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.
- eval_studio_client/api/__init__.py +65 -0
- eval_studio_client/api/api/__init__.py +3 -0
- eval_studio_client/api/api/dashboard_report_service_api.py +292 -0
- eval_studio_client/api/api/dashboard_service_api.py +16 -16
- eval_studio_client/api/api/dashboard_test_case_annotation_service_api.py +611 -0
- eval_studio_client/api/api/document_service_api.py +16 -16
- eval_studio_client/api/api/evaluation_service_api.py +12 -12
- eval_studio_client/api/api/evaluator_service_api.py +16 -16
- eval_studio_client/api/api/leaderboard_report_service_api.py +304 -17
- eval_studio_client/api/api/leaderboard_service_api.py +554 -16
- eval_studio_client/api/api/leaderboard_test_case_annotation_service_api.py +611 -0
- eval_studio_client/api/api/model_service_api.py +16 -16
- eval_studio_client/api/api/operation_service_api.py +821 -17
- eval_studio_client/api/api/perturbator_service_api.py +22 -22
- eval_studio_client/api/api/test_case_service_api.py +300 -16
- eval_studio_client/api/api/test_class_service_api.py +16 -16
- eval_studio_client/api/api/test_service_api.py +285 -16
- eval_studio_client/api/api/workflow_node_service_api.py +16 -16
- eval_studio_client/api/api/workflow_service_api.py +16 -16
- eval_studio_client/api/docs/AdversarialInputsServiceTestAdversarialInputsRobustnessRequest.md +2 -1
- eval_studio_client/api/docs/DashboardReportServiceApi.md +75 -0
- eval_studio_client/api/docs/DashboardServiceApi.md +5 -5
- eval_studio_client/api/docs/DashboardTestCaseAnnotationServiceApi.md +149 -0
- eval_studio_client/api/docs/DocumentServiceApi.md +5 -5
- eval_studio_client/api/docs/EvaluationServiceApi.md +4 -4
- eval_studio_client/api/docs/EvaluatorServiceApi.md +5 -5
- eval_studio_client/api/docs/LeaderboardReportServiceApi.md +75 -5
- eval_studio_client/api/docs/LeaderboardServiceApi.md +141 -5
- eval_studio_client/api/docs/LeaderboardTestCaseAnnotationServiceApi.md +149 -0
- eval_studio_client/api/docs/ModelServiceApi.md +5 -5
- eval_studio_client/api/docs/OperationServiceApi.md +215 -8
- eval_studio_client/api/docs/PerturbatorServiceApi.md +7 -7
- eval_studio_client/api/docs/RequiredTheDashboardTestCaseAnnotationToUpdate.md +35 -0
- eval_studio_client/api/docs/RequiredTheLeaderboardTestCaseAnnotationToUpdate.md +35 -0
- eval_studio_client/api/docs/RequiredTheLeaderboardToUpdate.md +1 -0
- eval_studio_client/api/docs/RequiredTheOperationToFinalize.md +1 -0
- eval_studio_client/api/docs/RequiredTheOperationToUpdate.md +1 -0
- eval_studio_client/api/docs/TestCaseServiceApi.md +75 -5
- eval_studio_client/api/docs/TestCaseServiceAppendTestCasesRequest.md +30 -0
- eval_studio_client/api/docs/TestClassServiceApi.md +5 -5
- eval_studio_client/api/docs/TestServiceApi.md +73 -5
- eval_studio_client/api/docs/V1ActualOutputMeta.md +30 -0
- eval_studio_client/api/docs/V1ActualOutputMetaDiff.md +36 -0
- eval_studio_client/api/docs/V1AgentChatActivityDiagram.md +31 -0
- eval_studio_client/api/docs/V1AgentChatActivityDiagramEdge.md +32 -0
- eval_studio_client/api/docs/V1AgentChatActivityDiagramNode.md +32 -0
- eval_studio_client/api/docs/V1AgentChatActivityDiagramRow.md +30 -0
- eval_studio_client/api/docs/V1AgentChatScriptUsage.md +33 -0
- eval_studio_client/api/docs/V1AgentChatScriptsBarChart.md +30 -0
- eval_studio_client/api/docs/V1AgentChatToolUsage.md +33 -0
- eval_studio_client/api/docs/V1AgentChatToolsBarChart.md +30 -0
- eval_studio_client/api/docs/V1AllMetricScores.md +29 -0
- eval_studio_client/api/docs/V1AppendTestCasesResponse.md +29 -0
- eval_studio_client/api/docs/V1BatchCreateLeaderboardsWithoutCacheRequest.md +31 -0
- eval_studio_client/api/docs/V1BatchCreateLeaderboardsWithoutCacheResponse.md +29 -0
- eval_studio_client/api/docs/V1BatchMarkOperationSeenByCreatorResponse.md +29 -0
- eval_studio_client/api/docs/V1CmpLeaderboardReportsRequest.md +33 -0
- eval_studio_client/api/docs/V1CmpLeaderboardReportsResponse.md +29 -0
- eval_studio_client/api/docs/V1ComparisonItem.md +36 -0
- eval_studio_client/api/docs/V1ComparisonMetricScore.md +30 -0
- eval_studio_client/api/docs/V1ComparisonResult.md +31 -0
- eval_studio_client/api/docs/V1ComparisonSummary.md +31 -0
- eval_studio_client/api/docs/V1CreateEvaluationRequest.md +1 -0
- eval_studio_client/api/docs/V1CreateTestFromTestCasesRequest.md +32 -0
- eval_studio_client/api/docs/V1CreateTestFromTestCasesResponse.md +29 -0
- eval_studio_client/api/docs/V1DashboardReport.md +31 -0
- eval_studio_client/api/docs/V1DashboardReportResult.md +39 -0
- eval_studio_client/api/docs/V1DashboardTestCaseAnnotation.md +36 -0
- eval_studio_client/api/docs/V1DataFragment.md +31 -0
- eval_studio_client/api/docs/V1DeepCompareLeaderboardsRequest.md +33 -0
- eval_studio_client/api/docs/V1DeepCompareLeaderboardsResponse.md +29 -0
- eval_studio_client/api/docs/V1DiffItem.md +36 -0
- eval_studio_client/api/docs/V1EvaluationType.md +12 -0
- eval_studio_client/api/docs/V1FlippedMetric.md +31 -0
- eval_studio_client/api/docs/V1GetDashboardReportResponse.md +29 -0
- eval_studio_client/api/docs/V1HumanDecision.md +12 -0
- eval_studio_client/api/docs/V1Info.md +1 -0
- eval_studio_client/api/docs/V1Leaderboard.md +1 -0
- eval_studio_client/api/docs/V1LeaderboardCmpReport.md +30 -0
- eval_studio_client/api/docs/V1LeaderboardComparisonItem.md +31 -0
- eval_studio_client/api/docs/V1LeaderboardInfo.md +30 -0
- eval_studio_client/api/docs/V1LeaderboardReportActualOutputMeta.md +6 -3
- eval_studio_client/api/docs/V1LeaderboardReportResult.md +11 -8
- eval_studio_client/api/docs/V1LeaderboardReportResultView.md +12 -0
- eval_studio_client/api/docs/V1LeaderboardTestCaseAnnotation.md +36 -0
- eval_studio_client/api/docs/V1ListDashboardTestCaseAnnotationsResponse.md +29 -0
- eval_studio_client/api/docs/V1ListLeaderboardTestCaseAnnotationsResponse.md +29 -0
- eval_studio_client/api/docs/V1ListOperationsResponse.md +1 -0
- eval_studio_client/api/docs/V1ListUnseenOperationsResponse.md +30 -0
- eval_studio_client/api/docs/V1MarkOperationSeenByCreatorResponse.md +29 -0
- eval_studio_client/api/docs/V1Metric.md +30 -0
- eval_studio_client/api/docs/V1MetricAverage.md +36 -0
- eval_studio_client/api/docs/V1MetricMeta.md +40 -0
- eval_studio_client/api/docs/V1MetricScore.md +1 -1
- eval_studio_client/api/docs/V1MetricScores.md +1 -1
- eval_studio_client/api/docs/V1ModelType.md +1 -1
- eval_studio_client/api/docs/V1ModelsComparisons.md +32 -0
- eval_studio_client/api/docs/V1ModelsComparisonsMetrics.md +33 -0
- eval_studio_client/api/docs/V1ModelsOverview.md +34 -0
- eval_studio_client/api/docs/V1Operation.md +1 -0
- eval_studio_client/api/docs/V1OperationView.md +12 -0
- eval_studio_client/api/docs/V1RetrievedContextDiff.md +36 -0
- eval_studio_client/api/docs/V1Stats.md +2 -0
- eval_studio_client/api/docs/V1TechnicalMetrics.md +30 -0
- eval_studio_client/api/docs/V1TechnicalMetricsDetail.md +33 -0
- eval_studio_client/api/docs/V1TestCaseLeaderboardItem.md +31 -0
- eval_studio_client/api/docs/V1TestCaseRelationshipInfo.md +31 -0
- eval_studio_client/api/docs/V1TestCaseResult.md +48 -0
- eval_studio_client/api/docs/V1TextSimilarityMetric.md +12 -0
- eval_studio_client/api/docs/V1UpdateDashboardTestCaseAnnotationResponse.md +29 -0
- eval_studio_client/api/docs/V1UpdateLeaderboardTestCaseAnnotationResponse.md +29 -0
- eval_studio_client/api/docs/WorkflowNodeServiceApi.md +5 -5
- eval_studio_client/api/docs/WorkflowServiceApi.md +5 -5
- eval_studio_client/api/models/__init__.py +62 -0
- eval_studio_client/api/models/adversarial_inputs_service_test_adversarial_inputs_robustness_request.py +17 -2
- eval_studio_client/api/models/required_the_dashboard_test_case_annotation_to_update.py +108 -0
- eval_studio_client/api/models/required_the_leaderboard_test_case_annotation_to_update.py +108 -0
- eval_studio_client/api/models/required_the_leaderboard_to_update.py +5 -2
- eval_studio_client/api/models/required_the_operation_to_finalize.py +6 -2
- eval_studio_client/api/models/required_the_operation_to_update.py +6 -2
- eval_studio_client/api/models/test_case_service_append_test_cases_request.py +89 -0
- eval_studio_client/api/models/v1_actual_output_meta.py +97 -0
- eval_studio_client/api/models/v1_actual_output_meta_diff.py +101 -0
- eval_studio_client/api/models/v1_agent_chat_activity_diagram.py +109 -0
- eval_studio_client/api/models/v1_agent_chat_activity_diagram_edge.py +97 -0
- eval_studio_client/api/models/v1_agent_chat_activity_diagram_node.py +97 -0
- eval_studio_client/api/models/v1_agent_chat_activity_diagram_row.py +97 -0
- eval_studio_client/api/models/v1_agent_chat_script_usage.py +101 -0
- eval_studio_client/api/models/v1_agent_chat_scripts_bar_chart.py +102 -0
- eval_studio_client/api/models/v1_agent_chat_tool_usage.py +101 -0
- eval_studio_client/api/models/v1_agent_chat_tools_bar_chart.py +102 -0
- eval_studio_client/api/models/v1_all_metric_scores.py +87 -0
- eval_studio_client/api/models/v1_append_test_cases_response.py +95 -0
- eval_studio_client/api/models/v1_batch_create_leaderboards_without_cache_request.py +99 -0
- eval_studio_client/api/models/v1_batch_create_leaderboards_without_cache_response.py +91 -0
- eval_studio_client/api/models/v1_batch_mark_operation_seen_by_creator_response.py +95 -0
- eval_studio_client/api/models/v1_cmp_leaderboard_reports_request.py +96 -0
- eval_studio_client/api/models/v1_cmp_leaderboard_reports_response.py +91 -0
- eval_studio_client/api/models/v1_comparison_item.py +130 -0
- eval_studio_client/api/models/v1_comparison_metric_score.py +89 -0
- eval_studio_client/api/models/v1_comparison_result.py +120 -0
- eval_studio_client/api/models/v1_comparison_summary.py +91 -0
- eval_studio_client/api/models/v1_create_evaluation_request.py +5 -2
- eval_studio_client/api/models/v1_create_test_from_test_cases_request.py +93 -0
- eval_studio_client/api/models/v1_create_test_from_test_cases_response.py +91 -0
- eval_studio_client/api/models/v1_dashboard_report.py +109 -0
- eval_studio_client/api/models/v1_dashboard_report_result.py +139 -0
- eval_studio_client/api/models/v1_dashboard_test_case_annotation.py +112 -0
- eval_studio_client/api/models/v1_data_fragment.py +91 -0
- eval_studio_client/api/models/v1_deep_compare_leaderboards_request.py +96 -0
- eval_studio_client/api/models/v1_deep_compare_leaderboards_response.py +91 -0
- eval_studio_client/api/models/v1_diff_item.py +137 -0
- eval_studio_client/api/models/v1_evaluation_type.py +39 -0
- eval_studio_client/api/models/v1_flipped_metric.py +91 -0
- eval_studio_client/api/models/v1_get_dashboard_report_response.py +91 -0
- eval_studio_client/api/models/v1_human_decision.py +38 -0
- eval_studio_client/api/models/v1_info.py +4 -2
- eval_studio_client/api/models/v1_leaderboard.py +5 -2
- eval_studio_client/api/models/v1_leaderboard_cmp_report.py +93 -0
- eval_studio_client/api/models/v1_leaderboard_comparison_item.py +91 -0
- eval_studio_client/api/models/v1_leaderboard_info.py +97 -0
- eval_studio_client/api/models/v1_leaderboard_report_actual_output_meta.py +23 -9
- eval_studio_client/api/models/v1_leaderboard_report_result.py +21 -10
- eval_studio_client/api/models/v1_leaderboard_report_result_view.py +38 -0
- eval_studio_client/api/models/v1_leaderboard_test_case_annotation.py +112 -0
- eval_studio_client/api/models/v1_list_dashboard_test_case_annotations_response.py +95 -0
- eval_studio_client/api/models/v1_list_leaderboard_test_case_annotations_response.py +95 -0
- eval_studio_client/api/models/v1_list_operations_response.py +5 -3
- eval_studio_client/api/models/v1_list_unseen_operations_response.py +97 -0
- eval_studio_client/api/models/v1_mark_operation_seen_by_creator_response.py +91 -0
- eval_studio_client/api/models/v1_metric.py +89 -0
- eval_studio_client/api/models/v1_metric_average.py +101 -0
- eval_studio_client/api/models/v1_metric_meta.py +109 -0
- eval_studio_client/api/models/v1_metric_score.py +6 -1
- eval_studio_client/api/models/v1_metric_scores.py +1 -1
- eval_studio_client/api/models/v1_model_type.py +2 -1
- eval_studio_client/api/models/v1_models_comparisons.py +93 -0
- eval_studio_client/api/models/v1_models_comparisons_metrics.py +103 -0
- eval_studio_client/api/models/v1_models_overview.py +97 -0
- eval_studio_client/api/models/v1_operation.py +6 -2
- eval_studio_client/api/models/v1_operation_view.py +38 -0
- eval_studio_client/api/models/v1_retrieved_context_diff.py +101 -0
- eval_studio_client/api/models/v1_stats.py +16 -2
- eval_studio_client/api/models/v1_technical_metrics.py +96 -0
- eval_studio_client/api/models/v1_technical_metrics_detail.py +95 -0
- eval_studio_client/api/models/v1_test_case_leaderboard_item.py +91 -0
- eval_studio_client/api/models/v1_test_case_relationship_info.py +91 -0
- eval_studio_client/api/models/v1_test_case_result.py +157 -0
- eval_studio_client/api/models/v1_text_similarity_metric.py +39 -0
- eval_studio_client/api/models/v1_update_dashboard_test_case_annotation_response.py +91 -0
- eval_studio_client/api/models/v1_update_leaderboard_test_case_annotation_response.py +91 -0
- eval_studio_client/api/models/v1_workflow_node_type.py +1 -0
- eval_studio_client/api/models/v1_workflow_type.py +1 -0
- eval_studio_client/api/test/test_adversarial_inputs_service_test_adversarial_inputs_robustness_request.py +6 -0
- eval_studio_client/api/test/test_dashboard_report_service_api.py +37 -0
- eval_studio_client/api/test/test_dashboard_test_case_annotation_service_api.py +43 -0
- eval_studio_client/api/test/test_leaderboard_report_service_api.py +6 -0
- eval_studio_client/api/test/test_leaderboard_service_api.py +12 -0
- eval_studio_client/api/test/test_leaderboard_test_case_annotation_service_api.py +43 -0
- eval_studio_client/api/test/test_operation_service_api.py +18 -0
- eval_studio_client/api/test/test_required_the_dashboard_test_case_annotation_to_update.py +57 -0
- eval_studio_client/api/test/test_required_the_leaderboard_test_case_annotation_to_update.py +57 -0
- eval_studio_client/api/test/test_required_the_leaderboard_to_update.py +2 -1
- eval_studio_client/api/test/test_required_the_operation_to_finalize.py +2 -1
- eval_studio_client/api/test/test_required_the_operation_to_update.py +2 -1
- eval_studio_client/api/test/test_test_case_service_api.py +6 -0
- eval_studio_client/api/test/test_test_case_service_append_test_cases_request.py +52 -0
- eval_studio_client/api/test/test_test_service_api.py +6 -0
- eval_studio_client/api/test/test_v1_abort_operation_response.py +2 -1
- eval_studio_client/api/test/test_v1_actual_output_meta.py +61 -0
- eval_studio_client/api/test/test_v1_actual_output_meta_diff.py +66 -0
- eval_studio_client/api/test/test_v1_agent_chat_activity_diagram.py +65 -0
- eval_studio_client/api/test/test_v1_agent_chat_activity_diagram_edge.py +53 -0
- eval_studio_client/api/test/test_v1_agent_chat_activity_diagram_node.py +53 -0
- eval_studio_client/api/test/test_v1_agent_chat_activity_diagram_row.py +56 -0
- eval_studio_client/api/test/test_v1_agent_chat_script_usage.py +54 -0
- eval_studio_client/api/test/test_v1_agent_chat_scripts_bar_chart.py +57 -0
- eval_studio_client/api/test/test_v1_agent_chat_tool_usage.py +54 -0
- eval_studio_client/api/test/test_v1_agent_chat_tools_bar_chart.py +57 -0
- eval_studio_client/api/test/test_v1_all_metric_scores.py +53 -0
- eval_studio_client/api/test/test_v1_append_test_cases_response.py +74 -0
- eval_studio_client/api/test/test_v1_batch_create_leaderboards_request.py +2 -1
- eval_studio_client/api/test/test_v1_batch_create_leaderboards_response.py +2 -1
- eval_studio_client/api/test/test_v1_batch_create_leaderboards_without_cache_request.py +120 -0
- eval_studio_client/api/test/test_v1_batch_create_leaderboards_without_cache_response.py +72 -0
- eval_studio_client/api/test/test_v1_batch_delete_leaderboards_response.py +2 -1
- eval_studio_client/api/test/test_v1_batch_get_leaderboards_response.py +2 -1
- eval_studio_client/api/test/test_v1_batch_get_operations_response.py +2 -1
- eval_studio_client/api/test/test_v1_batch_import_leaderboard_response.py +2 -1
- eval_studio_client/api/test/test_v1_batch_mark_operation_seen_by_creator_response.py +74 -0
- eval_studio_client/api/test/test_v1_cmp_leaderboard_reports_request.py +55 -0
- eval_studio_client/api/test/test_v1_cmp_leaderboard_reports_response.py +255 -0
- eval_studio_client/api/test/test_v1_comparison_item.py +233 -0
- eval_studio_client/api/test/test_v1_comparison_metric_score.py +52 -0
- eval_studio_client/api/test/test_v1_comparison_result.py +258 -0
- eval_studio_client/api/test/test_v1_comparison_summary.py +53 -0
- eval_studio_client/api/test/test_v1_create_evaluation_request.py +2 -1
- eval_studio_client/api/test/test_v1_create_leaderboard_request.py +2 -1
- eval_studio_client/api/test/test_v1_create_leaderboard_response.py +2 -1
- eval_studio_client/api/test/test_v1_create_leaderboard_without_cache_response.py +2 -1
- eval_studio_client/api/test/test_v1_create_test_from_test_cases_request.py +54 -0
- eval_studio_client/api/test/test_v1_create_test_from_test_cases_response.py +68 -0
- eval_studio_client/api/test/test_v1_dashboard_report.py +142 -0
- eval_studio_client/api/test/test_v1_dashboard_report_result.py +72 -0
- eval_studio_client/api/test/test_v1_dashboard_test_case_annotation.py +58 -0
- eval_studio_client/api/test/test_v1_data_fragment.py +57 -0
- eval_studio_client/api/test/test_v1_deep_compare_leaderboards_request.py +55 -0
- eval_studio_client/api/test/test_v1_deep_compare_leaderboards_response.py +255 -0
- eval_studio_client/api/test/test_v1_delete_leaderboard_response.py +2 -1
- eval_studio_client/api/test/test_v1_diff_item.py +226 -0
- eval_studio_client/api/test/test_v1_evaluation_type.py +33 -0
- eval_studio_client/api/test/test_v1_finalize_operation_response.py +2 -1
- eval_studio_client/api/test/test_v1_flipped_metric.py +53 -0
- eval_studio_client/api/test/test_v1_generate_test_cases_response.py +2 -1
- eval_studio_client/api/test/test_v1_get_dashboard_report_response.py +143 -0
- eval_studio_client/api/test/test_v1_get_info_response.py +4 -1
- eval_studio_client/api/test/test_v1_get_leaderboard_report_response.py +39 -2
- eval_studio_client/api/test/test_v1_get_leaderboard_response.py +2 -1
- eval_studio_client/api/test/test_v1_get_operation_response.py +2 -1
- eval_studio_client/api/test/test_v1_get_stats_response.py +3 -1
- eval_studio_client/api/test/test_v1_human_decision.py +33 -0
- eval_studio_client/api/test/test_v1_import_leaderboard_response.py +2 -1
- eval_studio_client/api/test/test_v1_import_test_cases_from_library_response.py +2 -1
- eval_studio_client/api/test/test_v1_info.py +4 -1
- eval_studio_client/api/test/test_v1_leaderboard.py +2 -1
- eval_studio_client/api/test/test_v1_leaderboard_cmp_report.py +254 -0
- eval_studio_client/api/test/test_v1_leaderboard_comparison_item.py +53 -0
- eval_studio_client/api/test/test_v1_leaderboard_info.py +57 -0
- eval_studio_client/api/test/test_v1_leaderboard_report.py +39 -2
- eval_studio_client/api/test/test_v1_leaderboard_report_actual_output_meta.py +33 -1
- eval_studio_client/api/test/test_v1_leaderboard_report_result.py +39 -2
- eval_studio_client/api/test/test_v1_leaderboard_report_result_view.py +33 -0
- eval_studio_client/api/test/test_v1_leaderboard_test_case_annotation.py +58 -0
- eval_studio_client/api/test/test_v1_list_dashboard_test_case_annotations_response.py +61 -0
- eval_studio_client/api/test/test_v1_list_leaderboard_test_case_annotations_response.py +61 -0
- eval_studio_client/api/test/test_v1_list_leaderboards_response.py +2 -1
- eval_studio_client/api/test/test_v1_list_most_recent_leaderboards_response.py +2 -1
- eval_studio_client/api/test/test_v1_list_operations_response.py +4 -2
- eval_studio_client/api/test/test_v1_list_unseen_operations_response.py +75 -0
- eval_studio_client/api/test/test_v1_mark_operation_seen_by_creator_response.py +72 -0
- eval_studio_client/api/test/test_v1_metric.py +52 -0
- eval_studio_client/api/test/test_v1_metric_average.py +58 -0
- eval_studio_client/api/test/test_v1_metric_meta.py +66 -0
- eval_studio_client/api/test/test_v1_models_comparisons.py +54 -0
- eval_studio_client/api/test/test_v1_models_comparisons_metrics.py +65 -0
- eval_studio_client/api/test/test_v1_models_overview.py +60 -0
- eval_studio_client/api/test/test_v1_operation.py +2 -1
- eval_studio_client/api/test/test_v1_operation_view.py +33 -0
- eval_studio_client/api/test/test_v1_process_workflow_node_response.py +2 -1
- eval_studio_client/api/test/test_v1_retrieved_context_diff.py +66 -0
- eval_studio_client/api/test/test_v1_stats.py +3 -1
- eval_studio_client/api/test/test_v1_technical_metrics.py +62 -0
- eval_studio_client/api/test/test_v1_technical_metrics_detail.py +55 -0
- eval_studio_client/api/test/test_v1_test_case_leaderboard_item.py +53 -0
- eval_studio_client/api/test/test_v1_test_case_relationship_info.py +53 -0
- eval_studio_client/api/test/test_v1_test_case_result.py +106 -0
- eval_studio_client/api/test/test_v1_text_similarity_metric.py +33 -0
- eval_studio_client/api/test/test_v1_update_dashboard_test_case_annotation_response.py +59 -0
- eval_studio_client/api/test/test_v1_update_leaderboard_response.py +2 -1
- eval_studio_client/api/test/test_v1_update_leaderboard_test_case_annotation_response.py +59 -0
- eval_studio_client/api/test/test_v1_update_operation_response.py +2 -1
- eval_studio_client/gen/openapiv2/eval_studio.swagger.json +2340 -210
- eval_studio_client/models.py +18 -6
- {eval_studio_client-1.2.4a2.dist-info → eval_studio_client-1.3.0.dist-info}/METADATA +2 -2
- {eval_studio_client-1.2.4a2.dist-info → eval_studio_client-1.3.0.dist-info}/RECORD +306 -111
- {eval_studio_client-1.2.4a2.dist-info → eval_studio_client-1.3.0.dist-info}/WHEEL +0 -0
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# V1DashboardTestCaseAnnotation
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**name** | **str** | | [optional] [readonly]
|
|
9
|
+
**create_time** | **datetime** | Output only. Timestamp when the DashboardTestCaseAnnotation was created. | [optional] [readonly]
|
|
10
|
+
**creator** | **str** | Output only. Name of the user or service that requested creation of the DashboardTestCaseAnnotation. | [optional] [readonly]
|
|
11
|
+
**update_time** | **datetime** | Output only. Optional. Timestamp when the DashboardTestCaseAnnotation was last updated. | [optional] [readonly]
|
|
12
|
+
**updater** | **str** | Output only. Optional. Name of the user or service that requested update of the DashboardTestCaseAnnotation. | [optional] [readonly]
|
|
13
|
+
**parent** | **str** | Parent Dashboard Test Case resource name. e.g.: \"dashboards/<UUID>/testCases/<UUID>\". | [optional]
|
|
14
|
+
**key** | **str** | Immutable. Annotation key. | [optional]
|
|
15
|
+
**value** | **object** | Annotation value. | [optional]
|
|
16
|
+
|
|
17
|
+
## Example
|
|
18
|
+
|
|
19
|
+
```python
|
|
20
|
+
from eval_studio_client.api.models.v1_dashboard_test_case_annotation import V1DashboardTestCaseAnnotation
|
|
21
|
+
|
|
22
|
+
# TODO update the JSON string below
|
|
23
|
+
json = "{}"
|
|
24
|
+
# create an instance of V1DashboardTestCaseAnnotation from a JSON string
|
|
25
|
+
v1_dashboard_test_case_annotation_instance = V1DashboardTestCaseAnnotation.from_json(json)
|
|
26
|
+
# print the JSON string representation of the object
|
|
27
|
+
print(V1DashboardTestCaseAnnotation.to_json())
|
|
28
|
+
|
|
29
|
+
# convert the object into a dict
|
|
30
|
+
v1_dashboard_test_case_annotation_dict = v1_dashboard_test_case_annotation_instance.to_dict()
|
|
31
|
+
# create an instance of V1DashboardTestCaseAnnotation from a dict
|
|
32
|
+
v1_dashboard_test_case_annotation_from_dict = V1DashboardTestCaseAnnotation.from_dict(v1_dashboard_test_case_annotation_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 +1,31 @@
|
|
|
1
|
+
# V1DataFragment
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**text** | **str** | Text content. | [optional]
|
|
9
|
+
**metrics** | **Dict[str, float]** | Metrics for this fragment. | [optional]
|
|
10
|
+
**meta** | **Dict[str, str]** | Additional metadata. | [optional]
|
|
11
|
+
|
|
12
|
+
## Example
|
|
13
|
+
|
|
14
|
+
```python
|
|
15
|
+
from eval_studio_client.api.models.v1_data_fragment import V1DataFragment
|
|
16
|
+
|
|
17
|
+
# TODO update the JSON string below
|
|
18
|
+
json = "{}"
|
|
19
|
+
# create an instance of V1DataFragment from a JSON string
|
|
20
|
+
v1_data_fragment_instance = V1DataFragment.from_json(json)
|
|
21
|
+
# print the JSON string representation of the object
|
|
22
|
+
print(V1DataFragment.to_json())
|
|
23
|
+
|
|
24
|
+
# convert the object into a dict
|
|
25
|
+
v1_data_fragment_dict = v1_data_fragment_instance.to_dict()
|
|
26
|
+
# create an instance of V1DataFragment from a dict
|
|
27
|
+
v1_data_fragment_from_dict = V1DataFragment.from_dict(v1_data_fragment_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 +1,33 @@
|
|
|
1
|
+
# V1DeepCompareLeaderboardsRequest
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**leaderboard_baseline_name** | **str** | Required. The resource name of the baseline leaderboard to compare against. | [optional]
|
|
9
|
+
**leaderboard_current_name** | **str** | Required. The resource name of the current leaderboard to compare. | [optional]
|
|
10
|
+
**text_similarity_metric** | [**V1TextSimilarityMetric**](V1TextSimilarityMetric.md) | | [optional]
|
|
11
|
+
**llm_model_baseline_name** | **str** | Required. The baseline LLM model name to compare. | [optional]
|
|
12
|
+
**llm_model_current_name** | **str** | Required. The current LLM model name to compare. | [optional]
|
|
13
|
+
|
|
14
|
+
## Example
|
|
15
|
+
|
|
16
|
+
```python
|
|
17
|
+
from eval_studio_client.api.models.v1_deep_compare_leaderboards_request import V1DeepCompareLeaderboardsRequest
|
|
18
|
+
|
|
19
|
+
# TODO update the JSON string below
|
|
20
|
+
json = "{}"
|
|
21
|
+
# create an instance of V1DeepCompareLeaderboardsRequest from a JSON string
|
|
22
|
+
v1_deep_compare_leaderboards_request_instance = V1DeepCompareLeaderboardsRequest.from_json(json)
|
|
23
|
+
# print the JSON string representation of the object
|
|
24
|
+
print(V1DeepCompareLeaderboardsRequest.to_json())
|
|
25
|
+
|
|
26
|
+
# convert the object into a dict
|
|
27
|
+
v1_deep_compare_leaderboards_request_dict = v1_deep_compare_leaderboards_request_instance.to_dict()
|
|
28
|
+
# create an instance of V1DeepCompareLeaderboardsRequest from a dict
|
|
29
|
+
v1_deep_compare_leaderboards_request_from_dict = V1DeepCompareLeaderboardsRequest.from_dict(v1_deep_compare_leaderboards_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
|
+
# V1DeepCompareLeaderboardsResponse
|
|
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_deep_compare_leaderboards_response import V1DeepCompareLeaderboardsResponse
|
|
14
|
+
|
|
15
|
+
# TODO update the JSON string below
|
|
16
|
+
json = "{}"
|
|
17
|
+
# create an instance of V1DeepCompareLeaderboardsResponse from a JSON string
|
|
18
|
+
v1_deep_compare_leaderboards_response_instance = V1DeepCompareLeaderboardsResponse.from_json(json)
|
|
19
|
+
# print the JSON string representation of the object
|
|
20
|
+
print(V1DeepCompareLeaderboardsResponse.to_json())
|
|
21
|
+
|
|
22
|
+
# convert the object into a dict
|
|
23
|
+
v1_deep_compare_leaderboards_response_dict = v1_deep_compare_leaderboards_response_instance.to_dict()
|
|
24
|
+
# create an instance of V1DeepCompareLeaderboardsResponse from a dict
|
|
25
|
+
v1_deep_compare_leaderboards_response_from_dict = V1DeepCompareLeaderboardsResponse.from_dict(v1_deep_compare_leaderboards_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
|
+
# V1DiffItem
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**diff_key** | **str** | Unique key identifying the diff (format: \"baseline_id|current_id\"). | [optional]
|
|
9
|
+
**items** | [**List[V1ComparisonItem]**](V1ComparisonItem.md) | List of comparison items. | [optional]
|
|
10
|
+
**summary** | [**V1ComparisonSummary**](V1ComparisonSummary.md) | | [optional]
|
|
11
|
+
**models_overview** | [**V1ModelsOverview**](V1ModelsOverview.md) | | [optional]
|
|
12
|
+
**models_comparisons** | [**V1ModelsComparisons**](V1ModelsComparisons.md) | | [optional]
|
|
13
|
+
**models_comparisons_metrics** | [**V1ModelsComparisonsMetrics**](V1ModelsComparisonsMetrics.md) | | [optional]
|
|
14
|
+
**technical_metrics** | [**V1TechnicalMetrics**](V1TechnicalMetrics.md) | | [optional]
|
|
15
|
+
**test_cases_leaderboard** | [**List[V1TestCaseLeaderboardItem]**](V1TestCaseLeaderboardItem.md) | Test cases leaderboard. | [optional]
|
|
16
|
+
|
|
17
|
+
## Example
|
|
18
|
+
|
|
19
|
+
```python
|
|
20
|
+
from eval_studio_client.api.models.v1_diff_item import V1DiffItem
|
|
21
|
+
|
|
22
|
+
# TODO update the JSON string below
|
|
23
|
+
json = "{}"
|
|
24
|
+
# create an instance of V1DiffItem from a JSON string
|
|
25
|
+
v1_diff_item_instance = V1DiffItem.from_json(json)
|
|
26
|
+
# print the JSON string representation of the object
|
|
27
|
+
print(V1DiffItem.to_json())
|
|
28
|
+
|
|
29
|
+
# convert the object into a dict
|
|
30
|
+
v1_diff_item_dict = v1_diff_item_instance.to_dict()
|
|
31
|
+
# create an instance of V1DiffItem from a dict
|
|
32
|
+
v1_diff_item_from_dict = V1DiffItem.from_dict(v1_diff_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 +1,12 @@
|
|
|
1
|
+
# V1EvaluationType
|
|
2
|
+
|
|
3
|
+
- EVALUATION_TYPE_UNSPECIFIED: Unspecified type. - EVALUATION_TYPE_LLM: LLM Evaluation, where evaluated model doesn't retrieve any context. - EVALUATION_TYPE_RAG: RAG Evaluation, where evaluated model retrieves context from a given collection. - EVALUATION_TYPE_AGENT: Agent Evaluation, where evaluated model is an agent that can interact with tools.
|
|
4
|
+
|
|
5
|
+
## Properties
|
|
6
|
+
|
|
7
|
+
Name | Type | Description | Notes
|
|
8
|
+
------------ | ------------- | ------------- | -------------
|
|
9
|
+
|
|
10
|
+
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
|
|
11
|
+
|
|
12
|
+
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
# V1FlippedMetric
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**metric_name** | **str** | Metric name. | [optional]
|
|
9
|
+
**baseline_value** | **float** | Baseline value. | [optional]
|
|
10
|
+
**current_value** | **float** | Current value. | [optional]
|
|
11
|
+
|
|
12
|
+
## Example
|
|
13
|
+
|
|
14
|
+
```python
|
|
15
|
+
from eval_studio_client.api.models.v1_flipped_metric import V1FlippedMetric
|
|
16
|
+
|
|
17
|
+
# TODO update the JSON string below
|
|
18
|
+
json = "{}"
|
|
19
|
+
# create an instance of V1FlippedMetric from a JSON string
|
|
20
|
+
v1_flipped_metric_instance = V1FlippedMetric.from_json(json)
|
|
21
|
+
# print the JSON string representation of the object
|
|
22
|
+
print(V1FlippedMetric.to_json())
|
|
23
|
+
|
|
24
|
+
# convert the object into a dict
|
|
25
|
+
v1_flipped_metric_dict = v1_flipped_metric_instance.to_dict()
|
|
26
|
+
# create an instance of V1FlippedMetric from a dict
|
|
27
|
+
v1_flipped_metric_from_dict = V1FlippedMetric.from_dict(v1_flipped_metric_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
|
+
# V1GetDashboardReportResponse
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**dashboard_report** | [**V1DashboardReport**](V1DashboardReport.md) | | [optional]
|
|
9
|
+
|
|
10
|
+
## Example
|
|
11
|
+
|
|
12
|
+
```python
|
|
13
|
+
from eval_studio_client.api.models.v1_get_dashboard_report_response import V1GetDashboardReportResponse
|
|
14
|
+
|
|
15
|
+
# TODO update the JSON string below
|
|
16
|
+
json = "{}"
|
|
17
|
+
# create an instance of V1GetDashboardReportResponse from a JSON string
|
|
18
|
+
v1_get_dashboard_report_response_instance = V1GetDashboardReportResponse.from_json(json)
|
|
19
|
+
# print the JSON string representation of the object
|
|
20
|
+
print(V1GetDashboardReportResponse.to_json())
|
|
21
|
+
|
|
22
|
+
# convert the object into a dict
|
|
23
|
+
v1_get_dashboard_report_response_dict = v1_get_dashboard_report_response_instance.to_dict()
|
|
24
|
+
# create an instance of V1GetDashboardReportResponse from a dict
|
|
25
|
+
v1_get_dashboard_report_response_from_dict = V1GetDashboardReportResponse.from_dict(v1_get_dashboard_report_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 +1,12 @@
|
|
|
1
|
+
# V1HumanDecision
|
|
2
|
+
|
|
3
|
+
HumanDecision represents the human decision on the result. - HUMAN_DECISION_UNSPECIFIED: Default value, means no decision has been made. - HUMAN_DECISION_APPROVED: The result was approved by human. - HUMAN_DECISION_REJECTED: The result was rejected by human.
|
|
4
|
+
|
|
5
|
+
## Properties
|
|
6
|
+
|
|
7
|
+
Name | Type | Description | Notes
|
|
8
|
+
------------ | ------------- | ------------- | -------------
|
|
9
|
+
|
|
10
|
+
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
|
|
11
|
+
|
|
12
|
+
|
|
@@ -17,6 +17,7 @@ Name | Type | Description | Notes
|
|
|
17
17
|
**public_instance** | **bool** | If the Eval Studio instance is public. | [optional]
|
|
18
18
|
**sharing_enabled** | **bool** | Whether the sharing capability is enabled. | [optional]
|
|
19
19
|
**experimental_features_enabled** | **bool** | Whether the experimental features are enabled. | [optional]
|
|
20
|
+
**model_type_allowlist** | **List[str]** | Allowlist of model types for UI that can be hosted in Eval Studio. E.g. MODEL_TYPE_H2OGPTE_RAG, MODEL_TYPE_OPENAI_CHAT, MODEL_TYPE_AMAZON_BEDROCK. Use \"*\" to allow all model types. | [optional]
|
|
20
21
|
|
|
21
22
|
## Example
|
|
22
23
|
|
|
@@ -31,6 +31,7 @@ Name | Type | Description | Notes
|
|
|
31
31
|
**type** | [**V1LeaderboardType**](V1LeaderboardType.md) | | [optional]
|
|
32
32
|
**demo** | **bool** | Output only. Whether the Leaderboard is a demo resource or not. Demo resources are read only. | [optional] [readonly]
|
|
33
33
|
**test_lab** | **str** | Optional. Resource name of the TestLab if Leaderboard was created from a imported TestLab. | [optional]
|
|
34
|
+
**evaluation_type** | [**V1EvaluationType**](V1EvaluationType.md) | | [optional]
|
|
34
35
|
|
|
35
36
|
## Example
|
|
36
37
|
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
# V1LeaderboardCmpReport
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**summary** | **str** | Summary of the comparison. | [optional]
|
|
9
|
+
**comparison_result** | [**V1ComparisonResult**](V1ComparisonResult.md) | | [optional]
|
|
10
|
+
|
|
11
|
+
## Example
|
|
12
|
+
|
|
13
|
+
```python
|
|
14
|
+
from eval_studio_client.api.models.v1_leaderboard_cmp_report import V1LeaderboardCmpReport
|
|
15
|
+
|
|
16
|
+
# TODO update the JSON string below
|
|
17
|
+
json = "{}"
|
|
18
|
+
# create an instance of V1LeaderboardCmpReport from a JSON string
|
|
19
|
+
v1_leaderboard_cmp_report_instance = V1LeaderboardCmpReport.from_json(json)
|
|
20
|
+
# print the JSON string representation of the object
|
|
21
|
+
print(V1LeaderboardCmpReport.to_json())
|
|
22
|
+
|
|
23
|
+
# convert the object into a dict
|
|
24
|
+
v1_leaderboard_cmp_report_dict = v1_leaderboard_cmp_report_instance.to_dict()
|
|
25
|
+
# create an instance of V1LeaderboardCmpReport from a dict
|
|
26
|
+
v1_leaderboard_cmp_report_from_dict = V1LeaderboardCmpReport.from_dict(v1_leaderboard_cmp_report_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
|
+
# V1LeaderboardComparisonItem
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**wins** | **int** | Number of wins. | [optional]
|
|
9
|
+
**question** | **str** | Question text. | [optional]
|
|
10
|
+
**changed_metrics_count** | **int** | Count of changed metrics. | [optional]
|
|
11
|
+
|
|
12
|
+
## Example
|
|
13
|
+
|
|
14
|
+
```python
|
|
15
|
+
from eval_studio_client.api.models.v1_leaderboard_comparison_item import V1LeaderboardComparisonItem
|
|
16
|
+
|
|
17
|
+
# TODO update the JSON string below
|
|
18
|
+
json = "{}"
|
|
19
|
+
# create an instance of V1LeaderboardComparisonItem from a JSON string
|
|
20
|
+
v1_leaderboard_comparison_item_instance = V1LeaderboardComparisonItem.from_json(json)
|
|
21
|
+
# print the JSON string representation of the object
|
|
22
|
+
print(V1LeaderboardComparisonItem.to_json())
|
|
23
|
+
|
|
24
|
+
# convert the object into a dict
|
|
25
|
+
v1_leaderboard_comparison_item_dict = v1_leaderboard_comparison_item_instance.to_dict()
|
|
26
|
+
# create an instance of V1LeaderboardComparisonItem from a dict
|
|
27
|
+
v1_leaderboard_comparison_item_from_dict = V1LeaderboardComparisonItem.from_dict(v1_leaderboard_comparison_item_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 +1,30 @@
|
|
|
1
|
+
# V1LeaderboardInfo
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**key** | **str** | Unique key identifying the leaderboard pair (format: \"baseline_id|current_id\"). | [optional]
|
|
9
|
+
**items** | [**List[V1LeaderboardComparisonItem]**](V1LeaderboardComparisonItem.md) | List of leaderboard comparison items. | [optional]
|
|
10
|
+
|
|
11
|
+
## Example
|
|
12
|
+
|
|
13
|
+
```python
|
|
14
|
+
from eval_studio_client.api.models.v1_leaderboard_info import V1LeaderboardInfo
|
|
15
|
+
|
|
16
|
+
# TODO update the JSON string below
|
|
17
|
+
json = "{}"
|
|
18
|
+
# create an instance of V1LeaderboardInfo from a JSON string
|
|
19
|
+
v1_leaderboard_info_instance = V1LeaderboardInfo.from_json(json)
|
|
20
|
+
# print the JSON string representation of the object
|
|
21
|
+
print(V1LeaderboardInfo.to_json())
|
|
22
|
+
|
|
23
|
+
# convert the object into a dict
|
|
24
|
+
v1_leaderboard_info_dict = v1_leaderboard_info_instance.to_dict()
|
|
25
|
+
# create an instance of V1LeaderboardInfo from a dict
|
|
26
|
+
v1_leaderboard_info_from_dict = V1LeaderboardInfo.from_dict(v1_leaderboard_info_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
|
+
|
|
@@ -1,13 +1,16 @@
|
|
|
1
1
|
# V1LeaderboardReportActualOutputMeta
|
|
2
2
|
|
|
3
|
-
ActualOutputMeta represents the metadata about the actual output.
|
|
3
|
+
ActualOutputMeta represents the metadata about the actual output. Each instance can contain any combination of the fields below.
|
|
4
4
|
|
|
5
5
|
## Properties
|
|
6
6
|
|
|
7
7
|
Name | Type | Description | Notes
|
|
8
8
|
------------ | ------------- | ------------- | -------------
|
|
9
|
-
**tokenization** | **str** |
|
|
10
|
-
**data** | [**List[V1LeaderboardReportActualOutputData]**](V1LeaderboardReportActualOutputData.md) |
|
|
9
|
+
**tokenization** | **str** | Optional. Actual output data tokenization like sentence_level_punkt. | [optional]
|
|
10
|
+
**data** | [**List[V1LeaderboardReportActualOutputData]**](V1LeaderboardReportActualOutputData.md) | Optional. Actual output data - list of text fragments coupled with the metric values. | [optional]
|
|
11
|
+
**agent_chat_activity_diagram** | [**V1AgentChatActivityDiagram**](V1AgentChatActivityDiagram.md) | | [optional]
|
|
12
|
+
**agent_chat_tools_bar_chart** | [**V1AgentChatToolsBarChart**](V1AgentChatToolsBarChart.md) | | [optional]
|
|
13
|
+
**agent_chat_scripts_bar_chart** | [**V1AgentChatScriptsBarChart**](V1AgentChatScriptsBarChart.md) | | [optional]
|
|
11
14
|
|
|
12
15
|
## Example
|
|
13
16
|
|
|
@@ -7,21 +7,24 @@ Name | Type | Description | Notes
|
|
|
7
7
|
------------ | ------------- | ------------- | -------------
|
|
8
8
|
**key** | **str** | Output only. Composite unique key of the result formed by the model key and test case key. | [optional] [readonly]
|
|
9
9
|
**input** | **str** | Output only. Input prompt or text to be processed. | [optional] [readonly]
|
|
10
|
-
**corpus** | **List[str]** | Output only. Collection of corpus documents to be used during evaluation. | [optional] [readonly]
|
|
11
|
-
**context** | **List[str]** | Output only. List of contextual information or references. | [optional] [readonly]
|
|
12
|
-
**categories** | **List[str]** | Output only. List of categories or labels for classification. | [optional] [readonly]
|
|
13
|
-
**relationships** | [**List[V1LeaderboardReportResultRelationship]**](V1LeaderboardReportResultRelationship.md) | Output only. List of relationships or associations between entities. | [optional] [readonly]
|
|
10
|
+
**corpus** | **List[str]** | Output only. Collection of corpus documents to be used during evaluation. Omitted if LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used. | [optional] [readonly]
|
|
11
|
+
**context** | **List[str]** | Output only. List of contextual information or references. Omitted if LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used. | [optional] [readonly]
|
|
12
|
+
**categories** | **List[str]** | Output only. List of categories or labels for classification. Omitted if LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used. | [optional] [readonly]
|
|
13
|
+
**relationships** | [**List[V1LeaderboardReportResultRelationship]**](V1LeaderboardReportResultRelationship.md) | Output only. List of relationships or associations between entities. Omitted if LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used. | [optional] [readonly]
|
|
14
14
|
**expected_output** | **str** | Output only. Expected output or target result. | [optional] [readonly]
|
|
15
|
-
**output_constraints** | **List[str]** | Output only. List of constraints that should be applied to the output. | [optional] [readonly]
|
|
16
|
-
**output_condition** | **str** | Output only. Condition that output should satisfy. | [optional] [readonly]
|
|
15
|
+
**output_constraints** | **List[str]** | Output only. List of constraints that should be applied to the output. Omitted if LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used. | [optional] [readonly]
|
|
16
|
+
**output_condition** | **str** | Output only. Condition that output should satisfy. Omitted if LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used. | [optional] [readonly]
|
|
17
17
|
**actual_output** | **str** | Output only. Actual output produced by the model. | [optional] [readonly]
|
|
18
|
-
**actual_duration** | **float** | Output only. Duration of processing in seconds. | [optional] [readonly]
|
|
19
|
-
**cost** | **float** | Output only. Cost of processing in currency units. | [optional] [readonly]
|
|
18
|
+
**actual_duration** | **float** | Output only. Duration of processing in seconds. Omitted if LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used. | [optional] [readonly]
|
|
19
|
+
**cost** | **float** | Output only. Cost of processing in currency units. Omitted if LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used. | [optional] [readonly]
|
|
20
20
|
**model_key** | **str** | Output only. Unique identifier for the model used. | [optional] [readonly]
|
|
21
21
|
**test_case_key** | **str** | Output only. Unique identifier for the test case. | [optional] [readonly]
|
|
22
22
|
**metrics** | [**List[V1MetricScore]**](V1MetricScore.md) | Optional. All metrics values for the result. | [optional]
|
|
23
23
|
**result_error_message** | **str** | Output only. Error message if processing resulted in failure. | [optional] [readonly]
|
|
24
24
|
**actual_output_meta** | [**List[V1LeaderboardReportActualOutputMeta]**](V1LeaderboardReportActualOutputMeta.md) | Output only. Additional metadata about the actual output. | [optional] [readonly]
|
|
25
|
+
**human_decision** | [**V1HumanDecision**](V1HumanDecision.md) | | [optional]
|
|
26
|
+
**comment** | **str** | Output only. Optional comment about the result. | [optional] [readonly]
|
|
27
|
+
**annotations** | **Dict[str, object]** | Output only. Annotations associated with the test case result. | [optional] [readonly]
|
|
25
28
|
|
|
26
29
|
## Example
|
|
27
30
|
|
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
# V1LeaderboardReportResultView
|
|
2
|
+
|
|
3
|
+
- LEADERBOARD_REPORT_RESULT_VIEW_UNSPECIFIED: Default value. The basic view with essential fields. - LEADERBOARD_REPORT_RESULT_VIEW_FULL: Full view with all fields populated. - LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY: Summary view with only key fields.
|
|
4
|
+
|
|
5
|
+
## Properties
|
|
6
|
+
|
|
7
|
+
Name | Type | Description | Notes
|
|
8
|
+
------------ | ------------- | ------------- | -------------
|
|
9
|
+
|
|
10
|
+
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
|
|
11
|
+
|
|
12
|
+
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# V1LeaderboardTestCaseAnnotation
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**name** | **str** | | [optional] [readonly]
|
|
9
|
+
**create_time** | **datetime** | Output only. Timestamp when the LeaderboardTestCaseAnnotation was created. | [optional] [readonly]
|
|
10
|
+
**creator** | **str** | Output only. Name of the user or service that requested creation of the LeaderboardTestCaseAnnotation. | [optional] [readonly]
|
|
11
|
+
**update_time** | **datetime** | Output only. Optional. Timestamp when the LeaderboardTestCaseAnnotation was last updated. | [optional] [readonly]
|
|
12
|
+
**updater** | **str** | Output only. Optional. Name of the user or service that requested update of the LeaderboardTestCaseAnnotation. | [optional] [readonly]
|
|
13
|
+
**parent** | **str** | Parent Leaderboard Test Case resource name. e.g.: \"leaderboards/<UUID>/testCases/<UUID>\". | [optional]
|
|
14
|
+
**key** | **str** | Immutable. Annotation key. | [optional]
|
|
15
|
+
**value** | **object** | Annotation value. | [optional]
|
|
16
|
+
|
|
17
|
+
## Example
|
|
18
|
+
|
|
19
|
+
```python
|
|
20
|
+
from eval_studio_client.api.models.v1_leaderboard_test_case_annotation import V1LeaderboardTestCaseAnnotation
|
|
21
|
+
|
|
22
|
+
# TODO update the JSON string below
|
|
23
|
+
json = "{}"
|
|
24
|
+
# create an instance of V1LeaderboardTestCaseAnnotation from a JSON string
|
|
25
|
+
v1_leaderboard_test_case_annotation_instance = V1LeaderboardTestCaseAnnotation.from_json(json)
|
|
26
|
+
# print the JSON string representation of the object
|
|
27
|
+
print(V1LeaderboardTestCaseAnnotation.to_json())
|
|
28
|
+
|
|
29
|
+
# convert the object into a dict
|
|
30
|
+
v1_leaderboard_test_case_annotation_dict = v1_leaderboard_test_case_annotation_instance.to_dict()
|
|
31
|
+
# create an instance of V1LeaderboardTestCaseAnnotation from a dict
|
|
32
|
+
v1_leaderboard_test_case_annotation_from_dict = V1LeaderboardTestCaseAnnotation.from_dict(v1_leaderboard_test_case_annotation_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 +1,29 @@
|
|
|
1
|
+
# V1ListDashboardTestCaseAnnotationsResponse
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**dashboard_test_case_annotations** | [**List[V1DashboardTestCaseAnnotation]**](V1DashboardTestCaseAnnotation.md) | The list of DashboardTestCaseAnnotations. | [optional]
|
|
9
|
+
|
|
10
|
+
## Example
|
|
11
|
+
|
|
12
|
+
```python
|
|
13
|
+
from eval_studio_client.api.models.v1_list_dashboard_test_case_annotations_response import V1ListDashboardTestCaseAnnotationsResponse
|
|
14
|
+
|
|
15
|
+
# TODO update the JSON string below
|
|
16
|
+
json = "{}"
|
|
17
|
+
# create an instance of V1ListDashboardTestCaseAnnotationsResponse from a JSON string
|
|
18
|
+
v1_list_dashboard_test_case_annotations_response_instance = V1ListDashboardTestCaseAnnotationsResponse.from_json(json)
|
|
19
|
+
# print the JSON string representation of the object
|
|
20
|
+
print(V1ListDashboardTestCaseAnnotationsResponse.to_json())
|
|
21
|
+
|
|
22
|
+
# convert the object into a dict
|
|
23
|
+
v1_list_dashboard_test_case_annotations_response_dict = v1_list_dashboard_test_case_annotations_response_instance.to_dict()
|
|
24
|
+
# create an instance of V1ListDashboardTestCaseAnnotationsResponse from a dict
|
|
25
|
+
v1_list_dashboard_test_case_annotations_response_from_dict = V1ListDashboardTestCaseAnnotationsResponse.from_dict(v1_list_dashboard_test_case_annotations_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
|
+
# V1ListLeaderboardTestCaseAnnotationsResponse
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**leaderboard_test_case_annotations** | [**List[V1LeaderboardTestCaseAnnotation]**](V1LeaderboardTestCaseAnnotation.md) | The list of LeaderboardTestCaseAnnotations. | [optional]
|
|
9
|
+
|
|
10
|
+
## Example
|
|
11
|
+
|
|
12
|
+
```python
|
|
13
|
+
from eval_studio_client.api.models.v1_list_leaderboard_test_case_annotations_response import V1ListLeaderboardTestCaseAnnotationsResponse
|
|
14
|
+
|
|
15
|
+
# TODO update the JSON string below
|
|
16
|
+
json = "{}"
|
|
17
|
+
# create an instance of V1ListLeaderboardTestCaseAnnotationsResponse from a JSON string
|
|
18
|
+
v1_list_leaderboard_test_case_annotations_response_instance = V1ListLeaderboardTestCaseAnnotationsResponse.from_json(json)
|
|
19
|
+
# print the JSON string representation of the object
|
|
20
|
+
print(V1ListLeaderboardTestCaseAnnotationsResponse.to_json())
|
|
21
|
+
|
|
22
|
+
# convert the object into a dict
|
|
23
|
+
v1_list_leaderboard_test_case_annotations_response_dict = v1_list_leaderboard_test_case_annotations_response_instance.to_dict()
|
|
24
|
+
# create an instance of V1ListLeaderboardTestCaseAnnotationsResponse from a dict
|
|
25
|
+
v1_list_leaderboard_test_case_annotations_response_from_dict = V1ListLeaderboardTestCaseAnnotationsResponse.from_dict(v1_list_leaderboard_test_case_annotations_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
|
+
|
|
@@ -6,6 +6,7 @@
|
|
|
6
6
|
Name | Type | Description | Notes
|
|
7
7
|
------------ | ------------- | ------------- | -------------
|
|
8
8
|
**operations** | [**List[V1Operation]**](V1Operation.md) | The list of Operations. | [optional]
|
|
9
|
+
**total_size** | **int** | The total number of Operations that match the request, irrespective of pagination. | [optional]
|
|
9
10
|
|
|
10
11
|
## Example
|
|
11
12
|
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
# V1ListUnseenOperationsResponse
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**operations** | [**List[V1Operation]**](V1Operation.md) | The list of Operations that the user has not seen. | [optional]
|
|
9
|
+
**total_size** | **int** | The total number of unseen Operations that match the request, irrespective of pagination. | [optional]
|
|
10
|
+
|
|
11
|
+
## Example
|
|
12
|
+
|
|
13
|
+
```python
|
|
14
|
+
from eval_studio_client.api.models.v1_list_unseen_operations_response import V1ListUnseenOperationsResponse
|
|
15
|
+
|
|
16
|
+
# TODO update the JSON string below
|
|
17
|
+
json = "{}"
|
|
18
|
+
# create an instance of V1ListUnseenOperationsResponse from a JSON string
|
|
19
|
+
v1_list_unseen_operations_response_instance = V1ListUnseenOperationsResponse.from_json(json)
|
|
20
|
+
# print the JSON string representation of the object
|
|
21
|
+
print(V1ListUnseenOperationsResponse.to_json())
|
|
22
|
+
|
|
23
|
+
# convert the object into a dict
|
|
24
|
+
v1_list_unseen_operations_response_dict = v1_list_unseen_operations_response_instance.to_dict()
|
|
25
|
+
# create an instance of V1ListUnseenOperationsResponse from a dict
|
|
26
|
+
v1_list_unseen_operations_response_from_dict = V1ListUnseenOperationsResponse.from_dict(v1_list_unseen_operations_response_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
|
+
# V1MarkOperationSeenByCreatorResponse
|
|
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_mark_operation_seen_by_creator_response import V1MarkOperationSeenByCreatorResponse
|
|
14
|
+
|
|
15
|
+
# TODO update the JSON string below
|
|
16
|
+
json = "{}"
|
|
17
|
+
# create an instance of V1MarkOperationSeenByCreatorResponse from a JSON string
|
|
18
|
+
v1_mark_operation_seen_by_creator_response_instance = V1MarkOperationSeenByCreatorResponse.from_json(json)
|
|
19
|
+
# print the JSON string representation of the object
|
|
20
|
+
print(V1MarkOperationSeenByCreatorResponse.to_json())
|
|
21
|
+
|
|
22
|
+
# convert the object into a dict
|
|
23
|
+
v1_mark_operation_seen_by_creator_response_dict = v1_mark_operation_seen_by_creator_response_instance.to_dict()
|
|
24
|
+
# create an instance of V1MarkOperationSeenByCreatorResponse from a dict
|
|
25
|
+
v1_mark_operation_seen_by_creator_response_from_dict = V1MarkOperationSeenByCreatorResponse.from_dict(v1_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 +1,30 @@
|
|
|
1
|
+
# V1Metric
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**key** | **str** | Metric key. | [optional]
|
|
9
|
+
**value** | **float** | Metric value (optional). | [optional]
|
|
10
|
+
|
|
11
|
+
## Example
|
|
12
|
+
|
|
13
|
+
```python
|
|
14
|
+
from eval_studio_client.api.models.v1_metric import V1Metric
|
|
15
|
+
|
|
16
|
+
# TODO update the JSON string below
|
|
17
|
+
json = "{}"
|
|
18
|
+
# create an instance of V1Metric from a JSON string
|
|
19
|
+
v1_metric_instance = V1Metric.from_json(json)
|
|
20
|
+
# print the JSON string representation of the object
|
|
21
|
+
print(V1Metric.to_json())
|
|
22
|
+
|
|
23
|
+
# convert the object into a dict
|
|
24
|
+
v1_metric_dict = v1_metric_instance.to_dict()
|
|
25
|
+
# create an instance of V1Metric from a dict
|
|
26
|
+
v1_metric_from_dict = V1Metric.from_dict(v1_metric_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
|
+
|