I built PharmX, an AI-powered document processing system that extracts structured medicine information from PDF files.

The system is designed to handle different PDF layouts and automatically:

Upload and process PDF documents

Detect medicine/product information

Extract medicine names

Extract prices when available

Handle PDFs where no relevant medicines are found

Return structured results that can be used by other applications

Process different document formats instead of relying on one fixed PDF template

The main challenge was making the extraction system flexible enough to work with varied PDFs rather than depending on a specific document layout.