This project provides an open-source chat UI specifically designed for interacting with Ollama, a popular tool for running large language models locally. It targets users who want a user-friendly interface to manage and converse with their Ollama-hosted models, offering a streamlined experience for local AI experimentation.

How It Works

The application is built using Next.js, a React framework, leveraging its server-side rendering and API routing capabilities. It acts as a frontend interface, communicating with a running Ollama server to send user prompts and receive model responses. The architecture allows for easy customization through environment variables, controlling aspects like the default model, system prompt, and generation temperature.

Quick Start & Requirements

• Install/Run:
  • Docker: docker run -p 3000:3000 ghcr.io/ivanfioravanti/chatbot-ollama:main
  • Locally: git clone ..., cd chatbot-ollama, npm ci, npm run dev (requires Ollama server running separately).
• Prerequisites: Node.js, npm, Ollama server.
• Setup Time: Minimal for Docker; local setup involves cloning, dependency installation, and running the Ollama server.

Highlighted Details

• Built on Next.js for a modern React-based UI.
• Configurable via environment variables for default model, system prompt, and temperature.
• Supports interaction with locally hosted LLMs via Ollama.

Maintenance & Community

The project is maintained by Ivan Fioravanti. Further community engagement details are not provided in the README.

Licensing & Compatibility

The project is open-source, but the specific license type is not explicitly stated in the README. Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The project is a UI layer for Ollama and requires a separate Ollama server instance to be running. The README indicates future development plans, suggesting the current feature set may be incomplete.