refigure

Converters where figures survive.

DOCX / XLSX → Markdown converters that treat embedded charts, composite diagrams and infographics as single semantic objects instead of silently dropping or fragmenting them: native OOXML chart-data extraction (no rasterize/OCR/VLM) plus positioned machine-readable markers as the zero-loss floor, optional VLM interpretation (prose + mermaid) on top, cached and reproducible offline.

Demo

Optional VLM interpretation — for a figure with no native chart data at all (a screenshot, not an OOXML chart part) AND no matching mermaid construct either (a dense radial sunburst — nothing in the 4 original mermaid types could represent it), --vlm both recovers the real content and produces a genuinely renderable diagram, not just recovered text:

Native chart-data extraction — real OOXML numCache, not a screenshot, not OCR:

Same extraction, from DOCX — Word embeds native charts too, not just Excel; refigure reads the same cached OOXML data either way:

Composite figures — positioned, zero-loss, even when the figure itself can't be rendered (no incumbent does this — see Docling issue #1287, open >1 year):

Quickstart

pip install "refigure[docx,xlsx]"

refigure report.docx                      # markdown to stdout

from refigure.docx import convert

result = convert("report.docx")
print(result.markdown)
print(f"{result.charts_found} charts, {result.groups_found} composite figures")

Optional VLM interpretation, for a composite figure the chart engine can't reconstruct on its own (see Features below):

pip install "refigure[docx,vlm]"
export OPENROUTER_API_KEY=...                 # or --vlm-api-key-file/--vlm-provider
refigure report.docx --vlm                    # needs the system soffice/LibreOffice binary too

Features

• Native chart-data extraction — reads OOXML numCache/strCache directly; no rasterize/OCR/VLM step for charts, real numbers every time.
• Positioned zero-loss markers for composite figures (DOCX) — grouped shapes/infographics that mammoth would otherwise silently fragment into disconnected pieces get a clean marker instead, with position and any caption text preserved. Absent even in well-funded incumbents — see Docling issue #1287.
• Optional VLM interpretation (DOCX composite figures, [vlm] extra, --vlm/Config(use_vlm=True)) — cloud description + a real rendered mermaid diagram (26 supported diagram types — flowcharts, pie/xy charts, sequence/state/ER diagrams, Gantt/timeline/sankey/treemap and more, see Status below) on top of the zero-loss floor, for figures with no native chart data at all (e.g. a dashboard screenshot). Provider-agnostic — OpenRouter by default, or direct OpenAI/Ollama/vLLM/LM Studio/Anthropic via --vlm-provider ([vlm-direct] extra). --strict upgrades one specific failure (the system soffice/LibreOffice binary missing) from a graceful skip to a hard error; every other VLM failure still degrades.
• Rich, typed result — ConversionResult (markdown + warnings + chart/group counts + vlm_used), not a bare string.
• CLI included — refigure console command, stdin/stdout-first, native batch mode, typed exit codes (see below).

CLI

refigure installs a console command — a thin wrapper over the same convert() used programmatically, no separate logic:

refigure report.docx                      # markdown to stdout
refigure report.docx -o report.md         # markdown to a file
cat report.docx | refigure --format docx  # stdin, format hint required
refigure reports/ -o out/                 # batch: directory, walked recursively
refigure a.docx b.xlsx -o out/            # batch: 2+ explicit sources

Batch mode (2+ sources, or a single directory) requires -o DIR, keeps going past a failed source by default (--fail-fast aborts on the first one instead), and always prints a summary (N/M converted, K failed) to stderr. --json emits the full result — markdown plus chart/group counts and warnings — instead of plain markdown. -v/-q control verbosity; --strict is forwarded to the same Config.strict the Python API uses.

Exit codes:

Real examples

Full convert() output on real, openly-licensed documents — not cherry-picked snippets. Each file's own header states its source, license and attribution.

Open any of these on GitHub and both views are right there: the raw ```mermaid fence an LLM/RAG pipeline would read, and its native GitHub rendering — no extra step, that's GitHub's own Markdown support.

Status

Published on PyPI as refigure. Tested against 27 real documents (15 DOCX + 12 XLSX) — 407 native charts found (400 rendered), 35 composite figures recovered as positioned zero-loss markers — see tests/integration/fixtures/manifest.yaml for provenance, licenses and attribution. CI gates on a combined unit+integration test-coverage floor of 95%.

The converters were extracted from a working document-analysis pipeline (government AI-policy corpus) into a single package with per-format extras ([docx] / [xlsx]). VLM interpretation of composite figures the chart engine can't reconstruct ([vlm] extra, Config(use_vlm=True), provider-agnostic — direct OpenAI/Anthropic via [vlm-direct], also needs the system soffice/LibreOffice binary, not installable via pip) is fully implemented, tested, and exposed through the refigure CLI (--vlm and friends — see CLI above and Quickstart). Mermaid-diagram recognition on top of that varies by diagram type and by what's actually on the source figure — common types (flowcharts, pie/xy charts) are picked reliably; more specialized ones depend on the figure carrying an unambiguous visual cue, and not every figure produces a diagram at all — a plain text description is a valid, honest fallback when it doesn't.

PDF is out of scope, on purpose — a boundary, not a gap. PDF has no equivalent of OOXML's cached chart data (numCache/strCache) for any mainstream chart generator, so the native, rasterize-free extraction this project is built on doesn't transfer to it — confirmed by research into PDF's own structure and how leading PDF converters handle charts today, not assumed. For mixed-format corpora, route by extension instead of expecting one tool to cover everything — Docling or MarkItDown for PDF, refigure for DOCX/XLSX where the chart data actually survives in the file:

import refigure.docx
import refigure.xlsx

if path.suffix == ".pdf":
    markdown = docling_convert(path)      # or any PDF-capable converter
elif path.suffix == ".docx":
    markdown = refigure.docx.convert(path).markdown
else:
    markdown = refigure.xlsx.convert(path).markdown

v0.1.0 published via trusted publishing (GitHub↔PyPI, no stored tokens). refigure-md is a reserved alternate name, not an active release.

License

Apache-2.0 — see LICENSE and NOTICE.