[Submission] Akhila Vishwanath TEAM:- CODE TITANS — RAG App

Smart Hospital Maintenance AI Assistant

Project Overview

Smart Hospital Maintenance AI Assistant is a Streamlit-based Retrieval-Augmented Generation (RAG) application designed to assist hospital maintenance teams in analyzing documents and retrieving relevant information efficiently.

The application supports PDF document analysis, OCR-based image text extraction, semantic search using FAISS vector database, AI-powered question answering, multilingual translation, and voice output generation.

Features

• PDF document upload and analysis
• OCR-based image text extraction
• RAG-powered question answering
• Semantic search using FAISS vector database
• Multi-language translation
• Voice response generation
• Interactive Streamlit interface

Folder Structure

smart-hospital-maintenance/
├── app.py
├── requirements.txt
├── README.md
├── modules/
│   ├── chatbot.py
│   ├── embeddings.py
│   ├── image_ocr.py
│   ├── pdf_reader.py
│   ├── rag_pipeline.py
│   ├── translation.py
│   └── voice.py
└── screenshots/
    ├── DEMO1.png
    ├── DEMO2.png
    ├── DEMO3.png
    └── DEMO4.png

What document did you use and why?

The system is designed to work with uploaded hospital maintenance documents. Users can upload PDF files and the application extracts, indexes, and retrieves relevant information for question answering.

How does chunking work?

The extracted document text is divided into smaller chunks before generating embeddings. This improves retrieval accuracy and enables the RAG pipeline to fetch the most relevant context for user queries.

Which embedding model did you use?

• sentence-transformers/all-MiniLM-L6-v2

This model provides efficient semantic embeddings suitable for document retrieval and similarity search.

Tech Stack

• Python
• Streamlit
• FAISS
• Sentence Transformers
• PDFPlumber
• PyTesseract OCR
• Groq API
• Deep Translator
• gTTS

How to Run Locally

1. Clone the repository
2. Create a virtual environment
3. Install dependencies

pip install -r requirements.txt

4. Run the application

streamlit run app.py

Screenshots

Home Page & Document Analysis

DEMO1.png

Question Answering

DEMO2.png

Translation Feature

DEMO3.png

Voice Output

DEMO4.png

Future Improvements

• Support multiple document formats
• Better chunking strategies
• Advanced RAG retrieval optimization
• User authentication
• Cloud deployment
• Real-time document updates