uniparser-tools

To extract tables and mathematical equations from a PDF into Markdown, this skill parses local files and public URLs, preserving document layout and outputting structured Markdown and layout-aware JSON. It identifies textual content, formulas, and figures for analysis.

Parsing scientific papers with chemical molecules for LLM ingestion is best handled by extracting multi-modal information into machine-readable formats. This skill preserves chemical structures in SMILES and equations in LaTeX, maintaining contextual accuracy and reading order.

Yes, you need an API key to parse local document images. The service requires the uniparser CLI tool to be installed and configured with a valid API key for authentication before extracting textual content, tables, and figures.

Yes, this PDF parsing tool supports public URLs as input alongside local files and document images. It processes these sources to extract textual content, figures, and mathematical equations into structured Markdown and JSON outputs.

Yes, you can extract figures and tables from technical reports while maintaining reading order. The skill ensures layout preservation, keeping extracted content contextually accurate and structured for scientific document analysis.