🤖 AI Chatbot

AI chatbot with semantic search (RAG), voice transcription, text-to-speech, user authentication, and a React frontend — powered by OpenAI and FastAPI.

Features

• 💬 AI Chat — Powered by OpenAI GPT (gpt-3.5-turbo) with personality modes: Friendly, Professional, Sarcastic, Motivational
• 🔍 Semantic RAG — ChromaDB-backed knowledge base with semantic search using OpenAI embeddings
• 🎙️ Voice Input — Whisper-based audio transcription endpoint
• 🔊 Text-to-Speech — gTTS integration for audio responses
• 🔐 Authentication — JWT-based user login with SQLite storage
• 📊 Usage Tracking — Per-user token and cost accounting
• 🐳 Docker Ready — Full Docker Compose setup for local development
• ✅ CI/CD — GitHub Actions workflow with integration tests

---

Tech Stack

Layer	Technology
Frontend	React 18, Axios
Backend	Python, FastAPI, Uvicorn
AI	OpenAI GPT, Whisper, Embeddings
Vector DB	ChromaDB
Auth	JWT (PyJWT)
Database	SQLite
TTS	gTTS
Deployment	Docker, Render, Hugging Face

---

Project Structure

ai-chatbot/
├── backend/
│   ├── app.py              # FastAPI backend (chat, auth, RAG, TTS, Whisper)
│   ├── requirements.txt    # Python dependencies
│   └── Dockerfile
├── frontend-react/
│   ├── src/
│   │   ├── App.js          # React UI (chat, auth, KB upload, audio)
│   │   └── index.css
│   └── package.json
├── tests/
│   ├── integration_api_test.py
│   └── test_integration_endpoints.py
├── deploy/
│   ├── docker_deploy.md
│   ├── render.md
│   └── hf_instructions.md
├── docker-compose.yml
└── README.md

---

Setup & Installation

Prerequisites

• Python 3.11+
• Node.js 18+
• OpenAI API Key

1. Clone the repository

git clone https://github.com/nithu0035/AI-chatbot.git
cd AI-chatbot/ai-chatbot

2. Backend Setup

cd backend
pip install -r requirements.txt

Create a .env file:

OPENAI_API_KEY=your_openai_api_key_here
JWT_SECRET=your_secret_key_here

Start the backend:

uvicorn app:app --host 0.0.0.0 --port 8000

3. Frontend Setup

cd frontend-react
npm install
npm start

Open your browser at http://localhost:3000

---

🐳 Run with Docker

# From the ai-chatbot/ directory
OPENAI_API_KEY=your_key JWT_SECRET=your_secret docker-compose up --build

Service	URL
Frontend	http://localhost:3000
Backend API	http://localhost:8000

---

API Endpoints

Method	Endpoint	Description
GET	/	Health check
POST	/register	Register a new user
POST	/login	Login and get JWT token
POST	/chat	Send a message and get AI reply
POST	/transcribe	Upload audio for Whisper transcription
POST	/tts	Convert text to speech
POST	/upload-kb	Upload document to knowledge base

---

Running Tests

cd tests
pip install pytest httpx
pytest integration_api_test.py

---

Deployment

See the deploy/ folder for step-by-step guides:

• Docker → deploy/docker_deploy.md
• Render → deploy/render.md
• Hugging Face Spaces → deploy/hf_instructions.md

---

📄 License

MIT

👤 Author

Gudipatoju Nitesh
GitHub: @nithu0035