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 +1,36 @@
|
|
|
1
|
+
# V1MetricAverage
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**metric_key** | **str** | Metric key. | [optional]
|
|
9
|
+
**baseline_avg** | **float** | Baseline average. | [optional]
|
|
10
|
+
**current_avg** | **float** | Current average. | [optional]
|
|
11
|
+
**diff** | **float** | Difference between current and baseline. | [optional]
|
|
12
|
+
**baseline_better_wins** | **int** | Baseline better wins count. | [optional]
|
|
13
|
+
**current_better_wins** | **int** | Current better wins count. | [optional]
|
|
14
|
+
**baseline_rank_avg** | **float** | Baseline rank average. | [optional]
|
|
15
|
+
**current_rank_avg** | **float** | Current rank average. | [optional]
|
|
16
|
+
|
|
17
|
+
## Example
|
|
18
|
+
|
|
19
|
+
```python
|
|
20
|
+
from eval_studio_client.api.models.v1_metric_average import V1MetricAverage
|
|
21
|
+
|
|
22
|
+
# TODO update the JSON string below
|
|
23
|
+
json = "{}"
|
|
24
|
+
# create an instance of V1MetricAverage from a JSON string
|
|
25
|
+
v1_metric_average_instance = V1MetricAverage.from_json(json)
|
|
26
|
+
# print the JSON string representation of the object
|
|
27
|
+
print(V1MetricAverage.to_json())
|
|
28
|
+
|
|
29
|
+
# convert the object into a dict
|
|
30
|
+
v1_metric_average_dict = v1_metric_average_instance.to_dict()
|
|
31
|
+
# create an instance of V1MetricAverage from a dict
|
|
32
|
+
v1_metric_average_from_dict = V1MetricAverage.from_dict(v1_metric_average_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 +1,40 @@
|
|
|
1
|
+
# V1MetricMeta
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**key** | **str** | Metric key. | [optional]
|
|
9
|
+
**display_name** | **str** | Display name. | [optional]
|
|
10
|
+
**data_type** | **str** | Data type. | [optional]
|
|
11
|
+
**display_value** | **str** | Display value format. | [optional]
|
|
12
|
+
**description** | **str** | Description. | [optional]
|
|
13
|
+
**value_range** | **List[float]** | Value range (min, max). | [optional]
|
|
14
|
+
**value_enum** | **List[str]** | Value enum (null if not applicable). | [optional]
|
|
15
|
+
**higher_is_better** | **bool** | Whether higher is better. | [optional]
|
|
16
|
+
**threshold** | **float** | Threshold value. | [optional]
|
|
17
|
+
**is_primary_metric** | **bool** | Is primary metric. | [optional]
|
|
18
|
+
**parent_metric** | **str** | Parent metric. | [optional]
|
|
19
|
+
**exclude** | **bool** | Exclude flag. | [optional]
|
|
20
|
+
|
|
21
|
+
## Example
|
|
22
|
+
|
|
23
|
+
```python
|
|
24
|
+
from eval_studio_client.api.models.v1_metric_meta import V1MetricMeta
|
|
25
|
+
|
|
26
|
+
# TODO update the JSON string below
|
|
27
|
+
json = "{}"
|
|
28
|
+
# create an instance of V1MetricMeta from a JSON string
|
|
29
|
+
v1_metric_meta_instance = V1MetricMeta.from_json(json)
|
|
30
|
+
# print the JSON string representation of the object
|
|
31
|
+
print(V1MetricMeta.to_json())
|
|
32
|
+
|
|
33
|
+
# convert the object into a dict
|
|
34
|
+
v1_metric_meta_dict = v1_metric_meta_instance.to_dict()
|
|
35
|
+
# create an instance of V1MetricMeta from a dict
|
|
36
|
+
v1_metric_meta_from_dict = V1MetricMeta.from_dict(v1_metric_meta_dict)
|
|
37
|
+
```
|
|
38
|
+
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
|
|
39
|
+
|
|
40
|
+
|
|
@@ -7,7 +7,7 @@ MetricScore represents the metric score.
|
|
|
7
7
|
Name | Type | Description | Notes
|
|
8
8
|
------------ | ------------- | ------------- | -------------
|
|
9
9
|
**key** | **str** | Required. Metric key. | [optional]
|
|
10
|
-
**value** | **float** |
|
|
10
|
+
**value** | **float** | Optional. Metric value. May be omitted if the metric could not be computed. Valid values include normal floats, as well as special values: NaN, Infinity, or -Infinity. | [optional]
|
|
11
11
|
|
|
12
12
|
## Example
|
|
13
13
|
|
|
@@ -5,7 +5,7 @@
|
|
|
5
5
|
|
|
6
6
|
Name | Type | Description | Notes
|
|
7
7
|
------------ | ------------- | ------------- | -------------
|
|
8
|
-
**scores** | [**List[V1MetricScore]**](V1MetricScore.md) |
|
|
8
|
+
**scores** | [**List[V1MetricScore]**](V1MetricScore.md) | Repeated. List of metric scores. | [optional]
|
|
9
9
|
|
|
10
10
|
## Example
|
|
11
11
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# V1ModelType
|
|
2
2
|
|
|
3
|
-
- MODEL_TYPE_UNSPECIFIED: Unspecified type. - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG. - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG. - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM. - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM. - MODEL_TYPE_OPENAI_CHAT: OpenAI chat. - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat. - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat. - MODEL_TYPE_H2OLLMOPS: H2O LLMOps. - MODEL_TYPE_OLLAMA: Ollama. - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock.
|
|
3
|
+
- MODEL_TYPE_UNSPECIFIED: Unspecified type. - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG. - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG. - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM. - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM. - MODEL_TYPE_OPENAI_CHAT: OpenAI chat. - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat. - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat. - MODEL_TYPE_H2OLLMOPS: H2O LLMOps. - MODEL_TYPE_OLLAMA: Ollama. - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock. - MODEL_TYPE_ANTHROPIC_CLAUDE: Anthropic Claude chat.
|
|
4
4
|
|
|
5
5
|
## Properties
|
|
6
6
|
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# V1ModelsComparisons
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**test_case_ranks_baseline** | **int** | Test case ranks for baseline. | [optional]
|
|
9
|
+
**test_case_ranks_current** | **int** | Test case ranks for current. | [optional]
|
|
10
|
+
**test_case_wins_baseline** | **int** | Test case wins for baseline. | [optional]
|
|
11
|
+
**test_case_wins_current** | **int** | Test case wins for current. | [optional]
|
|
12
|
+
|
|
13
|
+
## Example
|
|
14
|
+
|
|
15
|
+
```python
|
|
16
|
+
from eval_studio_client.api.models.v1_models_comparisons import V1ModelsComparisons
|
|
17
|
+
|
|
18
|
+
# TODO update the JSON string below
|
|
19
|
+
json = "{}"
|
|
20
|
+
# create an instance of V1ModelsComparisons from a JSON string
|
|
21
|
+
v1_models_comparisons_instance = V1ModelsComparisons.from_json(json)
|
|
22
|
+
# print the JSON string representation of the object
|
|
23
|
+
print(V1ModelsComparisons.to_json())
|
|
24
|
+
|
|
25
|
+
# convert the object into a dict
|
|
26
|
+
v1_models_comparisons_dict = v1_models_comparisons_instance.to_dict()
|
|
27
|
+
# create an instance of V1ModelsComparisons from a dict
|
|
28
|
+
v1_models_comparisons_from_dict = V1ModelsComparisons.from_dict(v1_models_comparisons_dict)
|
|
29
|
+
```
|
|
30
|
+
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
|
|
31
|
+
|
|
32
|
+
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
# V1ModelsComparisonsMetrics
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**metrics_ranks_baseline** | **float** | Metrics ranks for baseline. | [optional]
|
|
9
|
+
**metrics_ranks_current** | **float** | Metrics ranks for current. | [optional]
|
|
10
|
+
**metrics_wins_baseline** | **int** | Metrics wins for baseline. | [optional]
|
|
11
|
+
**metrics_wins_current** | **int** | Metrics wins for current. | [optional]
|
|
12
|
+
**metrics_averages** | [**List[V1MetricAverage]**](V1MetricAverage.md) | Metrics averages. | [optional]
|
|
13
|
+
|
|
14
|
+
## Example
|
|
15
|
+
|
|
16
|
+
```python
|
|
17
|
+
from eval_studio_client.api.models.v1_models_comparisons_metrics import V1ModelsComparisonsMetrics
|
|
18
|
+
|
|
19
|
+
# TODO update the JSON string below
|
|
20
|
+
json = "{}"
|
|
21
|
+
# create an instance of V1ModelsComparisonsMetrics from a JSON string
|
|
22
|
+
v1_models_comparisons_metrics_instance = V1ModelsComparisonsMetrics.from_json(json)
|
|
23
|
+
# print the JSON string representation of the object
|
|
24
|
+
print(V1ModelsComparisonsMetrics.to_json())
|
|
25
|
+
|
|
26
|
+
# convert the object into a dict
|
|
27
|
+
v1_models_comparisons_metrics_dict = v1_models_comparisons_metrics_instance.to_dict()
|
|
28
|
+
# create an instance of V1ModelsComparisonsMetrics from a dict
|
|
29
|
+
v1_models_comparisons_metrics_from_dict = V1ModelsComparisonsMetrics.from_dict(v1_models_comparisons_metrics_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 +1,34 @@
|
|
|
1
|
+
# V1ModelsOverview
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**baseline_model_key** | **str** | Baseline model key. | [optional]
|
|
9
|
+
**current_model_key** | **str** | Current model key. | [optional]
|
|
10
|
+
**baseline_model_name** | **str** | Baseline model name. | [optional]
|
|
11
|
+
**baseline_collection_id** | **List[str]** | Baseline collection IDs. | [optional]
|
|
12
|
+
**current_model_name** | **str** | Current model name. | [optional]
|
|
13
|
+
**current_collection_id** | **List[str]** | Current collection IDs. | [optional]
|
|
14
|
+
|
|
15
|
+
## Example
|
|
16
|
+
|
|
17
|
+
```python
|
|
18
|
+
from eval_studio_client.api.models.v1_models_overview import V1ModelsOverview
|
|
19
|
+
|
|
20
|
+
# TODO update the JSON string below
|
|
21
|
+
json = "{}"
|
|
22
|
+
# create an instance of V1ModelsOverview from a JSON string
|
|
23
|
+
v1_models_overview_instance = V1ModelsOverview.from_json(json)
|
|
24
|
+
# print the JSON string representation of the object
|
|
25
|
+
print(V1ModelsOverview.to_json())
|
|
26
|
+
|
|
27
|
+
# convert the object into a dict
|
|
28
|
+
v1_models_overview_dict = v1_models_overview_instance.to_dict()
|
|
29
|
+
# create an instance of V1ModelsOverview from a dict
|
|
30
|
+
v1_models_overview_from_dict = V1ModelsOverview.from_dict(v1_models_overview_dict)
|
|
31
|
+
```
|
|
32
|
+
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
|
|
33
|
+
|
|
34
|
+
|
|
@@ -17,6 +17,7 @@ Name | Type | Description | Notes
|
|
|
17
17
|
**done** | **bool** | If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available. | [optional]
|
|
18
18
|
**error** | [**RpcStatus**](RpcStatus.md) | | [optional]
|
|
19
19
|
**response** | [**ProtobufAny**](ProtobufAny.md) | | [optional]
|
|
20
|
+
**seen_by_creator_time** | **datetime** | Output only. Optional. Timestamp when the creator marked the Operation as seen. Once set, this field cannot be changed. Set via MarkOperationSeenByCreator method. | [optional] [readonly]
|
|
20
21
|
|
|
21
22
|
## Example
|
|
22
23
|
|
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
# V1OperationView
|
|
2
|
+
|
|
3
|
+
- OPERATION_VIEW_UNSPECIFIED: Default / unset value. The API will default to the OPERATION_VIEW_FULL. - OPERATION_VIEW_BASIC: Include basic metadata about the Operation, but not the response. - OPERATION_VIEW_FULL: Include everything.
|
|
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
|
+
# V1RetrievedContextDiff
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**chunks** | **List[str]** | Context chunks. | [optional]
|
|
9
|
+
**chunks_count** | **int** | Chunk count. | [optional]
|
|
10
|
+
**common_chunks** | **List[str]** | Common chunks between baseline and current. | [optional]
|
|
11
|
+
**common_count** | **int** | Common chunk count. | [optional]
|
|
12
|
+
**unique_chunks** | **List[str]** | Unique chunks. | [optional]
|
|
13
|
+
**unique_count** | **int** | Unique chunk count. | [optional]
|
|
14
|
+
**identical** | **bool** | Whether contexts are identical. | [optional]
|
|
15
|
+
**chunk_similarity** | **Dict[str, float]** | Chunk similarity scores. | [optional]
|
|
16
|
+
|
|
17
|
+
## Example
|
|
18
|
+
|
|
19
|
+
```python
|
|
20
|
+
from eval_studio_client.api.models.v1_retrieved_context_diff import V1RetrievedContextDiff
|
|
21
|
+
|
|
22
|
+
# TODO update the JSON string below
|
|
23
|
+
json = "{}"
|
|
24
|
+
# create an instance of V1RetrievedContextDiff from a JSON string
|
|
25
|
+
v1_retrieved_context_diff_instance = V1RetrievedContextDiff.from_json(json)
|
|
26
|
+
# print the JSON string representation of the object
|
|
27
|
+
print(V1RetrievedContextDiff.to_json())
|
|
28
|
+
|
|
29
|
+
# convert the object into a dict
|
|
30
|
+
v1_retrieved_context_diff_dict = v1_retrieved_context_diff_instance.to_dict()
|
|
31
|
+
# create an instance of V1RetrievedContextDiff from a dict
|
|
32
|
+
v1_retrieved_context_diff_from_dict = V1RetrievedContextDiff.from_dict(v1_retrieved_context_diff_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
|
+
|
|
@@ -9,6 +9,8 @@ Name | Type | Description | Notes
|
|
|
9
9
|
**topic_modeling_pending_jobs** | **str** | 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. | [optional]
|
|
10
10
|
**test_validation_pending_jobs** | **str** | 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. | [optional]
|
|
11
11
|
**failure_clustering_pending_jobs** | **str** | 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. | [optional]
|
|
12
|
+
**test_case_import_pending_jobs** | **str** | 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. | [optional]
|
|
13
|
+
**evaluation_worker_queue_length** | **str** | 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. | [optional]
|
|
12
14
|
|
|
13
15
|
## Example
|
|
14
16
|
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
# V1TechnicalMetrics
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**baseline** | [**V1TechnicalMetricsDetail**](V1TechnicalMetricsDetail.md) | | [optional]
|
|
9
|
+
**current** | [**V1TechnicalMetricsDetail**](V1TechnicalMetricsDetail.md) | | [optional]
|
|
10
|
+
|
|
11
|
+
## Example
|
|
12
|
+
|
|
13
|
+
```python
|
|
14
|
+
from eval_studio_client.api.models.v1_technical_metrics import V1TechnicalMetrics
|
|
15
|
+
|
|
16
|
+
# TODO update the JSON string below
|
|
17
|
+
json = "{}"
|
|
18
|
+
# create an instance of V1TechnicalMetrics from a JSON string
|
|
19
|
+
v1_technical_metrics_instance = V1TechnicalMetrics.from_json(json)
|
|
20
|
+
# print the JSON string representation of the object
|
|
21
|
+
print(V1TechnicalMetrics.to_json())
|
|
22
|
+
|
|
23
|
+
# convert the object into a dict
|
|
24
|
+
v1_technical_metrics_dict = v1_technical_metrics_instance.to_dict()
|
|
25
|
+
# create an instance of V1TechnicalMetrics from a dict
|
|
26
|
+
v1_technical_metrics_from_dict = V1TechnicalMetrics.from_dict(v1_technical_metrics_dict)
|
|
27
|
+
```
|
|
28
|
+
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
|
|
29
|
+
|
|
30
|
+
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
# V1TechnicalMetricsDetail
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**cost_sum** | **float** | Sum of costs. | [optional]
|
|
9
|
+
**duration_sum** | **float** | Sum of durations. | [optional]
|
|
10
|
+
**duration_min** | **float** | Minimum duration. | [optional]
|
|
11
|
+
**duration_max** | **float** | Maximum duration. | [optional]
|
|
12
|
+
**duration_avg** | **float** | Average duration. | [optional]
|
|
13
|
+
|
|
14
|
+
## Example
|
|
15
|
+
|
|
16
|
+
```python
|
|
17
|
+
from eval_studio_client.api.models.v1_technical_metrics_detail import V1TechnicalMetricsDetail
|
|
18
|
+
|
|
19
|
+
# TODO update the JSON string below
|
|
20
|
+
json = "{}"
|
|
21
|
+
# create an instance of V1TechnicalMetricsDetail from a JSON string
|
|
22
|
+
v1_technical_metrics_detail_instance = V1TechnicalMetricsDetail.from_json(json)
|
|
23
|
+
# print the JSON string representation of the object
|
|
24
|
+
print(V1TechnicalMetricsDetail.to_json())
|
|
25
|
+
|
|
26
|
+
# convert the object into a dict
|
|
27
|
+
v1_technical_metrics_detail_dict = v1_technical_metrics_detail_instance.to_dict()
|
|
28
|
+
# create an instance of V1TechnicalMetricsDetail from a dict
|
|
29
|
+
v1_technical_metrics_detail_from_dict = V1TechnicalMetricsDetail.from_dict(v1_technical_metrics_detail_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 +1,31 @@
|
|
|
1
|
+
# V1TestCaseLeaderboardItem
|
|
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_test_case_leaderboard_item import V1TestCaseLeaderboardItem
|
|
16
|
+
|
|
17
|
+
# TODO update the JSON string below
|
|
18
|
+
json = "{}"
|
|
19
|
+
# create an instance of V1TestCaseLeaderboardItem from a JSON string
|
|
20
|
+
v1_test_case_leaderboard_item_instance = V1TestCaseLeaderboardItem.from_json(json)
|
|
21
|
+
# print the JSON string representation of the object
|
|
22
|
+
print(V1TestCaseLeaderboardItem.to_json())
|
|
23
|
+
|
|
24
|
+
# convert the object into a dict
|
|
25
|
+
v1_test_case_leaderboard_item_dict = v1_test_case_leaderboard_item_instance.to_dict()
|
|
26
|
+
# create an instance of V1TestCaseLeaderboardItem from a dict
|
|
27
|
+
v1_test_case_leaderboard_item_from_dict = V1TestCaseLeaderboardItem.from_dict(v1_test_case_leaderboard_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 +1,31 @@
|
|
|
1
|
+
# V1TestCaseRelationshipInfo
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**type** | **str** | Type of the relationship. | [optional]
|
|
9
|
+
**target** | **str** | Target of the relationship. | [optional]
|
|
10
|
+
**target_type** | **str** | Type of the target. | [optional]
|
|
11
|
+
|
|
12
|
+
## Example
|
|
13
|
+
|
|
14
|
+
```python
|
|
15
|
+
from eval_studio_client.api.models.v1_test_case_relationship_info import V1TestCaseRelationshipInfo
|
|
16
|
+
|
|
17
|
+
# TODO update the JSON string below
|
|
18
|
+
json = "{}"
|
|
19
|
+
# create an instance of V1TestCaseRelationshipInfo from a JSON string
|
|
20
|
+
v1_test_case_relationship_info_instance = V1TestCaseRelationshipInfo.from_json(json)
|
|
21
|
+
# print the JSON string representation of the object
|
|
22
|
+
print(V1TestCaseRelationshipInfo.to_json())
|
|
23
|
+
|
|
24
|
+
# convert the object into a dict
|
|
25
|
+
v1_test_case_relationship_info_dict = v1_test_case_relationship_info_instance.to_dict()
|
|
26
|
+
# create an instance of V1TestCaseRelationshipInfo from a dict
|
|
27
|
+
v1_test_case_relationship_info_from_dict = V1TestCaseRelationshipInfo.from_dict(v1_test_case_relationship_info_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 +1,48 @@
|
|
|
1
|
+
# V1TestCaseResult
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**key** | **str** | Unique key for the test case. | [optional]
|
|
9
|
+
**input** | **str** | Input text. | [optional]
|
|
10
|
+
**corpus** | **List[str]** | Corpus URLs. | [optional]
|
|
11
|
+
**context** | **List[str]** | Context texts. | [optional]
|
|
12
|
+
**categories** | **List[str]** | Categories. | [optional]
|
|
13
|
+
**relationships** | [**List[V1TestCaseRelationshipInfo]**](V1TestCaseRelationshipInfo.md) | Relationships. | [optional]
|
|
14
|
+
**expected_output** | **str** | Expected output. | [optional]
|
|
15
|
+
**output_constraints** | **List[str]** | Output constraints. | [optional]
|
|
16
|
+
**output_condition** | **str** | Output condition. | [optional]
|
|
17
|
+
**actual_output** | **str** | Actual output generated. | [optional]
|
|
18
|
+
**actual_duration** | **float** | Duration in seconds. | [optional]
|
|
19
|
+
**cost** | **float** | Cost of evaluation. | [optional]
|
|
20
|
+
**model_key** | **str** | Model key. | [optional]
|
|
21
|
+
**test_key** | **str** | Test key. | [optional]
|
|
22
|
+
**test_case_key** | **str** | Test case key. | [optional]
|
|
23
|
+
**metrics** | [**List[V1Metric]**](V1Metric.md) | List of metrics. | [optional]
|
|
24
|
+
**metrics_meta** | **Dict[str, str]** | Metadata for metrics. | [optional]
|
|
25
|
+
**actual_output_meta** | [**List[V1ActualOutputMeta]**](V1ActualOutputMeta.md) | Actual output metadata. | [optional]
|
|
26
|
+
**metric_scores** | [**List[V1ComparisonMetricScore]**](V1ComparisonMetricScore.md) | Metric scores. | [optional]
|
|
27
|
+
**result_error_message** | **str** | Error message if processing resulted in failure. | [optional]
|
|
28
|
+
|
|
29
|
+
## Example
|
|
30
|
+
|
|
31
|
+
```python
|
|
32
|
+
from eval_studio_client.api.models.v1_test_case_result import V1TestCaseResult
|
|
33
|
+
|
|
34
|
+
# TODO update the JSON string below
|
|
35
|
+
json = "{}"
|
|
36
|
+
# create an instance of V1TestCaseResult from a JSON string
|
|
37
|
+
v1_test_case_result_instance = V1TestCaseResult.from_json(json)
|
|
38
|
+
# print the JSON string representation of the object
|
|
39
|
+
print(V1TestCaseResult.to_json())
|
|
40
|
+
|
|
41
|
+
# convert the object into a dict
|
|
42
|
+
v1_test_case_result_dict = v1_test_case_result_instance.to_dict()
|
|
43
|
+
# create an instance of V1TestCaseResult from a dict
|
|
44
|
+
v1_test_case_result_from_dict = V1TestCaseResult.from_dict(v1_test_case_result_dict)
|
|
45
|
+
```
|
|
46
|
+
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
|
|
47
|
+
|
|
48
|
+
|
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
# V1TextSimilarityMetric
|
|
2
|
+
|
|
3
|
+
- TEXT_SIMILARITY_METRIC_UNSPECIFIED: Default value - must not be used - TEXT_SIMILARITY_METRIC_EXACT_MATCH: Exact string matching - sentences must be identical (default) - TEXT_SIMILARITY_METRIC_COSINE_DISTANCE: Cosine distance of sentence embeddings - semantic similarity - TEXT_SIMILARITY_METRIC_BERT_SCORE: BERTScore - contextual embeddings similarity using BERT
|
|
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 +1,29 @@
|
|
|
1
|
+
# V1UpdateDashboardTestCaseAnnotationResponse
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**dashboard_test_case_annotation** | [**V1DashboardTestCaseAnnotation**](V1DashboardTestCaseAnnotation.md) | | [optional]
|
|
9
|
+
|
|
10
|
+
## Example
|
|
11
|
+
|
|
12
|
+
```python
|
|
13
|
+
from eval_studio_client.api.models.v1_update_dashboard_test_case_annotation_response import V1UpdateDashboardTestCaseAnnotationResponse
|
|
14
|
+
|
|
15
|
+
# TODO update the JSON string below
|
|
16
|
+
json = "{}"
|
|
17
|
+
# create an instance of V1UpdateDashboardTestCaseAnnotationResponse from a JSON string
|
|
18
|
+
v1_update_dashboard_test_case_annotation_response_instance = V1UpdateDashboardTestCaseAnnotationResponse.from_json(json)
|
|
19
|
+
# print the JSON string representation of the object
|
|
20
|
+
print(V1UpdateDashboardTestCaseAnnotationResponse.to_json())
|
|
21
|
+
|
|
22
|
+
# convert the object into a dict
|
|
23
|
+
v1_update_dashboard_test_case_annotation_response_dict = v1_update_dashboard_test_case_annotation_response_instance.to_dict()
|
|
24
|
+
# create an instance of V1UpdateDashboardTestCaseAnnotationResponse from a dict
|
|
25
|
+
v1_update_dashboard_test_case_annotation_response_from_dict = V1UpdateDashboardTestCaseAnnotationResponse.from_dict(v1_update_dashboard_test_case_annotation_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
|
+
# V1UpdateLeaderboardTestCaseAnnotationResponse
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
## Properties
|
|
5
|
+
|
|
6
|
+
Name | Type | Description | Notes
|
|
7
|
+
------------ | ------------- | ------------- | -------------
|
|
8
|
+
**leaderboard_test_case_annotation** | [**V1LeaderboardTestCaseAnnotation**](V1LeaderboardTestCaseAnnotation.md) | | [optional]
|
|
9
|
+
|
|
10
|
+
## Example
|
|
11
|
+
|
|
12
|
+
```python
|
|
13
|
+
from eval_studio_client.api.models.v1_update_leaderboard_test_case_annotation_response import V1UpdateLeaderboardTestCaseAnnotationResponse
|
|
14
|
+
|
|
15
|
+
# TODO update the JSON string below
|
|
16
|
+
json = "{}"
|
|
17
|
+
# create an instance of V1UpdateLeaderboardTestCaseAnnotationResponse from a JSON string
|
|
18
|
+
v1_update_leaderboard_test_case_annotation_response_instance = V1UpdateLeaderboardTestCaseAnnotationResponse.from_json(json)
|
|
19
|
+
# print the JSON string representation of the object
|
|
20
|
+
print(V1UpdateLeaderboardTestCaseAnnotationResponse.to_json())
|
|
21
|
+
|
|
22
|
+
# convert the object into a dict
|
|
23
|
+
v1_update_leaderboard_test_case_annotation_response_dict = v1_update_leaderboard_test_case_annotation_response_instance.to_dict()
|
|
24
|
+
# create an instance of V1UpdateLeaderboardTestCaseAnnotationResponse from a dict
|
|
25
|
+
v1_update_leaderboard_test_case_annotation_response_from_dict = V1UpdateLeaderboardTestCaseAnnotationResponse.from_dict(v1_update_leaderboard_test_case_annotation_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
|
+
|
|
@@ -7,7 +7,7 @@ Method | HTTP request | Description
|
|
|
7
7
|
[**workflow_node_service_batch_get_workflow_nodes**](WorkflowNodeServiceApi.md#workflow_node_service_batch_get_workflow_nodes) | **GET** /v1/workflows/*/nodes:batchGet | BatchGetWorkflowNodes retrieves all WorkflowNodes with the specified resource names. If any of the WorkflowNodes do not exist an error is returned. Deleted WorkflowNodes are returned without error. The order of resource names in the request and the returned WorkflowNodes might differ.
|
|
8
8
|
[**workflow_node_service_create_workflow_node**](WorkflowNodeServiceApi.md#workflow_node_service_create_workflow_node) | **POST** /v1/{parent}/nodes | CreateWorkflowNode creates a new WorkflowNode.
|
|
9
9
|
[**workflow_node_service_delete_workflow_node**](WorkflowNodeServiceApi.md#workflow_node_service_delete_workflow_node) | **DELETE** /v1/{name_8} | DeleteWorkflowNode deletes a WorkflowNode by name. If the WorkflowNode does not exist an error is returned. The edges are handled in a following way:
|
|
10
|
-
[**workflow_node_service_get_workflow_node**](WorkflowNodeServiceApi.md#workflow_node_service_get_workflow_node) | **GET** /v1/{
|
|
10
|
+
[**workflow_node_service_get_workflow_node**](WorkflowNodeServiceApi.md#workflow_node_service_get_workflow_node) | **GET** /v1/{name_12} | GetWorkflowNode retrieves a WorkflowNode by name. Deleted WorkflowNode is returned without error, it has a delete_time and deleter fields set.
|
|
11
11
|
[**workflow_node_service_get_workflow_node_prerequisites**](WorkflowNodeServiceApi.md#workflow_node_service_get_workflow_node_prerequisites) | **GET** /v1/{name}:getPrerequisites | GetWorkflowNodePrerequisites retrieves the WorkflowNodes and WorkflowEdges that are the prerequisites of the specified WorkflowNode. The list might be empty. Large data might be stored in storage and not returned in the response. It is client's responsibility to retrieve the data from storage using the content handlers. It is intended to be used by the Eval Studio Workers.
|
|
12
12
|
[**workflow_node_service_init_workflow_node**](WorkflowNodeServiceApi.md#workflow_node_service_init_workflow_node) | **POST** /v1/{name}:init | InitWorkflowNode initializes a WorkflowNode on first access.
|
|
13
13
|
[**workflow_node_service_process_workflow_node**](WorkflowNodeServiceApi.md#workflow_node_service_process_workflow_node) | **POST** /v1/{name}:process | ProcessWorkflowNode processes a WorkflowNode.
|
|
@@ -224,7 +224,7 @@ No authorization required
|
|
|
224
224
|
[[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)
|
|
225
225
|
|
|
226
226
|
# **workflow_node_service_get_workflow_node**
|
|
227
|
-
> V1GetWorkflowNodeResponse workflow_node_service_get_workflow_node(
|
|
227
|
+
> V1GetWorkflowNodeResponse workflow_node_service_get_workflow_node(name_12, view=view)
|
|
228
228
|
|
|
229
229
|
GetWorkflowNode retrieves a WorkflowNode by name. Deleted WorkflowNode is returned without error, it has a delete_time and deleter fields set.
|
|
230
230
|
|
|
@@ -248,12 +248,12 @@ configuration = eval_studio_client.api.Configuration(
|
|
|
248
248
|
with eval_studio_client.api.ApiClient(configuration) as api_client:
|
|
249
249
|
# Create an instance of the API class
|
|
250
250
|
api_instance = eval_studio_client.api.WorkflowNodeServiceApi(api_client)
|
|
251
|
-
|
|
251
|
+
name_12 = 'name_12_example' # str | Required. The name of the WorkflowNode to retrieve.
|
|
252
252
|
view = 'WORKFLOW_NODE_VIEW_UNSPECIFIED' # str | Optional. The level of detail to include in the response. - WORKFLOW_NODE_VIEW_UNSPECIFIED: Unspecified view. - WORKFLOW_NODE_VIEW_BASIC: Basic view. Lacks large data fields. TODO: describe what fields are omitted. - WORKFLOW_NODE_VIEW_FULL: Full view. Contains all fields. (optional) (default to 'WORKFLOW_NODE_VIEW_UNSPECIFIED')
|
|
253
253
|
|
|
254
254
|
try:
|
|
255
255
|
# GetWorkflowNode retrieves a WorkflowNode by name. Deleted WorkflowNode is returned without error, it has a delete_time and deleter fields set.
|
|
256
|
-
api_response = api_instance.workflow_node_service_get_workflow_node(
|
|
256
|
+
api_response = api_instance.workflow_node_service_get_workflow_node(name_12, view=view)
|
|
257
257
|
print("The response of WorkflowNodeServiceApi->workflow_node_service_get_workflow_node:\n")
|
|
258
258
|
pprint(api_response)
|
|
259
259
|
except Exception as e:
|
|
@@ -267,7 +267,7 @@ with eval_studio_client.api.ApiClient(configuration) as api_client:
|
|
|
267
267
|
|
|
268
268
|
Name | Type | Description | Notes
|
|
269
269
|
------------- | ------------- | ------------- | -------------
|
|
270
|
-
**
|
|
270
|
+
**name_12** | **str**| Required. The name of the WorkflowNode to retrieve. |
|
|
271
271
|
**view** | **str**| Optional. The level of detail to include in the response. - WORKFLOW_NODE_VIEW_UNSPECIFIED: Unspecified view. - WORKFLOW_NODE_VIEW_BASIC: Basic view. Lacks large data fields. TODO: describe what fields are omitted. - WORKFLOW_NODE_VIEW_FULL: Full view. Contains all fields. | [optional] [default to 'WORKFLOW_NODE_VIEW_UNSPECIFIED']
|
|
272
272
|
|
|
273
273
|
### Return type
|
|
@@ -10,7 +10,7 @@ Method | HTTP request | Description
|
|
|
10
10
|
[**workflow_service_delete_workflow**](WorkflowServiceApi.md#workflow_service_delete_workflow) | **DELETE** /v1/{name_9} | DeleteWorkflow deletes a Workflow by name. If the Workflow does not exist an error is returned.
|
|
11
11
|
[**workflow_service_find_workflows_by_collection_id**](WorkflowServiceApi.md#workflow_service_find_workflows_by_collection_id) | **GET** /v1/workflows:findWorkflowByH2OGPTeCollectionID | FindWorkflowByCollectionID finds a Workflow by used H2OGPTe collection ID.
|
|
12
12
|
[**workflow_service_get_guardrails_configuration**](WorkflowServiceApi.md#workflow_service_get_guardrails_configuration) | **GET** /v1/{name}:getGuardrailsConfiguration |
|
|
13
|
-
[**workflow_service_get_workflow**](WorkflowServiceApi.md#workflow_service_get_workflow) | **GET** /v1/{
|
|
13
|
+
[**workflow_service_get_workflow**](WorkflowServiceApi.md#workflow_service_get_workflow) | **GET** /v1/{name_13} | GetWorkflow retrieves a Workflow by name. Deleted Workflow is returned without error, it has a delete_time and deleter fields set.
|
|
14
14
|
[**workflow_service_grant_workflow_access**](WorkflowServiceApi.md#workflow_service_grant_workflow_access) | **POST** /v1/{name_2}:grantAccess | GrantWorkflowAccess grants access to a Workflow to a subject with a specified role.
|
|
15
15
|
[**workflow_service_list_workflow_access**](WorkflowServiceApi.md#workflow_service_list_workflow_access) | **GET** /v1/{name_2}:listAccess | ListWorkflowAccess lists access to a Workflow.
|
|
16
16
|
[**workflow_service_list_workflow_dependencies**](WorkflowServiceApi.md#workflow_service_list_workflow_dependencies) | **GET** /v1/{name}:nodeDependencies | ListWorkflowDependencies lists workflow nodes and map of the node dependencies.
|
|
@@ -427,7 +427,7 @@ No authorization required
|
|
|
427
427
|
[[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)
|
|
428
428
|
|
|
429
429
|
# **workflow_service_get_workflow**
|
|
430
|
-
> V1GetWorkflowResponse workflow_service_get_workflow(
|
|
430
|
+
> V1GetWorkflowResponse workflow_service_get_workflow(name_13)
|
|
431
431
|
|
|
432
432
|
GetWorkflow retrieves a Workflow by name. Deleted Workflow is returned without error, it has a delete_time and deleter fields set.
|
|
433
433
|
|
|
@@ -451,11 +451,11 @@ configuration = eval_studio_client.api.Configuration(
|
|
|
451
451
|
with eval_studio_client.api.ApiClient(configuration) as api_client:
|
|
452
452
|
# Create an instance of the API class
|
|
453
453
|
api_instance = eval_studio_client.api.WorkflowServiceApi(api_client)
|
|
454
|
-
|
|
454
|
+
name_13 = 'name_13_example' # str | Required. The name of the Workflow to retrieve.
|
|
455
455
|
|
|
456
456
|
try:
|
|
457
457
|
# GetWorkflow retrieves a Workflow by name. Deleted Workflow is returned without error, it has a delete_time and deleter fields set.
|
|
458
|
-
api_response = api_instance.workflow_service_get_workflow(
|
|
458
|
+
api_response = api_instance.workflow_service_get_workflow(name_13)
|
|
459
459
|
print("The response of WorkflowServiceApi->workflow_service_get_workflow:\n")
|
|
460
460
|
pprint(api_response)
|
|
461
461
|
except Exception as e:
|
|
@@ -469,7 +469,7 @@ with eval_studio_client.api.ApiClient(configuration) as api_client:
|
|
|
469
469
|
|
|
470
470
|
Name | Type | Description | Notes
|
|
471
471
|
------------- | ------------- | ------------- | -------------
|
|
472
|
-
**
|
|
472
|
+
**name_13** | **str**| Required. The name of the Workflow to retrieve. |
|
|
473
473
|
|
|
474
474
|
### Return type
|
|
475
475
|
|