A full-stack AI chatbot with Retrieval-Augmented Generation (RAG) using FastAPI, MongoDB, FAISS, and React.

The ABC Chatbot Project is an advanced AI chatbot solution designed with a modern full-stack architecture. It combines a FastAPI backend, MongoDB for data storage, FAISS for high-performance vector search, and a responsive React frontend widget. The chatbot supports Retrieval-Augmented Generation (RAG), providing intelligent responses to user queries using semantic search powered by Sentence Transformers. MongoDB collections store FAQs, contacts, and a chunked knowledge base, all indexed for both semantic and text-based querying. The frontend includes a floating chatbot widget that integrates seamlessly into web applications.

• Ensure MongoDB is running locally.

• Launch the backend (uvicorn app.main:app --reload).

• Start the React frontend (npm start).

• Open http://localhost:3000 in a browser.

• Use the floating chatbot widget to interact.

• The backend retrieves answers using FAISS and MongoDB.

AI Chatbot Project

A full-stack AI chatbot using FastAPI, MongoDB, FAISS, and React.

Features

• Retrieval-Augmented Generation (RAG)
• Semantic search via Sentence Transformers + FAISS
• MongoDB-backed knowledge base (FAQ, Contacts, etc.)
• React floating chatbot widget

Backend Setup

cd backend
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt


Build FAISS index and seed MongoDB:

Use seed_data.py and rag_ingest.py

Run backend:uvicorn app.main:app --reload
Frontend Setup:
cd frontend
npm install
npm start
Visit: http://localhost:3000