label. True means the test case should be labeled as passed (positive), false means failed (negative)."
7177
+ }
7178
+ }
7179
+ },
7180
+ "v1Leaderboard": {
7181
+ "type": "object",
7182
+ "properties": {
7183
+ "name": {
7184
+ "type": "string",
7185
+ "title": "Output only. Name of the Leaderboard resource. e.g.: \"leaderboards/\u003cUUID\u003e\"",
7186
+ "readOnly": true
7187
+ },
7188
+ "createTime": {
7189
+ "type": "string",
7190
+ "format": "date-time",
7191
+ "description": "Output only. Timestamp when the Leaderboard was created.",
7192
+ "readOnly": true
7193
+ },
7194
+ "creator": {
7195
+ "type": "string",
7196
+ "description": "Output only. Name of the user or service that requested creation of the Leaderboard.",
7197
+ "readOnly": true
7198
+ },
7199
+ "updateTime": {
7200
+ "type": "string",
7201
+ "format": "date-time",
7202
+ "description": "Output only. Optional. Timestamp when the Leaderboard was last updated.",
7203
+ "readOnly": true
7204
+ },
7205
+ "updater": {
7206
+ "type": "string",
7207
+ "description": "Output only. Optional. Name of the user or service that requested update of the Leaderboard.",
7208
+ "readOnly": true
7209
+ },
7210
+ "deleteTime": {
7211
+ "type": "string",
7212
+ "format": "date-time",
7213
+ "description": "Output only. Optional. Set when the Leaderboard is deleted. When set Leaderboard should be\nconsidered as deleted.",
7214
+ "readOnly": true
7215
+ },
7216
+ "deleter": {
7217
+ "type": "string",
7218
+ "description": "Output only. Optional. Name of the user or service that requested deletion of the Leaderboard.",
7219
+ "readOnly": true
7220
+ },
7221
+ "displayName": {
7222
+ "type": "string",
7223
+ "description": "Human readable name of the Leaderboard."
7224
+ },
7225
+ "description": {
7226
+ "type": "string",
7227
+ "description": "Optional. Arbitrary description of the Leaderboard."
7228
+ },
7229
+ "status": {
7230
+ "$ref": "#/definitions/v1LeaderboardStatus",
7231
+ "description": "Output only. Status of the Leaderboard. When set to LEADERBOARD_STATUS_COMPLETED, the result\nfield is populated.",
7232
+ "readOnly": true
7233
+ },
7234
+ "evaluator": {
7235
+ "type": "string",
7236
+ "description": "Immutable. Resource name of the Evaluator used in this Leaderboard."
7237
+ },
7238
+ "tests": {
7239
+ "type": "array",
7240
+ "items": {
7241
+ "type": "string"
7242
+ },
7243
+ "description": "Immutable. Resource names of the Tests used in this Leaderboard."
7244
+ },
7245
+ "model": {
7246
+ "type": "string",
7247
+ "description": "Immutable. Resource name of the Model used in this Leaderboard."
7248
+ },
7249
+ "createOperation": {
7250
+ "type": "string",
7251
+ "description": "Output only. Operation resource name that created this Leaderboard.",
7252
+ "readOnly": true
7253
+ },
7254
+ "leaderboardReport": {
7255
+ "type": "string",
7256
+ "title": "Deprecated. Reserve Name of the Leaderboard resource. e.g.: \"content/leaderboards/\u003cUUID\u003e\""
7257
+ },
7258
+ "leaderboardTable": {
7259
+ "type": "string",
7260
+ "description": "Output only. Leaderboard table in JSON format.",
7261
+ "readOnly": true
7262
+ },
7263
+ "leaderboardSummary": {
7264
+ "type": "string",
7265
+ "description": "Output only. Leaderboard summary in Markdown format.",
7266
+ "readOnly": true
7267
+ },
7268
+ "llmModels": {
7269
+ "type": "array",
7270
+ "items": {
7271
+ "type": "string"
7272
+ },
7273
+ "description": "Immutable. System names of the LLM models used in this Leaderboard."
7274
+ },
7275
+ "leaderboardProblems": {
7276
+ "type": "array",
7277
+ "items": {
7278
+ "type": "object",
7279
+ "$ref": "#/definitions/v1ProblemAndAction"
7280
+ },
7281
+ "description": "Output only. Leaderboard problems and actions.",
7282
+ "readOnly": true
7283
+ },
7284
+ "evaluatorParameters": {
7285
+ "type": "string",
7286
+ "description": "Optional. Evaluator parameters setup."
7287
+ },
7288
+ "insights": {
7289
+ "type": "array",
7290
+ "items": {
7291
+ "type": "object",
7292
+ "$ref": "#/definitions/v1Insight"
7293
+ },
7294
+ "description": "Output only. Insights from the Leaderboard.",
7295
+ "readOnly": true
7296
+ },
7297
+ "modelParameters": {
7298
+ "type": "string",
7299
+ "description": "Optional. Prameters overrides in JSON format."
7300
+ },
7301
+ "h2ogpteCollection": {
7302
+ "type": "string",
7303
+ "description": "The existing collection name in H2OGPTe."
7304
+ },
7305
+ "type": {
7306
+ "$ref": "#/definitions/v1LeaderboardType",
7307
+ "description": "Optional. Type of the leaderboard. Defaults to LEADERBOARD_TYPE_STANDALONE for\nCreateLeaderboard and CreateLeaderboardWithoutCache. Defaults to LEADERBOARD_TYPE_DASHBOARD for\nBatchCreateLeaderboards."
7308
+ },
7309
+ "demo": {
7310
+ "type": "boolean",
7311
+ "description": "Output only. Whether the Leaderboard is a demo resource or not. Demo resources are read only.",
7312
+ "readOnly": true
7313
+ },
7314
+ "testLab": {
7315
+ "type": "string",
7316
+ "description": "Optional. Resource name of the TestLab if Leaderboard was created from a imported TestLab."
7317
+ }
7318
+ }
7319
+ },
7320
+ "v1LeaderboardReport": {
7321
+ "type": "object",
7322
+ "properties": {
7323
+ "results": {
7324
+ "type": "array",
7325
+ "items": {
7326
+ "type": "object",
7327
+ "$ref": "#/definitions/v1LeaderboardReportResult"
7328
+ },
7329
+ "description": "Output only. List of per test case results.",
7330
+ "readOnly": true
7331
+ },
7332
+ "models": {
7333
+ "type": "array",
7334
+ "items": {
7335
+ "type": "object",
7336
+ "$ref": "#/definitions/v1LeaderboardReportModel"
7337
+ },
7338
+ "description": "Output only. List of models which were used to create the results.",
7339
+ "readOnly": true
7340
+ },
7341
+ "evaluator": {
7342
+ "$ref": "#/definitions/v1LeaderboardReportEvaluator",
7343
+ "description": "Output only. Details of the evaluator which evaluated the model outputs to create the results.",
7344
+ "readOnly": true
7345
+ }
7346
+ },
7347
+ "description": "LeaderboardReport represents the leaderboard report which is formed by the results, models and evaluator."
7348
+ },
7349
+ "v1LeaderboardReportActualOutputData": {
7350
+ "type": "object",
7351
+ "properties": {
7352
+ "text": {
7353
+ "type": "string",
7354
+ "description": "Output only. Text fragment.",
7355
+ "readOnly": true
7356
+ },
7357
+ "metrics": {
7358
+ "type": "object",
7359
+ "description": "Output only. Metrics parsed as string to Value map.",
7360
+ "readOnly": true
7361
+ }
7362
+ },
7363
+ "description": "ActualOutputData represents the actual output data."
7364
+ },
7365
+ "v1LeaderboardReportActualOutputMeta": {
7366
+ "type": "object",
7367
+ "properties": {
7368
+ "tokenization": {
7369
+ "type": "string",
7370
+ "description": "Output only. Actual output data tokenization like sentence_level_punkt.",
7371
+ "readOnly": true
7372
+ },
7373
+ "data": {
7374
+ "type": "array",
7375
+ "items": {
7376
+ "type": "object",
7377
+ "$ref": "#/definitions/v1LeaderboardReportActualOutputData"
7378
+ },
7379
+ "description": "Output only. Actual output data - list of text fragments coupled with the metric values.",
7380
+ "readOnly": true
7381
+ }
7382
+ },
7383
+ "description": "ActualOutputMeta represents the metadata about the actual output."
7384
+ },
7385
+ "v1LeaderboardReportEvaluator": {
7386
+ "type": "object",
7387
+ "properties": {
7388
+ "id": {
7389
+ "type": "string",
7390
+ "description": "Output only. Evaluator ID.",
7391
+ "readOnly": true
7392
+ },
7393
+ "name": {
7394
+ "type": "string",
7395
+ "description": "Output only. Evaluator short name based on its class name.",
7396
+ "readOnly": true
7397
+ },
7398
+ "displayName": {
7399
+ "type": "string",
7400
+ "description": "Output only. Evaluator display name.",
7401
+ "readOnly": true
7402
+ },
7403
+ "tagline": {
7404
+ "type": "string",
7405
+ "description": "Optional. Evaluator one row description."
7406
+ },
7407
+ "description": {
7408
+ "type": "string",
7409
+ "description": "Output only. Evaluator description.",
7410
+ "readOnly": true
7411
+ },
7412
+ "briefDescription": {
7413
+ "type": "string",
7414
+ "description": "Optional. Brief description."
7415
+ },
7416
+ "modelTypes": {
7417
+ "type": "array",
7418
+ "items": {
7419
+ "type": "string"
7420
+ },
7421
+ "description": "Output only. List of model types like rag.",
7422
+ "readOnly": true
7423
+ },
7424
+ "canExplain": {
7425
+ "type": "array",
7426
+ "items": {
7427
+ "type": "string"
7428
+ },
7429
+ "description": "Optional. List of experiment types the Explainer can explain like regression or multinomial."
7430
+ },
7431
+ "explanationScopes": {
7432
+ "type": "array",
7433
+ "items": {
7434
+ "type": "string"
7435
+ },
7436
+ "description": "Output only. List of explanation scopes like global or local.",
7437
+ "readOnly": true
7438
+ },
7439
+ "explanations": {
7440
+ "type": "array",
7441
+ "items": {
7442
+ "type": "object",
7443
+ "$ref": "#/definitions/v1LeaderboardReportExplanation"
7444
+ },
7445
+ "description": "Output only. List of explanation types created by the Evaluator.",
7446
+ "readOnly": true
7447
+ },
7448
+ "parameters": {
7449
+ "type": "array",
7450
+ "items": {
7451
+ "type": "object",
7452
+ "$ref": "#/definitions/v1LeaderboardReportEvaluatorParameter"
7453
+ },
7454
+ "description": "Output only. List of parameter type definitions.",
7455
+ "readOnly": true
7456
+ },
7457
+ "keywords": {
7458
+ "type": "array",
7459
+ "items": {
7460
+ "type": "string"
7461
+ },
7462
+ "description": "Output only. List of keywords.",
7463
+ "readOnly": true
7464
+ },
7465
+ "metricsMeta": {
7466
+ "type": "array",
7467
+ "items": {
7468
+ "type": "object",
7469
+ "$ref": "#/definitions/v1LeaderboardReportMetricsMetaEntry"
7470
+ },
7471
+ "description": "Output only. List of metrics metadata for metrics created by the Evaluator.",
7472
+ "readOnly": true
7473
+ }
7474
+ },
7475
+ "description": "Evaluator represents the evaluator which evaluated the model outputs to create the results."
7476
+ },
7477
+ "v1LeaderboardReportEvaluatorParameter": {
7478
+ "type": "object",
7479
+ "properties": {
7480
+ "name": {
7481
+ "type": "string",
7482
+ "description": "Output only. Evaluator parameter ID.",
7483
+ "readOnly": true
7484
+ },
7485
+ "description": {
7486
+ "type": "string",
7487
+ "description": "Output only. Parameter description.",
7488
+ "readOnly": true
7489
+ },
7490
+ "comment": {
7491
+ "type": "string",
7492
+ "description": "Optional. Parameter comment."
7493
+ },
7494
+ "type": {
7495
+ "type": "string",
7496
+ "description": "Output only. Parameter type like float or string.",
7497
+ "readOnly": true
7498
+ },
7499
+ "predefined": {
7500
+ "type": "array",
7501
+ "items": {},
7502
+ "description": "Optional. Predefined parameter values - numeric or non-numeric enum."
7503
+ },
7504
+ "tags": {
7505
+ "type": "array",
7506
+ "items": {
7507
+ "type": "string"
7508
+ },
7509
+ "description": "Optional. Parameter tags."
7510
+ },
7511
+ "min": {
7512
+ "type": "number",
7513
+ "format": "double",
7514
+ "description": "Optional. Parameter value lower range."
7515
+ },
7516
+ "max": {
7517
+ "type": "number",
7518
+ "format": "double",
7519
+ "description": "Optional. Parameter value upper range."
7520
+ },
7521
+ "category": {
7522
+ "type": "string",
7523
+ "description": "Optional. Parameter category."
7524
+ }
7525
+ },
7526
+ "description": "Evaluation parameter definition."
7527
+ },
7528
+ "v1LeaderboardReportExplanation": {
7529
+ "type": "object",
7530
+ "properties": {
7531
+ "explanationType": {
7532
+ "type": "string",
7533
+ "description": "Output only. Explanation type ID.",
7534
+ "readOnly": true
7535
+ },
7536
+ "name": {
7537
+ "type": "string",
7538
+ "description": "Output only. Explanation display name.",
7539
+ "readOnly": true
7540
+ },
7541
+ "category": {
7542
+ "type": "string",
7543
+ "description": "Output only. Explanation display category.",
7544
+ "readOnly": true
7545
+ },
7546
+ "scope": {
7547
+ "type": "string",
7548
+ "description": "Optional. Explanation scope like global or local."
7549
+ },
7550
+ "hasLocal": {
7551
+ "type": "string",
7552
+ "description": "Optional. Local explanation type id associated with (this) global explanation."
7553
+ },
7554
+ "formats": {
7555
+ "type": "array",
7556
+ "items": {
7557
+ "type": "string"
7558
+ },
7559
+ "description": "Optional. List of formats available for the explanation."
7560
+ }
7561
+ }
7562
+ },
7563
+ "v1LeaderboardReportMetricsMetaEntry": {
7564
+ "type": "object",
7565
+ "properties": {
7566
+ "key": {
7567
+ "type": "string",
7568
+ "description": "Output only. Metric key.",
7569
+ "readOnly": true
7570
+ },
7571
+ "displayName": {
7572
+ "type": "string",
7573
+ "description": "Output only. Metric display name.",
7574
+ "readOnly": true
7575
+ },
7576
+ "dataType": {
7577
+ "type": "string",
7578
+ "description": "Output only. Metric data type like float or string.",
7579
+ "readOnly": true
6325
7580
  },
6326
- "explanationName": {
7581
+ "displayValue": {
6327
7582
  "type": "string",
6328
- "description": "Name of the explanation."
7583
+ "description": "Output only. Metric display value.",
7584
+ "readOnly": true
6329
7585
  },
6330
- "explanationMime": {
7586
+ "description": {
6331
7587
  "type": "string",
6332
- "description": "MIME type of the explanation."
7588
+ "description": "Output only. Metric description.",
7589
+ "readOnly": true
6333
7590
  },
6334
- "resources": {
7591
+ "valueRange": {
6335
7592
  "type": "array",
6336
7593
  "items": {
6337
- "type": "string"
7594
+ "type": "number",
7595
+ "format": "double"
6338
7596
  },
6339
- "description": "List of resources that can be used to take actions based on the insight."
6340
- },
6341
- "insightType": {
6342
- "type": "string",
6343
- "description": "Type of the insight."
7597
+ "description": "Optional. Metric value range for numeric scores."
6344
7598
  },
6345
- "insightAttrs": {
6346
- "type": "object",
6347
- "additionalProperties": {
7599
+ "valueEnum": {
7600
+ "type": "array",
7601
+ "items": {
6348
7602
  "type": "string"
6349
7603
  },
6350
- "description": "Attributes of the insight."
6351
- }
6352
- },
6353
- "description": "Insight represents additional information about the evaluation."
6354
- },
6355
- "v1LabeledTestCase": {
6356
- "type": "object",
6357
- "properties": {
6358
- "name": {
6359
- "type": "string",
6360
- "description": "Required. The test case resource name."
7604
+ "description": "Optional. Metric value enum for non-numeric scores."
6361
7605
  },
6362
- "metricValue": {
7606
+ "higherIsBetter": {
7607
+ "type": "boolean",
7608
+ "description": "Output only. Metric higher is better.",
7609
+ "readOnly": true
7610
+ },
7611
+ "threshold": {
6363
7612
  "type": "number",
6364
- "format": "float",
6365
- "description": "Required. The metric value."
7613
+ "format": "double",
7614
+ "description": "Output only. Metric threshold.",
7615
+ "readOnly": true
6366
7616
  },
6367
- "label": {
7617
+ "isPrimaryMetric": {
6368
7618
  "type": "boolean",
6369
- "description": "Required. Human label. True means the test case should be labeled as passed (positive), false means failed (negative)."
7619
+ "description": "Output only. Metric is primary.",
7620
+ "readOnly": true
7621
+ },
7622
+ "parentMetric": {
7623
+ "type": "string",
7624
+ "description": "Output only. This metric parent.",
7625
+ "readOnly": true
7626
+ },
7627
+ "exclude": {
7628
+ "type": "boolean",
7629
+ "description": "Output only. Whether to exclude the metric.",
7630
+ "readOnly": true
6370
7631
  }
6371
- }
7632
+ },
7633
+ "description": "MetricsMetaEntry represents the metadata about the metric."
6372
7634
  },
6373
- "v1Leaderboard": {
7635
+ "v1LeaderboardReportModel": {
6374
7636
  "type": "object",
6375
7637
  "properties": {
6376
- "name": {
7638
+ "connection": {
6377
7639
  "type": "string",
6378
- "title": "Output only. Name of the Leaderboard resource. e.g.: \"leaderboards/\u003cUUID\u003e\"",
7640
+ "description": "Output only. Connection key.",
6379
7641
  "readOnly": true
6380
7642
  },
6381
- "createTime": {
7643
+ "modelType": {
6382
7644
  "type": "string",
6383
- "format": "date-time",
6384
- "description": "Output only. Timestamp when the Leaderboard was created.",
7645
+ "description": "Output only. Model type.",
6385
7646
  "readOnly": true
6386
7647
  },
6387
- "creator": {
7648
+ "name": {
6388
7649
  "type": "string",
6389
- "description": "Output only. Name of the user or service that requested creation of the Leaderboard.",
7650
+ "description": "Output only. Model display name.",
6390
7651
  "readOnly": true
6391
7652
  },
6392
- "updateTime": {
7653
+ "collectionId": {
6393
7654
  "type": "string",
6394
- "format": "date-time",
6395
- "description": "Output only. Optional. Timestamp when the Leaderboard was last updated.",
6396
- "readOnly": true
7655
+ "description": "Optional. Collection ID."
6397
7656
  },
6398
- "updater": {
7657
+ "collectionName": {
6399
7658
  "type": "string",
6400
- "description": "Output only. Optional. Name of the user or service that requested update of the Leaderboard.",
6401
- "readOnly": true
7659
+ "description": "Optional. Collection name."
6402
7660
  },
6403
- "deleteTime": {
7661
+ "llmModelName": {
6404
7662
  "type": "string",
6405
- "format": "date-time",
6406
- "description": "Output only. Optional. Set when the Leaderboard is deleted. When set Leaderboard should be\nconsidered as deleted.",
7663
+ "description": "Output only. LLM model name.",
6407
7664
  "readOnly": true
6408
7665
  },
6409
- "deleter": {
7666
+ "documents": {
7667
+ "type": "array",
7668
+ "items": {
7669
+ "type": "string"
7670
+ },
7671
+ "description": "Output only. List of documents.",
7672
+ "readOnly": true
7673
+ },
7674
+ "modelCfg": {
7675
+ "type": "object",
7676
+ "description": "Output only. Model configuration.",
7677
+ "readOnly": true
7678
+ },
7679
+ "key": {
6410
7680
  "type": "string",
6411
- "description": "Output only. Optional. Name of the user or service that requested deletion of the Leaderboard.",
7681
+ "description": "Output only. Model key.",
6412
7682
  "readOnly": true
6413
7683
  },
6414
- "displayName": {
7684
+ "llmModelMeta": {
7685
+ "type": "object",
7686
+ "description": "Output only. LLM model metadata - recursive dictionaries with an additional info like performance stats.",
7687
+ "readOnly": true
7688
+ }
7689
+ },
7690
+ "description": "Model represents the evaluated model whose outputs were evaluated to create the results."
7691
+ },
7692
+ "v1LeaderboardReportResult": {
7693
+ "type": "object",
7694
+ "properties": {
7695
+ "key": {
6415
7696
  "type": "string",
6416
- "description": "Human readable name of the Leaderboard."
7697
+ "description": "Output only. Composite unique key of the result formed by the model key and test case key.",
7698
+ "readOnly": true
6417
7699
  },
6418
- "description": {
7700
+ "input": {
6419
7701
  "type": "string",
6420
- "description": "Optional. Arbitrary description of the Leaderboard."
7702
+ "description": "Output only. Input prompt or text to be processed.",
7703
+ "readOnly": true
6421
7704
  },
6422
- "status": {
6423
- "$ref": "#/definitions/v1LeaderboardStatus",
6424
- "description": "Output only. Status of the Leaderboard. When set to LEADERBOARD_STATUS_COMPLETED, the result\nfield is populated.",
7705
+ "corpus": {
7706
+ "type": "array",
7707
+ "items": {
7708
+ "type": "string"
7709
+ },
7710
+ "description": "Output only. Collection of corpus documents to be used during evaluation.",
6425
7711
  "readOnly": true
6426
7712
  },
6427
- "evaluator": {
6428
- "type": "string",
6429
- "description": "Immutable. Resource name of the Evaluator used in this Leaderboard."
7713
+ "context": {
7714
+ "type": "array",
7715
+ "items": {
7716
+ "type": "string"
7717
+ },
7718
+ "description": "Output only. List of contextual information or references.",
7719
+ "readOnly": true
6430
7720
  },
6431
- "tests": {
7721
+ "categories": {
6432
7722
  "type": "array",
6433
7723
  "items": {
6434
7724
  "type": "string"
6435
7725
  },
6436
- "description": "Immutable. Resource names of the Tests used in this Leaderboard."
7726
+ "description": "Output only. List of categories or labels for classification.",
7727
+ "readOnly": true
6437
7728
  },
6438
- "model": {
6439
- "type": "string",
6440
- "description": "Immutable. Resource name of the Model used in this Leaderboard."
7729
+ "relationships": {
7730
+ "type": "array",
7731
+ "items": {
7732
+ "type": "object",
7733
+ "$ref": "#/definitions/v1LeaderboardReportResultRelationship"
7734
+ },
7735
+ "description": "Output only. List of relationships or associations between entities.",
7736
+ "readOnly": true
6441
7737
  },
6442
- "createOperation": {
7738
+ "expectedOutput": {
6443
7739
  "type": "string",
6444
- "description": "Output only. Operation resource name that created this Leaderboard.",
7740
+ "description": "Output only. Expected output or target result.",
6445
7741
  "readOnly": true
6446
7742
  },
6447
- "leaderboardReport": {
7743
+ "outputConstraints": {
7744
+ "type": "array",
7745
+ "items": {
7746
+ "type": "string"
7747
+ },
7748
+ "description": "Output only. List of constraints that should be applied to the output.",
7749
+ "readOnly": true
7750
+ },
7751
+ "outputCondition": {
6448
7752
  "type": "string",
6449
- "title": "Deprecated. Reserve Name of the Leaderboard resource. e.g.: \"content/leaderboards/\u003cUUID\u003e\""
7753
+ "description": "Output only. Condition that output should satisfy.",
7754
+ "readOnly": true
6450
7755
  },
6451
- "leaderboardTable": {
7756
+ "actualOutput": {
6452
7757
  "type": "string",
6453
- "description": "Output only. Leaderboard table in JSON format.",
7758
+ "description": "Output only. Actual output produced by the model.",
6454
7759
  "readOnly": true
6455
7760
  },
6456
- "leaderboardSummary": {
7761
+ "actualDuration": {
7762
+ "type": "number",
7763
+ "format": "double",
7764
+ "description": "Output only. Duration of processing in seconds.",
7765
+ "readOnly": true
7766
+ },
7767
+ "cost": {
7768
+ "type": "number",
7769
+ "format": "double",
7770
+ "description": "Output only. Cost of processing in currency units.",
7771
+ "readOnly": true
7772
+ },
7773
+ "modelKey": {
6457
7774
  "type": "string",
6458
- "description": "Output only. Leaderboard summary in Markdown format.",
7775
+ "description": "Output only. Unique identifier for the model used.",
6459
7776
  "readOnly": true
6460
7777
  },
6461
- "llmModels": {
6462
- "type": "array",
6463
- "items": {
6464
- "type": "string"
6465
- },
6466
- "description": "Immutable. System names of the LLM models used in this Leaderboard."
7778
+ "testCaseKey": {
7779
+ "type": "string",
7780
+ "description": "Output only. Unique identifier for the test case.",
7781
+ "readOnly": true
6467
7782
  },
6468
- "leaderboardProblems": {
7783
+ "metrics": {
6469
7784
  "type": "array",
6470
7785
  "items": {
6471
7786
  "type": "object",
6472
- "$ref": "#/definitions/v1ProblemAndAction"
7787
+ "$ref": "#/definitions/v1MetricScore"
6473
7788
  },
6474
- "description": "Output only. Leaderboard problems and actions.",
6475
- "readOnly": true
7789
+ "description": "Optional. All metrics values for the result."
6476
7790
  },
6477
- "evaluatorParameters": {
7791
+ "resultErrorMessage": {
6478
7792
  "type": "string",
6479
- "description": "Optional. Evaluator parameters setup."
7793
+ "description": "Output only. Error message if processing resulted in failure.",
7794
+ "readOnly": true
6480
7795
  },
6481
- "insights": {
7796
+ "actualOutputMeta": {
6482
7797
  "type": "array",
6483
7798
  "items": {
6484
7799
  "type": "object",
6485
- "$ref": "#/definitions/v1Insight"
7800
+ "$ref": "#/definitions/v1LeaderboardReportActualOutputMeta"
6486
7801
  },
6487
- "description": "Output only. Insights from the Leaderboard.",
7802
+ "description": "Output only. Additional metadata about the actual output.",
6488
7803
  "readOnly": true
6489
- },
6490
- "modelParameters": {
7804
+ }
7805
+ }
7806
+ },
7807
+ "v1LeaderboardReportResultRelationship": {
7808
+ "type": "object",
7809
+ "properties": {
7810
+ "type": {
6491
7811
  "type": "string",
6492
- "description": "Optional. Prameters overrides in JSON format."
7812
+ "description": "Output only. Type of the relationship.",
7813
+ "readOnly": true
6493
7814
  },
6494
- "h2ogpteCollection": {
7815
+ "target": {
6495
7816
  "type": "string",
6496
- "description": "The existing collection name in H2OGPTe."
6497
- },
6498
- "type": {
6499
- "$ref": "#/definitions/v1LeaderboardType",
6500
- "description": "Optional. Type of the leaderboard. Defaults to LEADERBOARD_TYPE_STANDALONE for\nCreateLeaderboard and CreateLeaderboardWithoutCache. Defaults to LEADERBOARD_TYPE_DASHBOARD for\nBatchCreateLeaderboards."
6501
- },
6502
- "demo": {
6503
- "type": "boolean",
6504
- "description": "Output only. Whether the Leaderboard is a demo resource or not. Demo resources are read only.",
7817
+ "description": "Output only. Source result of the relationship.",
6505
7818
  "readOnly": true
6506
7819
  },
6507
- "testLab": {
7820
+ "targetType": {
6508
7821
  "type": "string",
6509
- "description": "Optional. Resource name of the TestLab if Leaderboard was created from a imported TestLab."
7822
+ "description": "Output only. Target type of the relationship like test_case.",
7823
+ "readOnly": true
6510
7824
  }
6511
- }
7825
+ },
7826
+ "description": "Relationship represents the relationship between result entries."
6512
7827
  },
6513
7828
  "v1LeaderboardStatus": {
6514
7829
  "type": "string",
@@ -6767,6 +8082,19 @@
6767
8082
  }
6768
8083
  }
6769
8084
  },
8085
+ "v1ListTestCaseRelationshipsResponse": {
8086
+ "type": "object",
8087
+ "properties": {
8088
+ "testCaseRelationships": {
8089
+ "type": "array",
8090
+ "items": {
8091
+ "type": "object",
8092
+ "$ref": "#/definitions/v1TestCaseRelationship"
8093
+ },
8094
+ "description": "The TestCaseRelationships that were requested."
8095
+ }
8096
+ }
8097
+ },
6770
8098
  "v1ListTestCasesResponse": {
6771
8099
  "type": "object",
6772
8100
  "properties": {
@@ -6819,6 +8147,34 @@
6819
8147
  }
6820
8148
  }
6821
8149
  },
8150
+ "v1MetricScore": {
8151
+ "type": "object",
8152
+ "properties": {
8153
+ "key": {
8154
+ "type": "string",
8155
+ "description": "Required. Metric key."
8156
+ },
8157
+ "value": {
8158
+ "type": "number",
8159
+ "format": "double",
8160
+ "description": "Required. Metric value - consider NaN, Infinity or -Infinity for float representation."
8161
+ }
8162
+ },
8163
+ "description": "MetricScore represents the metric score."
8164
+ },
8165
+ "v1MetricScores": {
8166
+ "type": "object",
8167
+ "properties": {
8168
+ "scores": {
8169
+ "type": "array",
8170
+ "items": {
8171
+ "type": "object",
8172
+ "$ref": "#/definitions/v1MetricScore"
8173
+ },
8174
+ "description": "Required. The metric scores."
8175
+ }
8176
+ }
8177
+ },
6822
8178
  "v1Model": {
6823
8179
  "type": "object",
6824
8180
  "properties": {
@@ -6994,6 +8350,15 @@
6994
8350
  }
6995
8351
  }
6996
8352
  },
8353
+ "v1PerturbTestInPlaceResponse": {
8354
+ "type": "object",
8355
+ "properties": {
8356
+ "test": {
8357
+ "$ref": "#/definitions/v1Test",
8358
+ "description": "The perturbed Test."
8359
+ }
8360
+ }
8361
+ },
6997
8362
  "v1PerturbTestResponse": {
6998
8363
  "type": "object",
6999
8364
  "properties": {
@@ -7247,6 +8612,26 @@
7247
8612
  }
7248
8613
  }
7249
8614
  },
8615
+ "v1RepeatedString": {
8616
+ "type": "object",
8617
+ "properties": {
8618
+ "content": {
8619
+ "type": "array",
8620
+ "items": {
8621
+ "type": "string"
8622
+ }
8623
+ }
8624
+ }
8625
+ },
8626
+ "v1ResetWorkflowNodeResponse": {
8627
+ "type": "object",
8628
+ "properties": {
8629
+ "node": {
8630
+ "$ref": "#/definitions/v1WorkflowNode",
8631
+ "description": "The WorkflowNode that was reset."
8632
+ }
8633
+ }
8634
+ },
7250
8635
  "v1Test": {
7251
8636
  "type": "object",
7252
8637
  "properties": {
@@ -7388,6 +8773,19 @@
7388
8773
  },
7389
8774
  "description": "Output only. The list of perturbators applied to this test case.",
7390
8775
  "readOnly": true
8776
+ },
8777
+ "topics": {
8778
+ "type": "array",
8779
+ "items": {
8780
+ "type": "string"
8781
+ },
8782
+ "description": "Output only. The list of topics used to generate this test case.",
8783
+ "readOnly": true
8784
+ },
8785
+ "generator": {
8786
+ "$ref": "#/definitions/v1TestCasesGenerator",
8787
+ "description": "Output only. Optional. Test case generator that was used to generate this test case.",
8788
+ "readOnly": true
7391
8789
  }
7392
8790
  }
7393
8791
  },
@@ -7797,6 +9195,19 @@
7797
9195
  "modelParameters": {
7798
9196
  "type": "string",
7799
9197
  "description": "Optional. Immutable. Model parameter overrides in JSON format."
9198
+ },
9199
+ "document": {
9200
+ "type": "string",
9201
+ "description": "The resource name of a Document."
9202
+ },
9203
+ "h2ogpteCollection": {
9204
+ "type": "string",
9205
+ "description": "Existing h2oGPTe collection."
9206
+ },
9207
+ "clonedFromWorkflow": {
9208
+ "type": "string",
9209
+ "description": "Optional. Output only. The Workflow that this Workflow was cloned from.",
9210
+ "readOnly": true
7800
9211
  }
7801
9212
  },
7802
9213
  "description": "Workflow represents a workflow in Eval Studio. It consists of WorkflowNodes and WorkflowEdges."
@@ -8067,7 +9478,10 @@
8067
9478
  "WORKFLOW_NODE_TYPE_TEST_GENERATION",
8068
9479
  "WORKFLOW_NODE_TYPE_PERTURBATION",
8069
9480
  "WORKFLOW_NODE_TYPE_AUTOMATED_EVALUATION",
8070
- "WORKFLOW_NODE_TYPE_HUMAN_EVALUATION"
9481
+ "WORKFLOW_NODE_TYPE_HUMAN_EVALUATION",
9482
+ "WORKFLOW_NODE_TYPE_MARGINAL_ANALYSIS",
9483
+ "WORKFLOW_NODE_TYPE_VALIDATION",
9484
+ "WORKFLOW_NODE_TYPE_ADVERSARIAL_INPUTS"
8071
9485
  ],
8072
9486
  "default": "WORKFLOW_NODE_TYPE_UNSPECIFIED",
8073
9487
  "description": "WorkflowNodeType represents the type of a WorkflowNode."