Member Junction
    Preparing search index...

    Options specific to PagedContentSegmenter.

    interface PagedContentSegmentationOptions {
        IncludePageLabel?: boolean;
        MaxSegmentTokens?: number;
        MergeSmallPages?: boolean;
        MinSegmentTokens?: number;
        OverlapTokens?: number;
    }

    Hierarchy (View Summary)

    Index

    Properties

    IncludePageLabel?: boolean

    Prefix each segment's text with a "Page N" label. Default: false.

    MaxSegmentTokens?: number

    Hard ceiling on tokens per text segment. The base class splits any oversized segment via TextChunker so no segmenter can exceed it. Default: 512.

    MergeSmallPages?: boolean

    Merge consecutive pages until the token target is reached, instead of emitting one segment per page. Useful for documents with very short pages (slide decks) where a single slide is too little context to retrieve on. Default: false.

    MinSegmentTokens?: number

    Segments whose text estimates below this many tokens are merged forward into the next segment, preventing a spray of near-empty vectors. Default: 0 (off).

    OverlapTokens?: number

    Overlap tokens applied when an oversized segment must be split. Default: 10% of max.