refigure

Converters where figures survive.

DOCX/XLSX → Markdown that keeps charts and infographics machine-readable instead of losing them to OCR or a vision model: native OOXML chart data (numCache/strCache) recovers exact numbers with zero GPU calls, zero VLM calls, zero lost precision — by default, not as a fallback.

That default path is also why the base install (pip install "refigure[docx,xlsx]") is ~500x lighter than PyTorch-based alternatives (5.6MB vs. multi-GB) — the core conversion needs no ML model at all. That number is about the core architecture, not every distribution format: the Docker image trades it back deliberately, bundling VLM providers + LibreOffice for a turnkey composite-figure path (see Docker below).

VLM interpretation itself is there for the rare figure with no native data at all (a dashboard screenshot) — never required just to get real numbers out of a chart, on any distribution format.

Ships as a library, CLI, MCP server, and a one-click Claude Desktop bundle — every surface returns the same native-fidelity output, not a degraded summary for agents.

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).
• MCP server included — refigure-mcp console command ([mcp] extra), stdio or Streamable HTTP, tools/resources/prompts, batch conversion with per-file isolation (see below).
• Docker image — ghcr.io/helgdemidov/refigure, both console commands on PATH, soffice/LibreOffice baked in — the VLM composite-figure path works turnkey, no manual LibreOffice install. Multi-arch — linux/amd64 + linux/arm64, native Apple Silicon (see below).
• .mcpb bundle for Claude Desktop — one-click install, no terminal (docx+xlsx only, see below).

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")

Or without a permanent install, via uv/uvx:

uvx --from "refigure[docx,xlsx]" refigure report.docx

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

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

Installation & usage

One converter, four ways to run it — pick whichever fits your pipeline. Click a heading to expand it.

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

pip install "refigure[mcp,docx,xlsx]"
refigure-mcp                              # stdio — the MCP client launches it

{
  "mcpServers": {
    "refigure": { "command": "refigure-mcp" }
  }
}

{
  "mcpServers": {
    "refigure": {
      "command": "uvx",
      "args": ["--from", "refigure[mcp,docx,xlsx,vlm-direct]", "refigure-mcp"]
    }
  }
}

echo "sk-... = alice" > tokens.txt
refigure-mcp --transport http --mcp-auth-token-file tokens.txt

docker pull ghcr.io/helgdemidov/refigure:latest

docker run --rm -v "$PWD:/data:ro" ghcr.io/helgdemidov/refigure:latest \
  refigure /data/report.docx

{
  "mcpServers": {
    "refigure": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/helgdemidov/refigure:latest", "refigure-mcp"]
    }
  }
}

echo "sk-... = alice" > tokens.txt
docker run --rm -p 8000:8000 -v "$PWD/tokens.txt:/data/tokens.txt:ro" \
  ghcr.io/helgdemidov/refigure:latest \
  refigure-mcp --transport http --mcp-http-host 0.0.0.0 \
  --mcp-auth-token-file /data/tokens.txt

Real examples

Concentrated excerpts (≤200 lines each) of real convert() output on real, openly-licensed documents — the actual markdown a pipeline would ingest, not a screenshot or a cherry-picked one-liner. Each file's own header states its source, license and attribution; trimmed sections are marked inline, never fabricated to fill space.

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

• Validated against 27 real documents (15 DOCX + 12 XLSX) — 407 native charts found (400 rendered), 35 composite figures recovered as positioned zero-loss markers. Full provenance: tests/integration/fixtures/manifest.yaml.
• Tested: CI gates on a combined unit+integration coverage floor of 95%.
• Published as v0.3.3 — PyPI (trusted publishing, no stored tokens), GHCR, and the official MCP Registry as io.github.HelgDemidov/refigure. refigure-md is a reserved alternate name, not an active release.

Extracted from a working document-analysis pipeline (a government AI-policy research corpus), not built from scratch for this release.

VLM interpretation of composite figures the chart engine can't reconstruct is fully implemented and tested, not a stub — [vlm] extra, provider-agnostic (direct OpenAI/Anthropic via [vlm-direct]), also needs the system soffice/LibreOffice binary.

Mermaid-diagram recognition depends on diagram type and on what the source figure actually contains:

• Common types (flowcharts, pie/xy charts) are picked reliably.
• More specialized ones need an unambiguous visual cue on the source figure.
• Not every figure produces a diagram — a plain-text description is an honest fallback, not a failure.

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:

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

Use Docling or MarkItDown for PDF, refigure for DOCX/XLSX where the chart data actually survives in the file.

License

Apache-2.0 — see LICENSE and NOTICE.