logo

Chrome Extension extension

PDF text extractor extension using Node.js and JS, also leveraging Python for Persian OCR and PDF parsing.

Role

Fullstack Developer

Challenge

Extracting Persian text from uploaded PDFs using Node.js + Python

Result

Successfully parsed Persian PDFs using Python OCR and extracted text for the extension.

Project Overview

Chrome Extension (RAGM) is a specialized browser tool designed for psychology sessions. It connects to an external API (like GeminAI) to provide personalized hints and guidance based on the transcripts and subtitles of therapy sessions.

Key features include:

  • Session Transcript Analysis — Extracts subtitles and spoken content from online or uploaded sessions.
  • Dynamic Hints Generation — Sends contextual hints to the AI API based on what was spoken and provides tailored feedback for therapists or users.
  • PDF Integration — Users can upload session PDFs, which are processed for relevant content and timing, then sent to the API to generate accurate responses.
  • Customizable Prompts — Prompts can be adapted depending on the user's needs, ensuring flexibility and personalization in advice or guidance.
  • Language Support — Works with both Persian and English content seamlessly.

Technologies used:

  • Node.js and JavaScript for browser extension functionality
  • Python for subtitle parsing and text processing
  • OCR for extracting text from PDF files
  • GeminAI API for AI-driven hints and contextual guidance

This extension acts as a smart companion for psychology sessions, allowing therapists and users to get real-time, personalized insights. It is especially useful for session follow-ups, note-taking, and generating context-aware suggestions.