Description

Brief description of your contribution

Type of Contribution

• Example Tutorial
• Showcase Project
• Article/Integration Guide
• Documentation Update
• Bug Fix
• Other (please describe)

Checklist

• My code follows the cookbook's style guidelines
• I have included comprehensive documentation
• I have tested my code and it works as expected
• I have included all necessary dependencies and setup instructions
• My MDX file includes proper frontmatter (title, description, keywords)
• I have linked to any external repositories or live demos

Project Details

What problem does this solve?
Many developers struggle with extracting meaningful, structured data from long-form PDFs—especially ones with inconsistent formatting, multi-column layouts, or embedded tables. This project solves that by providing an offline, lightweight PDF parsing toolkit that can extract structured text, headings (H1-H3), and tables into a clean JSON format.

What makes this contribution valuable to other developers?
This toolkit uses multiple parsing libraries to maximize accuracy and coverage, allowing developers to skip over the tedious process of manually extracting content from PDFs. It is especially useful for researchers, technical writers, and anyone building search or summarization features over document data. Being offline-first makes it reliable for sensitive or restricted environments.

GitHub Repository
Live Demo (View Shared Graph)

External Links (if applicable):

• GitHub Repository: https://github.com/iamaayushijain/perplexity-lens
• Live Demo: https://youtu.be/SCPklDuSR3U
• Blog Post/Article: https://ashjin.hashnode.dev/perplexity-lens-supercharge-your-web-experience-with-personalized-knowledge-graphs

Testing

Smart Text Selection: Selected various text samples on different web pages to check if AI-generated explanations were provided accurately and quickly.

Webpage Summarization: Used the “Summarize” feature on diverse sites (articles, blogs, documentation) to verify concise and relevant summaries.

Retrieval-Augmented Insights (RAG): Hovered and clicked on words/phrases for context retrieval and ensured that RAG-based results were accurate and contextually relevant.

Knowledge Graph Visualization: Added multiple concepts, navigating, zooming, and dragging nodes to confirm the D3.js graph responded smoothly and displayed correct connections.

Public Sharing: Generated and accessed shared graph URLs to validate that public sharing worked as intended, without exposing private data.

Screenshots (if applicable)

Additional Notes