eval-studio-client 1.2.5__py3-none-any.whl → 1.3.0a1__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-1.2.5.dist-info → eval_studio_client-1.3.0a1.dist-info}/METADATA +2 -2
- {eval_studio_client-1.2.5.dist-info → eval_studio_client-1.3.0a1.dist-info}/RECORD +306 -111
- {eval_studio_client-1.2.5.dist-info → eval_studio_client-1.3.0a1.dist-info}/WHEEL +0 -0
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
# coding: utf-8
|
|
2
|
+
|
|
3
|
+
"""
|
|
4
|
+
ai/h2o/eval_studio/v1/insight.proto
|
|
5
|
+
|
|
6
|
+
No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
|
|
7
|
+
|
|
8
|
+
The version of the OpenAPI document: version not set
|
|
9
|
+
Generated by OpenAPI Generator (https://openapi-generator.tech)
|
|
10
|
+
|
|
11
|
+
Do not edit the class manually.
|
|
12
|
+
""" # noqa: E501
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
from __future__ import annotations
|
|
16
|
+
import pprint
|
|
17
|
+
import re # noqa: F401
|
|
18
|
+
import json
|
|
19
|
+
|
|
20
|
+
from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictFloat, StrictInt, StrictStr
|
|
21
|
+
from typing import Any, ClassVar, Dict, List, Optional, Union
|
|
22
|
+
from typing import Optional, Set
|
|
23
|
+
from typing_extensions import Self
|
|
24
|
+
|
|
25
|
+
class V1RetrievedContextDiff(BaseModel):
|
|
26
|
+
"""
|
|
27
|
+
V1RetrievedContextDiff
|
|
28
|
+
""" # noqa: E501
|
|
29
|
+
chunks: Optional[List[StrictStr]] = Field(default=None, description="Context chunks.")
|
|
30
|
+
chunks_count: Optional[StrictInt] = Field(default=None, description="Chunk count.", alias="chunksCount")
|
|
31
|
+
common_chunks: Optional[List[StrictStr]] = Field(default=None, description="Common chunks between baseline and current.", alias="commonChunks")
|
|
32
|
+
common_count: Optional[StrictInt] = Field(default=None, description="Common chunk count.", alias="commonCount")
|
|
33
|
+
unique_chunks: Optional[List[StrictStr]] = Field(default=None, description="Unique chunks.", alias="uniqueChunks")
|
|
34
|
+
unique_count: Optional[StrictInt] = Field(default=None, description="Unique chunk count.", alias="uniqueCount")
|
|
35
|
+
identical: Optional[StrictBool] = Field(default=None, description="Whether contexts are identical.")
|
|
36
|
+
chunk_similarity: Optional[Dict[str, Union[StrictFloat, StrictInt]]] = Field(default=None, description="Chunk similarity scores.", alias="chunkSimilarity")
|
|
37
|
+
__properties: ClassVar[List[str]] = ["chunks", "chunksCount", "commonChunks", "commonCount", "uniqueChunks", "uniqueCount", "identical", "chunkSimilarity"]
|
|
38
|
+
|
|
39
|
+
model_config = ConfigDict(
|
|
40
|
+
populate_by_name=True,
|
|
41
|
+
validate_assignment=True,
|
|
42
|
+
protected_namespaces=(),
|
|
43
|
+
)
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
def to_str(self) -> str:
|
|
47
|
+
"""Returns the string representation of the model using alias"""
|
|
48
|
+
return pprint.pformat(self.model_dump(by_alias=True))
|
|
49
|
+
|
|
50
|
+
def to_json(self) -> str:
|
|
51
|
+
"""Returns the JSON representation of the model using alias"""
|
|
52
|
+
# TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
|
|
53
|
+
return json.dumps(self.to_dict())
|
|
54
|
+
|
|
55
|
+
@classmethod
|
|
56
|
+
def from_json(cls, json_str: str) -> Optional[Self]:
|
|
57
|
+
"""Create an instance of V1RetrievedContextDiff from a JSON string"""
|
|
58
|
+
return cls.from_dict(json.loads(json_str))
|
|
59
|
+
|
|
60
|
+
def to_dict(self) -> Dict[str, Any]:
|
|
61
|
+
"""Return the dictionary representation of the model using alias.
|
|
62
|
+
|
|
63
|
+
This has the following differences from calling pydantic's
|
|
64
|
+
`self.model_dump(by_alias=True)`:
|
|
65
|
+
|
|
66
|
+
* `None` is only added to the output dict for nullable fields that
|
|
67
|
+
were set at model initialization. Other fields with value `None`
|
|
68
|
+
are ignored.
|
|
69
|
+
"""
|
|
70
|
+
excluded_fields: Set[str] = set([
|
|
71
|
+
])
|
|
72
|
+
|
|
73
|
+
_dict = self.model_dump(
|
|
74
|
+
by_alias=True,
|
|
75
|
+
exclude=excluded_fields,
|
|
76
|
+
exclude_none=True,
|
|
77
|
+
)
|
|
78
|
+
return _dict
|
|
79
|
+
|
|
80
|
+
@classmethod
|
|
81
|
+
def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
|
|
82
|
+
"""Create an instance of V1RetrievedContextDiff from a dict"""
|
|
83
|
+
if obj is None:
|
|
84
|
+
return None
|
|
85
|
+
|
|
86
|
+
if not isinstance(obj, dict):
|
|
87
|
+
return cls.model_validate(obj, strict=False)
|
|
88
|
+
|
|
89
|
+
_obj = cls.model_validate({
|
|
90
|
+
"chunks": obj.get("chunks"),
|
|
91
|
+
"chunksCount": obj.get("chunksCount"),
|
|
92
|
+
"commonChunks": obj.get("commonChunks"),
|
|
93
|
+
"commonCount": obj.get("commonCount"),
|
|
94
|
+
"uniqueChunks": obj.get("uniqueChunks"),
|
|
95
|
+
"uniqueCount": obj.get("uniqueCount"),
|
|
96
|
+
"identical": obj.get("identical"),
|
|
97
|
+
"chunkSimilarity": obj.get("chunkSimilarity")
|
|
98
|
+
}, strict=False)
|
|
99
|
+
return _obj
|
|
100
|
+
|
|
101
|
+
|
|
@@ -29,7 +29,9 @@ class V1Stats(BaseModel):
|
|
|
29
29
|
topic_modeling_pending_jobs: Optional[StrictStr] = Field(default=None, description="Number of pending jobs in the topic modeling queue. It's marked as optional to always be part of the response, even when the value is zero.", alias="topicModelingPendingJobs")
|
|
30
30
|
test_validation_pending_jobs: Optional[StrictStr] = Field(default=None, description="Number of pending jobs in the test validation queue. It's marked as optional to always be part of the response, even when the value is zero.", alias="testValidationPendingJobs")
|
|
31
31
|
failure_clustering_pending_jobs: Optional[StrictStr] = Field(default=None, description="Number of pending jobs in the failure clustering queue. It's marked as optional to always be part of the response, even when the value is zero.", alias="failureClusteringPendingJobs")
|
|
32
|
-
|
|
32
|
+
test_case_import_pending_jobs: Optional[StrictStr] = Field(default=None, description="Number of pending jobs in the test case import queue. It's marked as optional to always be part of the response, even when the value is zero.", alias="testCaseImportPendingJobs")
|
|
33
|
+
evaluation_worker_queue_length: Optional[StrictStr] = Field(default=None, description="Number of pending jobs in the evaluation worker queue. It's marked as optional to always be part of the response, even when the value is zero.", alias="evaluationWorkerQueueLength")
|
|
34
|
+
__properties: ClassVar[List[str]] = ["topicModelingPendingJobs", "testValidationPendingJobs", "failureClusteringPendingJobs", "testCaseImportPendingJobs", "evaluationWorkerQueueLength"]
|
|
33
35
|
|
|
34
36
|
model_config = ConfigDict(
|
|
35
37
|
populate_by_name=True,
|
|
@@ -85,6 +87,16 @@ class V1Stats(BaseModel):
|
|
|
85
87
|
if self.failure_clustering_pending_jobs is None and "failure_clustering_pending_jobs" in self.model_fields_set:
|
|
86
88
|
_dict['failureClusteringPendingJobs'] = None
|
|
87
89
|
|
|
90
|
+
# set to None if test_case_import_pending_jobs (nullable) is None
|
|
91
|
+
# and model_fields_set contains the field
|
|
92
|
+
if self.test_case_import_pending_jobs is None and "test_case_import_pending_jobs" in self.model_fields_set:
|
|
93
|
+
_dict['testCaseImportPendingJobs'] = None
|
|
94
|
+
|
|
95
|
+
# set to None if evaluation_worker_queue_length (nullable) is None
|
|
96
|
+
# and model_fields_set contains the field
|
|
97
|
+
if self.evaluation_worker_queue_length is None and "evaluation_worker_queue_length" in self.model_fields_set:
|
|
98
|
+
_dict['evaluationWorkerQueueLength'] = None
|
|
99
|
+
|
|
88
100
|
return _dict
|
|
89
101
|
|
|
90
102
|
@classmethod
|
|
@@ -99,7 +111,9 @@ class V1Stats(BaseModel):
|
|
|
99
111
|
_obj = cls.model_validate({
|
|
100
112
|
"topicModelingPendingJobs": obj.get("topicModelingPendingJobs"),
|
|
101
113
|
"testValidationPendingJobs": obj.get("testValidationPendingJobs"),
|
|
102
|
-
"failureClusteringPendingJobs": obj.get("failureClusteringPendingJobs")
|
|
114
|
+
"failureClusteringPendingJobs": obj.get("failureClusteringPendingJobs"),
|
|
115
|
+
"testCaseImportPendingJobs": obj.get("testCaseImportPendingJobs"),
|
|
116
|
+
"evaluationWorkerQueueLength": obj.get("evaluationWorkerQueueLength")
|
|
103
117
|
}, strict=False)
|
|
104
118
|
return _obj
|
|
105
119
|
|
|
@@ -0,0 +1,96 @@
|
|
|
1
|
+
# coding: utf-8
|
|
2
|
+
|
|
3
|
+
"""
|
|
4
|
+
ai/h2o/eval_studio/v1/insight.proto
|
|
5
|
+
|
|
6
|
+
No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
|
|
7
|
+
|
|
8
|
+
The version of the OpenAPI document: version not set
|
|
9
|
+
Generated by OpenAPI Generator (https://openapi-generator.tech)
|
|
10
|
+
|
|
11
|
+
Do not edit the class manually.
|
|
12
|
+
""" # noqa: E501
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
from __future__ import annotations
|
|
16
|
+
import pprint
|
|
17
|
+
import re # noqa: F401
|
|
18
|
+
import json
|
|
19
|
+
|
|
20
|
+
from pydantic import BaseModel, ConfigDict
|
|
21
|
+
from typing import Any, ClassVar, Dict, List, Optional
|
|
22
|
+
from eval_studio_client.api.models.v1_technical_metrics_detail import V1TechnicalMetricsDetail
|
|
23
|
+
from typing import Optional, Set
|
|
24
|
+
from typing_extensions import Self
|
|
25
|
+
|
|
26
|
+
class V1TechnicalMetrics(BaseModel):
|
|
27
|
+
"""
|
|
28
|
+
V1TechnicalMetrics
|
|
29
|
+
""" # noqa: E501
|
|
30
|
+
baseline: Optional[V1TechnicalMetricsDetail] = None
|
|
31
|
+
current: Optional[V1TechnicalMetricsDetail] = None
|
|
32
|
+
__properties: ClassVar[List[str]] = ["baseline", "current"]
|
|
33
|
+
|
|
34
|
+
model_config = ConfigDict(
|
|
35
|
+
populate_by_name=True,
|
|
36
|
+
validate_assignment=True,
|
|
37
|
+
protected_namespaces=(),
|
|
38
|
+
)
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
def to_str(self) -> str:
|
|
42
|
+
"""Returns the string representation of the model using alias"""
|
|
43
|
+
return pprint.pformat(self.model_dump(by_alias=True))
|
|
44
|
+
|
|
45
|
+
def to_json(self) -> str:
|
|
46
|
+
"""Returns the JSON representation of the model using alias"""
|
|
47
|
+
# TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
|
|
48
|
+
return json.dumps(self.to_dict())
|
|
49
|
+
|
|
50
|
+
@classmethod
|
|
51
|
+
def from_json(cls, json_str: str) -> Optional[Self]:
|
|
52
|
+
"""Create an instance of V1TechnicalMetrics from a JSON string"""
|
|
53
|
+
return cls.from_dict(json.loads(json_str))
|
|
54
|
+
|
|
55
|
+
def to_dict(self) -> Dict[str, Any]:
|
|
56
|
+
"""Return the dictionary representation of the model using alias.
|
|
57
|
+
|
|
58
|
+
This has the following differences from calling pydantic's
|
|
59
|
+
`self.model_dump(by_alias=True)`:
|
|
60
|
+
|
|
61
|
+
* `None` is only added to the output dict for nullable fields that
|
|
62
|
+
were set at model initialization. Other fields with value `None`
|
|
63
|
+
are ignored.
|
|
64
|
+
"""
|
|
65
|
+
excluded_fields: Set[str] = set([
|
|
66
|
+
])
|
|
67
|
+
|
|
68
|
+
_dict = self.model_dump(
|
|
69
|
+
by_alias=True,
|
|
70
|
+
exclude=excluded_fields,
|
|
71
|
+
exclude_none=True,
|
|
72
|
+
)
|
|
73
|
+
# override the default output from pydantic by calling `to_dict()` of baseline
|
|
74
|
+
if self.baseline:
|
|
75
|
+
_dict['baseline'] = self.baseline.to_dict()
|
|
76
|
+
# override the default output from pydantic by calling `to_dict()` of current
|
|
77
|
+
if self.current:
|
|
78
|
+
_dict['current'] = self.current.to_dict()
|
|
79
|
+
return _dict
|
|
80
|
+
|
|
81
|
+
@classmethod
|
|
82
|
+
def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
|
|
83
|
+
"""Create an instance of V1TechnicalMetrics from a dict"""
|
|
84
|
+
if obj is None:
|
|
85
|
+
return None
|
|
86
|
+
|
|
87
|
+
if not isinstance(obj, dict):
|
|
88
|
+
return cls.model_validate(obj, strict=False)
|
|
89
|
+
|
|
90
|
+
_obj = cls.model_validate({
|
|
91
|
+
"baseline": V1TechnicalMetricsDetail.from_dict(obj["baseline"]) if obj.get("baseline") is not None else None,
|
|
92
|
+
"current": V1TechnicalMetricsDetail.from_dict(obj["current"]) if obj.get("current") is not None else None
|
|
93
|
+
}, strict=False)
|
|
94
|
+
return _obj
|
|
95
|
+
|
|
96
|
+
|
|
@@ -0,0 +1,95 @@
|
|
|
1
|
+
# coding: utf-8
|
|
2
|
+
|
|
3
|
+
"""
|
|
4
|
+
ai/h2o/eval_studio/v1/insight.proto
|
|
5
|
+
|
|
6
|
+
No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
|
|
7
|
+
|
|
8
|
+
The version of the OpenAPI document: version not set
|
|
9
|
+
Generated by OpenAPI Generator (https://openapi-generator.tech)
|
|
10
|
+
|
|
11
|
+
Do not edit the class manually.
|
|
12
|
+
""" # noqa: E501
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
from __future__ import annotations
|
|
16
|
+
import pprint
|
|
17
|
+
import re # noqa: F401
|
|
18
|
+
import json
|
|
19
|
+
|
|
20
|
+
from pydantic import BaseModel, ConfigDict, Field, StrictFloat, StrictInt
|
|
21
|
+
from typing import Any, ClassVar, Dict, List, Optional, Union
|
|
22
|
+
from typing import Optional, Set
|
|
23
|
+
from typing_extensions import Self
|
|
24
|
+
|
|
25
|
+
class V1TechnicalMetricsDetail(BaseModel):
|
|
26
|
+
"""
|
|
27
|
+
V1TechnicalMetricsDetail
|
|
28
|
+
""" # noqa: E501
|
|
29
|
+
cost_sum: Optional[Union[StrictFloat, StrictInt]] = Field(default=None, description="Sum of costs.", alias="costSum")
|
|
30
|
+
duration_sum: Optional[Union[StrictFloat, StrictInt]] = Field(default=None, description="Sum of durations.", alias="durationSum")
|
|
31
|
+
duration_min: Optional[Union[StrictFloat, StrictInt]] = Field(default=None, description="Minimum duration.", alias="durationMin")
|
|
32
|
+
duration_max: Optional[Union[StrictFloat, StrictInt]] = Field(default=None, description="Maximum duration.", alias="durationMax")
|
|
33
|
+
duration_avg: Optional[Union[StrictFloat, StrictInt]] = Field(default=None, description="Average duration.", alias="durationAvg")
|
|
34
|
+
__properties: ClassVar[List[str]] = ["costSum", "durationSum", "durationMin", "durationMax", "durationAvg"]
|
|
35
|
+
|
|
36
|
+
model_config = ConfigDict(
|
|
37
|
+
populate_by_name=True,
|
|
38
|
+
validate_assignment=True,
|
|
39
|
+
protected_namespaces=(),
|
|
40
|
+
)
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
def to_str(self) -> str:
|
|
44
|
+
"""Returns the string representation of the model using alias"""
|
|
45
|
+
return pprint.pformat(self.model_dump(by_alias=True))
|
|
46
|
+
|
|
47
|
+
def to_json(self) -> str:
|
|
48
|
+
"""Returns the JSON representation of the model using alias"""
|
|
49
|
+
# TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
|
|
50
|
+
return json.dumps(self.to_dict())
|
|
51
|
+
|
|
52
|
+
@classmethod
|
|
53
|
+
def from_json(cls, json_str: str) -> Optional[Self]:
|
|
54
|
+
"""Create an instance of V1TechnicalMetricsDetail from a JSON string"""
|
|
55
|
+
return cls.from_dict(json.loads(json_str))
|
|
56
|
+
|
|
57
|
+
def to_dict(self) -> Dict[str, Any]:
|
|
58
|
+
"""Return the dictionary representation of the model using alias.
|
|
59
|
+
|
|
60
|
+
This has the following differences from calling pydantic's
|
|
61
|
+
`self.model_dump(by_alias=True)`:
|
|
62
|
+
|
|
63
|
+
* `None` is only added to the output dict for nullable fields that
|
|
64
|
+
were set at model initialization. Other fields with value `None`
|
|
65
|
+
are ignored.
|
|
66
|
+
"""
|
|
67
|
+
excluded_fields: Set[str] = set([
|
|
68
|
+
])
|
|
69
|
+
|
|
70
|
+
_dict = self.model_dump(
|
|
71
|
+
by_alias=True,
|
|
72
|
+
exclude=excluded_fields,
|
|
73
|
+
exclude_none=True,
|
|
74
|
+
)
|
|
75
|
+
return _dict
|
|
76
|
+
|
|
77
|
+
@classmethod
|
|
78
|
+
def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
|
|
79
|
+
"""Create an instance of V1TechnicalMetricsDetail from a dict"""
|
|
80
|
+
if obj is None:
|
|
81
|
+
return None
|
|
82
|
+
|
|
83
|
+
if not isinstance(obj, dict):
|
|
84
|
+
return cls.model_validate(obj, strict=False)
|
|
85
|
+
|
|
86
|
+
_obj = cls.model_validate({
|
|
87
|
+
"costSum": obj.get("costSum"),
|
|
88
|
+
"durationSum": obj.get("durationSum"),
|
|
89
|
+
"durationMin": obj.get("durationMin"),
|
|
90
|
+
"durationMax": obj.get("durationMax"),
|
|
91
|
+
"durationAvg": obj.get("durationAvg")
|
|
92
|
+
}, strict=False)
|
|
93
|
+
return _obj
|
|
94
|
+
|
|
95
|
+
|
|
@@ -0,0 +1,91 @@
|
|
|
1
|
+
# coding: utf-8
|
|
2
|
+
|
|
3
|
+
"""
|
|
4
|
+
ai/h2o/eval_studio/v1/insight.proto
|
|
5
|
+
|
|
6
|
+
No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
|
|
7
|
+
|
|
8
|
+
The version of the OpenAPI document: version not set
|
|
9
|
+
Generated by OpenAPI Generator (https://openapi-generator.tech)
|
|
10
|
+
|
|
11
|
+
Do not edit the class manually.
|
|
12
|
+
""" # noqa: E501
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
from __future__ import annotations
|
|
16
|
+
import pprint
|
|
17
|
+
import re # noqa: F401
|
|
18
|
+
import json
|
|
19
|
+
|
|
20
|
+
from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
|
|
21
|
+
from typing import Any, ClassVar, Dict, List, Optional
|
|
22
|
+
from typing import Optional, Set
|
|
23
|
+
from typing_extensions import Self
|
|
24
|
+
|
|
25
|
+
class V1TestCaseLeaderboardItem(BaseModel):
|
|
26
|
+
"""
|
|
27
|
+
V1TestCaseLeaderboardItem
|
|
28
|
+
""" # noqa: E501
|
|
29
|
+
wins: Optional[StrictInt] = Field(default=None, description="Number of wins.")
|
|
30
|
+
question: Optional[StrictStr] = Field(default=None, description="Question text.")
|
|
31
|
+
changed_metrics_count: Optional[StrictInt] = Field(default=None, description="Count of changed metrics.", alias="changedMetricsCount")
|
|
32
|
+
__properties: ClassVar[List[str]] = ["wins", "question", "changedMetricsCount"]
|
|
33
|
+
|
|
34
|
+
model_config = ConfigDict(
|
|
35
|
+
populate_by_name=True,
|
|
36
|
+
validate_assignment=True,
|
|
37
|
+
protected_namespaces=(),
|
|
38
|
+
)
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
def to_str(self) -> str:
|
|
42
|
+
"""Returns the string representation of the model using alias"""
|
|
43
|
+
return pprint.pformat(self.model_dump(by_alias=True))
|
|
44
|
+
|
|
45
|
+
def to_json(self) -> str:
|
|
46
|
+
"""Returns the JSON representation of the model using alias"""
|
|
47
|
+
# TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
|
|
48
|
+
return json.dumps(self.to_dict())
|
|
49
|
+
|
|
50
|
+
@classmethod
|
|
51
|
+
def from_json(cls, json_str: str) -> Optional[Self]:
|
|
52
|
+
"""Create an instance of V1TestCaseLeaderboardItem from a JSON string"""
|
|
53
|
+
return cls.from_dict(json.loads(json_str))
|
|
54
|
+
|
|
55
|
+
def to_dict(self) -> Dict[str, Any]:
|
|
56
|
+
"""Return the dictionary representation of the model using alias.
|
|
57
|
+
|
|
58
|
+
This has the following differences from calling pydantic's
|
|
59
|
+
`self.model_dump(by_alias=True)`:
|
|
60
|
+
|
|
61
|
+
* `None` is only added to the output dict for nullable fields that
|
|
62
|
+
were set at model initialization. Other fields with value `None`
|
|
63
|
+
are ignored.
|
|
64
|
+
"""
|
|
65
|
+
excluded_fields: Set[str] = set([
|
|
66
|
+
])
|
|
67
|
+
|
|
68
|
+
_dict = self.model_dump(
|
|
69
|
+
by_alias=True,
|
|
70
|
+
exclude=excluded_fields,
|
|
71
|
+
exclude_none=True,
|
|
72
|
+
)
|
|
73
|
+
return _dict
|
|
74
|
+
|
|
75
|
+
@classmethod
|
|
76
|
+
def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
|
|
77
|
+
"""Create an instance of V1TestCaseLeaderboardItem from a dict"""
|
|
78
|
+
if obj is None:
|
|
79
|
+
return None
|
|
80
|
+
|
|
81
|
+
if not isinstance(obj, dict):
|
|
82
|
+
return cls.model_validate(obj, strict=False)
|
|
83
|
+
|
|
84
|
+
_obj = cls.model_validate({
|
|
85
|
+
"wins": obj.get("wins"),
|
|
86
|
+
"question": obj.get("question"),
|
|
87
|
+
"changedMetricsCount": obj.get("changedMetricsCount")
|
|
88
|
+
}, strict=False)
|
|
89
|
+
return _obj
|
|
90
|
+
|
|
91
|
+
|
|
@@ -0,0 +1,91 @@
|
|
|
1
|
+
# coding: utf-8
|
|
2
|
+
|
|
3
|
+
"""
|
|
4
|
+
ai/h2o/eval_studio/v1/insight.proto
|
|
5
|
+
|
|
6
|
+
No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
|
|
7
|
+
|
|
8
|
+
The version of the OpenAPI document: version not set
|
|
9
|
+
Generated by OpenAPI Generator (https://openapi-generator.tech)
|
|
10
|
+
|
|
11
|
+
Do not edit the class manually.
|
|
12
|
+
""" # noqa: E501
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
from __future__ import annotations
|
|
16
|
+
import pprint
|
|
17
|
+
import re # noqa: F401
|
|
18
|
+
import json
|
|
19
|
+
|
|
20
|
+
from pydantic import BaseModel, ConfigDict, Field, StrictStr
|
|
21
|
+
from typing import Any, ClassVar, Dict, List, Optional
|
|
22
|
+
from typing import Optional, Set
|
|
23
|
+
from typing_extensions import Self
|
|
24
|
+
|
|
25
|
+
class V1TestCaseRelationshipInfo(BaseModel):
|
|
26
|
+
"""
|
|
27
|
+
V1TestCaseRelationshipInfo
|
|
28
|
+
""" # noqa: E501
|
|
29
|
+
type: Optional[StrictStr] = Field(default=None, description="Type of the relationship.")
|
|
30
|
+
target: Optional[StrictStr] = Field(default=None, description="Target of the relationship.")
|
|
31
|
+
target_type: Optional[StrictStr] = Field(default=None, description="Type of the target.", alias="targetType")
|
|
32
|
+
__properties: ClassVar[List[str]] = ["type", "target", "targetType"]
|
|
33
|
+
|
|
34
|
+
model_config = ConfigDict(
|
|
35
|
+
populate_by_name=True,
|
|
36
|
+
validate_assignment=True,
|
|
37
|
+
protected_namespaces=(),
|
|
38
|
+
)
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
def to_str(self) -> str:
|
|
42
|
+
"""Returns the string representation of the model using alias"""
|
|
43
|
+
return pprint.pformat(self.model_dump(by_alias=True))
|
|
44
|
+
|
|
45
|
+
def to_json(self) -> str:
|
|
46
|
+
"""Returns the JSON representation of the model using alias"""
|
|
47
|
+
# TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
|
|
48
|
+
return json.dumps(self.to_dict())
|
|
49
|
+
|
|
50
|
+
@classmethod
|
|
51
|
+
def from_json(cls, json_str: str) -> Optional[Self]:
|
|
52
|
+
"""Create an instance of V1TestCaseRelationshipInfo from a JSON string"""
|
|
53
|
+
return cls.from_dict(json.loads(json_str))
|
|
54
|
+
|
|
55
|
+
def to_dict(self) -> Dict[str, Any]:
|
|
56
|
+
"""Return the dictionary representation of the model using alias.
|
|
57
|
+
|
|
58
|
+
This has the following differences from calling pydantic's
|
|
59
|
+
`self.model_dump(by_alias=True)`:
|
|
60
|
+
|
|
61
|
+
* `None` is only added to the output dict for nullable fields that
|
|
62
|
+
were set at model initialization. Other fields with value `None`
|
|
63
|
+
are ignored.
|
|
64
|
+
"""
|
|
65
|
+
excluded_fields: Set[str] = set([
|
|
66
|
+
])
|
|
67
|
+
|
|
68
|
+
_dict = self.model_dump(
|
|
69
|
+
by_alias=True,
|
|
70
|
+
exclude=excluded_fields,
|
|
71
|
+
exclude_none=True,
|
|
72
|
+
)
|
|
73
|
+
return _dict
|
|
74
|
+
|
|
75
|
+
@classmethod
|
|
76
|
+
def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
|
|
77
|
+
"""Create an instance of V1TestCaseRelationshipInfo from a dict"""
|
|
78
|
+
if obj is None:
|
|
79
|
+
return None
|
|
80
|
+
|
|
81
|
+
if not isinstance(obj, dict):
|
|
82
|
+
return cls.model_validate(obj, strict=False)
|
|
83
|
+
|
|
84
|
+
_obj = cls.model_validate({
|
|
85
|
+
"type": obj.get("type"),
|
|
86
|
+
"target": obj.get("target"),
|
|
87
|
+
"targetType": obj.get("targetType")
|
|
88
|
+
}, strict=False)
|
|
89
|
+
return _obj
|
|
90
|
+
|
|
91
|
+
|
|
@@ -0,0 +1,157 @@
|
|
|
1
|
+
# coding: utf-8
|
|
2
|
+
|
|
3
|
+
"""
|
|
4
|
+
ai/h2o/eval_studio/v1/insight.proto
|
|
5
|
+
|
|
6
|
+
No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
|
|
7
|
+
|
|
8
|
+
The version of the OpenAPI document: version not set
|
|
9
|
+
Generated by OpenAPI Generator (https://openapi-generator.tech)
|
|
10
|
+
|
|
11
|
+
Do not edit the class manually.
|
|
12
|
+
""" # noqa: E501
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
from __future__ import annotations
|
|
16
|
+
import pprint
|
|
17
|
+
import re # noqa: F401
|
|
18
|
+
import json
|
|
19
|
+
|
|
20
|
+
from pydantic import BaseModel, ConfigDict, Field, StrictFloat, StrictInt, StrictStr
|
|
21
|
+
from typing import Any, ClassVar, Dict, List, Optional, Union
|
|
22
|
+
from eval_studio_client.api.models.v1_actual_output_meta import V1ActualOutputMeta
|
|
23
|
+
from eval_studio_client.api.models.v1_comparison_metric_score import V1ComparisonMetricScore
|
|
24
|
+
from eval_studio_client.api.models.v1_metric import V1Metric
|
|
25
|
+
from eval_studio_client.api.models.v1_test_case_relationship_info import V1TestCaseRelationshipInfo
|
|
26
|
+
from typing import Optional, Set
|
|
27
|
+
from typing_extensions import Self
|
|
28
|
+
|
|
29
|
+
class V1TestCaseResult(BaseModel):
|
|
30
|
+
"""
|
|
31
|
+
V1TestCaseResult
|
|
32
|
+
""" # noqa: E501
|
|
33
|
+
key: Optional[StrictStr] = Field(default=None, description="Unique key for the test case.")
|
|
34
|
+
input: Optional[StrictStr] = Field(default=None, description="Input text.")
|
|
35
|
+
corpus: Optional[List[StrictStr]] = Field(default=None, description="Corpus URLs.")
|
|
36
|
+
context: Optional[List[StrictStr]] = Field(default=None, description="Context texts.")
|
|
37
|
+
categories: Optional[List[StrictStr]] = Field(default=None, description="Categories.")
|
|
38
|
+
relationships: Optional[List[V1TestCaseRelationshipInfo]] = Field(default=None, description="Relationships.")
|
|
39
|
+
expected_output: Optional[StrictStr] = Field(default=None, description="Expected output.", alias="expectedOutput")
|
|
40
|
+
output_constraints: Optional[List[StrictStr]] = Field(default=None, description="Output constraints.", alias="outputConstraints")
|
|
41
|
+
output_condition: Optional[StrictStr] = Field(default=None, description="Output condition.", alias="outputCondition")
|
|
42
|
+
actual_output: Optional[StrictStr] = Field(default=None, description="Actual output generated.", alias="actualOutput")
|
|
43
|
+
actual_duration: Optional[Union[StrictFloat, StrictInt]] = Field(default=None, description="Duration in seconds.", alias="actualDuration")
|
|
44
|
+
cost: Optional[Union[StrictFloat, StrictInt]] = Field(default=None, description="Cost of evaluation.")
|
|
45
|
+
model_key: Optional[StrictStr] = Field(default=None, description="Model key.", alias="modelKey")
|
|
46
|
+
test_key: Optional[StrictStr] = Field(default=None, description="Test key.", alias="testKey")
|
|
47
|
+
test_case_key: Optional[StrictStr] = Field(default=None, description="Test case key.", alias="testCaseKey")
|
|
48
|
+
metrics: Optional[List[V1Metric]] = Field(default=None, description="List of metrics.")
|
|
49
|
+
metrics_meta: Optional[Dict[str, StrictStr]] = Field(default=None, description="Metadata for metrics.", alias="metricsMeta")
|
|
50
|
+
actual_output_meta: Optional[List[V1ActualOutputMeta]] = Field(default=None, description="Actual output metadata.", alias="actualOutputMeta")
|
|
51
|
+
metric_scores: Optional[List[V1ComparisonMetricScore]] = Field(default=None, description="Metric scores.", alias="metricScores")
|
|
52
|
+
result_error_message: Optional[StrictStr] = Field(default=None, description="Error message if processing resulted in failure.", alias="resultErrorMessage")
|
|
53
|
+
__properties: ClassVar[List[str]] = ["key", "input", "corpus", "context", "categories", "relationships", "expectedOutput", "outputConstraints", "outputCondition", "actualOutput", "actualDuration", "cost", "modelKey", "testKey", "testCaseKey", "metrics", "metricsMeta", "actualOutputMeta", "metricScores", "resultErrorMessage"]
|
|
54
|
+
|
|
55
|
+
model_config = ConfigDict(
|
|
56
|
+
populate_by_name=True,
|
|
57
|
+
validate_assignment=True,
|
|
58
|
+
protected_namespaces=(),
|
|
59
|
+
)
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
def to_str(self) -> str:
|
|
63
|
+
"""Returns the string representation of the model using alias"""
|
|
64
|
+
return pprint.pformat(self.model_dump(by_alias=True))
|
|
65
|
+
|
|
66
|
+
def to_json(self) -> str:
|
|
67
|
+
"""Returns the JSON representation of the model using alias"""
|
|
68
|
+
# TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
|
|
69
|
+
return json.dumps(self.to_dict())
|
|
70
|
+
|
|
71
|
+
@classmethod
|
|
72
|
+
def from_json(cls, json_str: str) -> Optional[Self]:
|
|
73
|
+
"""Create an instance of V1TestCaseResult from a JSON string"""
|
|
74
|
+
return cls.from_dict(json.loads(json_str))
|
|
75
|
+
|
|
76
|
+
def to_dict(self) -> Dict[str, Any]:
|
|
77
|
+
"""Return the dictionary representation of the model using alias.
|
|
78
|
+
|
|
79
|
+
This has the following differences from calling pydantic's
|
|
80
|
+
`self.model_dump(by_alias=True)`:
|
|
81
|
+
|
|
82
|
+
* `None` is only added to the output dict for nullable fields that
|
|
83
|
+
were set at model initialization. Other fields with value `None`
|
|
84
|
+
are ignored.
|
|
85
|
+
"""
|
|
86
|
+
excluded_fields: Set[str] = set([
|
|
87
|
+
])
|
|
88
|
+
|
|
89
|
+
_dict = self.model_dump(
|
|
90
|
+
by_alias=True,
|
|
91
|
+
exclude=excluded_fields,
|
|
92
|
+
exclude_none=True,
|
|
93
|
+
)
|
|
94
|
+
# override the default output from pydantic by calling `to_dict()` of each item in relationships (list)
|
|
95
|
+
_items = []
|
|
96
|
+
if self.relationships:
|
|
97
|
+
for _item_relationships in self.relationships:
|
|
98
|
+
if _item_relationships:
|
|
99
|
+
_items.append(_item_relationships.to_dict())
|
|
100
|
+
_dict['relationships'] = _items
|
|
101
|
+
# override the default output from pydantic by calling `to_dict()` of each item in metrics (list)
|
|
102
|
+
_items = []
|
|
103
|
+
if self.metrics:
|
|
104
|
+
for _item_metrics in self.metrics:
|
|
105
|
+
if _item_metrics:
|
|
106
|
+
_items.append(_item_metrics.to_dict())
|
|
107
|
+
_dict['metrics'] = _items
|
|
108
|
+
# override the default output from pydantic by calling `to_dict()` of each item in actual_output_meta (list)
|
|
109
|
+
_items = []
|
|
110
|
+
if self.actual_output_meta:
|
|
111
|
+
for _item_actual_output_meta in self.actual_output_meta:
|
|
112
|
+
if _item_actual_output_meta:
|
|
113
|
+
_items.append(_item_actual_output_meta.to_dict())
|
|
114
|
+
_dict['actualOutputMeta'] = _items
|
|
115
|
+
# override the default output from pydantic by calling `to_dict()` of each item in metric_scores (list)
|
|
116
|
+
_items = []
|
|
117
|
+
if self.metric_scores:
|
|
118
|
+
for _item_metric_scores in self.metric_scores:
|
|
119
|
+
if _item_metric_scores:
|
|
120
|
+
_items.append(_item_metric_scores.to_dict())
|
|
121
|
+
_dict['metricScores'] = _items
|
|
122
|
+
return _dict
|
|
123
|
+
|
|
124
|
+
@classmethod
|
|
125
|
+
def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
|
|
126
|
+
"""Create an instance of V1TestCaseResult from a dict"""
|
|
127
|
+
if obj is None:
|
|
128
|
+
return None
|
|
129
|
+
|
|
130
|
+
if not isinstance(obj, dict):
|
|
131
|
+
return cls.model_validate(obj, strict=False)
|
|
132
|
+
|
|
133
|
+
_obj = cls.model_validate({
|
|
134
|
+
"key": obj.get("key"),
|
|
135
|
+
"input": obj.get("input"),
|
|
136
|
+
"corpus": obj.get("corpus"),
|
|
137
|
+
"context": obj.get("context"),
|
|
138
|
+
"categories": obj.get("categories"),
|
|
139
|
+
"relationships": [V1TestCaseRelationshipInfo.from_dict(_item) for _item in obj["relationships"]] if obj.get("relationships") is not None else None,
|
|
140
|
+
"expectedOutput": obj.get("expectedOutput"),
|
|
141
|
+
"outputConstraints": obj.get("outputConstraints"),
|
|
142
|
+
"outputCondition": obj.get("outputCondition"),
|
|
143
|
+
"actualOutput": obj.get("actualOutput"),
|
|
144
|
+
"actualDuration": obj.get("actualDuration"),
|
|
145
|
+
"cost": obj.get("cost"),
|
|
146
|
+
"modelKey": obj.get("modelKey"),
|
|
147
|
+
"testKey": obj.get("testKey"),
|
|
148
|
+
"testCaseKey": obj.get("testCaseKey"),
|
|
149
|
+
"metrics": [V1Metric.from_dict(_item) for _item in obj["metrics"]] if obj.get("metrics") is not None else None,
|
|
150
|
+
"metricsMeta": obj.get("metricsMeta"),
|
|
151
|
+
"actualOutputMeta": [V1ActualOutputMeta.from_dict(_item) for _item in obj["actualOutputMeta"]] if obj.get("actualOutputMeta") is not None else None,
|
|
152
|
+
"metricScores": [V1ComparisonMetricScore.from_dict(_item) for _item in obj["metricScores"]] if obj.get("metricScores") is not None else None,
|
|
153
|
+
"resultErrorMessage": obj.get("resultErrorMessage")
|
|
154
|
+
}, strict=False)
|
|
155
|
+
return _obj
|
|
156
|
+
|
|
157
|
+
|