Integrate spaCy NLP for concise study notes with dynamic note cards and pdf export

[rixitgithub]

Integrate spaCy NLP for concise study notes with dynamic note cards and pdf export

Overview

This PR introduces a new feature to EduAid that lets users generate concise study notes from their input text, edit those notes on the fly, and download them as a PDF. The feature combines advanced NLP summarization on the backend with a polished, interactive React component on the frontend, positioning EduAid as a complete, user-friendly study platform.

What’s New

• Short Notes Generation: A new /summarize Flask endpoint processes input text using spaCy to generate a set of concise note cards.
• Dynamic Note Cards: Each note card contains a header (extracted noun chunk) and a corresponding point (the sentence itself) based on the ranked importance.
• Editing Capability: Users can easily edit generated notes within the StudyNotes React component.
• PDF Download: Integrated pdf-lib to allow users to download their study notes as a well-formatted PDF, complete with embedded logo, title, and wrapped text.
• Improved Error Handling: Enhanced error management on the backend to gracefully handle missing input and unexpected errors.

Backend (Flask API)

Endpoint Setup

• Route: /summarize (POST)
• Input: JSON payload with key input_text
• Error Handling: Returns a 400 error if input is missing; uses try-except blocks to catch and log exceptions.

Text Processing and Summarization

• Utilizes the spaCy en_core_web_sm model to:
  • Calculate word frequencies (excluding stop words and punctuation)
  • Score sentences based on summed word frequencies
  • Rank sentences and extract them without a fixed cap on the number of cards

Note Card Generation

• Dynamically creates note cards:
  • Header: Extracted from the first meaningful noun chunk (or a fallback verb/noun, defaulting to "Note")
  • Point: Contains the original sentence, prefixed with a dash for clarity
• Response Format:

{
  "notes": [
    {"header": "Colonies", "points": ["- The original Thirteen Colonies were administered by Great Britain."]},
    {"header": "Population", "points": ["- The population grew rapidly."]},
    {"header": "Purchase", "points": ["- The Louisiana Purchase doubled the territory."]}
  ]
}

Frontend (React Component - StudyNotes.jsx)

Component Functionality

• Display: Renders note cards styled with Tailwind CSS in a dark-themed UI. Each card shows the header and a clean list of points.
• Editing:
  • An "Edit" button toggles edit mode for each card.
  • Users can update the header and individual points.
  • "Save" updates the localStorage and state; "Cancel" reverts changes.
• PDF Generation:
  • Uses pdf-lib to create an A4 PDF with:
    • An embedded logo (PNG byte array)
    • A title ("EduAid Study Notes")
    • Text wrapping to avoid WinAnsi encoding issues (newlines are stripped)
  • Triggers a download of the PDF file named study_notes.pdf.
• Navigation: Provides buttons for "Download as PDF," "Back to Input," and "Go to Quiz," ensuring a smooth user workflow.

Bug Fixes Implemented

• PDF Newline Error: Text is cleaned using a replace function (e.g., .replace(/[\n\r]+/g, " ")) to prevent WinAnsi encoding errors.
• Card Length Adjustment: Backend logic now ensures each card has one concise point, keeping the content readable.

Demo Video

Watch the demo video to see the feature in action:

add_notes.mp4

Screenshot Table

Screenshot Description	Image
Note Cards Display
PDF Preview

Workflow

1. Input Stage: The user enters text on the main page.
2. Summarization: The text is sent to the /summarize endpoint, which returns structured note cards.
3. Editing & Storage: The StudyNotes component displays these cards, allows editing, and saves changes to localStorage.
4. PDF Download: Users can download the final notes as a PDF, ensuring a shareable and printable format.

Conclusion

This feature significantly enhances the EduAid platform by offering an intuitive way to condense long texts into manageable, editable study notes with a seamless download option. It is a high-value addition that enriches the student learning experience while maintaining a polished and robust design.