Skip to content

Latest commit

Β 

History

10 Commits

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸ“„πŸ€– PDF Question and Answer System Using LLM and FAISS

Intelligent Document Analysis with Generative AI, Semantic Search & Conversational Intelligence



πŸš€ Overview

The PDF Question and Answer System Using LLM and FAISS is an AI-powered document intelligence platform that transforms static PDF documents into interactive knowledge sources.

Users can upload PDFs, ask natural language questions, and receive context-aware answers generated through the combination of Semantic Search, Vector Embeddings, and Google Gemini LLM. Image

Image Image Image

✨ Key Features

πŸ”Ή Upload and analyze PDF documents

πŸ”Ή Semantic search using FAISS

πŸ”Ή Context-aware answers using Gemini AI

πŸ”Ή HuggingFace embeddings for document understanding

πŸ”Ή Multi-turn conversational memory

πŸ”Ή Real-time chat interface with Streamlit

πŸ”Ή Export conversation history as PDF

πŸ”Ή Fast vector similarity search

πŸ”Ή Research-paper and technical-document support


πŸ› οΈ Tech Stack

Category Technology
🐍 Language Python
🎨 Frontend Streamlit
πŸ€– LLM Google Gemini
🧠 Embeddings HuggingFace MiniLM
πŸ” Vector Search FAISS
πŸ“„ PDF Processing PyPDF2
πŸ“€ Export FPDF
πŸš€ AI Domain Generative AI, NLP, Semantic Search

WhatsApp.Video.2026-06-10.at.13.04.09.1.1.mp4

πŸ“š Research Publication

πŸ† Published in IEEE

πŸ“„ PDF Question and Answer System Using LLM and FAISS

πŸ‘₯ Authors

  • Mudabbir Naragaddi
  • Esha Yalagi
  • Omkar Yametkar
  • Dhulesh Shivakale
  • Prof. Savita Bagewadi

πŸ“– Conference

2025 IEEE 4th International Conference for Advancement in Technology (ICONAT 2025)

πŸ“Œ DOI

10.1109/ICONAT66879.2025.11362602

πŸ”— Publication Links


Image Image

πŸ“Έ Project Workflow

πŸ“„ Upload PDF
        β”‚
        β–Ό
πŸ“‘ Extract Text
        β”‚
        β–Ό
βœ‚οΈ Text Chunking
        β”‚
        β–Ό
🧠 Generate Embeddings
        β”‚
        β–Ό
πŸ” Store in FAISS
        β”‚
        β–Ό
❓ User Query
        β”‚
        β–Ό
πŸ“š Retrieve Relevant Chunks
        β”‚
        β–Ό
πŸ€– Gemini AI Response
        β”‚
        β–Ό
πŸ“€ Export Chat History

🎯 Applications

  • πŸ“š Academic Research
  • βš–οΈ Legal Document Analysis
  • 🏒 Enterprise Knowledge Management
  • πŸ“„ Technical Documentation
  • πŸŽ“ Educational Assistance
  • πŸ”¬ Research Paper Exploration

πŸ‘¨β€πŸ’» Authors

Esha Yalagi

B.E. Computer Science (Artificial Intelligence) KLE Technological University, Belagavi

Mudabbir Naragaddi

Omkar Yametkar

Dhulesh Shivakale

Prof. Savita Bagewadi


⭐ If you found this project useful, please give it a star! ⭐

About

πŸ“„ IEEE-Published AI-powered PDF Question Answering System using Google Gemini, FAISS, HuggingFace Embeddings, and Streamlit for semantic document search, contextual question answering, and intelligent document analysis.

Topics

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages