API Reference
Cmdlet
New-OfficeReaderHierarchyOptions
Creates discoverable token and hierarchy settings for Get-OfficeDocumentHierarchy.
Remarks
Creates discoverable token and hierarchy settings for Get-OfficeDocumentHierarchy.
Examples
Create embedding-ready chunks.
PS>
$options = New-OfficeReaderHierarchyOptions -MaxTokens 500 -OverlapTokens 50 -IncludeContextInText
Get-OfficeDocumentHierarchy -Path .\handbook.pdf -ChunkingOptions $options
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
New-OfficeReaderHierarchyOptions [-IncludeContextInText] [-MaxContextCharacters <Int32>] [-MaxHierarchyDepth <Int32>] [-MaxInputChunks <Int32>] [-MaxOutputChunks <Int32>] [-MaxTokens <Int32>] [-OverlapTokens <Int32>] [-PreferMarkdown] [<CommonParameters>]#Parameter set:
All Parameter SetsParameters
- IncludeContextInText SwitchParameter
- Include hierarchy context in chunk text.
- MaxContextCharacters Int32
- Maximum heading-context characters retained.
- MaxHierarchyDepth Int32
- Maximum heading hierarchy depth.
- MaxInputChunks Int32
- Maximum source chunks accepted.
- MaxOutputChunks Int32
- Maximum chunks returned.
- MaxTokens Int32
- Maximum tokens per output chunk.
- OverlapTokens Int32
- Tokens repeated between adjacent chunks.
- PreferMarkdown SwitchParameter
- Prefer Markdown text where the reader supports it.
Outputs
OfficeIMO.Reader.ReaderHierarchicalChunkingOptions