These are the input classes that are available in the Python SDK. Use the links below to learn more about each class.
Training config for the AI_AGENT problem type
AbacusUsageMetricsDatasetConfigDataset config for Abacus Usage Metrics Application Connector
AccuracyBelowThresholdConditionConfigAccuracy Below Threshold Condition Config for Monitor Alerts
AlertActionConfigAn abstract class for alert action configs
AlertConditionConfigAn abstract class for alert condition configs
BatchPredictionArgsAn abstract class for Batch Prediction args specific to problem type.
BiasViolationConditionConfigBias Violation Condition Config for Monitor Alerts
BlobInputBinary large object input data.
ChatLLMBatchPredictionArgsBatch Prediction Config for the ChatLLM problem type
ChatLLMPredictionArgumentsPrediction arguments for the CHAT_LLM problem type
ChatLLMTrainingConfigTraining config for the CHAT_LLM problem type
ClusteringTimeseriesTrainingConfigTraining config for the CLUSTERING_TIMESERIES problem type
ClusteringTrainingConfigTraining config for the CLUSTERING problem type
ConfluenceDatasetConfigDataset config for Confluence Application Connector
ConstraintConfigConstraint configuration.
ConstraintProjectFeatureGroupConfigConstraint project feature group configuration.
CumulativeForecastingPredictionArgumentsPrediction arguments for the CUMULATIVE_FORECASTING problem type
CumulativeForecastingTrainingConfigTraining config for the CUMULATIVE_FORECASTING problem type
CustomAlgorithmTrainingConfigTraining config for the CUSTOM_ALGORITHM problem type
CustomTrainedModelTrainingConfigTraining config for the CUSTOM_TRAINED_MODEL problem type
DataIntegrityViolationConditionConfigData Integrity Violation Condition Config for Monitor Alerts
DatabaseConnectorExportConfigDatabase connector export config for feature groups
DatasetConfigAn abstract class for dataset configs specific to application connectors.
DatasetDocumentProcessingConfigDocument processing configuration for dataset imports.
DeployableAlgorithmAlgorithm that can be deployed to a model.
DocumentClassificationTrainingConfigTraining config for the DOCUMENT_CLASSIFICATION problem type
DocumentProcessingConfigDocument processing configuration.
DocumentRetrieverConfigConfigs for document retriever. If any configuration value is not explicitly provided, Abacus.AI will automatically infer default values based on the data.
DocumentSummarizationTrainingConfigTraining config for the DOCUMENT_SUMMARIZATION problem type
DocumentVisualizationTrainingConfigTraining config for the DOCUMENT_VISUALIZATION problem type
EmailActionConfigEmail Action Config for Monitor Alerts
EventAnomalyTrainingConfigTraining config for the EVENT_ANOMALY problem type
FeatureDriftConditionConfigFeature Drift Condition Config for Monitor Alerts
FeatureGroupExportConfigAn abstract class for feature group exports.
FeatureMappingConfigFeature mapping configuration for a feature group type.
FeatureStorePredictionArgumentsPrediction arguments for the FEATURE_STORE problem type
FieldDescriptorConfigs for vector store indexing.
FileConnectorExportConfigFile connector export config for feature groups
ForecastingBatchPredictionArgsBatch Prediction Config for the FORECASTING problem type
ForecastingMonitorConfigForecasting Monitor Configuration
ForecastingPredictionArgumentsPrediction arguments for the FORECASTING problem type
ForecastingTrainingConfigTraining config for the FORECASTING problem type
FreshserviceDatasetConfigDataset config for Freshservice Application Connector
GoogleAnalyticsDatasetConfigDataset config for Google Analytics Application Connector
GoogleDriveDatasetConfigDataset config for Google Drive Application Connector
HistoryLengthDriftConditionConfigHistory Length Drift Condition Config for Monitor Alerts
HotkeyPromptA config class for a Data Science Co-Pilot Hotkey
IncrementalDatabaseConnectorConfigConfig information for incremental datasets from database connectors
ItemAttributesStdDevThresholdItem Attributes Std Dev Threshold for Monitor Alerts
JiraDatasetConfigDataset config for Jira Application Connector
LastNMergeConfigMerge LAST N chunks/versions of an incremental dataset.
MergeConfigAn abstract class for the merge config of a feature group
MonitorFilteringConfigMonitor Filtering Configuration
MonitorThresholdConfigMonitor Threshold Config for Monitor Alerts
NSamplingConfigThe number of distinct values of the key columns to include in the sample, or number of rows if key columns not specified.
NamedEntityExtractionBatchPredictionArgsBatch Prediction Config for the NAMED_ENTITY_EXTRACTION problem type
NamedEntityExtractionTrainingConfigTraining config for the NAMED_ENTITY_EXTRACTION problem type
NaturalLanguageSearchPredictionArgumentsPrediction arguments for the NATURAL_LANGUAGE_SEARCH problem type
NaturalLanguageSearchTrainingConfigTraining config for the NATURAL_LANGUAGE_SEARCH problem type
OneDriveDatasetConfigDataset config for OneDrive Application Connector
OptimizationPredictionArgumentsPrediction arguments for the OPTIMIZATION problem type
OptimizationTrainingConfigTraining config for the OPTIMIZATION problem type
OutputVariableMappingA config class for python function arguments
ParsingConfigCustom config for dataset parsing.
PercentSamplingConfigThe fraction of distinct values of the feature group to include in the sample.
PersonalizationBatchPredictionArgsBatch Prediction Config for the PERSONALIZATION problem type
PersonalizationTrainingConfigTraining config for the PERSONALIZATION problem type
PredictionArgumentsAn abstract class for prediction arguments specific to problem type.
PredictionCountConditionConfigDeployment Prediction Condition Config for Deployment Alerts. By default we monitor if predictions made over a time window has reduced significantly.
PredictiveModelingBatchPredictionArgsBatch Prediction Config for the PREDICTIVE_MODELING problem type
PretrainedModelsBatchPredictionArgsBatch Prediction Config for the PRETRAINED_MODELS problem type
ProjectFeatureGroupConfigAn abstract class for project feature group configuration.
ProjectFeatureGroupTypeMappingsConfigProject feature group type mappings.
PythonFunctionArgumentA config class for python function arguments
RegressionPredictionArgumentsPrediction arguments for the PREDICTIVE_MODELING problem type
RegressionTrainingConfigTraining config for the PREDICTIVE_MODELING problem type
RestrictFeatureMappingsRestrict Feature Mappings for Monitor Filtering
ReviewModeProjectFeatureGroupConfigReview mode project feature group configuration.
SamplingConfigAn abstract class for the sampling config of a feature group
SentenceBoundaryDetectionBatchPredictionArgsBatch Prediction Config for the SENTENCE_BOUNDARY_DETECTION problem type
SentenceBoundaryDetectionTrainingConfigTraining config for the SENTENCE_BOUNDARY_DETECTION problem type
SentimentDetectionTrainingConfigTraining config for the SENTIMENT_DETECTION problem type
SharepointDatasetConfigDataset config for Sharepoint Application Connector
StdDevThresholdStd Dev Threshold types
TargetDriftConditionConfigTarget Drift Condition Config for Monitor Alerts
ThemeAnalysisBatchPredictionArgsBatch Prediction Config for the THEME_ANALYSIS problem type
ThemeAnalysisTrainingConfigTraining config for the THEME ANALYSIS problem type
TimeWindowConfigTime Window Configuration
TimeWindowMergeConfigMerge rows within a given timewindow of the most recent timestamp
TimeseriesAnomalyPredictionArgumentsPrediction arguments for the TS_ANOMALY problem type
TimeseriesAnomalyTrainingConfigTraining config for the TS_ANOMALY problem type
TrainablePlugAndPlayBatchPredictionArgsBatch Prediction Config for the TrainablePlugAndPlay problem type
TrainingConfigAn abstract class for the training config options used to train the model.
VectorStoreConfigConfigs for vector store indexing.
WorkflowGraphAn Agent workflow graph. The edges define the node invokation order. The workflow must follow linear invokation order.
WorkflowGraphEdgeAn edge in an Agent workflow graph.
WorkflowGraphNodeA node in an Agent workflow graph.
WorkflowNodeInputMappingA mapping of input to a workflow node.
WorkflowNodeInputSchemaA react-jsonschema-form conformant schema for workflow node input.
WorkflowNodeOutputMappingA mapping of output to a workflow node.
WorkflowNodeOutputSchemaA react-jsonschema-form schema for a workflow node output.
ZendeskDatasetConfigDataset config for Zendesk Application Connector