kapi exec segmentation

$ kapi segmentation [files...]

Split source text into sentence or chunk segments (stand-off overlay)

Commandexec segmentation

Aliasessegment

Try it (demo)

Demo mode — illustrative output from a built-in stub, not a real model. Install the CLI to run with your own API key.

$ kapi segmentation messages.json

Flags

Flag	Type	Default	Description
--concurrency, -j	int	0	max parallel files (0 = auto)
--credential	string		Stored credential name
--encoding, -e	string	UTF-8	input file encoding
--engine	string	srx	Which segmenter to use; the default needs no configuration (Rule-based (hybrid SRX/UAX-29), Unicode baseline (UAX-29), LLM (semantic chunks))
--fail-on-unknown	bool	false	exit with error if any file cannot be processed (default: skip with warning)
--format, -f	string		override input format detection
--instruction	string		Optional guidance for how to chunk
--json	bool	false	output results as JSON
--layer	string		Segmentation overlay layer name; empty uses the engine's natural layer
--map, -m	stringArray		map glob pattern to format (e.g. '*.docx=okf_openxml:test')
--max-chunk-runes	int	0	Soft upper bound on chunk size in characters (0 = model default)
--model	string		Model name
--no-warn	bool	false	suppress warnings for skipped files
--output, -o	string		output path template (variables: {dir}, {name}, {ext}, {lang})
--output-dir	string		write outputs under DIR/{lang}/ (default: beside the input, mirroring its locale layout)
--overwrite-segmentation	bool	false	Re-segment already-segmented blocks replacing previous segmentation
--pack	bool	false	when transforming a .kpz, also eject the result to the .kpz (auto-pack)
--parallel-blocks	int	0	fan out block processing across N goroutines (0 = off)
--progress, -p	bool	false	show progress bar
--provider	string		AI provider id (anthropic
--renumber-codes	bool	false	Renumber inline code IDs when materializing segments to a bilingual format
--rules-path	string		Path to a custom SRX 2.0 rules file (overrides the built-in ruleset)
--segment-source	bool	true	Segment the source text
--segment-target	bool	false	Segment existing target text
--source-lang	string	en	source language (e.g. en, en-US)
--strict	bool	false	alias for --fail-on-unknown
--target-lang	string		target language (e.g. fr, de-DE)
--trace	string		write flow trace JSON to file (for flow visualization)
--treat-isolated-codes-as-whitespace	bool	false	Treat isolated inline codes as whitespace during segmentation
--trim-leading-whitespace	bool	true	Exclude leading whitespace from each segment span
--trim-trailing-whitespace	bool	true	Exclude trailing whitespace from each segment span

More examples

$ kapi segmentation app.xliff

← Back to the Command Reference