📄 PDF Chatbot — RAG-based Document Q&A System

A conversational AI chatbot that lets you upload any PDF and ask questions about it in natural language. Built using Retrieval-Augmented Generation (RAG) architecture.

🔗 Live Demo

Click here to try it

🛠️ Tech Stack

• Frontend: Streamlit
• LLM: Google Gemini
• Embeddings: Google Gemini Embedding
• Vector Store: FAISS
• PDF Processing: LangChain PyPDFLoader
• Language: Python

⚙️ How It Works

1. Upload any PDF document
2. PDF is split into chunks of 1000 characters with 200 character overlap
3. Each chunk is converted to vector embeddings using Gemini
4. Embeddings are stored in a FAISS vector database
5. When you ask a question, FAISS finds the 8 most relevant chunks
6. Those chunks are sent to Gemini with your question
7. Gemini answers based only on your PDF content

🚀 Run Locally

git clone https://github.com/mohammed-ma01/pdf-chatbot.git
cd pdf-chatbot
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt

Create a .env file: GOOGLE_API_KEY=your_key_here

Run:

streamlit run app.py

👤 Author

Mohammed Mubeen Ahmed | CSE AI/ML | GitHub