Overview Use Cases Connectors Authentication Getting Started with the Python SDK API Reference API Classes API Inputs AIAgentBatchPredictionArgs AIAgentTrainingConfig AbacusUsageMetricsDatasetConfig AccuracyBelowThresholdConditionConfig AgentConversationMessage AgentFlowButtonResponseSection AlertActionConfig AlertConditionConfig ApplicationConnectorDatasetConfig AttachmentParsingConfig Base64ImageResponseSection BatchPredictionArgs BiasViolationConditionConfig Blob BlobInput ChartResponseSection ChatLLMBatchPredictionArgs ChatLLMPredictionArguments ChatLLMTrainingConfig ClusteringTimeseriesTrainingConfig ClusteringTrainingConfig CodeResponseSection CollapseResponseSection ConfluenceDatasetConfig ConstraintConfig ConstraintProjectFeatureGroupConfig CrawlerTransformConfig CumulativeForecastingPredictionArguments CumulativeForecastingTrainingConfig CustomAlgorithmTrainingConfig CustomTrainedModelTrainingConfig DataGenerationConfig DataIntegrityViolationConditionConfig DatabaseConnectorExportConfig DataframeResponseSection DatasetConfig DatasetDocumentProcessingConfig DeployableAlgorithm DocumentClassificationTrainingConfig DocumentProcessingConfig DocumentRetrieverConfig DocumentSummarizationTrainingConfig DocumentVisualizationTrainingConfig EmailActionConfig EventAnomalyTrainingConfig ExtractDocumentDataConfig FeatureDriftConditionConfig FeatureGroupExportConfig FeatureMappingConfig FeatureStorePredictionArguments FieldDescriptor FileConnectorExportConfig ForecastingBatchPredictionArgs ForecastingMonitorConfig ForecastingPredictionArguments ForecastingTrainingConfig FreshserviceDatasetConfig GoogleAnalyticsDatasetConfig GoogleDriveDatasetConfig HistoryLengthDriftConditionConfig HotkeyPrompt ImageUrlResponseSection IncrementalDatabaseConnectorConfig ItemAttributesStdDevThreshold JSONSchema JiraDatasetConfig KafkaDatasetConfig LastNMergeConfig ListResponseSection MarkdownConfig MergeConfig MonitorFilteringConfig MonitorThresholdConfig NSamplingConfig NamedEntityExtractionBatchPredictionArgs NamedEntityExtractionTrainingConfig NaturalLanguageSearchPredictionArguments NaturalLanguageSearchTrainingConfig OneDriveDatasetConfig OperatorConfig OptimizationPredictionArguments OptimizationTrainingConfig OutputVariableMapping ParsingConfig PercentSamplingConfig PersonalizationBatchPredictionArgs PersonalizationTrainingConfig PredictionArguments PredictionCountConditionConfig PredictiveModelingBatchPredictionArgs PretrainedModelsBatchPredictionArgs ProjectFeatureGroupConfig ProjectFeatureGroupTypeMappingsConfig PythonFunctionArgument RegressionPredictionArguments RegressionTrainingConfig ResponseSection RestrictFeatureMappings ReviewModeProjectFeatureGroupConfig RuntimeSchemaResponseSection SamplingConfig Segment SentenceBoundaryDetectionBatchPredictionArgs SentenceBoundaryDetectionTrainingConfig SentimentDetectionTrainingConfig SharepointDatasetConfig StdDevThreshold StreamingConnectorDatasetConfig TargetDriftConditionConfig TeamsScraperDatasetConfig TextResponseSection ThemeAnalysisBatchPredictionArgs ThemeAnalysisTrainingConfig TimeWindowConfig TimeWindowMergeConfig TimeseriesAnomalyPredictionArguments TimeseriesAnomalyTrainingConfig TrainablePlugAndPlayBatchPredictionArgs TrainingConfig UnionTransformConfig UnpivotConfig VectorStoreConfig WorkflowGraph WorkflowGraphEdge WorkflowGraphNode WorkflowNodeInputMapping WorkflowNodeInputSchema WorkflowNodeOutputMapping WorkflowNodeOutputSchema WorkflowNodeTemplateConfig WorkflowNodeTemplateInput WorkflowNodeTemplateOutput ZendeskDatasetConfig Documentation Chat Bot API Search Video Tutorials ChatLLM

VectorStoreConfig

Config for indexing options of a document retriever. Default values of optional arguments are heuristically selected by the Abacus.AI platform based on the underlying data.

KEY	TYPE	Description
scoreMultiplierColumn	str	If provided, will use the values in this metadata column to modify the relevance score of returned chunks for all queries.
indexMetadataColumns	bool	If True, metadata columns of the FG will also be used for indexing and querying.
useDocumentSummary	bool	If True, uses the summary of the document in addition to chunks of the document for indexing and querying.
textEncoder	VectorStoreTextEncoder	Encoder used to index texts from the documents.
summaryInstructions	str	Instructions for the LLM to generate the document summary.
chunkSizeFactors	list	Chunking data with multiple sizes. The specified list of factors are used to calculate more sizes, in addition to `chunk_size`.
chunkOverlapFraction	float	The fraction of overlap between chunks.
pruneVectors	bool	Transform vectors using SVD so that the average component of vectors in the corpus are removed.
chunkSize	int	The size of text chunks in the vector store.