Ollama Web UI

A modern web interface for Ollama — chat with your local models, privately. Clean design, essential chat features, and no data leaving your machine.

Features

Chat Interface

• 🚀 Real-time streaming responses
• 🧠 Reasoning model support — displays the thinking process (e.g. DeepSeek R1) in a collapsible block, with a toggle to turn it on/off
• 💬 Multi-conversation management
• 🔄 Conversation history
• 📝 Markdown and code syntax highlighting support
• 🌓 Clean and modern UI design

Model Management

• 📋 List available models
• 🔄 Auto-select first available model
• 🎯 Easy model switching

Settings & Configuration

• ⚙️ Configurable Ollama server URL
• 💾 Settings persistence
• 📤 Export chat history to JSON
• 📥 Import chat history from JSON

Getting Started

Prerequisites

• Ollama installed and running on your machine
• Node.js 20.9+ installed (for development; required by Next.js 16)
• Docker (optional, for containerized deployment)

Installation

Method 1: Docker (Recommended)

1. Using Docker Compose (includes Ollama service):

wget https://raw.githubusercontent.com/oslook/ollama-webui/main/docker-compose.yml
docker compose up -d

2. Using Docker directly:

docker run -d -p 3000:3000 ghcr.io/oslook/ollama-webui:latest

Method 2: Development Setup

1. Clone the repository:

git clone https://github.com/oslook/ollama-webui.git
cd ollama-webui

2. Install dependencies:

bun install

3. Start the development server:

bun run dev

4. Open http://localhost:3000 in your browser

Usage

1. Ensure your Ollama server is running (default: http://127.0.0.1:11434)
2. Select a model from the dropdown menu
3. Start chatting!

For reasoning models such as DeepSeek R1, use the Thinking toggle next to the message input to show or hide the model's reasoning process. When shown, it appears in a collapsible block above each answer.

Configuration

• Click the settings icon (⚙️) to:
  • Configure Ollama server URL
  • Export chat history
  • Import chat history

Deploying on the internet (CORS)

The browser talks to Ollama directly, so when this app is hosted on a public domain the Ollama server must allow cross-origin requests. On the Ollama host set:

OLLAMA_HOST=0.0.0.0
OLLAMA_ORIGINS=*

then restart Ollama. Note that an HTTPS site cannot reach an http:// Ollama URL (mixed content) — serve Ollama over HTTPS or put it behind a reverse proxy. See the Ollama FAQ for details.

Docker Support

Available Tags

• latest: Latest stable release
• main: Latest development build
• vX.Y.Z: Specific version releases

Environment Variables

Variable	Description	Default
NODE_ENV	Node environment	production
PORT	Port to run the server on	3000

Building Locally

# Build the image
docker build -t ollama-webui .

# Run the container
docker run -d -p 3000:3000 ollama-webui

Using Docker Compose

The included docker-compose.yml provides two services:

1. ollama-webui: The web interface
2. ollama: The Ollama server (optional)

To use only the web interface:

docker compose up -d ollama-webui

To run both services:

docker compose up -d

Built With

• Next.js - React Framework
• React 19 - UI Library
• TypeScript - Type Safety
• Tailwind CSS - CSS Framework
• DaisyUI - UI Components
• Zustand - State management (persisted to localStorage)
• react-markdown - Markdown rendering

Contributing

Feel free to submit issues and enhancement requests!

License

This project is licensed under the MIT License - see the LICENSE file for details.

---

Note: This project was generated by an AI agent and has been human-verified for functionality and best practices. The implementation combines modern web development patterns with practical user experience considerations.