Building Agentic Document Intelligence Pipelines: Creating Scientific Figures with AutoFigure

Summary

This tutorial introduces AutoFigure, a practical toolkit for generating scientific figures directly from text descriptions, paper-like content, and structured methodological explanations. Steps include setting up the AutoFigure environment, fixing dependency issues such as Pillow compatibility, preparing SVG and PNG rendering tools, building a custom reference figure, configuring an API-backed generation workflow, and converting a detailed agentic document intelligence pipeline into a publication-style scientific diagram. The tutorial also covers offline SVG rendering, inspecting generated files, creating a sample paper and PDF, and exporting final outputs to a reusable gallery and zip archive. Code snippets show configuration with default models (e.g., google/gemini-3.1-pro-preview), maximum iterations, and quality threshold settings.