🤖 Ollama Chatbot

A full-stack AI chatbot with conversation memory, built with FastAPI + Next.js + Ollama (local LLM).

Tech Stack

• Backend: Python, FastAPI
• Frontend: Next.js (React, TypeScript, Tailwind CSS)
• AI: Ollama — runs fully locally, no API key needed

  Swap any model by changing OLLAMA_MODEL in backend/.env

Features

• 💬 Real-time chat interface
• 🧠 Full conversation history — model remembers context
• 🔒 Runs 100% locally — no data sent to external APIs
• ⚡ FastAPI async backend with CORS support
• 🎨 Clean dark UI with loading animations

Project Structure

ollama-chatbot/
├── backend/
│   ├── main.py          # FastAPI app
│   ├── .env             # Config (model name, Ollama URL)
│   └── requirements.txt
└── frontend/
    └── app/
        └── page.tsx     # Chat UI

How to Run

Prerequisites

• Python 3.10+
• Node.js 18+
• Ollama installed and running locally

1. Start Ollama model

ollama run tinyllama

2. Backend

cd backend
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
uvicorn main:app --reload --port 8000

3. Frontend

cd frontend
npm install
npm run dev

Open http://localhost:3000

API Endpoints

Method	Endpoint	Description
GET	/	Health check
POST	/chat	Send message with full history
DELETE	/chat	Clear conversation