Skills Artificial Intelligence Selecting Output Formats for Extraction

Selecting Output Formats for Extraction

v20261016
xberg-picking-a-format
Learn how to configure xberg's --format and --content-format flags to optimize document extraction for different consumers. Covers LLM context, RAG indexing, JSON parsing, and token reduction strategies for efficient data pipelines.
Get Skill
242 downloads
Overview

Picking a format

Xberg has two orthogonal format knobs. Get them right up front and the
downstream code stays simple.

KnobWhat it controlsValuesDefault
--formatHow the CLI prints the resulttext, json, toontext (extract), json (batch)
--content-formatHow extracted content is rendered inside resultplain, markdown, djot, html, json, doctagsplain
--token-reductionStrip whitespace / boilerplate for LLM contextsoff, light, moderate, aggressive, maximumoff

--format json returns an envelope wrapping the ExtractedDocument — the
document lives under .result for extract and under .results[] for
batch, with content, metadata, tables, and images as fields of
that nested document. --format text prints just content.
--content-format is what shows up inside that content field.

Decision tree

Who consumes the output?
├── LLM (Claude, GPT, Gemini, local) — embed/prompt context
│       --format text --content-format markdown
├── Vector store / RAG indexer
│       --format json --content-format markdown
│       (markdown preserves structure for chunking)
├── Downstream parser that expects machine-readable JSON
│       --format json --content-format plain
│       (cleanest text + structured metadata)
├── Human review / archival
│       --format text --content-format markdown
├── HTML re-rendering / web display
│       --format json --content-format html
├── Lossless intermediate for pandoc / academic tooling
│       --format json --content-format djot
└── Token-budget-constrained pipeline
        --format text --content-format plain
        (drops markup; add --token-reduction moderate for further savings)

Examples

Feed a PDF directly into an LLM:

xberg extract paper.pdf --content-format markdown

Index a corpus into a RAG store with tables and headings preserved:

xberg batch docs/*.pdf --format json --content-format markdown \
  | jq -c '.result | {content: .content, tables: .tables}'

Strip a file to bare text for a token-tight summarizer:

xberg extract long.pdf \
  --content-format plain \
  --token-reduction moderate

Pull metadata only, ignore content:

xberg extract file.pdf --format json | jq '.result.metadata'

When in doubt

  • Default to markdown as the content format. It is the best

compromise across LLMs, RAG, and human review, and Xberg has the
most faithful renderer for it.

  • Reach for plain only when downstream cannot tolerate any markup.
  • Reach for djot only if you're already in a djot/pandoc pipeline.
  • Reach for html only when re-rendering for the web.
  • Reach for json for a heading-driven content tree, or doctags for Docling-compatible output.

Token-reduction (orthogonal)

--token-reduction collapses whitespace, strips repeated headers/footers,
and trims boilerplate. It composes with any --content-format:

  • off (default), light, moderate, aggressive, maximum.

Use moderate as a safe starting point for LLM context windows. maximum
is lossy — verify before relying on it.

See references/cli-reference.md for the full flag set and
references/configuration.md for the equivalent output_format and
token_reduction keys in xberg.toml.

Info
Name xberg-picking-a-format
Version v20261016
Size 46.16KB
Updated At 2026-10-17
Language