API Reference
Cmdlet
Get-OfficeDocumentHierarchy
Creates bounded token-aware chunks and a deterministic document hierarchy.
Remarks
Creates bounded token-aware chunks and a deterministic document hierarchy.
Examples
Create embedding-ready chunks with heading context.
PS>
$options = [OfficeIMO.Reader.ReaderHierarchicalChunkingOptions]::new(); $options.MaxTokens = 500; $result = Get-OfficeDocumentHierarchy -Path .\handbook.pdf -ChunkingOptions $options
Returns chunks, token evidence, overlap counts, and flattened parent/child nodes.
Common Parameters
This command supports the common parameters: -Debug, -ErrorAction, -ErrorVariable, -InformationAction, -InformationVariable, -OutVariable, -OutBuffer, -PipelineVariable, -Verbose, -WarningAction, and -WarningVariable.
For more information, see about_CommonParameters.
Syntax
Get-OfficeDocumentHierarchy [-ChunkingOptions <ReaderHierarchicalChunkingOptions>] -Path <String> [-Reader <OfficeDocumentReader>] [-ReaderOptions <ReaderOptions>] [<CommonParameters>]#Parameter set:
All Parameter SetsParameters
- ChunkingOptions ReaderHierarchicalChunkingOptions
- Optional token budget, overlap, hierarchy, and token-counter settings.
- Path String
- Path to read.
- Reader OfficeDocumentReader
- ReaderOptions ReaderOptions
- Optional source-reading limits and format behavior.
Outputs
OfficeIMO.Reader.ReaderChunkHierarchyResult