AI Agent Web Application

A full-stack AI-powered web application featuring a FastAPI backend and a Next.js frontend. This project supports AI chat, voice chat, and user usage tracking.

Technology Stack

• Frontend: Next.js 16, React 19, Tailwind CSS 4, Axios.
• Backend: FastAPI, Motor (MongoDB Async Driver), Pydantic, Jose (JWT).
• Database: MongoDB.
• AI Engine: Ollama (local) or OpenAI API.

---

Prerequisites

Before setting up the project, ensure you have the following installed:

• Node.js (v18 or later)
• Python (v3.9 or later)
• MongoDB (Running locally or a cloud URI)
• Ollama (Optional, for local AI models)

---

Project Setup

1. Clone the repository

git clone <repository-url>
cd ai-agent-web

2. Backend Setup

Windows (PowerShell)

cd backend
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txt

macOS / Linux

cd backend
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Environment Configuration

Create a .env file in the backend/ directory:

MONGO_URL=mongodb://localhost:27017
SECRET_KEY=your-secret-key-change-me
OLLAMA_URL=http://localhost:11434/api/generate
MODEL=qwen2.5-coder:1.5b-base

3. Frontend Setup

All Platforms

cd frontend
npm install

Environment Configuration

Create a .env.local file in the frontend/ directory (if needed for API URLs).

---

Running the Application

Start the Backend

From the backend/ directory (with virtual environment active):

uvicorn main:app --reload

The backend will be available at http://localhost:8000.

Start the Frontend

From the frontend/ directory:

npm run dev

The frontend will be available at http://localhost:3000.

---

Features

• AI Chat: Interact with AI models via a clean web interface.
• Voice Chat: Simulated voice interaction (requires login).
• Authentication: JWT-based user registration and login.
• Usage Limits: Daily chat and voice limits for guests and registered users.
• Chat History: Persists chat sessions in MongoDB for authenticated users.

---

Troubleshooting

• MongoDB Connection: Ensure MongoDB is running and the MONGO_URL in backend/.env is correct.
• AI Connection: If using Ollama, ensure it is running and the model specified in MODEL is pulled (ollama pull qwen2.5-coder:1.5b-base).
• Python Path: On Windows, if python doesn't work, try py. On macOS/Linux, use python3.