eval-studio-client 1.2.4a2__py3-none-any.whl → 1.3.0__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 (306) hide show
  1. eval_studio_client/api/__init__.py +65 -0
  2. eval_studio_client/api/api/__init__.py +3 -0
  3. eval_studio_client/api/api/dashboard_report_service_api.py +292 -0
  4. eval_studio_client/api/api/dashboard_service_api.py +16 -16
  5. eval_studio_client/api/api/dashboard_test_case_annotation_service_api.py +611 -0
  6. eval_studio_client/api/api/document_service_api.py +16 -16
  7. eval_studio_client/api/api/evaluation_service_api.py +12 -12
  8. eval_studio_client/api/api/evaluator_service_api.py +16 -16
  9. eval_studio_client/api/api/leaderboard_report_service_api.py +304 -17
  10. eval_studio_client/api/api/leaderboard_service_api.py +554 -16
  11. eval_studio_client/api/api/leaderboard_test_case_annotation_service_api.py +611 -0
  12. eval_studio_client/api/api/model_service_api.py +16 -16
  13. eval_studio_client/api/api/operation_service_api.py +821 -17
  14. eval_studio_client/api/api/perturbator_service_api.py +22 -22
  15. eval_studio_client/api/api/test_case_service_api.py +300 -16
  16. eval_studio_client/api/api/test_class_service_api.py +16 -16
  17. eval_studio_client/api/api/test_service_api.py +285 -16
  18. eval_studio_client/api/api/workflow_node_service_api.py +16 -16
  19. eval_studio_client/api/api/workflow_service_api.py +16 -16
  20. eval_studio_client/api/docs/AdversarialInputsServiceTestAdversarialInputsRobustnessRequest.md +2 -1
  21. eval_studio_client/api/docs/DashboardReportServiceApi.md +75 -0
  22. eval_studio_client/api/docs/DashboardServiceApi.md +5 -5
  23. eval_studio_client/api/docs/DashboardTestCaseAnnotationServiceApi.md +149 -0
  24. eval_studio_client/api/docs/DocumentServiceApi.md +5 -5
  25. eval_studio_client/api/docs/EvaluationServiceApi.md +4 -4
  26. eval_studio_client/api/docs/EvaluatorServiceApi.md +5 -5
  27. eval_studio_client/api/docs/LeaderboardReportServiceApi.md +75 -5
  28. eval_studio_client/api/docs/LeaderboardServiceApi.md +141 -5
  29. eval_studio_client/api/docs/LeaderboardTestCaseAnnotationServiceApi.md +149 -0
  30. eval_studio_client/api/docs/ModelServiceApi.md +5 -5
  31. eval_studio_client/api/docs/OperationServiceApi.md +215 -8
  32. eval_studio_client/api/docs/PerturbatorServiceApi.md +7 -7
  33. eval_studio_client/api/docs/RequiredTheDashboardTestCaseAnnotationToUpdate.md +35 -0
  34. eval_studio_client/api/docs/RequiredTheLeaderboardTestCaseAnnotationToUpdate.md +35 -0
  35. eval_studio_client/api/docs/RequiredTheLeaderboardToUpdate.md +1 -0
  36. eval_studio_client/api/docs/RequiredTheOperationToFinalize.md +1 -0
  37. eval_studio_client/api/docs/RequiredTheOperationToUpdate.md +1 -0
  38. eval_studio_client/api/docs/TestCaseServiceApi.md +75 -5
  39. eval_studio_client/api/docs/TestCaseServiceAppendTestCasesRequest.md +30 -0
  40. eval_studio_client/api/docs/TestClassServiceApi.md +5 -5
  41. eval_studio_client/api/docs/TestServiceApi.md +73 -5
  42. eval_studio_client/api/docs/V1ActualOutputMeta.md +30 -0
  43. eval_studio_client/api/docs/V1ActualOutputMetaDiff.md +36 -0
  44. eval_studio_client/api/docs/V1AgentChatActivityDiagram.md +31 -0
  45. eval_studio_client/api/docs/V1AgentChatActivityDiagramEdge.md +32 -0
  46. eval_studio_client/api/docs/V1AgentChatActivityDiagramNode.md +32 -0
  47. eval_studio_client/api/docs/V1AgentChatActivityDiagramRow.md +30 -0
  48. eval_studio_client/api/docs/V1AgentChatScriptUsage.md +33 -0
  49. eval_studio_client/api/docs/V1AgentChatScriptsBarChart.md +30 -0
  50. eval_studio_client/api/docs/V1AgentChatToolUsage.md +33 -0
  51. eval_studio_client/api/docs/V1AgentChatToolsBarChart.md +30 -0
  52. eval_studio_client/api/docs/V1AllMetricScores.md +29 -0
  53. eval_studio_client/api/docs/V1AppendTestCasesResponse.md +29 -0
  54. eval_studio_client/api/docs/V1BatchCreateLeaderboardsWithoutCacheRequest.md +31 -0
  55. eval_studio_client/api/docs/V1BatchCreateLeaderboardsWithoutCacheResponse.md +29 -0
  56. eval_studio_client/api/docs/V1BatchMarkOperationSeenByCreatorResponse.md +29 -0
  57. eval_studio_client/api/docs/V1CmpLeaderboardReportsRequest.md +33 -0
  58. eval_studio_client/api/docs/V1CmpLeaderboardReportsResponse.md +29 -0
  59. eval_studio_client/api/docs/V1ComparisonItem.md +36 -0
  60. eval_studio_client/api/docs/V1ComparisonMetricScore.md +30 -0
  61. eval_studio_client/api/docs/V1ComparisonResult.md +31 -0
  62. eval_studio_client/api/docs/V1ComparisonSummary.md +31 -0
  63. eval_studio_client/api/docs/V1CreateEvaluationRequest.md +1 -0
  64. eval_studio_client/api/docs/V1CreateTestFromTestCasesRequest.md +32 -0
  65. eval_studio_client/api/docs/V1CreateTestFromTestCasesResponse.md +29 -0
  66. eval_studio_client/api/docs/V1DashboardReport.md +31 -0
  67. eval_studio_client/api/docs/V1DashboardReportResult.md +39 -0
  68. eval_studio_client/api/docs/V1DashboardTestCaseAnnotation.md +36 -0
  69. eval_studio_client/api/docs/V1DataFragment.md +31 -0
  70. eval_studio_client/api/docs/V1DeepCompareLeaderboardsRequest.md +33 -0
  71. eval_studio_client/api/docs/V1DeepCompareLeaderboardsResponse.md +29 -0
  72. eval_studio_client/api/docs/V1DiffItem.md +36 -0
  73. eval_studio_client/api/docs/V1EvaluationType.md +12 -0
  74. eval_studio_client/api/docs/V1FlippedMetric.md +31 -0
  75. eval_studio_client/api/docs/V1GetDashboardReportResponse.md +29 -0
  76. eval_studio_client/api/docs/V1HumanDecision.md +12 -0
  77. eval_studio_client/api/docs/V1Info.md +1 -0
  78. eval_studio_client/api/docs/V1Leaderboard.md +1 -0
  79. eval_studio_client/api/docs/V1LeaderboardCmpReport.md +30 -0
  80. eval_studio_client/api/docs/V1LeaderboardComparisonItem.md +31 -0
  81. eval_studio_client/api/docs/V1LeaderboardInfo.md +30 -0
  82. eval_studio_client/api/docs/V1LeaderboardReportActualOutputMeta.md +6 -3
  83. eval_studio_client/api/docs/V1LeaderboardReportResult.md +11 -8
  84. eval_studio_client/api/docs/V1LeaderboardReportResultView.md +12 -0
  85. eval_studio_client/api/docs/V1LeaderboardTestCaseAnnotation.md +36 -0
  86. eval_studio_client/api/docs/V1ListDashboardTestCaseAnnotationsResponse.md +29 -0
  87. eval_studio_client/api/docs/V1ListLeaderboardTestCaseAnnotationsResponse.md +29 -0
  88. eval_studio_client/api/docs/V1ListOperationsResponse.md +1 -0
  89. eval_studio_client/api/docs/V1ListUnseenOperationsResponse.md +30 -0
  90. eval_studio_client/api/docs/V1MarkOperationSeenByCreatorResponse.md +29 -0
  91. eval_studio_client/api/docs/V1Metric.md +30 -0
  92. eval_studio_client/api/docs/V1MetricAverage.md +36 -0
  93. eval_studio_client/api/docs/V1MetricMeta.md +40 -0
  94. eval_studio_client/api/docs/V1MetricScore.md +1 -1
  95. eval_studio_client/api/docs/V1MetricScores.md +1 -1
  96. eval_studio_client/api/docs/V1ModelType.md +1 -1
  97. eval_studio_client/api/docs/V1ModelsComparisons.md +32 -0
  98. eval_studio_client/api/docs/V1ModelsComparisonsMetrics.md +33 -0
  99. eval_studio_client/api/docs/V1ModelsOverview.md +34 -0
  100. eval_studio_client/api/docs/V1Operation.md +1 -0
  101. eval_studio_client/api/docs/V1OperationView.md +12 -0
  102. eval_studio_client/api/docs/V1RetrievedContextDiff.md +36 -0
  103. eval_studio_client/api/docs/V1Stats.md +2 -0
  104. eval_studio_client/api/docs/V1TechnicalMetrics.md +30 -0
  105. eval_studio_client/api/docs/V1TechnicalMetricsDetail.md +33 -0
  106. eval_studio_client/api/docs/V1TestCaseLeaderboardItem.md +31 -0
  107. eval_studio_client/api/docs/V1TestCaseRelationshipInfo.md +31 -0
  108. eval_studio_client/api/docs/V1TestCaseResult.md +48 -0
  109. eval_studio_client/api/docs/V1TextSimilarityMetric.md +12 -0
  110. eval_studio_client/api/docs/V1UpdateDashboardTestCaseAnnotationResponse.md +29 -0
  111. eval_studio_client/api/docs/V1UpdateLeaderboardTestCaseAnnotationResponse.md +29 -0
  112. eval_studio_client/api/docs/WorkflowNodeServiceApi.md +5 -5
  113. eval_studio_client/api/docs/WorkflowServiceApi.md +5 -5
  114. eval_studio_client/api/models/__init__.py +62 -0
  115. eval_studio_client/api/models/adversarial_inputs_service_test_adversarial_inputs_robustness_request.py +17 -2
  116. eval_studio_client/api/models/required_the_dashboard_test_case_annotation_to_update.py +108 -0
  117. eval_studio_client/api/models/required_the_leaderboard_test_case_annotation_to_update.py +108 -0
  118. eval_studio_client/api/models/required_the_leaderboard_to_update.py +5 -2
  119. eval_studio_client/api/models/required_the_operation_to_finalize.py +6 -2
  120. eval_studio_client/api/models/required_the_operation_to_update.py +6 -2
  121. eval_studio_client/api/models/test_case_service_append_test_cases_request.py +89 -0
  122. eval_studio_client/api/models/v1_actual_output_meta.py +97 -0
  123. eval_studio_client/api/models/v1_actual_output_meta_diff.py +101 -0
  124. eval_studio_client/api/models/v1_agent_chat_activity_diagram.py +109 -0
  125. eval_studio_client/api/models/v1_agent_chat_activity_diagram_edge.py +97 -0
  126. eval_studio_client/api/models/v1_agent_chat_activity_diagram_node.py +97 -0
  127. eval_studio_client/api/models/v1_agent_chat_activity_diagram_row.py +97 -0
  128. eval_studio_client/api/models/v1_agent_chat_script_usage.py +101 -0
  129. eval_studio_client/api/models/v1_agent_chat_scripts_bar_chart.py +102 -0
  130. eval_studio_client/api/models/v1_agent_chat_tool_usage.py +101 -0
  131. eval_studio_client/api/models/v1_agent_chat_tools_bar_chart.py +102 -0
  132. eval_studio_client/api/models/v1_all_metric_scores.py +87 -0
  133. eval_studio_client/api/models/v1_append_test_cases_response.py +95 -0
  134. eval_studio_client/api/models/v1_batch_create_leaderboards_without_cache_request.py +99 -0
  135. eval_studio_client/api/models/v1_batch_create_leaderboards_without_cache_response.py +91 -0
  136. eval_studio_client/api/models/v1_batch_mark_operation_seen_by_creator_response.py +95 -0
  137. eval_studio_client/api/models/v1_cmp_leaderboard_reports_request.py +96 -0
  138. eval_studio_client/api/models/v1_cmp_leaderboard_reports_response.py +91 -0
  139. eval_studio_client/api/models/v1_comparison_item.py +130 -0
  140. eval_studio_client/api/models/v1_comparison_metric_score.py +89 -0
  141. eval_studio_client/api/models/v1_comparison_result.py +120 -0
  142. eval_studio_client/api/models/v1_comparison_summary.py +91 -0
  143. eval_studio_client/api/models/v1_create_evaluation_request.py +5 -2
  144. eval_studio_client/api/models/v1_create_test_from_test_cases_request.py +93 -0
  145. eval_studio_client/api/models/v1_create_test_from_test_cases_response.py +91 -0
  146. eval_studio_client/api/models/v1_dashboard_report.py +109 -0
  147. eval_studio_client/api/models/v1_dashboard_report_result.py +139 -0
  148. eval_studio_client/api/models/v1_dashboard_test_case_annotation.py +112 -0
  149. eval_studio_client/api/models/v1_data_fragment.py +91 -0
  150. eval_studio_client/api/models/v1_deep_compare_leaderboards_request.py +96 -0
  151. eval_studio_client/api/models/v1_deep_compare_leaderboards_response.py +91 -0
  152. eval_studio_client/api/models/v1_diff_item.py +137 -0
  153. eval_studio_client/api/models/v1_evaluation_type.py +39 -0
  154. eval_studio_client/api/models/v1_flipped_metric.py +91 -0
  155. eval_studio_client/api/models/v1_get_dashboard_report_response.py +91 -0
  156. eval_studio_client/api/models/v1_human_decision.py +38 -0
  157. eval_studio_client/api/models/v1_info.py +4 -2
  158. eval_studio_client/api/models/v1_leaderboard.py +5 -2
  159. eval_studio_client/api/models/v1_leaderboard_cmp_report.py +93 -0
  160. eval_studio_client/api/models/v1_leaderboard_comparison_item.py +91 -0
  161. eval_studio_client/api/models/v1_leaderboard_info.py +97 -0
  162. eval_studio_client/api/models/v1_leaderboard_report_actual_output_meta.py +23 -9
  163. eval_studio_client/api/models/v1_leaderboard_report_result.py +21 -10
  164. eval_studio_client/api/models/v1_leaderboard_report_result_view.py +38 -0
  165. eval_studio_client/api/models/v1_leaderboard_test_case_annotation.py +112 -0
  166. eval_studio_client/api/models/v1_list_dashboard_test_case_annotations_response.py +95 -0
  167. eval_studio_client/api/models/v1_list_leaderboard_test_case_annotations_response.py +95 -0
  168. eval_studio_client/api/models/v1_list_operations_response.py +5 -3
  169. eval_studio_client/api/models/v1_list_unseen_operations_response.py +97 -0
  170. eval_studio_client/api/models/v1_mark_operation_seen_by_creator_response.py +91 -0
  171. eval_studio_client/api/models/v1_metric.py +89 -0
  172. eval_studio_client/api/models/v1_metric_average.py +101 -0
  173. eval_studio_client/api/models/v1_metric_meta.py +109 -0
  174. eval_studio_client/api/models/v1_metric_score.py +6 -1
  175. eval_studio_client/api/models/v1_metric_scores.py +1 -1
  176. eval_studio_client/api/models/v1_model_type.py +2 -1
  177. eval_studio_client/api/models/v1_models_comparisons.py +93 -0
  178. eval_studio_client/api/models/v1_models_comparisons_metrics.py +103 -0
  179. eval_studio_client/api/models/v1_models_overview.py +97 -0
  180. eval_studio_client/api/models/v1_operation.py +6 -2
  181. eval_studio_client/api/models/v1_operation_view.py +38 -0
  182. eval_studio_client/api/models/v1_retrieved_context_diff.py +101 -0
  183. eval_studio_client/api/models/v1_stats.py +16 -2
  184. eval_studio_client/api/models/v1_technical_metrics.py +96 -0
  185. eval_studio_client/api/models/v1_technical_metrics_detail.py +95 -0
  186. eval_studio_client/api/models/v1_test_case_leaderboard_item.py +91 -0
  187. eval_studio_client/api/models/v1_test_case_relationship_info.py +91 -0
  188. eval_studio_client/api/models/v1_test_case_result.py +157 -0
  189. eval_studio_client/api/models/v1_text_similarity_metric.py +39 -0
  190. eval_studio_client/api/models/v1_update_dashboard_test_case_annotation_response.py +91 -0
  191. eval_studio_client/api/models/v1_update_leaderboard_test_case_annotation_response.py +91 -0
  192. eval_studio_client/api/models/v1_workflow_node_type.py +1 -0
  193. eval_studio_client/api/models/v1_workflow_type.py +1 -0
  194. eval_studio_client/api/test/test_adversarial_inputs_service_test_adversarial_inputs_robustness_request.py +6 -0
  195. eval_studio_client/api/test/test_dashboard_report_service_api.py +37 -0
  196. eval_studio_client/api/test/test_dashboard_test_case_annotation_service_api.py +43 -0
  197. eval_studio_client/api/test/test_leaderboard_report_service_api.py +6 -0
  198. eval_studio_client/api/test/test_leaderboard_service_api.py +12 -0
  199. eval_studio_client/api/test/test_leaderboard_test_case_annotation_service_api.py +43 -0
  200. eval_studio_client/api/test/test_operation_service_api.py +18 -0
  201. eval_studio_client/api/test/test_required_the_dashboard_test_case_annotation_to_update.py +57 -0
  202. eval_studio_client/api/test/test_required_the_leaderboard_test_case_annotation_to_update.py +57 -0
  203. eval_studio_client/api/test/test_required_the_leaderboard_to_update.py +2 -1
  204. eval_studio_client/api/test/test_required_the_operation_to_finalize.py +2 -1
  205. eval_studio_client/api/test/test_required_the_operation_to_update.py +2 -1
  206. eval_studio_client/api/test/test_test_case_service_api.py +6 -0
  207. eval_studio_client/api/test/test_test_case_service_append_test_cases_request.py +52 -0
  208. eval_studio_client/api/test/test_test_service_api.py +6 -0
  209. eval_studio_client/api/test/test_v1_abort_operation_response.py +2 -1
  210. eval_studio_client/api/test/test_v1_actual_output_meta.py +61 -0
  211. eval_studio_client/api/test/test_v1_actual_output_meta_diff.py +66 -0
  212. eval_studio_client/api/test/test_v1_agent_chat_activity_diagram.py +65 -0
  213. eval_studio_client/api/test/test_v1_agent_chat_activity_diagram_edge.py +53 -0
  214. eval_studio_client/api/test/test_v1_agent_chat_activity_diagram_node.py +53 -0
  215. eval_studio_client/api/test/test_v1_agent_chat_activity_diagram_row.py +56 -0
  216. eval_studio_client/api/test/test_v1_agent_chat_script_usage.py +54 -0
  217. eval_studio_client/api/test/test_v1_agent_chat_scripts_bar_chart.py +57 -0
  218. eval_studio_client/api/test/test_v1_agent_chat_tool_usage.py +54 -0
  219. eval_studio_client/api/test/test_v1_agent_chat_tools_bar_chart.py +57 -0
  220. eval_studio_client/api/test/test_v1_all_metric_scores.py +53 -0
  221. eval_studio_client/api/test/test_v1_append_test_cases_response.py +74 -0
  222. eval_studio_client/api/test/test_v1_batch_create_leaderboards_request.py +2 -1
  223. eval_studio_client/api/test/test_v1_batch_create_leaderboards_response.py +2 -1
  224. eval_studio_client/api/test/test_v1_batch_create_leaderboards_without_cache_request.py +120 -0
  225. eval_studio_client/api/test/test_v1_batch_create_leaderboards_without_cache_response.py +72 -0
  226. eval_studio_client/api/test/test_v1_batch_delete_leaderboards_response.py +2 -1
  227. eval_studio_client/api/test/test_v1_batch_get_leaderboards_response.py +2 -1
  228. eval_studio_client/api/test/test_v1_batch_get_operations_response.py +2 -1
  229. eval_studio_client/api/test/test_v1_batch_import_leaderboard_response.py +2 -1
  230. eval_studio_client/api/test/test_v1_batch_mark_operation_seen_by_creator_response.py +74 -0
  231. eval_studio_client/api/test/test_v1_cmp_leaderboard_reports_request.py +55 -0
  232. eval_studio_client/api/test/test_v1_cmp_leaderboard_reports_response.py +255 -0
  233. eval_studio_client/api/test/test_v1_comparison_item.py +233 -0
  234. eval_studio_client/api/test/test_v1_comparison_metric_score.py +52 -0
  235. eval_studio_client/api/test/test_v1_comparison_result.py +258 -0
  236. eval_studio_client/api/test/test_v1_comparison_summary.py +53 -0
  237. eval_studio_client/api/test/test_v1_create_evaluation_request.py +2 -1
  238. eval_studio_client/api/test/test_v1_create_leaderboard_request.py +2 -1
  239. eval_studio_client/api/test/test_v1_create_leaderboard_response.py +2 -1
  240. eval_studio_client/api/test/test_v1_create_leaderboard_without_cache_response.py +2 -1
  241. eval_studio_client/api/test/test_v1_create_test_from_test_cases_request.py +54 -0
  242. eval_studio_client/api/test/test_v1_create_test_from_test_cases_response.py +68 -0
  243. eval_studio_client/api/test/test_v1_dashboard_report.py +142 -0
  244. eval_studio_client/api/test/test_v1_dashboard_report_result.py +72 -0
  245. eval_studio_client/api/test/test_v1_dashboard_test_case_annotation.py +58 -0
  246. eval_studio_client/api/test/test_v1_data_fragment.py +57 -0
  247. eval_studio_client/api/test/test_v1_deep_compare_leaderboards_request.py +55 -0
  248. eval_studio_client/api/test/test_v1_deep_compare_leaderboards_response.py +255 -0
  249. eval_studio_client/api/test/test_v1_delete_leaderboard_response.py +2 -1
  250. eval_studio_client/api/test/test_v1_diff_item.py +226 -0
  251. eval_studio_client/api/test/test_v1_evaluation_type.py +33 -0
  252. eval_studio_client/api/test/test_v1_finalize_operation_response.py +2 -1
  253. eval_studio_client/api/test/test_v1_flipped_metric.py +53 -0
  254. eval_studio_client/api/test/test_v1_generate_test_cases_response.py +2 -1
  255. eval_studio_client/api/test/test_v1_get_dashboard_report_response.py +143 -0
  256. eval_studio_client/api/test/test_v1_get_info_response.py +4 -1
  257. eval_studio_client/api/test/test_v1_get_leaderboard_report_response.py +39 -2
  258. eval_studio_client/api/test/test_v1_get_leaderboard_response.py +2 -1
  259. eval_studio_client/api/test/test_v1_get_operation_response.py +2 -1
  260. eval_studio_client/api/test/test_v1_get_stats_response.py +3 -1
  261. eval_studio_client/api/test/test_v1_human_decision.py +33 -0
  262. eval_studio_client/api/test/test_v1_import_leaderboard_response.py +2 -1
  263. eval_studio_client/api/test/test_v1_import_test_cases_from_library_response.py +2 -1
  264. eval_studio_client/api/test/test_v1_info.py +4 -1
  265. eval_studio_client/api/test/test_v1_leaderboard.py +2 -1
  266. eval_studio_client/api/test/test_v1_leaderboard_cmp_report.py +254 -0
  267. eval_studio_client/api/test/test_v1_leaderboard_comparison_item.py +53 -0
  268. eval_studio_client/api/test/test_v1_leaderboard_info.py +57 -0
  269. eval_studio_client/api/test/test_v1_leaderboard_report.py +39 -2
  270. eval_studio_client/api/test/test_v1_leaderboard_report_actual_output_meta.py +33 -1
  271. eval_studio_client/api/test/test_v1_leaderboard_report_result.py +39 -2
  272. eval_studio_client/api/test/test_v1_leaderboard_report_result_view.py +33 -0
  273. eval_studio_client/api/test/test_v1_leaderboard_test_case_annotation.py +58 -0
  274. eval_studio_client/api/test/test_v1_list_dashboard_test_case_annotations_response.py +61 -0
  275. eval_studio_client/api/test/test_v1_list_leaderboard_test_case_annotations_response.py +61 -0
  276. eval_studio_client/api/test/test_v1_list_leaderboards_response.py +2 -1
  277. eval_studio_client/api/test/test_v1_list_most_recent_leaderboards_response.py +2 -1
  278. eval_studio_client/api/test/test_v1_list_operations_response.py +4 -2
  279. eval_studio_client/api/test/test_v1_list_unseen_operations_response.py +75 -0
  280. eval_studio_client/api/test/test_v1_mark_operation_seen_by_creator_response.py +72 -0
  281. eval_studio_client/api/test/test_v1_metric.py +52 -0
  282. eval_studio_client/api/test/test_v1_metric_average.py +58 -0
  283. eval_studio_client/api/test/test_v1_metric_meta.py +66 -0
  284. eval_studio_client/api/test/test_v1_models_comparisons.py +54 -0
  285. eval_studio_client/api/test/test_v1_models_comparisons_metrics.py +65 -0
  286. eval_studio_client/api/test/test_v1_models_overview.py +60 -0
  287. eval_studio_client/api/test/test_v1_operation.py +2 -1
  288. eval_studio_client/api/test/test_v1_operation_view.py +33 -0
  289. eval_studio_client/api/test/test_v1_process_workflow_node_response.py +2 -1
  290. eval_studio_client/api/test/test_v1_retrieved_context_diff.py +66 -0
  291. eval_studio_client/api/test/test_v1_stats.py +3 -1
  292. eval_studio_client/api/test/test_v1_technical_metrics.py +62 -0
  293. eval_studio_client/api/test/test_v1_technical_metrics_detail.py +55 -0
  294. eval_studio_client/api/test/test_v1_test_case_leaderboard_item.py +53 -0
  295. eval_studio_client/api/test/test_v1_test_case_relationship_info.py +53 -0
  296. eval_studio_client/api/test/test_v1_test_case_result.py +106 -0
  297. eval_studio_client/api/test/test_v1_text_similarity_metric.py +33 -0
  298. eval_studio_client/api/test/test_v1_update_dashboard_test_case_annotation_response.py +59 -0
  299. eval_studio_client/api/test/test_v1_update_leaderboard_response.py +2 -1
  300. eval_studio_client/api/test/test_v1_update_leaderboard_test_case_annotation_response.py +59 -0
  301. eval_studio_client/api/test/test_v1_update_operation_response.py +2 -1
  302. eval_studio_client/gen/openapiv2/eval_studio.swagger.json +2340 -210
  303. eval_studio_client/models.py +18 -6
  304. {eval_studio_client-1.2.4a2.dist-info → eval_studio_client-1.3.0.dist-info}/METADATA +2 -2
  305. {eval_studio_client-1.2.4a2.dist-info → eval_studio_client-1.3.0.dist-info}/RECORD +306 -111
  306. {eval_studio_client-1.2.4a2.dist-info → eval_studio_client-1.3.0.dist-info}/WHEEL +0 -0
@@ -0,0 +1,30 @@
1
+ # V1AgentChatActivityDiagramRow
2
+
3
+ AgentChatActivityDiagramRow represents a row in the activity diagram.
4
+
5
+ ## Properties
6
+
7
+ Name | Type | Description | Notes
8
+ ------------ | ------------- | ------------- | -------------
9
+ **nodes** | [**List[V1AgentChatActivityDiagramNode]**](V1AgentChatActivityDiagramNode.md) | Output only. List of nodes in this row. | [optional] [readonly]
10
+
11
+ ## Example
12
+
13
+ ```python
14
+ from eval_studio_client.api.models.v1_agent_chat_activity_diagram_row import V1AgentChatActivityDiagramRow
15
+
16
+ # TODO update the JSON string below
17
+ json = "{}"
18
+ # create an instance of V1AgentChatActivityDiagramRow from a JSON string
19
+ v1_agent_chat_activity_diagram_row_instance = V1AgentChatActivityDiagramRow.from_json(json)
20
+ # print the JSON string representation of the object
21
+ print(V1AgentChatActivityDiagramRow.to_json())
22
+
23
+ # convert the object into a dict
24
+ v1_agent_chat_activity_diagram_row_dict = v1_agent_chat_activity_diagram_row_instance.to_dict()
25
+ # create an instance of V1AgentChatActivityDiagramRow from a dict
26
+ v1_agent_chat_activity_diagram_row_from_dict = V1AgentChatActivityDiagramRow.from_dict(v1_agent_chat_activity_diagram_row_dict)
27
+ ```
28
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
29
+
30
+
@@ -0,0 +1,33 @@
1
+ # V1AgentChatScriptUsage
2
+
3
+ AgentChatScriptUsage represents usage statistics for a single script.
4
+
5
+ ## Properties
6
+
7
+ Name | Type | Description | Notes
8
+ ------------ | ------------- | ------------- | -------------
9
+ **name** | **str** | Output only. Name of the script. | [optional] [readonly]
10
+ **success_count** | **int** | Output only. Number of successful executions. | [optional] [readonly]
11
+ **failure_count** | **int** | Output only. Number of failed executions. | [optional] [readonly]
12
+ **total_count** | **int** | Output only. Total number of executions. | [optional] [readonly]
13
+
14
+ ## Example
15
+
16
+ ```python
17
+ from eval_studio_client.api.models.v1_agent_chat_script_usage import V1AgentChatScriptUsage
18
+
19
+ # TODO update the JSON string below
20
+ json = "{}"
21
+ # create an instance of V1AgentChatScriptUsage from a JSON string
22
+ v1_agent_chat_script_usage_instance = V1AgentChatScriptUsage.from_json(json)
23
+ # print the JSON string representation of the object
24
+ print(V1AgentChatScriptUsage.to_json())
25
+
26
+ # convert the object into a dict
27
+ v1_agent_chat_script_usage_dict = v1_agent_chat_script_usage_instance.to_dict()
28
+ # create an instance of V1AgentChatScriptUsage from a dict
29
+ v1_agent_chat_script_usage_from_dict = V1AgentChatScriptUsage.from_dict(v1_agent_chat_script_usage_dict)
30
+ ```
31
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
32
+
33
+
@@ -0,0 +1,30 @@
1
+ # V1AgentChatScriptsBarChart
2
+
3
+ AgentChatScriptsBarChart represents the bar chart for agent chat scripts usage.
4
+
5
+ ## Properties
6
+
7
+ Name | Type | Description | Notes
8
+ ------------ | ------------- | ------------- | -------------
9
+ **scripts** | [**Dict[str, V1AgentChatScriptUsage]**](V1AgentChatScriptUsage.md) | Output only. Map of script name to script usage statistics. | [optional] [readonly]
10
+
11
+ ## Example
12
+
13
+ ```python
14
+ from eval_studio_client.api.models.v1_agent_chat_scripts_bar_chart import V1AgentChatScriptsBarChart
15
+
16
+ # TODO update the JSON string below
17
+ json = "{}"
18
+ # create an instance of V1AgentChatScriptsBarChart from a JSON string
19
+ v1_agent_chat_scripts_bar_chart_instance = V1AgentChatScriptsBarChart.from_json(json)
20
+ # print the JSON string representation of the object
21
+ print(V1AgentChatScriptsBarChart.to_json())
22
+
23
+ # convert the object into a dict
24
+ v1_agent_chat_scripts_bar_chart_dict = v1_agent_chat_scripts_bar_chart_instance.to_dict()
25
+ # create an instance of V1AgentChatScriptsBarChart from a dict
26
+ v1_agent_chat_scripts_bar_chart_from_dict = V1AgentChatScriptsBarChart.from_dict(v1_agent_chat_scripts_bar_chart_dict)
27
+ ```
28
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
29
+
30
+
@@ -0,0 +1,33 @@
1
+ # V1AgentChatToolUsage
2
+
3
+ AgentChatToolUsage represents usage statistics for a single tool.
4
+
5
+ ## Properties
6
+
7
+ Name | Type | Description | Notes
8
+ ------------ | ------------- | ------------- | -------------
9
+ **name** | **str** | Output only. Name of the tool. | [optional] [readonly]
10
+ **success_count** | **int** | Output only. Number of successful invocations. | [optional] [readonly]
11
+ **failure_count** | **int** | Output only. Number of failed invocations. | [optional] [readonly]
12
+ **total_count** | **int** | Output only. Total number of invocations. | [optional] [readonly]
13
+
14
+ ## Example
15
+
16
+ ```python
17
+ from eval_studio_client.api.models.v1_agent_chat_tool_usage import V1AgentChatToolUsage
18
+
19
+ # TODO update the JSON string below
20
+ json = "{}"
21
+ # create an instance of V1AgentChatToolUsage from a JSON string
22
+ v1_agent_chat_tool_usage_instance = V1AgentChatToolUsage.from_json(json)
23
+ # print the JSON string representation of the object
24
+ print(V1AgentChatToolUsage.to_json())
25
+
26
+ # convert the object into a dict
27
+ v1_agent_chat_tool_usage_dict = v1_agent_chat_tool_usage_instance.to_dict()
28
+ # create an instance of V1AgentChatToolUsage from a dict
29
+ v1_agent_chat_tool_usage_from_dict = V1AgentChatToolUsage.from_dict(v1_agent_chat_tool_usage_dict)
30
+ ```
31
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
32
+
33
+
@@ -0,0 +1,30 @@
1
+ # V1AgentChatToolsBarChart
2
+
3
+ AgentChatToolsBarChart represents the bar chart for agent chat tools usage.
4
+
5
+ ## Properties
6
+
7
+ Name | Type | Description | Notes
8
+ ------------ | ------------- | ------------- | -------------
9
+ **tools** | [**Dict[str, V1AgentChatToolUsage]**](V1AgentChatToolUsage.md) | Output only. Map of tool name to tool usage statistics. | [optional] [readonly]
10
+
11
+ ## Example
12
+
13
+ ```python
14
+ from eval_studio_client.api.models.v1_agent_chat_tools_bar_chart import V1AgentChatToolsBarChart
15
+
16
+ # TODO update the JSON string below
17
+ json = "{}"
18
+ # create an instance of V1AgentChatToolsBarChart from a JSON string
19
+ v1_agent_chat_tools_bar_chart_instance = V1AgentChatToolsBarChart.from_json(json)
20
+ # print the JSON string representation of the object
21
+ print(V1AgentChatToolsBarChart.to_json())
22
+
23
+ # convert the object into a dict
24
+ v1_agent_chat_tools_bar_chart_dict = v1_agent_chat_tools_bar_chart_instance.to_dict()
25
+ # create an instance of V1AgentChatToolsBarChart from a dict
26
+ v1_agent_chat_tools_bar_chart_from_dict = V1AgentChatToolsBarChart.from_dict(v1_agent_chat_tools_bar_chart_dict)
27
+ ```
28
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
29
+
30
+
@@ -0,0 +1,29 @@
1
+ # V1AllMetricScores
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **scores** | **List[float]** | Required. Metric scores for all baseline test cases. | [optional]
9
+
10
+ ## Example
11
+
12
+ ```python
13
+ from eval_studio_client.api.models.v1_all_metric_scores import V1AllMetricScores
14
+
15
+ # TODO update the JSON string below
16
+ json = "{}"
17
+ # create an instance of V1AllMetricScores from a JSON string
18
+ v1_all_metric_scores_instance = V1AllMetricScores.from_json(json)
19
+ # print the JSON string representation of the object
20
+ print(V1AllMetricScores.to_json())
21
+
22
+ # convert the object into a dict
23
+ v1_all_metric_scores_dict = v1_all_metric_scores_instance.to_dict()
24
+ # create an instance of V1AllMetricScores from a dict
25
+ v1_all_metric_scores_from_dict = V1AllMetricScores.from_dict(v1_all_metric_scores_dict)
26
+ ```
27
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
28
+
29
+
@@ -0,0 +1,29 @@
1
+ # V1AppendTestCasesResponse
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **test_cases** | [**List[V1TestCase]**](V1TestCase.md) | The list of added TestCases. | [optional]
9
+
10
+ ## Example
11
+
12
+ ```python
13
+ from eval_studio_client.api.models.v1_append_test_cases_response import V1AppendTestCasesResponse
14
+
15
+ # TODO update the JSON string below
16
+ json = "{}"
17
+ # create an instance of V1AppendTestCasesResponse from a JSON string
18
+ v1_append_test_cases_response_instance = V1AppendTestCasesResponse.from_json(json)
19
+ # print the JSON string representation of the object
20
+ print(V1AppendTestCasesResponse.to_json())
21
+
22
+ # convert the object into a dict
23
+ v1_append_test_cases_response_dict = v1_append_test_cases_response_instance.to_dict()
24
+ # create an instance of V1AppendTestCasesResponse from a dict
25
+ v1_append_test_cases_response_from_dict = V1AppendTestCasesResponse.from_dict(v1_append_test_cases_response_dict)
26
+ ```
27
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
28
+
29
+
@@ -0,0 +1,31 @@
1
+ # V1BatchCreateLeaderboardsWithoutCacheRequest
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **requests** | [**List[V1CreateLeaderboardRequest]**](V1CreateLeaderboardRequest.md) | Required. Contains list of requests for leaderboards to be created. | [optional]
9
+ **dashboard_display_name** | **str** | Optional. Display name for the dashboard that will group the leaderboards. | [optional]
10
+ **dashboard_description** | **str** | Optional. Description for the dashboard that will group the leaderboards. | [optional]
11
+
12
+ ## Example
13
+
14
+ ```python
15
+ from eval_studio_client.api.models.v1_batch_create_leaderboards_without_cache_request import V1BatchCreateLeaderboardsWithoutCacheRequest
16
+
17
+ # TODO update the JSON string below
18
+ json = "{}"
19
+ # create an instance of V1BatchCreateLeaderboardsWithoutCacheRequest from a JSON string
20
+ v1_batch_create_leaderboards_without_cache_request_instance = V1BatchCreateLeaderboardsWithoutCacheRequest.from_json(json)
21
+ # print the JSON string representation of the object
22
+ print(V1BatchCreateLeaderboardsWithoutCacheRequest.to_json())
23
+
24
+ # convert the object into a dict
25
+ v1_batch_create_leaderboards_without_cache_request_dict = v1_batch_create_leaderboards_without_cache_request_instance.to_dict()
26
+ # create an instance of V1BatchCreateLeaderboardsWithoutCacheRequest from a dict
27
+ v1_batch_create_leaderboards_without_cache_request_from_dict = V1BatchCreateLeaderboardsWithoutCacheRequest.from_dict(v1_batch_create_leaderboards_without_cache_request_dict)
28
+ ```
29
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
30
+
31
+
@@ -0,0 +1,29 @@
1
+ # V1BatchCreateLeaderboardsWithoutCacheResponse
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **operation** | [**V1Operation**](V1Operation.md) | | [optional]
9
+
10
+ ## Example
11
+
12
+ ```python
13
+ from eval_studio_client.api.models.v1_batch_create_leaderboards_without_cache_response import V1BatchCreateLeaderboardsWithoutCacheResponse
14
+
15
+ # TODO update the JSON string below
16
+ json = "{}"
17
+ # create an instance of V1BatchCreateLeaderboardsWithoutCacheResponse from a JSON string
18
+ v1_batch_create_leaderboards_without_cache_response_instance = V1BatchCreateLeaderboardsWithoutCacheResponse.from_json(json)
19
+ # print the JSON string representation of the object
20
+ print(V1BatchCreateLeaderboardsWithoutCacheResponse.to_json())
21
+
22
+ # convert the object into a dict
23
+ v1_batch_create_leaderboards_without_cache_response_dict = v1_batch_create_leaderboards_without_cache_response_instance.to_dict()
24
+ # create an instance of V1BatchCreateLeaderboardsWithoutCacheResponse from a dict
25
+ v1_batch_create_leaderboards_without_cache_response_from_dict = V1BatchCreateLeaderboardsWithoutCacheResponse.from_dict(v1_batch_create_leaderboards_without_cache_response_dict)
26
+ ```
27
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
28
+
29
+
@@ -0,0 +1,29 @@
1
+ # V1BatchMarkOperationSeenByCreatorResponse
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **operations** | [**List[V1Operation]**](V1Operation.md) | The updated Operations. | [optional]
9
+
10
+ ## Example
11
+
12
+ ```python
13
+ from eval_studio_client.api.models.v1_batch_mark_operation_seen_by_creator_response import V1BatchMarkOperationSeenByCreatorResponse
14
+
15
+ # TODO update the JSON string below
16
+ json = "{}"
17
+ # create an instance of V1BatchMarkOperationSeenByCreatorResponse from a JSON string
18
+ v1_batch_mark_operation_seen_by_creator_response_instance = V1BatchMarkOperationSeenByCreatorResponse.from_json(json)
19
+ # print the JSON string representation of the object
20
+ print(V1BatchMarkOperationSeenByCreatorResponse.to_json())
21
+
22
+ # convert the object into a dict
23
+ v1_batch_mark_operation_seen_by_creator_response_dict = v1_batch_mark_operation_seen_by_creator_response_instance.to_dict()
24
+ # create an instance of V1BatchMarkOperationSeenByCreatorResponse from a dict
25
+ v1_batch_mark_operation_seen_by_creator_response_from_dict = V1BatchMarkOperationSeenByCreatorResponse.from_dict(v1_batch_mark_operation_seen_by_creator_response_dict)
26
+ ```
27
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
28
+
29
+
@@ -0,0 +1,33 @@
1
+ # V1CmpLeaderboardReportsRequest
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **leaderboard_report_baseline** | **str** | Required. The baseline Leaderboard Report to compare against (JSON string). | [optional]
9
+ **leaderboard_report_current** | **str** | Required. The current Leaderboard Report to compare (JSON string). | [optional]
10
+ **text_similarity_metric** | [**V1TextSimilarityMetric**](V1TextSimilarityMetric.md) | | [optional]
11
+ **llm_model_name_baseline** | **str** | Required. The baseline LLM model name to compare. | [optional]
12
+ **llm_model_name_current** | **str** | Required. The current LLM model name to compare. | [optional]
13
+
14
+ ## Example
15
+
16
+ ```python
17
+ from eval_studio_client.api.models.v1_cmp_leaderboard_reports_request import V1CmpLeaderboardReportsRequest
18
+
19
+ # TODO update the JSON string below
20
+ json = "{}"
21
+ # create an instance of V1CmpLeaderboardReportsRequest from a JSON string
22
+ v1_cmp_leaderboard_reports_request_instance = V1CmpLeaderboardReportsRequest.from_json(json)
23
+ # print the JSON string representation of the object
24
+ print(V1CmpLeaderboardReportsRequest.to_json())
25
+
26
+ # convert the object into a dict
27
+ v1_cmp_leaderboard_reports_request_dict = v1_cmp_leaderboard_reports_request_instance.to_dict()
28
+ # create an instance of V1CmpLeaderboardReportsRequest from a dict
29
+ v1_cmp_leaderboard_reports_request_from_dict = V1CmpLeaderboardReportsRequest.from_dict(v1_cmp_leaderboard_reports_request_dict)
30
+ ```
31
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
32
+
33
+
@@ -0,0 +1,29 @@
1
+ # V1CmpLeaderboardReportsResponse
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **leaderboard_cmp_report** | [**V1LeaderboardCmpReport**](V1LeaderboardCmpReport.md) | | [optional]
9
+
10
+ ## Example
11
+
12
+ ```python
13
+ from eval_studio_client.api.models.v1_cmp_leaderboard_reports_response import V1CmpLeaderboardReportsResponse
14
+
15
+ # TODO update the JSON string below
16
+ json = "{}"
17
+ # create an instance of V1CmpLeaderboardReportsResponse from a JSON string
18
+ v1_cmp_leaderboard_reports_response_instance = V1CmpLeaderboardReportsResponse.from_json(json)
19
+ # print the JSON string representation of the object
20
+ print(V1CmpLeaderboardReportsResponse.to_json())
21
+
22
+ # convert the object into a dict
23
+ v1_cmp_leaderboard_reports_response_dict = v1_cmp_leaderboard_reports_response_instance.to_dict()
24
+ # create an instance of V1CmpLeaderboardReportsResponse from a dict
25
+ v1_cmp_leaderboard_reports_response_from_dict = V1CmpLeaderboardReportsResponse.from_dict(v1_cmp_leaderboard_reports_response_dict)
26
+ ```
27
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
28
+
29
+
@@ -0,0 +1,36 @@
1
+ # V1ComparisonItem
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **question** | **str** | The question being evaluated. | [optional]
9
+ **diff_flipped_metrics** | [**List[V1FlippedMetric]**](V1FlippedMetric.md) | List of metrics that flipped between baseline and current. | [optional]
10
+ **baseline_test_case_result** | [**V1TestCaseResult**](V1TestCaseResult.md) | | [optional]
11
+ **baseline_diff_actual_output_meta** | [**V1ActualOutputMetaDiff**](V1ActualOutputMetaDiff.md) | | [optional]
12
+ **baseline_diff_retrieved_context** | [**V1RetrievedContextDiff**](V1RetrievedContextDiff.md) | | [optional]
13
+ **current_test_case_result** | [**V1TestCaseResult**](V1TestCaseResult.md) | | [optional]
14
+ **current_diff_actual_output_meta** | [**V1ActualOutputMetaDiff**](V1ActualOutputMetaDiff.md) | | [optional]
15
+ **current_diff_retrieved_context** | [**V1RetrievedContextDiff**](V1RetrievedContextDiff.md) | | [optional]
16
+
17
+ ## Example
18
+
19
+ ```python
20
+ from eval_studio_client.api.models.v1_comparison_item import V1ComparisonItem
21
+
22
+ # TODO update the JSON string below
23
+ json = "{}"
24
+ # create an instance of V1ComparisonItem from a JSON string
25
+ v1_comparison_item_instance = V1ComparisonItem.from_json(json)
26
+ # print the JSON string representation of the object
27
+ print(V1ComparisonItem.to_json())
28
+
29
+ # convert the object into a dict
30
+ v1_comparison_item_dict = v1_comparison_item_instance.to_dict()
31
+ # create an instance of V1ComparisonItem from a dict
32
+ v1_comparison_item_from_dict = V1ComparisonItem.from_dict(v1_comparison_item_dict)
33
+ ```
34
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
35
+
36
+
@@ -0,0 +1,30 @@
1
+ # V1ComparisonMetricScore
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **metric_name** | **str** | Metric name. | [optional]
9
+ **metric_score** | **float** | Metric score value. | [optional]
10
+
11
+ ## Example
12
+
13
+ ```python
14
+ from eval_studio_client.api.models.v1_comparison_metric_score import V1ComparisonMetricScore
15
+
16
+ # TODO update the JSON string below
17
+ json = "{}"
18
+ # create an instance of V1ComparisonMetricScore from a JSON string
19
+ v1_comparison_metric_score_instance = V1ComparisonMetricScore.from_json(json)
20
+ # print the JSON string representation of the object
21
+ print(V1ComparisonMetricScore.to_json())
22
+
23
+ # convert the object into a dict
24
+ v1_comparison_metric_score_dict = v1_comparison_metric_score_instance.to_dict()
25
+ # create an instance of V1ComparisonMetricScore from a dict
26
+ v1_comparison_metric_score_from_dict = V1ComparisonMetricScore.from_dict(v1_comparison_metric_score_dict)
27
+ ```
28
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
29
+
30
+
@@ -0,0 +1,31 @@
1
+ # V1ComparisonResult
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **diffs** | [**List[V1DiffItem]**](V1DiffItem.md) | List of differences between leaderboards. | [optional]
9
+ **leaderboards** | [**List[V1LeaderboardInfo]**](V1LeaderboardInfo.md) | Leaderboard information. | [optional]
10
+ **metrics_meta** | [**Dict[str, V1MetricMeta]**](V1MetricMeta.md) | Metadata about metrics. | [optional]
11
+
12
+ ## Example
13
+
14
+ ```python
15
+ from eval_studio_client.api.models.v1_comparison_result import V1ComparisonResult
16
+
17
+ # TODO update the JSON string below
18
+ json = "{}"
19
+ # create an instance of V1ComparisonResult from a JSON string
20
+ v1_comparison_result_instance = V1ComparisonResult.from_json(json)
21
+ # print the JSON string representation of the object
22
+ print(V1ComparisonResult.to_json())
23
+
24
+ # convert the object into a dict
25
+ v1_comparison_result_dict = v1_comparison_result_instance.to_dict()
26
+ # create an instance of V1ComparisonResult from a dict
27
+ v1_comparison_result_from_dict = V1ComparisonResult.from_dict(v1_comparison_result_dict)
28
+ ```
29
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
30
+
31
+
@@ -0,0 +1,31 @@
1
+ # V1ComparisonSummary
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **recommendation_winner** | **str** | Winner of the comparison (baseline, current, or tie). | [optional]
9
+ **recommendation** | **str** | Recommendation text. | [optional]
10
+ **recommendation_confidence** | **str** | Confidence level of the recommendation. | [optional]
11
+
12
+ ## Example
13
+
14
+ ```python
15
+ from eval_studio_client.api.models.v1_comparison_summary import V1ComparisonSummary
16
+
17
+ # TODO update the JSON string below
18
+ json = "{}"
19
+ # create an instance of V1ComparisonSummary from a JSON string
20
+ v1_comparison_summary_instance = V1ComparisonSummary.from_json(json)
21
+ # print the JSON string representation of the object
22
+ print(V1ComparisonSummary.to_json())
23
+
24
+ # convert the object into a dict
25
+ v1_comparison_summary_dict = v1_comparison_summary_instance.to_dict()
26
+ # create an instance of V1ComparisonSummary from a dict
27
+ v1_comparison_summary_from_dict = V1ComparisonSummary.from_dict(v1_comparison_summary_dict)
28
+ ```
29
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
30
+
31
+
@@ -15,6 +15,7 @@ Name | Type | Description | Notes
15
15
  **model_parameters** | **str** | Optional. Parameters overrides in JSON format. | [optional]
16
16
  **h2ogpte_collection** | **str** | The existing collection name in H2OGPTe. | [optional]
17
17
  **default_h2ogpte_model** | [**V1Model**](V1Model.md) | | [optional]
18
+ **evaluation_type** | [**V1EvaluationType**](V1EvaluationType.md) | | [optional]
18
19
 
19
20
  ## Example
20
21
 
@@ -0,0 +1,32 @@
1
+ # V1CreateTestFromTestCasesRequest
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **tests_json** | **str** | Test Cases in JSON format. | [optional]
9
+ **url** | **str** | URL pointing to the Test Cases in JSON format to import. | [optional]
10
+ **test_display_name** | **str** | Required. Display name of the newly created Test. | [optional]
11
+ **test_description** | **str** | Optional. Description of the newly created Tests. | [optional]
12
+
13
+ ## Example
14
+
15
+ ```python
16
+ from eval_studio_client.api.models.v1_create_test_from_test_cases_request import V1CreateTestFromTestCasesRequest
17
+
18
+ # TODO update the JSON string below
19
+ json = "{}"
20
+ # create an instance of V1CreateTestFromTestCasesRequest from a JSON string
21
+ v1_create_test_from_test_cases_request_instance = V1CreateTestFromTestCasesRequest.from_json(json)
22
+ # print the JSON string representation of the object
23
+ print(V1CreateTestFromTestCasesRequest.to_json())
24
+
25
+ # convert the object into a dict
26
+ v1_create_test_from_test_cases_request_dict = v1_create_test_from_test_cases_request_instance.to_dict()
27
+ # create an instance of V1CreateTestFromTestCasesRequest from a dict
28
+ v1_create_test_from_test_cases_request_from_dict = V1CreateTestFromTestCasesRequest.from_dict(v1_create_test_from_test_cases_request_dict)
29
+ ```
30
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
31
+
32
+
@@ -0,0 +1,29 @@
1
+ # V1CreateTestFromTestCasesResponse
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **test** | [**V1Test**](V1Test.md) | | [optional]
9
+
10
+ ## Example
11
+
12
+ ```python
13
+ from eval_studio_client.api.models.v1_create_test_from_test_cases_response import V1CreateTestFromTestCasesResponse
14
+
15
+ # TODO update the JSON string below
16
+ json = "{}"
17
+ # create an instance of V1CreateTestFromTestCasesResponse from a JSON string
18
+ v1_create_test_from_test_cases_response_instance = V1CreateTestFromTestCasesResponse.from_json(json)
19
+ # print the JSON string representation of the object
20
+ print(V1CreateTestFromTestCasesResponse.to_json())
21
+
22
+ # convert the object into a dict
23
+ v1_create_test_from_test_cases_response_dict = v1_create_test_from_test_cases_response_instance.to_dict()
24
+ # create an instance of V1CreateTestFromTestCasesResponse from a dict
25
+ v1_create_test_from_test_cases_response_from_dict = V1CreateTestFromTestCasesResponse.from_dict(v1_create_test_from_test_cases_response_dict)
26
+ ```
27
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
28
+
29
+
@@ -0,0 +1,31 @@
1
+ # V1DashboardReport
2
+
3
+ DashboardReport represents the dashboard report which is formed by the results, models and evaluator.
4
+
5
+ ## Properties
6
+
7
+ Name | Type | Description | Notes
8
+ ------------ | ------------- | ------------- | -------------
9
+ **results** | [**List[V1DashboardReportResult]**](V1DashboardReportResult.md) | Output only. List of per test case results. | [optional] [readonly]
10
+ **evaluator** | [**List[V1LeaderboardReportEvaluator]**](V1LeaderboardReportEvaluator.md) | Output only. Details of the evaluators which evaluated the model outputs to create the results. | [optional] [readonly]
11
+
12
+ ## Example
13
+
14
+ ```python
15
+ from eval_studio_client.api.models.v1_dashboard_report import V1DashboardReport
16
+
17
+ # TODO update the JSON string below
18
+ json = "{}"
19
+ # create an instance of V1DashboardReport from a JSON string
20
+ v1_dashboard_report_instance = V1DashboardReport.from_json(json)
21
+ # print the JSON string representation of the object
22
+ print(V1DashboardReport.to_json())
23
+
24
+ # convert the object into a dict
25
+ v1_dashboard_report_dict = v1_dashboard_report_instance.to_dict()
26
+ # create an instance of V1DashboardReport from a dict
27
+ v1_dashboard_report_from_dict = V1DashboardReport.from_dict(v1_dashboard_report_dict)
28
+ ```
29
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
30
+
31
+
@@ -0,0 +1,39 @@
1
+ # V1DashboardReportResult
2
+
3
+
4
+ ## Properties
5
+
6
+ Name | Type | Description | Notes
7
+ ------------ | ------------- | ------------- | -------------
8
+ **key** | **str** | Output only. Composite unique key of the result formed by the model key and test case key. | [optional] [readonly]
9
+ **input** | **str** | Output only. Input prompt or text to be processed. | [optional] [readonly]
10
+ **expected_output** | **str** | Output only. Expected output or target result. | [optional] [readonly]
11
+ **actual_output** | **str** | Output only. Actual output produced by the model. | [optional] [readonly]
12
+ **model_key** | **str** | Output only. Unique identifier for the model used. | [optional] [readonly]
13
+ **test_case_key** | **str** | Output only. Unique identifier for the test case. | [optional] [readonly]
14
+ **metrics** | [**Dict[str, V1MetricScores]**](V1MetricScores.md) | Optional. All metrics values for the result. Maps evaluator ID to MetricScore. | [optional]
15
+ **result_error_map** | **Dict[str, str]** | Output only. Error message if processing resulted in failure. Maps evaluator ID to error message. | [optional] [readonly]
16
+ **human_decision** | [**V1HumanDecision**](V1HumanDecision.md) | | [optional]
17
+ **comment** | **str** | Output only. Optional comment about the result. | [optional] [readonly]
18
+ **annotations** | **Dict[str, object]** | Output only. Additional annotations for the result. | [optional] [readonly]
19
+
20
+ ## Example
21
+
22
+ ```python
23
+ from eval_studio_client.api.models.v1_dashboard_report_result import V1DashboardReportResult
24
+
25
+ # TODO update the JSON string below
26
+ json = "{}"
27
+ # create an instance of V1DashboardReportResult from a JSON string
28
+ v1_dashboard_report_result_instance = V1DashboardReportResult.from_json(json)
29
+ # print the JSON string representation of the object
30
+ print(V1DashboardReportResult.to_json())
31
+
32
+ # convert the object into a dict
33
+ v1_dashboard_report_result_dict = v1_dashboard_report_result_instance.to_dict()
34
+ # create an instance of V1DashboardReportResult from a dict
35
+ v1_dashboard_report_result_from_dict = V1DashboardReportResult.from_dict(v1_dashboard_report_result_dict)
36
+ ```
37
+ [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
38
+
39
+