Skip to content

23kl/rag_exam

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

7 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿง  Smart QnA Generator Smart QnA Generator is an intelligent system designed to extract content from PDF documents and generate highly relevant, context-aware questions and answers. It leverages advanced language models and vector-based similarity checks to ensure quality and relevance, making it a valuable tool for educational, research, and training purposes.

๐ŸŽฅ Video Demo

ipd.vid.1.1.1.mp4

๐Ÿš€ Features ๐Ÿ“„ PDF Content Extraction Parses both text and images from uploaded PDF documents for comprehensive content understanding.

๐Ÿ’ฌ Contextual Question Generation Utilizes DeepSeek combined with LangChain to generate high-quality, meaningful questions based on extracted document content.

โœ… Answer Validation Employs Chroma vector database to compare generated answers with the source text and ensure contextual accuracy.

๐Ÿ–ผ Image-Enhanced Answers Enhances answers by matching keywords to relevant images extracted from the same PDF, offering visual context alongside text.

๐Ÿ›  Technology Used Frontend: React.js HTML5, CSS3, JavaScript

Backend: Node.js Express.js

AI/ML Tools: DeepSeek LLM LangChain for chaining context Chroma for vector similarity LoRA/QLoRA fine-tuning (used during model optimization)

Document Processing: PyMuPDF (for PDF parsing) OpenCV (for image alignment)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages