Skip to content

README.md

Latest commit

 

History

History
18 lines (13 loc) · 1.19 KB

README.md

File metadata and controls

18 lines (13 loc) · 1.19 KB

𝐕𝐢𝐬𝐢𝐨𝐧𝐆𝐏𝐓 𝐄𝐱𝐭𝐫𝐚𝐜𝐭𝐨𝐫

Built an AI-powered system for structured data extraction, enabling highly optimized and intelligent processing of PDFs and image-based documents.

VisionGPT Extractor is a Generative AI-powered OCR tool designed to extract structured data from image-based PDFs and images with high accuracy. Leveraging the GPT-5-mini model via Azure API, this tool not only performs OCR but also intelligently understands table layouts and text context, reducing the need for manual data entry.

Technologies: Python, GPT-5-mini, Azure API, OCR, JSON, AI data validation, automation

Features

  • Extracts text and tables from image-based PDFs and images.
  • Utilizes GPT-5-mini for high-quality AI-based data extraction.
  • Performs multiple validation cycles to ensure data reliability:
    • Runs three separate extraction cycles for each file.
    • Compares results from all cycles.
    • Includes only data rows that appear in at least two out of three cycles in the final output.
  • Generates a clean JSON output ready for downstream processing.
  • Supports large-scale document processing with minimal manual effort.