mat-synthesis-extraction

Goal

Given a folder of scientific paper PDFs, extract all synthesis procedures described in each paper and structure them according to the GeneralSynthesisOntology developed in LeMat-Synth [1]. Output is one JSON file per paper containing a list of per-material synthesis records.

The ontology captures: target compound, compound type, synthesis method, starting materials (with amounts/units/purity), sequential process steps (with actions, conditions, equipment), and overall equipment list.

Instructions

Step 1 — Parse PDFs to text

Run the PDF parser to extract plain text from all PDFs in the input folder.