Skip to main content

Search OfficeIMO

Enter a topic, API type, or PowerShell command.

Documentation Search all OfficeIMO/
Cmdlet

New-OfficeDocumentHierarchyOptions

Module
PSWriteOffice
Inputs
None
Outputs
OfficeIMO.Reader.ReaderHierarchicalChunkingOptions

Creates discoverable token and hierarchy settings for Read-OfficeDocument -As Hierarchy.

Syntax

New-OfficeDocumentHierarchyOptions
[-IncludeContextInText]
[-MaximumContextCharacters <Int32>]
[-MaximumHierarchyDepth <Int32>]
[-MaximumInputChunks <Int32>]
[-MaximumOutputChunks <Int32>]
[-MaximumTokens <Int32>]
[-OverlapTokens <Int32>]
[-PreferMarkdown]
[<CommonParameters>]
#
Parameter set: Default

Examples

Create embedding-ready chunks.

$options = New-OfficeDocumentHierarchyOptions -MaximumTokens 500 -OverlapTokens 50 -IncludeContextInText
Read-OfficeDocument -As Hierarchy -Path .\handbook.pdf -HierarchyOptions $options

Parameters

-IncludeContextInText SwitchParameter optional
Include hierarchy context in chunk text.
-MaximumContextCharacters Int32 optional
Maximum heading-context characters retained.
-MaximumHierarchyDepth Int32 optional
Maximum heading hierarchy depth.
-MaximumInputChunks Int32 optional
Maximum source chunks accepted.
-MaximumOutputChunks Int32 optional
Maximum chunks returned.
-MaximumTokens Int32 optional
Maximum tokens per output chunk.
-OverlapTokens Int32 optional
Tokens repeated between adjacent chunks.
-PreferMarkdown SwitchParameter optional
Prefer Markdown text where the reader supports it.

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.