AI-Powered Customer Support Automation

An AI-driven customer support automation system that can answer knowledge-base questions instantly.

Features

• RAG-powered search over company knowledge base.
• FastAPI backend for fast API responses.
• React + Material UI frontend for a polished chat interface.
• Uses HuggingFace embeddings + OpenAI / Llama models.
• .env for API keys and config.

Tech Stack

• Backend: FastAPI, LlamaIndex, HuggingFace Embeddings
• Frontend: React, Material UI
• Database (vector store): In-memory for demo (can integrate Pinecone/FAISS)

Getting Started

Backend Setup

cd backend
python -m venv venv
source venv/bin/activate  # Mac/Linux
venv\Scripts\activate     # Windows
pip install -r requirements.txt

Create .env in backend/:

OPENAI_API_KEY=your_key
OPENAI_API_BASE=https://api.openai.com/v1
MODEL_NAME=gpt-4o-mini

Run:

uvicorn app:app --reload

Frontend Setup

cd frontend
npm install
npm start

Usage

Start backend (uvicorn) Start frontend (npm start) Ask a question in the UI → AI answers using your KB.

Screenshots