---

---

📚 Smart Knowledge AI Assistant

🧠 Industry-Level RAG (Retrieval-Augmented Generation) System for Intelligent Document Q&A

---

🚀 Live Demo

🔗 Try the App Here: 👉 https://smart-knowledge-ai-rag-eigycfwp9rfdq7sn6kedz2.streamlit.app/

---

📸 Screenshots

🏠 Home UI

📂 Upload Documents

🤖 AI Generated Answer

---

🧠 Overview

Smart Knowledge AI Assistant is a production-ready Generative AI application that allows users to:

• 📄 Upload documents (PDF/TXT)
• 💬 Ask questions based on documents
• 🔍 Perform semantic search using embeddings
• 🧠 Get accurate, structured AI-generated answers
• 📌 View source references

---

⚙️ Features

• ✅ RAG (Retrieval-Augmented Generation)
• 📂 Multi-document upload support
• 🔎 Semantic search with FAISS
• 🤖 Gemini 2.5 Flash LLM integration
• 🧾 Source citation for answers
• 💬 Chat history tracking
• 🌐 Works with or without documents

---

🏗️ Tech Stack

Layer	Technology
UI	Streamlit
LLM	Gemini 2.5 Flash
Embeddings	HuggingFace (MiniLM)
Vector DB	FAISS
Framework	LangChain

---

📁 Project Structure

smart-knowledge-ai-rag/
│
├── app/
│   └── app.py
│
├── core/
│   ├── embeddings.py
│   ├── llm.py
│   └── vectorstore.py
│
├── services/
│   ├── doc_loader.py
│   └── rag_pipeline.py
│
├── assets/
│   ├── home.png
│   ├── upload.png
│   └── answer.png
│
├── data/
├── requirements.txt
├── README.md
├── .gitignore
└── LICENSE

---

🔄 How It Works

1. 📄 User uploads documents
2. ✂️ Documents are split into chunks
3. 🔍 Embeddings are created
4. 📦 Stored in FAISS vector database
5. ❓ User asks a question
6. 📌 Relevant chunks retrieved
7. 🤖 Gemini generates structured answer

---

⚡ Installation

git clone https://github.com/22AD040/smart-knowledge-ai-rag.git
cd smart-knowledge-ai-rag

pip install -r requirements.txt

---

🔐 Environment Setup

Create .env file:

GEMINI_API_KEY=your_api_key_here

---

▶️ Run Locally

streamlit run app/app.py

---

☁️ Deployment

Deployed using Streamlit Cloud

Steps:

1. Push code to GitHub
2. Connect repo in Streamlit
3. Add secrets:

GEMINI_API_KEY="your_api_key"

4. Deploy 🚀

---

🎯 Use Cases

• 📚 Academic Assistant
• 🏢 Company Knowledge Base
• ⚖️ Legal Document Analysis
• 📄 Research Paper Q&A
• 🧑‍💼 HR Policy Assistant

---

📈 Future Improvements

• 💬 ChatGPT-style UI
• 🧠 Memory-based conversations
• 📊 Better document visualization
• ⚡ Faster retrieval (caching)
• 🔐 User authentication

---

🤝 Contributing

Contributions are welcome! Feel free to fork and improve 🚀

---

📜 License

This project is licensed under the MIT License

---

👩‍💻 Author

Ratchita B 🎓 Generative AI Intern 💡 Passionate about AI, ML & Real-world Applications

---

⭐ Show Your Support

If you like this project:

👉 Give a ⭐ on GitHub 👉 Share with others 👉 Use it in your projects

---